Regional item recommendation method and device based on GEP and electronic equipment

Abstract

The invention provides a region project recommendation method and device based on GEP and electronic equipment, and relates to the technical field of data processing.The method comprises the steps that in response to a received scheme recommendation instruction, a GEP growth difference value of a current year of a target region indicated by the scheme recommendation instruction is calculated; based on the GEP growth difference value of the current year, a non-dominated sorting genetic algorithm is adopted to carry out multi-target optimization on all candidate items corresponding to the target area so as to obtain a plurality of item recommendation schemes, and the item recommendation schemes are used for achieving filling of the GEP growth difference value of the current year of the target area; for each project recommendation scheme, calculating a target index value and a comprehensive index value of the project recommendation scheme; the project recommendation report of the current year is generated, the characteristics of each group of project recommendation schemes can be deeply analyzed for the user, and the user can be better helped to select the project suitable for the region.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and electronic device for recommending regional projects based on GEP. Background Art

[0002] Existing project recommendation technologies primarily focus on recommending projects for specific audiences, such as investors, or in specific scenarios, such as those based on specific technical areas like industrial park material flows and carbon credits. These methods are highly targeted, and their technical frameworks are deeply tied to specific fields. This leads to significant scenario limitations and a single-dimensional nature. Directly applying these methods to regional project recommendations results in poor results. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a method, device and electronic device for recommending regional projects based on GEP, so as to solve the problem that the existing project recommendation mechanism is difficult to apply and has poor accuracy when recommending regional projects.

[0004] In a first aspect, the present invention provides a regional project recommendation method based on GEP, the method comprising: calculating, in response to a received scheme recommendation instruction, the GEP growth difference of the target area indicated by the scheme recommendation instruction in the current year; based on the GEP growth difference of the current year, using a non-dominated sorting genetic algorithm to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes, the project recommendation schemes being used to achieve the filling of the GEP growth difference of the target area in the current year; for each project recommendation scheme, calculating the target indicator value and comprehensive indicator value of the project recommendation scheme; generating a project recommendation report for the current year, the project recommendation report at least including a list of project recommendation schemes formed by sorting based on the target indicator value / comprehensive indicator value.

[0005] In an optional embodiment, it also includes predicting the GEP target value and GEP growth difference of the target area indicated by the scheme recommendation instruction in future years in response to the received scheme prediction instruction; determining the reserve projects and corresponding priorities for future years based on all project recommendation schemes of the current year; determining the reserve projects and corresponding evaluation information for future years based on all project recommendation schemes of the current year, and the evaluation information is used to assist in the screening of reserve projects and determine the priority of reserve projects.

[0006] In an optional embodiment, the scheme recommendation instruction is also used to indicate the error limit value corresponding to the GEP growth difference of the current year in the target area, and based on the error limit value and the GEP growth difference of the current year, the upper limit value of the GEP growth difference of the current year and the lower limit value of the GEP growth difference of the current year are determined respectively; based on the upper limit value of the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes; and based on the lower limit value of the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes.

[0007] In an optional embodiment, the scheme recommendation instruction is also used to indicate the project additional conditions of the target area in the current year. Based on the project additional conditions, the multiple project recommendation schemes obtained are screened to determine the project recommendation schemes that meet the project additional conditions; and a project recommendation report for the current year is generated, and the project recommendation report also includes project recommendation schemes that meet the project additional conditions.

[0008] In an optional embodiment, multiple project recommendation solutions are obtained by: Solve the following multi-objective optimization function by using non-dominated sorting genetic algorithm , obtain multiple sets of Pareto non-dominated solutions as corresponding multiple project recommendation plans:

[0009] ; ; ; The constraints are: ; ; ; ; ; ; in, The target area corresponds to reserve projects, , is the total number of reserve items, For the The material supply growth value of each reserve project, For the The growth value of the regulation service of the reserve project, For the The cultural service growth value of each reserve project, For the GEP growth value of each reserve project, GEP growth difference / GEP growth difference upper limit / GEP growth difference lower limit, is the growth difference of material supply, To adjust the service growth difference, Add value to cultural services.

