Intelligently optimized job welfare allocation decision-making method and device and electronic equipment

Abstract

The invention belongs to the technical field of work meeting big data processing, and particularly discloses an intelligent optimized work meeting welfare allocation decision-making method and device and electronic equipment, and the method comprises the steps: obtaining work meeting member welfare related data; calculating the selection probability of each welfare item by each member based on the related welfare data of the members of the work meeting; generating a plurality of welfare distribution schemes based on the relevant welfare data of the members of the work meeting and the selection probability of each member for each welfare item; and performing optimization adjustment on the plurality of welfare allocation schemes according to a preset optimization target to obtain an optimal welfare allocation scheme. According to the method, the finally obtained welfare allocation scheme can obtain effective multi-dimensional data support, and the fund utilization efficiency is improved while the member welfare satisfaction degree is improved.

Description

Technical Field

[0001] This application belongs to the field of trade union big data processing technology, and more specifically, relates to an intelligent and optimized trade union welfare distribution decision-making method, device and electronic device. Background Technology

[0002] Many labor unions adopt a fixed welfare package model when distributing benefits, meaning that all members, regardless of their welfare level or personal preferences, receive the same combination of welfare items. This fixed model fails to meet the diverse needs of members, resulting in generally low member satisfaction. Some labor unions rely on the experience and subjective judgment of their staff to allocate benefits. This method lacks data support and scientific basis, making it difficult to accurately grasp the true needs of members. Furthermore, manual allocation is easily affected by human factors, making it difficult to guarantee fairness and accuracy.

[0003] The aforementioned welfare distribution methods lack data support and are based on a single dimension, failing to achieve a comprehensive balance between member welfare satisfaction and fund utilization efficiency. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the purpose of this application is to provide an intelligent and optimized decision-making method, device and electronic device for union welfare distribution, which aims to solve the problem that the existing welfare distribution methods lack data support and have a single dimension, resulting in the inability to achieve a comprehensive balance between member welfare satisfaction and fund utilization efficiency.

[0005] To achieve the above objectives, firstly, this application provides an intelligent and optimized method for union welfare distribution decision-making, comprising: Obtain data related to union member benefits; Based on the aforementioned union member welfare-related data, calculate the probability of each member choosing each welfare item. Based on the aforementioned union member welfare-related data and the probability of each member selecting each welfare item, multiple welfare allocation schemes are generated. The multiple welfare allocation schemes are optimized and adjusted according to the preset optimization objectives to obtain the optimal welfare allocation scheme.

[0006] This application comprehensively considers data related to union member welfare, calculates the probability of each member choosing each welfare item based on multiple factors, generates multiple welfare allocation plans for selection, and then continuously optimizes and adjusts the welfare allocation plans based on actual needs, so that the final welfare allocation plan is effectively supported by multi-dimensional data, thereby improving member welfare satisfaction and fund utilization efficiency.

[0007] According to the intelligent optimization method for union welfare allocation provided in this application, after obtaining union member welfare-related data, the method further includes: The data related to union member welfare was cleaned to remove outliers and missing values, and then normalized.

[0008] This application processes data related to union member benefits to facilitate subsequent calculations.

[0009] According to the intelligent optimization decision-making method for union welfare allocation provided in this application, the step of calculating the probability of each member choosing each welfare item based on the union member welfare-related data includes: Based on the aforementioned union member welfare-related data, machine learning recommendation algorithms are used to analyze each member's preferences for different types of welfare programs. Combining the current characteristics of welfare programs and market trends, the probability of each member choosing each welfare program is calculated.

[0010] According to the intelligent optimization method for union welfare allocation decision-making provided in this application, multiple welfare allocation schemes are generated based on the union member welfare-related data and the selection probability of each member for each welfare item, including: Based on the union member welfare-related data and the probability of each member choosing each welfare item, multiple welfare allocation schemes are generated using the Monte Carlo simulation method.

[0011] This application generates a large number of initial welfare allocation schemes through Monte Carlo simulation, covering a wide solution space and improving optimization accuracy.

[0012] According to the intelligent optimization decision-making method for union welfare distribution provided in this application, the multiple welfare distribution schemes are optimized and adjusted according to a preset optimization objective, including: The multiple welfare allocation schemes are optimized and adjusted according to a preset optimization objective using a genetic algorithm.

