Multi-project fund configuration method and device based on teaching and learning optimization algorithm

Abstract

The embodiment of the invention provides a multi-project fund configuration method and device based on a teaching and learning optimization algorithm, and the method comprises the steps: taking a total fund budget and an annual fund budget mean value in a planning period as constraints, taking the minimum annual fund demand variance as a target function, and constructing a multi-project fund configuration model; solving an optimal solution of the multi-project fund configuration model based on a teaching and learning optimization algorithm, wherein the optimal solution is the optimal starting time of a group of general projects enabling the target function value to be minimum; and determining a multi-project optimal fund configuration scheme based on the optimal starting time of the general project.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of resource allocation optimization, and in particular, to a multi-project funding allocation method and device based on a teaching and learning optimization algorithm. Background Art

[0002] With the continuous development of science and technology and the advancement of new military reforms, the complexity of equipment systems and the number of equipment development projects have increased dramatically, and the dependence on economic resources has also increased. In this context, the construction of equipment development projects faces increasingly higher requirements, especially how to reasonably allocate limited financial resources to ensure the smooth progress of various projects, which has become a key issue that cannot be ignored in military equipment construction.

[0003] The development plan for military equipment construction is consistent with the overall national plan, and usually adopts a five-year plan to make systematic arrangements for equipment construction. In the process of planning, different equipment development projects are usually proposed by various departments first, and after being summarized and screened, they are prioritized according to funding and technical feasibility. Then, comprehensive balance and adjustment are made based on the overall budget and resource conditions. However, there are some significant problems in the actual operation of the existing funding allocation scheme. Due to the diversity and complexity of equipment development projects, funding allocation is often not accurate and reasonable. In the case of limited funds, some important projects may not be supported in time due to insufficient funds, resulting in project progress being hindered; while other low-priority projects may be over-invested, resulting in waste of funds and idle resources. Therefore, a more scientific evaluation and adjustment mechanism needs to be established for the funding allocation of equipment development projects. Summary of the invention

[0004] The embodiments described herein provide a method and apparatus for allocating funds for multiple projects based on a teaching and learning optimization algorithm, and a computer-readable storage medium storing a computer program.

[0005] According to a first aspect of the present disclosure, a multi-project funding allocation method based on a teaching and learning optimization algorithm is provided, including: taking the total funding budget and the annual funding budget mean within the planning period as constraints, and taking the minimization of the annual funding demand variance as the objective function, constructing a multi-project funding allocation model; solving the optimal solution of the multi-project funding allocation model based on the teaching and learning optimization algorithm, the optimal solution being the optimal start time of a group of general projects that minimizes the objective function value; and determining the optimal funding allocation plan for multiple projects based on the optimal start time of the general projects.

[0006] In some embodiments of the present disclosure, taking the total budget and the annual budget average during the planning period as constraints, and taking the minimization of the annual budget demand variance as the objective function, constructing a multi-project funding allocation model includes: obtaining equipment development projects during the planning period, the equipment development projects include carry-over projects and new projects, and the new projects include key projects and general projects; determining the total funding demand distribution function during the planning period based on the start-up priority and cost demand distribution function of the carry-over projects, key projects and general projects; constructing a multi-project funding allocation model based on the total funding demand distribution function and taking the minimization of the annual funding demand variance as the objective function.

[0007] In some embodiments of the present disclosure, based on the start-up priorities and cost requirement distribution functions of carry-over projects, key projects and general projects, determining the total cost requirement distribution function during the planning period includes: determining the cost requirement distribution curve of the carry-over project according to the start time of the carry-over project; estimating the total budget estimate, development cycle and investment peak point of the new project based on the expert analysis of similar development projects, and describing the cost requirement distribution of the new project based on the Weibull distribution function.

[0008] In some embodiments of the present disclosure, the planning period is 5 years, and the total funding demand distribution function during the planning period is: ; in, is the funding distribution curve of the jth carry-over project, is the funding distribution curve of the ith general project, is the funding distribution curve of the kth key project, is the start time of the carry-forward project, is the start time of a general project. Pick Any integer value between .

[0009] In some embodiments of the present disclosure, the objective function of the multi-project funding allocation model is: ; in, represents the annual funding requirement variance, Indicates the future Total annual funding requirements, represents the average annual expenditure, Indicates time The number of samples taken, .