[0010] In an optional implementation, the target indicators include at least the GEP compliance rate, total investment requirements, and rate of return. The comprehensive indicator value of each project recommendation is calculated by the following method: ; For the The comprehensive index value of the recommended solution for each project, is the comprehensive index calculation function, 、 、 They are the weight coefficients corresponding to GEP compliance rate, total investment demand and rate of return respectively. An indicator value matrix consisting of GEP compliance rate, total investment demand, and rate of return corresponding to all project recommendation plans.

[0011] In an optional embodiment, the indicator value matrix is ​​constructed in the following manner: An N×3 basic matrix consisting of the GEP compliance rate, total investment requirements, and rate of return corresponding to all project recommended solutions; Normalize the basis matrix to generate the indicator value matrix.

[0012] In a second aspect, the present invention provides a regional project recommendation device based on GEP, the device comprising: A response module, configured to calculate the GEP growth difference of the target area indicated by the solution recommendation instruction in the current year in response to the received solution recommendation instruction; The optimization module is used to perform multi-objective optimization on all candidate projects corresponding to the target area based on the GEP growth difference of the current year using a non-dominated sorting genetic algorithm to obtain multiple project recommendation schemes. The project recommendation schemes are used to fill the GEP growth difference of the target area in the current year; The analysis module is used to calculate the target index value and comprehensive index value of each project recommendation plan; The report module is used to generate a project recommendation report for the current year. The project recommendation report at least includes a list of project recommendation plans sorted based on target indicator values / comprehensive indicator values.

[0013] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the regional project recommendation method based on GEP as described in any of the aforementioned embodiments.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the regional project recommendation method based on GEP as described in any of the aforementioned embodiments are executed.

[0015] The present application provides a method, device and electronic device for recommending regional projects based on GEP, wherein the method includes, in response to a received solution recommendation instruction, calculating the GEP growth difference of the target area indicated by the solution recommendation instruction in the current year; based on the GEP growth difference of the current year, using a non-dominated sorting genetic algorithm to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes, and the project recommendation schemes are used to fill the GEP growth difference of the target area in the current year; for each project recommendation scheme, calculating the target index value and comprehensive index value of the project recommendation scheme; generating a project recommendation report for the current year, the project recommendation report at least includes a list of project recommendation schemes formed by sorting based on the target index value / comprehensive index value. The present application decomposes the regional GEP target and obtains different project recommendation schemes by combining a multi-objective optimization algorithm. The project recommendation is more accurate, and the characteristics of each group of project recommendation schemes can be analyzed more deeply for users, which can better help users select projects suitable for the region. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic diagram of the structure of a regional project recommendation system based on GEP provided in an embodiment of the present application; Figure 2 A flowchart of a regional project recommendation method based on GEP provided in an embodiment of the present application; Figure 3 A schematic diagram of a reserve project evaluation matrix provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a regional project recommendation device based on GEP provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] First, the application scenario of this application is described. The technical solution of this application is applicable to regional project recommendation, and can be used to assist in decision-making of regional projects.

[0019] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0020] Example 1 Figure 1 This is a schematic diagram of the structure of a regional project recommendation system based on GEP provided in an embodiment of the present application. Figure 1 As shown, the present application provides a regional project recommendation system based on GEP, including a basic database, a data entry module, a scheme comparison and management module, a GEP target decision module and a project recommendation module.

[0021] Among them, the basic database is used to store basic data for implementing the regional project recommendation method. The basic data includes at least the GEP status data, GEP target data and regional project library corresponding to the region. The GEP status data includes the status data of supply products, regulation services, cultural services and the current total value of GEP. The GEP target data includes the target values ​​of supply products, regulation services, cultural services and GEP. The regional project library includes the project category, construction period, project-level ecological product value data of all reserve projects corresponding to each region that can be obtained by the system, as well as the project category, construction period, project-level ecological product value data of projects under construction.