[0013] This application utilizes a genetic algorithm for iterative optimization, balancing global search and local development, effectively avoiding local optima, and outputting a high-quality welfare configuration scheme.

[0014] By adjusting parameters and rules, such as changing the number of simulations and algorithm parameters, it is possible to adapt to the different union members' needs, welfare programs, and budget constraints.

[0015] Secondly, this application provides an intelligent and optimized union welfare distribution decision-making device, comprising: The acquisition module is used to acquire data related to union member benefits; The calculation module is used to calculate the probability of each member choosing each welfare item based on the aforementioned union member welfare-related data; The generation module is used to generate multiple welfare allocation schemes based on the union member welfare-related data and the probability of each member selecting each welfare item; The optimization module is used to optimize and adjust the multiple welfare allocation schemes according to preset optimization objectives to obtain the optimal welfare allocation scheme.

[0016] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the intelligent optimized union welfare distribution decision-making method described in the first aspect or any possible implementation thereof.

[0017] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the intelligent optimized union welfare distribution decision-making method described in the first aspect or any possible implementation of the first aspect.

[0018] Fifthly, this application provides a computer program product that, when run on a processor, causes the processor to execute the intelligent optimized union welfare distribution decision-making method described in the first aspect or any possible implementation of the first aspect.

[0019] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0020] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art: This application comprehensively considers data related to union member welfare, calculates the probability of each member choosing each welfare item based on multiple factors, generates multiple welfare allocation plans for selection, and then continuously optimizes and adjusts the welfare allocation plans based on actual needs, so that the final welfare allocation plan is effectively supported by multi-dimensional data, thereby improving member welfare satisfaction and fund utilization efficiency. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the intelligent optimized union welfare distribution decision-making method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the optimized and adjusted process provided in the embodiments of this application; Figure 3 This is a schematic diagram of the intelligent optimized union welfare distribution decision-making device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0025] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0026] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, for example, multiple processing units means two or more processing units, multiple elements means two or more elements, etc.

[0027] First, let's introduce the following: Many labor unions use a fixed welfare package model, where all members receive the same combination of benefits regardless of their welfare level or personal preferences. For example, during holidays, all members receive the same food gift box worth 300 yuan. While this model is simple and easy to implement, it completely ignores the individual needs of members. Different members have different expectations and preferences for benefits; for instance, younger members may prefer gym memberships or electronic products, while older members may prefer health and wellness products. A fixed welfare distribution model fails to meet the diverse needs of members, resulting in generally low member satisfaction.

[0028] Some labor unions rely on staff experience and subjective judgment to allocate benefits. This method lacks data support and scientific basis, making it difficult to accurately grasp the true needs of members. For example, staff may believe that a certain type of benefit is more popular based on past experience, but the actual situation may vary due to factors such as time, season, and changes in membership structure. Manual allocation is also susceptible to interference from human factors, making it difficult to guarantee fairness and accuracy.

[0029] Some existing methods for optimizing benefits allocation focus on a single objective. For example, some prioritize maximizing member satisfaction without considering budget constraints, while others focus solely on cost control, neglecting member benefit expectations. For instance, some methods, in an effort to improve member satisfaction, may excessively increase the procurement of high-value benefit programs, leading to budget overruns; while other methods, in an effort to control costs, may excessively reduce the quantity or quality of benefit programs, resulting in a significant drop in member satisfaction. This single-dimensional optimization fails to achieve a comprehensive balance between member benefit satisfaction and efficient use of funds.

[0030] Traditional welfare allocation methods rely primarily on manual decision-making, lacking the support of big data analysis and intelligent algorithms. When faced with complex member needs, numerous welfare program choices, and limited budgets, manual decision-making is prone to bias and struggles to find the optimal welfare allocation solution. For example, it is difficult for humans to deeply analyze and mine vast amounts of historical member selection data and satisfaction feedback data, making it impossible to accurately predict members' welfare intentions and changing needs, thus failing to provide a precise basis for welfare allocation decisions.

[0031] In summary, existing union welfare distribution technologies have problems, including the inability of traditional methods to meet the personalized needs of members, unreasonable distribution, and the fact that existing optimization methods are one-dimensional and lack intelligent decision support, making it difficult to balance member satisfaction and budget constraints.

[0032] Next, combined Figures 1-2 This application introduces the intelligent optimization decision-making method for union welfare distribution provided in the embodiments.