[0010] In some embodiments of the present disclosure, solving the optimal solution of a multi-project funding allocation model based on a teaching and learning optimization algorithm includes: obtaining constraint data and objective functions of the multi-objective funding allocation model, initializing the number of students and the maximum number of iterations; in the teaching phase, randomly initializing the solution, calculating the average of all solutions, selecting the solution that minimizes the objective function value among the initialization solutions as the teacher, and updating the current optimal solution based on the teacher influence; in the learning phase, randomly selecting two students to learn from each other, and updating the current optimal solution based on the difference between the two students; and iteratively executing the teaching phase and the learning phase, updating the current optimal solution and the average value, and when the maximum number of iterations is reached, stopping the algorithm and outputting the optimal solution.

[0011] In some embodiments of the present disclosure, in the teaching stage, the solution is randomly initialized, the average value of all solutions is calculated, and the solution with the minimum objective function value in the initialized solution is selected as the teacher. The current optimal solution is updated according to the teacher influence, including: randomly initializing the solution, selecting the solution with the minimum objective function value in the initialized solution as the teacher, and calculating the average value of the initialized solution; for each student, a new solution is calculated by the following formula: ; In the formula, Indicates the old solution, represents the new solution, rand is a random number generated between [0,1], M is the average value of all students, is the teaching factor that determines the value of M, ; If the objective function value of the new solution is less than the objective function value of the old solution, the new solution is accepted.

[0012] In some embodiments of the present disclosure, during the learning phase, two students are randomly selected to learn from each other, and updating the current optimal solution based on the difference between the two students includes: for each student, another student is randomly selected from the population, and the current solution is calculated by the following formula:

[0013] In the formula, Are a student Another student randomly selected from the population, represents a random value, f() refers to the objective function to be optimized; if the objective function value of the current solution is less than the objective function value of the old solution, the current solution is accepted.

[0014] According to the second aspect of the present disclosure, a multi-project funding configuration device based on a teaching and learning optimization algorithm is provided. The device includes at least one processor; and at least one memory storing a computer program. When the computer program is executed by at least one processor, the device: takes the total budget and the annual budget mean in the planning period as constraints, and takes the minimum variance of the annual funding demand as the objective function, to construct a multi-project funding configuration model; solves the optimal solution of the multi-project funding configuration model based on the teaching and learning optimization algorithm; and determines the optimal funding configuration plan for multiple projects based on the optimal start time of general projects.

[0015] In some embodiments of the present disclosure, when the computer program is executed by at least one processor, the device causes the device to construct a multi-project funding allocation model through the following operations: obtaining equipment development projects within the planning period, the equipment development projects include carry-over projects and new projects, and the new projects include key projects and general projects; based on the start-up priorities and cost requirement distribution functions of carry-over projects, key projects and general projects, determining the total funding requirement distribution function within the planning period; based on the total funding requirement distribution function, constructing a multi-project funding allocation model with the minimization of annual funding requirement variance as the objective function.

[0016] In some embodiments of the present disclosure, when the computer program is executed by at least one processor, the device causes the device to determine the total funding requirement distribution function during the planning period through the following operations: determine the cost requirement distribution curve of the carry-over project based on the start time of the carry-over project; estimate the total funding estimate, development cycle and investment peak point of the new project based on the expert analysis of similar development projects, and describe the funding requirement distribution of the new project based on the Weibull distribution function.

[0017] In some embodiments of the present disclosure, when the computer program is executed by at least one processor, the device causes the device to solve the optimal solution of the multi-project funding configuration model based on the teaching and learning optimization algorithm through the following operations: obtaining the constraint data and objective function of the multi-objective funding configuration model, initializing the number of students and the maximum number of iterations; in the teaching stage, randomly initializing the solution, calculating the average of all solutions, selecting the solution with the smallest objective function value among the initialized solutions as the teacher, and updating the current optimal solution according to the teacher influence; in the learning stage, randomly selecting two students to learn from each other, and updating the current optimal solution based on the difference between the two students; and iteratively executing the teaching stage and the learning stage, updating the current optimal solution and the average value, and stopping the algorithm when the maximum number of iterations is reached or the difference between the solutions is less than a preset value, and outputting the optimal solution.

[0018] According to a third aspect of the present disclosure, a computer-readable storage medium storing a computer program is provided, wherein the computer program, when executed by a processor, implements the steps of the multi-project funding configuration method based on the teaching and learning optimization algorithm according to the first aspect of the present disclosure.