[0022] The area here can be a city, a county, or a district within a city, etc.

[0023] The data entry module is used to respond to operations issued by the user through the human-computer interaction interface and generate corresponding instructions.

[0024] The human-computer interaction interface may include a region edit box for selecting a region. It may also include a tolerance edit box for setting the tolerance range of the GEP growth difference. It may also include an additional condition edit box for setting additional conditions for the project recommendation, such as investment requirements, industry preferences, and benefit requirements.

[0025] The scheme comparison and management module is used to extract the reserve projects and projects under construction, as well as supply products, regulation services, cultural services and other parameters of GEP corresponding to the target area from the basic database, analyze the value of ecological products, and combine the multi-objective optimization algorithm for comparison and screening to obtain a project portfolio that meets the overall development goals of the region, and provide an introduction to the relevant advantages of each portfolio.

[0026] The GEP target decision module is used to conduct overall and individual statistics and analysis of each project recommendation plan, and finally form and output a project recommendation report.

[0027] The project recommendation module is used to continue to predict the next few years based on meeting this year's needs, plan in advance and recommend several projects as reserves.

[0028] like Figure 2 As shown, when the system executes the regional project recommendation method, the following steps may be included: S1. In response to a received solution recommendation instruction, calculate the GEP growth difference of the target area indicated by the solution recommendation instruction in the current year.

[0029] The data entry module first loads the target area's GEP status data (including the current values ​​of supply products, regulatory services, and cultural services, as well as the total GEP value), GEP target data (sub-item and total target values), and project database data (category, construction period, ecological product value contribution, total investment, and social benefit indicators, such as income and wealth creation, for ongoing and reserved projects) from the basic database. After data loading, it undergoes integrity verification and preprocessing to eliminate invalid or contradictory data, and standardizes ecological value indicators for different projects (e.g., by unifying monetary units or weighting coefficients).

[0030] Specifically, the parameters that the basic database can provide are shown in Table 1 below.

[0031] Table 1 Basic database parameter table

[0032] Then, the material supply growth difference MG, regulatory service growth difference RG, cultural service growth difference CG, and GEP growth difference of the target area in the current year can be calculated respectively.

[0033] ; ; ; ; in, is the GEP growth difference, is the growth difference of material supply, To adjust the service growth difference, Add value to cultural services, is the GEP growth target value, is the target value for material supply growth, To adjust the service growth target value, To serve the cultural growth target value, In the target area The current GEP value of the required projects, In the target area The current value of material supply for the required projects, In the target area The current value of the adjustment service of the required project, In the target area The current value of cultural services for a required project.

[0034] S2. Based on the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes. The project recommendation schemes are used to fill the GEP growth difference of the current year in the target area.

[0035] The project selection management module can use a multi-objective optimization algorithm to generate N project recommendations based on the current year's GEP, supply products, regulatory services, and cultural service increases as core constraints. Multiple project recommendations can be obtained through the following methods.

[0036] Specifically, we can define the decision variables: ; in, Indicates whether to select projects, .

[0037] Solve the following multi-objective optimization function using the non-dominated sorting genetic algorithm (NSGA-II) , obtain multiple sets of Pareto non-dominated solutions as corresponding multiple project recommendation plans:

[0038] ; ; ; The constraints are: ; ; ; ; ; ; in, The target area corresponds to reserve projects, , is the total number of reserve items, For the The material supply growth value of each reserve project, For the The growth value of the regulation service of the reserve project, For the The cultural service growth value of each reserve project, For the GEP growth value of each reserve project, GEP growth difference / GEP growth difference upper limit / GEP growth difference lower limit, is the growth difference of material supply, To adjust the service growth difference, Add value to cultural services.

[0039] S3. For each project recommendation, calculate the target indicator value and comprehensive indicator value of the project recommendation.