[0033] Figure 1 This is a flowchart illustrating the intelligent optimization decision-making method for union welfare distribution provided in this application embodiment, as shown below. Figure 1 As shown, the method includes the following steps: Step 100: Obtain data related to union member benefits; Optionally, union member welfare-related data may include member welfare levels, past welfare selection records, and information on various welfare programs, covering welfare program value, inventory quantity, etc.

[0034] Step 110: Based on the data related to union member benefits, calculate the probability of each member choosing each benefit item; Based on the historical welfare selection data of union members and the historical welfare selection data of other members with similar preferences, the probability of each member choosing each welfare item can be calculated.

[0035] Step 120: Based on union member welfare-related data and the probability of each member selecting each welfare item, generate multiple welfare allocation schemes; Multiple welfare allocation schemes can be generated through simulation. In each simulation, the range of welfare items that members can choose is determined according to their welfare level. Based on the probability of members' welfare intentions, a combination of welfare items is randomly assigned to each member. The overall welfare procurement cost under this combination is calculated to see if it exceeds the budget, as well as the member's satisfaction with the allocated welfare.

[0036] Step 130: Optimize and adjust multiple welfare allocation schemes according to preset optimization objectives to obtain the optimal welfare allocation scheme.

[0037] Optionally, preset optimization goals can be set according to actual needs, such as the lowest cost or the highest member satisfaction.

[0038] The generated welfare allocation scheme is optimized and adjusted to achieve the optimal welfare allocation scheme that maximizes member welfare satisfaction under specific objectives, such as limited welfare funds.

[0039] The intelligent optimization decision-making method for union welfare allocation provided in this application comprehensively considers union member welfare-related data, calculates the probability of each member choosing each welfare item based on multiple factors, generates multiple welfare allocation schemes for selection, and then continuously optimizes and adjusts the welfare allocation schemes based on actual needs, so that the final welfare allocation scheme is effectively supported by multi-dimensional data, thereby improving member welfare satisfaction and fund utilization efficiency.

[0040] In some embodiments, after step 100, the method further includes: The data related to union member welfare was cleaned to remove outliers and missing values, and then normalized.

[0041] The collected union member welfare-related data was cleaned to remove outliers and missing values, and then normalized to facilitate subsequent calculations.

[0042] For example, information on 100 union members can be collected, including their welfare levels (divided into three levels: A, B, and C) and their welfare selection records over the past two years; information on 10 welfare items can be compiled, such as their value ranging from 50 to 500 yuan and their sufficient inventory; then the data can be cleaned and normalized to ensure its accuracy and consistency.

[0043] In some embodiments, step 110 specifically includes: Based on union member welfare data, machine learning recommendation algorithms are used to analyze members’ preferences for different types of welfare programs. Combining current welfare program characteristics and market trends, the probability of each member choosing each welfare program is calculated.

[0044] Alternatively, the machine learning recommendation algorithm can be a collaborative filtering algorithm, a content-based recommendation algorithm, etc.

[0045] Based on members' past benefit selection data, machine learning recommendation algorithms are used to analyze members' preferences for different types of benefit programs. Combined with the current characteristics of benefit programs and market trends, the probability of each member choosing each benefit program is calculated.

[0046] For example, for member Zhang San, based on his past frequency of choosing similar types of welfare items and his evaluation, combined with data from other members with similar selection preferences, the probability of his intention to choose various welfare items is calculated, such as the probability of choosing a gym membership being 0.6 and the probability of choosing movie tickets being 0.3, etc.

[0047] In some embodiments, step 120 specifically includes: Based on union member welfare data and the probability of each member choosing each welfare item, multiple welfare allocation schemes are generated using the Monte Carlo simulation method.

[0048] Monte Carlo simulation is used to generate samples of welfare allocation schemes. In each simulation, the range of welfare items that members can choose is determined according to their welfare level. Welfare item combinations are randomly assigned to each member based on their welfare intention probability. The overall welfare procurement cost under this combination is calculated to determine whether it exceeds the budget, and the member's satisfaction with the allocated welfare is also calculated (this can be calculated using a satisfaction function constructed based on the member's preference for welfare items, welfare value, and other factors). The simulation process is repeated until the set number of simulations is reached, thereby generating a large number of possible welfare allocation scheme samples, providing a data foundation for subsequent optimization. The specific steps are as follows: 1a. Input settings: Number of simulations N; Number of members: M; The probability of a user's intention to receive benefits is calculated based on the benefits selected by users during historical benefit distributions and their satisfaction feedback. It is denoted by P. i (X j This indicates that member i is interested in welfare program X. j The probability of intention; The basic rules for this benefit distribution, such as the amount limits for benefit items for different user levels, etc., include the maximum total value of benefits for a single member. express.