[0019] According to the multi-project funding allocation method and device based on the teaching and learning optimization algorithm of the embodiment of the present disclosure, based on the project arrangement priority and the project cost distribution law, it is possible to predict the launch time, investment demand, funding gap, redundancy, etc. of each project, ensure that the funding demand of the project is accurately estimated, and can adapt to the needs of various equipment construction projects. According to the different project characteristics, the funding allocation strategy can be flexibly adjusted. By constructing a funding budget calculation model, the reasonable allocation of funding resources among different projects is achieved. Based on the constraints of the annual funding budget mean and the total funding budget, the goal is to minimize the variance of the annual funding demand, thereby balancing the funding supply among the projects, effectively eliminating the conflict of funding resource allocation among projects, reducing redundant funds and waste, and ensuring that each project is adequately funded within its specified time frame. By optimizing the solution space through the teaching and learning optimization algorithm, the maximum utilization of funds is achieved, the situation of idle funds or funding shortages is avoided, and the efficiency of resource use is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure, wherein: Figure 1 An exemplary flow chart of a multi-project development fund allocation method 100 based on a teaching and learning optimization algorithm according to an embodiment of the present disclosure is shown; Figure 2 is a schematic diagram of a flow chart of solving an optimal solution according to a teaching and learning optimization algorithm according to an embodiment of the present disclosure; Figure 3 is a schematic diagram of the change of the annual funding demand curve before and after the adjustment according to the embodiment of the present disclosure; Figure 4 It is a schematic block diagram of a multi-project funding configuration device 400 based on a teaching and learning optimization algorithm according to an embodiment of the present disclosure.

[0021] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0023] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which the subject matter of the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein.

[0024] In the actual project implementation process, project priorities may change due to external environmental changes, technological updates, or strategic adjustments. At this time, the equipment development plan should be flexible and be able to adjust resource allocation between projects in a timely manner to ensure that resources are used most effectively, while avoiding the occurrence of untimely or idle funding due to unbalanced resource allocation.

[0025] The disclosed embodiment proposes a funding allocation method for equipment construction projects based on a teaching and learning optimization algorithm to eliminate conflicts in funding resource allocation, make funding investment balanced and effective, and ensure the orderly advancement of equipment construction planning projects.

[0026] Figure 1 An exemplary flow chart of a multi-project development fund allocation method 100 based on a teaching and learning optimization algorithm according to an embodiment of the present disclosure is shown.

[0027] exist Figure 1 In box S102, a multi-project funding allocation model is constructed with the total budget within the planning period and the mean of the annual budget as constraints and the minimization of the variance of the annual funding demand as the objective function.

[0028] In some embodiments of the present disclosure, equipment development projects within the planning period are first obtained, and the equipment development projects include carry-over projects and new projects, and the new projects include key projects and general projects.

[0029] The equipment development funding allocation system is allocated according to the type, priority and development progress of the equipment project. The goal of this system is to ensure that limited resources can be used in the best way while maintaining the continuity and stability of each project. First, key projects are given priority, while general projects are given a balance of development; second, carryover projects are given priority to ensure the continuity of project investment.

[0030] Among them, key projects are usually those with high technical difficulty, short development cycle and great strategic impact. Due to their urgency and importance, these projects must be given priority to ensure timely and adequate support of their funds and resources. Therefore, the funding allocation of key projects has a priority position in the entire plan. When formulating the five-year plan, the funding needs and planning arrangements of key projects are relatively fixed and will not be adjusted on a large scale.

[0031] Compared with key projects, general projects have longer development cycles, lower technical requirements, and less impact on equipment development. Therefore, when formulating equipment development plans, general project funding allocation is more flexible. Through reasonable funding optimization allocation, the start-up time and funding input of general projects can be adjusted in a timely manner according to the overall budget and resource distribution rules to ensure balanced allocation of funds in each year during the planning period.

[0032] Carryover projects are those projects that have already been launched and invested a certain amount of funds. Since the development cycle and total budget estimate of these projects have been clearly defined, carryover projects are usually not adjusted significantly in subsequent planning. In accordance with the principle of giving priority to carryover projects, subsequent funding arrangements will take into account the investment continuity and sustainability of these projects to ensure that they can continue to move forward as planned. The original funding investment rules need to be revised based on the funds already invested and the time distribution. This means that in subsequent planning, the funding investment for these projects needs to be reasonably adjusted to ensure their smooth completion.