[0040] The GEP target decision module can calculate the benefit indicators of each group of project recommendation plans. It calculates the comprehensive score of each plan through parameters such as the GEP compliance rate, total investment requirements, and rate of return of each group. It uses priority sorting and comprehensive evaluation to help users quickly understand the advantages and disadvantages of different plans.

[0041] The target indicators include at least GEP compliance rate, total investment requirements, and rate of return. In one embodiment, the candidate combinations can be ranked according to the GEP compliance rate:

[0042] in, For the The GEP compliance rate of the recommended solutions for each project, For the The recommended project The GEP change of each project, For the The number of projects in the project recommendation scheme.

[0043] The recommended plans for each project are ranked in ascending order based on their GEP compliance rates.

[0044] In another embodiment, the candidate combinations may be ranked according to the total investment requirements:

[0045] in, For the The total investment requirements of the recommended project plan, For the The recommended project Project investment, For the The number of projects in the project recommendation scheme.

[0046] The recommended plans for each project are ranked in descending order based on their total investment requirements.

[0047] In another embodiment, the candidate combinations may be ranked according to their yields:

[0048] in, For the The rate of return of the recommended solution for each project, For the The recommended project Project income, For the The number of projects in the project recommendation plan, For the The total investment of the recommended project plan.

[0049] Sort the recommended plans for each project in descending order based on their rate of return.

[0050] Furthermore, the comprehensive index value of each project recommendation solution can be calculated in the following way: ; For the The comprehensive index value of the recommended solution for each project, is the comprehensive index calculation function, 、 、 They are the weight coefficients corresponding to GEP compliance rate, total investment demand and rate of return respectively. An indicator value matrix consisting of GEP compliance rate, total investment demand, and rate of return corresponding to all project recommendation plans.

[0051] Specifically, the indicator value matrix can be constructed in the following way: An N×3 basic matrix is ​​constructed based on the GEP compliance rate, total investment requirements, and rate of return corresponding to all recommended project solutions. The basic matrix is ​​normalized to generate an indicator value matrix.

[0052] In one embodiment, the basic matrix may be normalized by the following steps: Organize the efficiency indicators of each candidate combination into an N×3 basic matrix X:

[0053] Where N is the number of candidate combination solutions.

[0054] Perform minimum-maximum normalization on each indicator and scale it to the [0,1] interval:

[0055] in, The minimum GEP compliance rate among all project recommended solutions. The minimum value of the total investment requirements of all recommended projects, The minimum value of the rate of return of all project recommendations, The maximum GEP compliance rate among all project recommended solutions, The maximum value of the total investment requirements of all project recommendations, is the maximum value of the rate of return of all project recommendation solutions, S is the scaling matrix, is the normalized basic matrix, is an n-dimensional vector of all 1s.

[0056] S4. Generate a project recommendation report for the current year. The project recommendation report at least includes a list of project recommendation plans sorted based on target indicator values / comprehensive indicator values.

[0057] The project recommendation module integrates the analysis results of all recommended project proposals to generate a final project recommendation report. This report includes a list of recommended proposals (including at least project name, investment amount, construction period, and GEP contribution), a comparative analysis chart, and implementation recommendations. The report supports custom export formats.

[0058] The GEP-based regional project recommendation method provided in the embodiment of the present application decomposes the regional GEP goals and combines them with a multi-objective optimization algorithm to obtain different project recommendation schemes. The project recommendations are more accurate and the characteristics of each group of project recommendation schemes can be analyzed more deeply for users. It can better assist users in selecting projects suitable for the region, help regions dynamically adjust GEP goals, and improve the scientific nature and operability of ecological governance.

[0059] Example 2 In one embodiment of the present application, the solution recommendation instruction is also used to indicate the error limit value corresponding to the GEP growth difference value of the current year in the target area. If the user sets the error limit value, the solution comparison management module can determine the upper limit value of the GEP growth difference value of the current year and the lower limit value of the GEP growth difference value of the current year based on the error limit value and the GEP growth difference value of the current year, respectively. And based on the upper limit value of the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation solutions. At the same time, based on the lower limit value of the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation solutions.