[0049] 2a. Initialization: At the start of each simulation, an empty list of benefits items is initialized for each member i, along with its total allocated value v. i =0.

[0050] 3a. Randomly assign welfare items: Calculate the residual value space: For member i, its residual value space is:

[0051] Filtering available items: Select items from the welfare program pool with a value less than or equal to... The welfare programs form a subset S of optional programs. i .

[0052] Randomly select an item: if S i Not empty, based on member i to S i Various welfare programs X j Intention probability P i (X j Randomly select a welfare program X j Assign to member i, update v i =v i +Value(X) j ), and repeat the steps of calculating the remaining value space and filtering optional items; if S i If the value is empty, it means that the simulation allocation for that member is complete, and the simulation can continue to the next member until all members have been simulated, at which point a simulation allocation scheme will be output.

[0053] 4a. Completeness check of the allocation plan: For each member i, if the total value of benefits allocated to them in the simulation scheme is... Not achieved If 90% of the benefits are utilized, the allocation scheme is considered to have an excessively low utilization rate, which is unfair to member i, and the scheme should be discarded. In practice, the 90% threshold can be adjusted as needed.

[0054] 5a. Check the total budget of the allocation plan: Calculate the total budget for each allocation plan. If the budget is not exceeded, the plan is retained; otherwise, it is discarded. The formula for calculating the budget utilization rate for each allocation plan is as follows:

[0055] A large number of initial welfare allocation schemes are generated through Monte Carlo simulation, covering a wide solution space and improving optimization accuracy.

[0056] In some embodiments, step 130 specifically includes: Multiple welfare distribution schemes are optimized and adjusted according to preset optimization objectives using a genetic algorithm.

[0057] The welfare distribution scheme generated in the simulation and prediction stage can be optimized and adjusted by genetic algorithms. Genetic algorithms iteratively optimize the welfare distribution scheme by simulating natural selection and genetic mechanisms, and gradually approach the optimal solution.

[0058] Figure 2 This is a schematic diagram of the optimized and adjusted process provided in the embodiments of this application, such as... Figure 2 As shown, the specific steps for optimization and adjustment are as follows: 1b. Initialize the population: 1.1b. Population Size Setting: Determine the population size P for the genetic algorithm based on the number of welfare distribution schemes. size The population size is generally set at 10%–20% of the number of welfare allocation schemes to ensure sufficient population diversity.

[0059] 1.2b. Chromosome Encoding: Each simulated welfare allocation scheme is encoded as a chromosome. A chromosome can be represented as a two-dimensional array, where each row corresponds to a gene of the chromosome, representing a member, and the columns represent welfare items. An element value of 1 indicates that the corresponding member is allocated to that welfare item, and 0 indicates that no member is allocated.

[0060] 1.3b. Initialize the population: Randomly select P from the welfare allocation scheme. size One scheme was used as the initial population.

[0061] 2b. Define the fitness function: Fitness function: Used to measure the merits of each welfare allocation scheme (chromosome), taking into account both member satisfaction and budget utilization. The fitness calculation formula for the k-th scheme is as follows:

[0062] Wherein, overall satisfaction (k) represents the average satisfaction of all members in the k-th scheme, and the calculation method is as follows: First, calculate member satisfaction. For each member i, based on the set of welfare items {X} assigned to them... i1 X i2 ,..., }, Calculate member satisfaction:

[0063] Among them, L i P represents the number of welfare items allocated to member i. i (X ij This indicates that member i is interested in welfare program X. ij The probability of intention, value (X)ij ) represents welfare program X ij The value of.

[0064] Then calculate the overall satisfaction level of the plan, that is, calculate the average satisfaction level of all members:

[0065] Budget utilization rate (k) represents the ratio of the total value of benefits allocated to all members under the k-th option to the maximum total benefits budget:

[0066] in, This represents the welfare value allocated to member i by the k-th plan.

[0067] α is a weighting coefficient, usually between 0.7 and 0.9, which represents the importance of member satisfaction in fitness.