[0033] Then, based on the start-up priority and cost demand distribution function of carry-over projects, key projects and general projects, the total funding demand distribution function during the planning period is determined.

[0034] In some embodiments of the present disclosure, the planning period is set to 5 years. In order to ensure the investment stability of the carryover projects from the previous five-year plan, the funding needs of the carryover projects should be given priority. The starting year of the carry-over project is before the five-year plan, and its cost distribution curve function is, which is known.

[0035] For new projects included in the five-year plan, the total budget, development cycle and investment peak point of the new projects are estimated through experts' analysis of similar development projects, and the Weibull distribution function is used to describe the future funding distribution of the new projects and obtain the theoretical distribution function.

[0036] Specifically, when describing the distribution of project funds, the application of Weibull distribution helps to understand the changing pattern of project funding requirements at different time points, especially the funding investment during the development cycle. The probability density function (PDF) of Weibull distribution can be expressed as: ; Here, λ is the scale parameter and k is the shape parameter, which controls the shape of the distribution (usually affecting how concentrated or dispersed the funding distribution is).

[0037] By analyzing similar development projects, experts can estimate the following key parameters: total budget (the total estimated cost of the entire project during the development cycle, usually the sum of the funds required for all project stages), development cycle (the overall development cycle of the project, which may include various stages such as design, development, testing, and delivery), and investment peak point (the highest point of funding demand for the project during the development cycle, which usually occurs at a certain stage, such as the mid-stage of the project, which may be a period of high resource investment and cost). Based on these parameters, experts use Weibull distribution to simulate the project's funding distribution: ; F(t) represents the proportion of the project's funds consumed before time t to the total funds. By adjusting the parameters λ (total project funds) and k (project start time) in the Weibull distribution, the change of the project's funding needs over time can be accurately reflected. This function can predict the actual funding needs each year.

[0038] As mentioned above, new projects include general projects and key projects. The start time of a general project is , and its cost distribution curve function is , Unknown, and It can only take values ​​of 0, 1, 2, 3, and 4. For key projects among the new projects, due to the urgency of their development, they should be given priority at the beginning of the five-year planning period. Therefore, the starting time of the first key project is = 0, the cost distribution function is After obtaining the cost distribution curves of all projects, the total R&D cost demand curve for the five-year planning period is obtained by superimposing them.

[0039] Assume that arrangements need to be made during the next planning period Equipment development projects, of which the number of carried-over projects is , the number of new projects is , obtained through review key projects, then the new general projects are The total funding during the five-year planning period is The starting point of the five-year plan is The unit is year. The balance degree of the funding demand distribution curve is measured by variance The smaller the variance, the better the balance of resource consumption.

[0040] Therefore, the distribution function of total funding demand during the five-year planning period is: ; in, is the funding distribution curve of the jth carry-over project, is the funding distribution curve of the ith general project, is the funding distribution curve of the kth key project, is the start time of the carry-forward project, is the start time of a general project. Pick Any integer value between .

[0041] Finally, based on the total funding demand distribution function and taking the minimization of annual funding demand variance as the objective function, a multi-project funding allocation model is constructed.

[0042] Since the start year of new general projects is different, the total demand distribution curve of R&D expenses within five years will also change. By determining the fluctuation of the cost demand distribution curve around the five-year cost index mean, one or several curves with the fluctuation range that meet the requirements can be selected to obtain the optimal curve distribution (i.e., variance One or more optimal solutions for project planning and arrangement under the condition of minimum time.

[0043] In some embodiments of the present disclosure, the objective function for defining the five-year development project arrangement is: ; in, represents the annual funding requirement variance, Indicates the future Total annual funding requirements, represents the average annual expenditure, Indicates time The number of samples taken, For the A general project, Pick For any integer value between Get the value, find The optimal solution can be found by minimizing the value of .

[0044] By setting different numbers of samples, different item arrangements can be obtained. Since the number of sample points is related to the realization of the entire optimization effect, a set of The value may not be an integer, and the actual arrangement is usually made on an annual basis. Minimum The project distribution and the corresponding future carry-over are determined by rounding off a set of values.