[0060] In other words, the upper limit of the GEP growth difference and the lower limit of the GEP growth difference in the current year can be used to optimize and generate corresponding project recommendation plans for recommendation to users, which can provide users with more possibilities.

[0061] Furthermore, sampling can be performed between the upper limit of the GEP growth difference and the lower limit of the GEP growth difference for the current year to determine multiple sampling values, which need to include the upper limit of the GEP growth difference and the lower limit of the GEP growth difference for the current year. The scheme selection management module can then obtain multiple project recommendation schemes based on the multiple sampling values ​​and in accordance with the aforementioned optimization method. This not only enriches the user's selection of project scheme combinations, but also supports reserve projects for future years.

[0062] Example 3 The solution recommendation instruction is also used to indicate the additional project conditions for the target area for the current year. The project recommendation module can also filter the multiple project recommendation solutions obtained based on the additional project conditions to determine the project recommendation solutions that meet the additional project conditions. A project recommendation report for the current year is generated, and the project recommendation report also includes the project recommendation solutions that meet the additional project conditions.

[0063] The additional conditions here can be set as shown in Table 2: Table 2 Additional conditions setting table

[0064] The project recommendation module can refer to the additional conditions and corresponding priorities selected by the user to filter out the project recommendation solutions that meet the conditions from all project recommendation solutions, and generate corresponding summary information to be added to the project recommendation report.

[0065] In this way, the personalized requirements of users can be met, so that users can find projects that are more suitable for the target area or meet other criteria.

[0066] Example 4 The data entry module can also respond to the scenario prediction instruction and forward it to the project recommendation module. The project recommendation module can predict the GEP target value and GEP growth difference for the target area indicated by the scenario recommendation instruction in the future year. Based on all the project recommendation plans for the current year, the reserve projects for the future year and their corresponding priorities are determined. Based on all the project recommendation plans for the current year, the reserve projects for the future year and their corresponding evaluation information are determined. The evaluation information is used to assist in the screening of reserve projects and determine the priority of reserve projects.

[0067] The project recommendation module can predict the GEP target demand for the next few years based on the project recommendation plans obtained in the current year, and generate a long-term recommendation list based on the corresponding reserve projects in the basic database. Users can also mark and annotate each project through the human-computer interaction interface. By dynamically adjusting the GEP target setting and reserve projects, the system can continuously optimize the recommendation strategy to ensure the sustainability of regional GEP growth. For example, if a certain type of project contributes significantly to long-term goals but has a long construction period, the system can give priority to including it in the reserve plan.

[0068] Specifically, the GEP growth rate of the recommended project plan in year j can be predicted in the following way:

[0069] in, Indicates the Project Recommendation The comprehensive GEP growth contribution of For the The recommended project Project No. Annual GEP change, Indicates the The weight of the project, Determined based on factors such as the project's investment scale and project type. represents the project contribution intensity coefficient, Used to measure the GEP contribution of project unit investment, Indicates the The total investment of the project, Indicates the The construction period of each project (in years) Indicates the current value of the region GEP, represents the long-term contribution reward coefficient, Used to reward project portfolios that contribute significantly to long-term goals.

[0070] The first Long-term contribution factors of the recommended project plan: Specifically, to more accurately assess the contribution of the project recommendation to the long-term GEP goals, the long-term contribution factor of the project portfolio can be measured using the following formula:

[0071] in, represents the long-term contribution factor of the recommended solution for the nth project, T represents the predicted time range (in years), represents the long-term contribution weighted coefficient, Used to evaluate the comprehensive impact of project investment and construction cycle on long-term GEP goals.

[0072] In one embodiment, the system is also equipped with a dynamic adjustment mechanism. The project recommendation module can make real-time adjustments to the GEP target setting and the reserve projects in the target area in the basic database based on the actual effect of the current GEP growth and future forecast values.