[0068] 3b. Select Operation: A tournament selection method is used, where t chromosomes (usually t=3 or t=5) are randomly selected from the population for comparison, and the chromosome with the highest fitness is selected to enter the mating pool. This process is repeated until the number of chromosomes in the mating pool reaches the population size P. size .

[0069] 4b. Cross operation: 4.1b. Set the crossover probability P crossover The value is usually between 0.6 and 0.9.

[0070] 4.2b. Randomly select two parent chromosomes from the mating pool and generate a random number r. c The random number is between 0 and 1.

[0071] 4.3b, if r c ≤P crossover Then, a single-point crossover is performed at a random position on the two parent chromosomes to generate two offspring chromosomes that are added to the offspring population.

[0072] 4.4b, if r c >P crossover In this case, the parent chromosome is directly copied into the daughter chromosome without crossover.

[0073] 4.5b. Repeat the crossover operation until the number of chromosomes in the offspring reaches the population size P. size .

[0074] 5b. Mutation operation: Mutation operation trigger probability P mutation1This is the probability that determines whether to perform a mutation on a chromosome, typically ranging from 0.01 to 0.1. This probability controls the proportion of chromosomes in the offspring that undergo mutation; a higher value increases population diversity but may also destroy some excellent solutions.

[0075] The proportion of mutated genes P mutation2 For chromosomes that require mutation operations, this parameter determines the proportion of mutated genes to the total number of genes on the chromosome, typically ranging from 0.01 to 0.05. This proportion controls the degree of gene alteration on each chromosome during the mutation operation. Higher values ​​result in more drastic changes but may also increase the risk of disrupting optimal solution structures.

[0076] 5.1b. Determine whether to perform mutation: For each chromosome in the offspring chromosome population output after the crossover operation, generate a random number r. m1 The random number is between 0 and 1. If r m1 ≤P mutation1 If so, then a mutation operation is performed on that chromosome.

[0077] 5.2b. Identify the mutated gene: For the chromosome that needs to be mutated, iterate through each gene and generate a random number r. m2 The random number is between 0 and 1. If r m2 ≤P mutation2 If so, then the gene will be mutated.

[0078] 5.3b. Mutating the selected gene: Gene mutation is performed using the item substitution method. The specific steps are as follows: 5.3.1b. This gene locus represents the welfare program allocated to member i. One program X is randomly selected from this locus and allocated to member i. j ; 5.3.2b, X j The project is removed from the project set already allocated to member i, and the total allocated value for member i is updated: v i =v i -Value(X) j ); 5.3.3b. Calculate the residual value space of member i: ; 5.3.4b. Select welfare projects from the pool with a value less than or equal to... Furthermore, the welfare items not allocated to member i form a subset S of optional items. i ; 5.3.5b, If S i If the result is not empty, randomly select one welfare program X. kAllocate to member i and update the total allocated value for member i: v i =v i +Value(X) k ); 5.3.6b, If S i If empty, do not mutate the gene.

[0079] 6b. Iterative Updates: 6.1b. Set the iteration termination condition: one is to reach the maximum number of iterations G. max The iteration terminates if two conditions are met: first, the conditions for convergence are satisfied; second, the conditions for convergence are satisfied.

[0080] 6.2b. Convergence Criterion Determination: When the fitness value changes by less than a certain threshold ε over multiple consecutive generations, the convergence condition can be considered met. For example, ε can be set to 10. -4 Or 10 -6 The specific value can be adjusted as needed during actual calculations. The specific determination method is as follows: 6.2.1b. Set a convergence monitoring window size W (e.g., W=5 or 10) to record the optimal fitness value of the most recent W generations; 6.2.2b. After each iteration, add the current best fitness value to the convergence monitoring window. If the window is full, remove the best fitness value of the earliest generation. 6.2.3b. Calculate the difference Δ between the maximum and minimum optimal fitness values ​​within the window. fitness ; 6.2.4b, Δ fitness If the result is less than ε, the algorithm is considered to have converged and the iteration stops; otherwise, the iteration continues.

[0081] 6.3b. Perform iterative operations: In each iteration, perform selection, crossover, and mutation operations sequentially to generate a new generation of population. Calculate the fitness value of each individual in the new generation of population, and record the chromosome with the highest fitness in the current population and its fitness value.

[0082] 6.4b. Output the optimal solution: When the maximum number of iterations G is reached... max If the convergence condition is met, the optimal solution is output, which is the welfare allocation scheme represented by the chromosome with the highest fitness currently recorded.