[0045] Reference Figure 1As shown, then in box S104, the optimal solution of the multi-project funding configuration model is solved based on the teaching and learning optimization algorithm. The optimal solution is the optimal start time of a group of general projects that minimizes the objective function value.

[0046] Among them, the Teaching and Learning-Based Optimization (TLBO) algorithm is a heuristic optimization algorithm that simulates the interaction between teachers and students in the teaching process. The algorithm can find the global optimal solution in high-dimensional space and is suitable for solving complex optimization problems.

[0047] In TLBO, the population is regarded as a class of students. Each student represents a possible solution to the optimization problem, and the score represents the fitness value. Through the iteration of the two stages of teaching and learning, the student's solution is continuously optimized, and finally an approximate optimal solution is obtained. Figure 2 1 is a flow chart of solving the optimal solution according to the teaching and learning optimization algorithm of the embodiment of the present disclosure. Figure 2 As shown, first obtain the objective function that needs to be optimized and then initialize it, including N: the number of students, n: the number of dimensions of the problem, that is, the maximum number of iterations, Teacher: the best student, the teacher in the group, and Mean: the mean of all students.

[0048] During the teaching phase, each student improves his or her solution based on the teacher’s knowledge. A random number is used to determine the degree of influence of the teacher on the student (T F ). If the current student's solution is better than his old solution, the new solution is accepted.

[0049] Learning phase: Each student randomly selects another student from the population to exchange knowledge. If the new solution is better than the existing solution, the new solution is accepted.

[0050] If the termination condition is not met, the teacher and mean are updated iteratively: according to the current student's solution, the teacher and mean are updated to determine which students are the best. When the stopping condition is met (for example, the maximum number of iterations or the fitness no longer changes significantly), the algorithm ends.

[0051] In some embodiments of the present disclosure, the constraint data and objective function of the multi-objective funding allocation model are first obtained. The goal of the model is to optimize the funding allocation for each year and each project based on factors such as total funding constraints, annual funding constraints, project priorities, and possible carry-over funds, so that the funding allocation is the most balanced. According to the above analysis, the objective function of the five-year planning research and development project arrangement is: in, Indicates the future Total annual research and development funding requirements, It represents the average amount of funds obtained after each adjustment. Indicates the time when adjustment is made The number of samples taken, .

[0052] Consider the distribution of general items as a multivariate function ,in Arrange the starting position for the item, using the point Represents a multivariate discrete number space An array of starting points that meet the conditions , then the purpose of the model is transformed into research The multi-project funding allocation problem is modeled as an optimization problem. The specific implementation steps include: Each student can be represented as a solution vector, which represents the funding allocation of different projects in different years. In the teaching stage, the solution is randomly initialized, the average of all solutions is calculated, and the solution with the smallest objective function value among the initialization solutions is selected as the teacher. The current optimal solution is updated according to the teacher's influence. This includes: randomly initializing the solution, and selecting the solution with the smallest objective function value among the initialization solutions as the teacher.

[0053] For each student, calculate the new solution using the following formula: ; In the formula, Indicates the old solution, represents the new solution, rand is a random number generated between [0,1], M is the average value of all students, is the teaching factor that determines the value of M, The teacher uses the teaching factor T F To guide each student, The value of is random (1 or 2). If = 1, the teacher will directly affect the student's update; if T F = 2, the average value of all students is used to guide the student. If the objective function value of the new solution is less than the objective function value of the old solution, that is, Then accept the new solution.

[0054] In the learning phase, two students are randomly selected to learn from each other, and the current optimal solution is updated based on the difference between the two students. For each student, another student is randomly selected and the current solution is calculated using the following formula:

[0055] In the formula, Are a student Another student randomly selected from the population, represents a random value, and f() refers to the objective function to be optimized. That is, if Get information for current students If the objective function value of the current solution is less than the objective function value of the old solution, that is, , then accept the current solution.

[0056] After each iteration, the teacher needs to be updated (the best student at the moment is selected) and the mean M of all students needs to be updated for use in the next iteration. The above teaching and learning phases are iterated to update the current optimal solution and the mean value. When the maximum number of iterations is reached or the difference between the solutions is less than the preset value, the algorithm is stopped and the optimal solution is output as the optimal project funding allocation plan.

[0057] Finally, in block S106 , the optimal funding allocation plan for multiple projects is determined based on the optimal start time of the general project.