[0073] GEP target value adjusted according to current implementation situation It can be calculated by the following formula:

[0074] in, It represents the GEP target growth value initially set for the target area, and δ represents the target adjustment coefficient, which is used to adjust the amplitude of the target correction. The predicted GEP change for the nth project recommendation solution, Indicates the actual growth value of GEP of currently implemented projects.

[0075] In one embodiment, a dynamic adjustment mechanism for reserve projects is provided for each region. Specifically, each project is evaluated according to the following priority scoring formula, and further evaluation can be performed on the projects in the project recommendation plan obtained in the current year:

[0076] in, Indicates the The reserve priority score of each project, Indicates the The GEP growth value of each project, η represents the construction period impact coefficient, and η is used to measure the impact of the project construction period on the priority.

[0077] Then, it can be converted into a standard score through linear transformation :

[0078] in, Indicates the The standard score corresponding to each item, Indicates the current project library The minimum value of Indicates the current project library The maximum value of .

[0079] Each project can be graded based on its standard score. The grading logic can be found in Table 3 below.

[0080] Table 3 Project rating logic table

[0081] For example, projects with the top three ratings can be considered as reserve projects corresponding to the target area and can be given priority consideration in program recommendations for future years.

[0082] In this way, the system provided by this application uses a dynamic project adjustment mechanism to generate more accurate, scientific, persistent and relevant project recommendation plans for users, providing a reference for project planning directions for various regions and market entities.

[0083] In one embodiment, the project recommendation report may also include evaluation information of each project recommendation plan and the project, and assist decision-making through multi-dimensional comparison.

[0084] For details, see Figure 3 , key indicators (GEP growth rate , long-term contribution factors ) are integrated into a visual matrix to assist decision making through multi-dimensional comparison, for example: (1) High +High : Priority launch (such as long-term, high-potential projects).

[0085] (2) High +Low : Included in reserves and continuously tracked (such as strategic infrastructure projects).

[0086] (3) Low +High : Short-term sprint projects (such as ecological restoration projects with quick results).

[0087] (4) Low +Low : Elimination or optimization (such as inefficient and duplicate projects).

[0088] In this way, users can more intuitively see the advantages and disadvantages of each project, and choose appropriate projects according to their needs, so as to set GEP indicator goals more reasonably and improve the level of modernization of ecological and environmental governance.

[0089] Example 5 like Figure 4 As shown, based on the same inventive concept, an embodiment of the present application further provides a regional project recommendation device 40 based on GEP, the device comprising: The response module 410 is configured to calculate the GEP growth difference of the target area indicated by the solution recommendation instruction in the current year in response to the received solution recommendation instruction; Optimization module 420 is used to perform multi-objective optimization on all candidate projects corresponding to the target area based on the GEP growth difference of the current year using a non-dominated sorting genetic algorithm to obtain multiple project recommendation schemes, which are used to fill the GEP growth difference of the target area in the current year; The analysis module 430 is used to calculate the target index value and comprehensive index value of each project recommendation plan; The reporting module 440 is used to generate a project recommendation report for the current year. The project recommendation report at least includes a list of project recommendation solutions sorted based on target indicator values / comprehensive indicator values.

[0090] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown in FIG, the electronic device 500 includes a processor 510, a memory 520 and a bus 530.

[0091] The memory 520 stores machine-readable instructions executable by the processor 510. When the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530. When the machine-readable instructions are executed by the processor 510, the steps of a regional project recommendation method based on GEP in the above-mentioned method embodiment can be executed. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0092] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it can execute the steps of a regional project recommendation method based on GEP in the above-mentioned method embodiment. The specific implementation method can be found in the method embodiment and will not be repeated here.

[0093] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0094] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0095] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0097] It should be noted that if the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0098] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0099] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A regional project recommendation method based on GEP, characterized in that: The method comprises: In response to the received plan recommendation instruction, calculating the GEP growth difference of the target area indicated by the plan recommendation instruction in the current year; Based on the GEP growth difference of the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation schemes. The project recommendation schemes are used to fill the GEP growth difference of the target area in the current year; For each project recommendation, calculate the target index value and comprehensive index value of the project recommendation; Generate a project recommendation report for the current year, wherein the project recommendation report at least includes a list of project recommendation plans formed by sorting based on target indicator values / comprehensive indicator values.