[0083] By using genetic algorithms for iterative optimization, balancing global search and local development, we can effectively avoid local optima and output high-quality welfare configuration schemes.

[0084] Figure 3 This is a schematic diagram of the structure of an intelligent optimized union welfare distribution decision-making device provided in an embodiment of this application, as shown below. Figure 3As shown, the system includes an acquisition module 310, a calculation module 320, a generation module 330, and an optimization module 330, wherein: Module 310 is used to acquire data related to union member benefits; The calculation module 320 is used to calculate the probability of each member choosing each welfare item based on union member welfare-related data; The generation module 330 is used to generate multiple welfare allocation schemes based on union member welfare-related data and the probability of each member's selection of each welfare item; The optimization module 340 is used to optimize and adjust multiple welfare distribution schemes according to preset optimization goals to obtain the optimal welfare distribution scheme.

[0085] Based on the methods in the above embodiments, Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown in the illustration, this application provides an electronic device that may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440. The processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions stored in the memory 430 to execute the intelligent optimized union welfare distribution decision-making method described in the above embodiment.

[0086] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the intelligent optimized union welfare distribution decision-making method described in the various embodiments of this application.

[0087] Based on the methods in the above embodiments, this application provides a computer-readable storage medium storing a computer program that, when run on a processor, causes the processor to execute the intelligent optimized union welfare distribution decision-making method in the above embodiments.

[0088] Based on the methods in the above embodiments, this application provides a computer program product that, when run on a processor, causes the processor to execute the intelligent optimized union welfare distribution decision-making method in the above embodiments.

[0089] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0090] The method steps in this application embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0091] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0092] It is understood that the various numerical designations used in the embodiments of this application are merely for the convenience of description and are not intended to limit the scope of the embodiments of this application.

[0093] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A smart and optimized decision-making method for union welfare distribution, characterized in that, include: Obtain data related to union member benefits; Based on the aforementioned union member welfare-related data, calculate the probability of each member choosing each welfare item. Based on the aforementioned union member welfare-related data and the probability of each member selecting each welfare item, multiple welfare allocation schemes are generated. The multiple welfare allocation schemes are optimized and adjusted according to the preset optimization objectives to obtain the optimal welfare allocation scheme.

2. The intelligent optimization decision-making method for union welfare distribution according to claim 1, characterized in that, After obtaining the data related to union member benefits, the method further includes: The data related to union member welfare was cleaned to remove outliers and missing values, and then normalized.

3. The intelligent optimization decision-making method for union welfare distribution according to claim 1, characterized in that, The calculation of the probability of each member choosing each welfare item based on the aforementioned union member welfare-related data includes: Based on the aforementioned union member welfare-related data, machine learning recommendation algorithms are used to analyze each member's preferences for different types of welfare programs. Combining the current characteristics of welfare programs and market trends, the probability of each member choosing each welfare program is calculated.

4. The intelligent optimized union welfare distribution decision-making method according to claim 1, characterized in that, Based on the union member welfare-related data and the probability of each member selecting each welfare item, multiple welfare allocation schemes are generated, including: Based on the union member welfare-related data and the probability of each member choosing each welfare item, multiple welfare allocation schemes are generated using the Monte Carlo simulation method.

5. The intelligent optimization decision-making method for union welfare distribution according to claim 1, characterized in that, The optimization and adjustment of the multiple welfare allocation schemes according to the preset optimization objectives includes: The multiple welfare allocation schemes are optimized and adjusted according to a preset optimization objective using a genetic algorithm.

6. A smart and optimized union welfare distribution decision-making device, characterized in that, include: The acquisition module is used to acquire data related to union member benefits; The calculation module is used to calculate the probability of each member choosing each welfare item based on the aforementioned union member welfare-related data; The generation module is used to generate multiple welfare allocation schemes based on the union member welfare-related data and the probability of each member selecting each welfare item; The optimization module is used to optimize and adjust the multiple welfare allocation schemes according to preset optimization objectives to obtain the optimal welfare allocation scheme.

7. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the intelligently optimized union welfare allocation decision-making method as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is run on a processor, the processor performs the intelligent optimized union welfare distribution decision-making method as described in any one of claims 1-5.

9. A computer program product, characterized in that, When the computer program product is run on a processor, the processor performs the intelligent optimized union welfare distribution decision-making method as described in any one of claims 1-5.

Images