[0058] By calculation, for the A general project, Pick For any integer value between Value, The minimum value of corresponds to the optimal solution, which is the start-up time of a new general project in multiple projects. By setting different numbers of samples, different project arrangements can be obtained. Since the number of sample points is related to the realization of the entire optimization effect, a set of possible The value is not an integer, but the actual arrangement is usually made on an annual basis. Minimum The distribution of project funding requirements and the corresponding future carry-over are determined by rounding off a set of values.

[0059] Assuming that the total funding for the next five-year plan period is 1.25 billion yuan, the annual funding arrangement will average 250 million yuan. Considering that there may be some potential projects that need to be arranged, 5% of flexible funds are usually reserved for emergency procurement and other situations. The five-year plan funding indicator is adjusted to 1.1875 billion yuan, an average of 237.5 million yuan per year. The adjusted total funding and annual funding limit are used as inputs to the algorithm to calculate the optimal solution.

[0060] The more samples there are, the more accurately the distribution of the curve can be reflected, but the longer the calculation time is, and the amount of carry-over funds will also be different. The disclosed embodiment takes into account issues such as carry-over, reserved funds, and calculation accuracy, and ultimately selects 100 sample points to calculate the optimal project arrangement method. Based on this solution, the launch time of each new general project can be arranged to determine the distribution of all projects within the five years. After determining the overall distribution, the theoretical annual investment intensity of the five years can be further determined based on the total annual project funding demand and the five-year funding indicators.

[0061] Table 1 shows the distribution of funding requirements for the next nine years when all projects start in the first year, and Table 2 shows the distribution of funding requirements for the next nine years under the optimal solution for all projects.

[0062] Table 1 Distribution of future funding requirements for all projects at the beginning of the first year (Unit: million yuan)

[0063] Table 2 Distribution of funding requirements for all projects in the next nine years under the optimal solution (unit: million yuan)

[0064] By comparing and analyzing Table 1 and Table 2, it is found that if no adjustment is made, that is, all projects are launched in the first year, as shown in Table 1, the total funding demand in the next five years will be 1.3386 billion yuan, which exceeds the planned funding indicator by 0.886 billion yuan, and the funding allocation will be difficult to meet the demand. After the optimal solution is adjusted, as shown in Table 2, the funding demand in the next five years is reduced to 1.19069 billion yuan, with an average annual demand of 2.3814 billion yuan, which is lower than the 1.25 billion yuan of the five-year plan. At this time, if the expected indicators are followed, that is, the remaining 5% is used as flexible funds, then the funds that can be guaranteed in each year are shown in Table 2. The funding demand gap is very small. Even if the full amount is guaranteed according to the project forecast demand, a certain amount of funds can still be retained as flexible funds to guarantee the funding needs of potential research and development projects or to make up for the funding gap caused by emergencies in ongoing projects.

[0065] Figure 3 Schematic diagram of the change of the annual funding demand curve before and after the adjustment according to the embodiment of the present disclosure. Figure 3As shown in the figure, the annual funding requirements for all projects in the five-year planning period before the adjustment were 257.13, 299.38, 324.64, 274.58, and 182.87 (millions), respectively. The annual funding requirements for all projects in the five-year planning period before the adjustment were 238.37, 237.22, 238.16, 238.21, and 238.73 (millions). It can be seen from the curve that the annual funding requirements after the adjustment fluctuate very little. The difference between the adjusted distribution curve and the annual funding indicator is 110.3 million yuan, and the total variance of the distribution curve with its own mean is 268.15 million yuan. The carryover amounts in the first three years after five years are 176.35 million yuan, 96.61 million yuan, and 450.3 million yuan respectively.

[0066] Figure 4 4 is a schematic block diagram of a multi-project funding configuration device 400 based on a teaching and learning optimization algorithm according to an embodiment of the present disclosure. Figure 4 As shown, the device 400 may include a processor 410 and a memory 420 storing a computer program. When the computer program is executed by the processor 410, the device 400 may perform the following operations: Figure 1 The steps of the multi-project funding allocation method 100 based on the teaching and learning optimization algorithm are shown. In one example, the device 400 can be a computer device or a cloud computing node. The device 400 can: construct a multi-project funding allocation model with the total funding budget and the annual funding budget mean in the planning period as constraints and the minimum variance of the annual funding demand as the objective function; solve the optimal solution of the multi-project funding allocation model based on the teaching and learning optimization algorithm, and the optimal solution is the optimal start time of a group of general projects that minimizes the objective function value; determine the optimal funding allocation plan for multiple projects based on the optimal start time of the general projects.