2. The method according to claim 1, characterized in that Also includes: In response to the received solution prediction instruction, predict the GEP target value and GEP growth difference of the target area indicated by the solution recommendation instruction in the future year; Based on all the project recommendations for the current year, determine the reserve projects for the next year and their corresponding priorities; Based on all project recommendations for the current year, reserve projects for future years and corresponding evaluation information are determined. The evaluation information is used to assist in screening reserve projects and determine their priorities.

3. The method according to claim 1, characterized in that The solution recommendation instruction is also used to indicate the error limit value corresponding to the GEP growth difference of the current year in the target area. Based on the error limit value and the GEP growth difference value of the current year, respectively determining the GEP growth difference upper limit value of the current year and the GEP growth difference lower limit value of the current year; Based on the upper limit of the GEP growth difference in the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation plans; Based on the lower limit of the GEP growth difference in the current year, a non-dominated sorting genetic algorithm is used to perform multi-objective optimization on all candidate projects corresponding to the target area to obtain multiple project recommendation plans.

4. The method according to claim 1, wherein The program recommendation instruction also indicates additional conditions for the current year's project in the target area. Based on the project additional conditions, the obtained multiple project recommendation plans are screened to determine the project recommendation plans that meet the project additional conditions; Generate a project recommendation report for the current year, wherein the project recommendation report also includes project recommendation plans that meet the project additional conditions.

5. The method according to claim 1 or 3, characterized in that Get multiple project recommendations through the following methods: Solve the following multi-objective optimization function by using non-dominated sorting genetic algorithm , obtain multiple sets of Pareto non-dominated solutions as corresponding multiple project recommendation plans: ； ； ； The constraints are: ； ； ； ； ； ； in, The target area corresponds to reserve projects, , is the total number of reserve items, For the The material supply growth value of each reserve project, For the The growth value of the regulation service of the reserve project, For the The cultural service growth value of each reserve project, For the GEP growth value of each reserve project, GEP growth difference / GEP growth difference upper limit / GEP growth difference lower limit, is the growth difference of material supply, To adjust the service growth difference, Add value to cultural services.

6. The method according to claim 1, wherein The target indicators include at least the GEP compliance rate, total investment requirements, and rate of return. The comprehensive indicator value of each project recommendation is calculated in the following way: ； For the The comprehensive index value of the recommended solution for each project, is the comprehensive index calculation function, 、 、 They are the weight coefficients corresponding to GEP compliance rate, total investment demand and rate of return respectively. An indicator value matrix consisting of GEP compliance rate, total investment demand, and rate of return corresponding to all project recommendation plans.

7. The method according to claim 6, characterized in that The indicator value matrix is ​​constructed in the following way: An N×3 basic matrix consisting of the GEP compliance rate, total investment requirements, and rate of return corresponding to all project recommended solutions; The basic matrix is ​​normalized to generate an indicator value matrix.

8. A regional project recommendation device based on GEP, characterized in that: The device comprises: a response module, configured to calculate, in response to the received solution recommendation instruction, a GEP growth difference of the current year for the target area indicated by the solution recommendation instruction; An optimization module is used to perform multi-objective optimization on all candidate projects corresponding to the target area based on the GEP growth difference of the current year using a non-dominated sorting genetic algorithm to obtain multiple project recommendation schemes, which are used to fill the GEP growth difference of the target area in the current year; The analysis module is used to calculate the target index value and comprehensive index value of each project recommendation plan; The report module is used to generate a project recommendation report for the current year, wherein the project recommendation report at least includes a list of project recommendation plans formed by sorting based on target indicator values / comprehensive indicator values.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the GEP-based regional project recommendation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the regional project recommendation method based on GEP are executed as claimed in any one of claims 1 to 7.

Images