[0067] In some embodiments of the present disclosure, device 400 can obtain equipment development projects within the planning period, the equipment development projects include carry-over projects and new projects, and the new projects include key projects and general projects; based on the startup priority and cost requirement distribution function of carry-over projects, key projects and general projects, determine the total funding requirement distribution function within the planning period; and based on the total funding requirement distribution function, construct a multi-project funding allocation model with the minimization of annual funding requirement variance as the objective function.

[0068] In some embodiments of the present disclosure, the device 400 can solve the optimal solution of the multi-project funding configuration model based on the teaching and learning optimization algorithm through the following steps: obtain the constraint data and objective function of the multi-objective funding configuration model, initialize the number of students and the maximum number of iterations; in the teaching stage, randomly initialize the solution, calculate the average of all solutions, select the solution that minimizes the objective function value among the initialized solutions as the teacher, and update the current optimal solution according to the teacher's influence, each initialized solution includes the start time and funding allocation of the project; in the learning stage, randomly select two students to learn from each other, and update the current optimal solution based on the difference between the two students; and iteratively execute the teaching stage and the learning stage, update the current optimal solution and the average value, and when the maximum number of iterations is reached or the difference between the solutions is less than the preset value, stop the algorithm and output the optimal solution.

[0069] In an embodiment of the present disclosure, the processor 410 may be, for example, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a processor based on a multi-core processor architecture, etc. The memory 420 may be any type of memory implemented using data storage technology, including but not limited to random access memory, read-only memory, semiconductor-based memory, flash memory, disk storage, etc.

[0070] In addition, in the embodiment of the present disclosure, the apparatus 400 may also include an input device 430, such as a keyboard, a mouse, etc. In addition, the apparatus 400 may also include an output device 440, such as a display, etc., for outputting the optimal funding allocation plan for multiple projects.

[0071] In other embodiments of the present disclosure, a computer-readable storage medium storing a computer program is further provided, wherein the computer program can achieve the following when executed by a processor: Figure 1 The steps of a multi-project funding allocation method 100 based on a teaching and learning optimization algorithm are shown.

[0072] In summary, according to the multi-project funding allocation method and device based on the teaching and learning optimization algorithm of the embodiment of the present disclosure, based on the project arrangement priority and the project cost distribution law, it is possible to predict the launch time, investment demand, funding gap, redundancy, etc. of each project, ensure that the funding demand of the project is accurately estimated, and can adapt to the needs of various equipment construction projects. According to the different project characteristics, the funding allocation strategy can be flexibly adjusted. By constructing a funding budget calculation model, the reasonable allocation of funding resources among different projects is achieved. Based on the constraints of the annual funding budget mean and the total funding budget, the goal is to minimize the variance of the annual funding demand, thereby balancing the funding supply among the projects, effectively eliminating the conflict of funding resource allocation among projects, reducing redundant funds and waste, and ensuring that each project is adequately funded within its specified time frame. By optimizing the solution space through the teaching and learning optimization algorithm, the maximum utilization of funds is achieved, the situation of idle funds or funding shortages is avoided, and the efficiency of resource use is improved.

[0073] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device and method according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0074] Unless the context clearly indicates otherwise, the singular form of the words used herein and in the appended claims includes the plural and vice versa. Thus, when referring to the singular, the plural form of the corresponding term is generally included. Similarly, the words "comprise" and "include" are to be interpreted as inclusive rather than exclusive. Likewise, the terms "include" and "or" should be interpreted as inclusive unless such interpretation is expressly prohibited herein. Where the term "example" is used herein, particularly when it is located after a group of terms, the "example" is merely exemplary and illustrative and should not be considered exclusive or comprehensive.

[0075] Further aspects and scopes of adaptability become apparent from the description provided herein. It should be understood that various aspects of the present application can be implemented individually or in combination with one or more other aspects. It should also be understood that the description and specific embodiments herein are intended for purposes of illustration only and are not intended to limit the scope of the present application.

[0076] Several embodiments of the present disclosure are described in detail above, but it is obvious that those skilled in the art can make various modifications and variations to the embodiments of the present disclosure without departing from the spirit and scope of the present disclosure. The protection scope of the present disclosure is defined by the attached claims.

Claims

1. A multi-project funding allocation method based on teaching and learning optimization algorithm, characterized in that: include: Taking the total budget and the mean of the annual budget in the planning period as constraints and the minimum variance of the annual funding demand as the objective function, a multi-project funding allocation model is constructed. Solving the optimal solution of the multi-project funding allocation model based on the teaching and learning optimization algorithm, the optimal solution is the optimal start time of a group of general projects that minimizes the value of the objective function; as well as The optimal funding allocation plan for multiple projects is determined based on the optimal start time of the general project.

2. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 1 is characterized in that: The multi-project funding allocation model is constructed by taking the total budget and the annual budget mean within the planning period as constraints and minimizing the variance of annual funding requirements as the objective function, including: Obtain equipment development projects within the planning period, including carry-over projects and new projects, and including key projects and general projects; Determine the total funding requirement distribution function during the planning period based on the start-up priorities and cost requirement distribution functions of the carry-over projects, key projects and general projects; and Based on the total funding demand distribution function, a multi-project funding allocation model is constructed with the minimum annual funding demand variance as the objective function.

3. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 2 is characterized in that: The determination of the total funding demand distribution function during the planning period based on the start-up priorities and cost demand distribution functions of the carry-over projects, key projects and general projects includes: Determine the cost demand distribution curve of the carry-forward project according to the start time of the carry-forward project; Based on the experts' analysis of similar development projects, the total budget estimate, development cycle and investment peak point of the new project are estimated, and the funding demand distribution of the new project is described based on the Weibull distribution function.

4. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 2 is characterized in that: The planning period is 5 years, and the total funding demand distribution function during the planning period is: ； in, is the funding distribution curve of the jth carry-over project, is the funding distribution curve of the ith general project, is the funding distribution curve of the kth key project, is the start time of the carry-forward project, is the start time of a general project. Pick Any integer value between .

5. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 4 is characterized in that: The objective function of the multi-project funding allocation model is: ； in, represents the annual funding requirement variance, Indicates the future Total annual funding requirements, represents the average annual expenditure, Indicates time The number of samples taken, .

6. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 1 is characterized in that: The optimal solution of the multi-project funding allocation model based on the teaching and learning optimization algorithm includes: Obtain constraint data and objective function of the multi-project funding allocation model, and initialize the number of students and the maximum number of iterations; In the teaching phase, the solution is initialized randomly, the average of all solutions is calculated, the solution that minimizes the objective function value among the initialized solutions is selected as the teacher, and the current optimal solution is updated according to the teacher's influence; In the learning phase, two students are randomly selected to learn from each other, and the current optimal solution is updated based on the difference between the two students; and The teaching phase and the learning phase are iteratively executed to update the current optimal solution and the average value. When the maximum number of iterations is reached, the algorithm is stopped and the optimal solution is output.

7. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 6 is characterized in that: In the teaching stage, the solution is randomly initialized, the average value of all solutions is calculated, and the solution that minimizes the objective function value among the initialized solutions is selected as the teacher. The current optimal solution is updated according to the teacher's influence, including: Randomly initialize the solution, and select the solution that minimizes the objective function value among the initialization solutions as the teacher; For each student, calculate the new solution using the following formula: ； In the formula, Indicates the old solution, represents the new solution, rand is a random number generated between [0,1], M is the average value of all students, is the teaching factor that determines the value of M, ; If the objective function value of the new solution is less than that of the old solution, the new solution is accepted.

8. The multi-project funding allocation method based on the teaching and learning optimization algorithm according to claim 6 is characterized in that: In the learning phase, two students are randomly selected to learn from each other, and the current optimal solution is updated based on the difference between the two students, including: For each student, another student is randomly selected from the population and the current solution is calculated using the following formula: ； In the formula, Are a student Another student randomly selected from the population, represents a random value, and f() refers to the objective function to be optimized; If the objective function value of the current solution is less than that of the old solution, the current solution is accepted.

9. A multi-project funding allocation device based on a teaching and learning optimization algorithm, characterized in that: The device comprises: at least one processor; and at least one memory storing a computer program; Wherein, when the computer program is executed by the at least one processor, the device executes the steps of the multi-project funding configuration method based on the teaching and learning optimization algorithm according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the computer program implements the steps of the multi-project funding allocation method based on the teaching and learning optimization algorithm according to any one of claims 1 to 8.

Images