Economic management data analysis device and method

Abstract

The invention provides an economic management data analysis device and method, and the method comprises the steps: obtaining original data based on an original enterprise insurance management system and a crawler engine, carrying out the preprocessing of the original data, and carrying out the investment and asset data analysis based on the preprocessing of the original data; according to the method, the Boolean's rule and the multi-objective optimization algorithm are combined, maximization of benefits of enterprises is taken as an objective function, insurance premium related data, compensation and claim settlement data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction are adopted to optimize the NSGA-II algorithm, and decision making is carried out. According to the method, the existing data are fully utilized, the relevance between the data is mined, and the insurance premium strategy and the investment strategy are optimized, so that the maximization of enterprise revenue is realized. Meanwhile, through continuous monitoring and strategy adjustment, the enterprise can adapt to the continuously changing market environment, and the competitive advantages of the enterprise are kept.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to an economic management data analysis device and method. Background Art

[0002] The financial insurance industry is an important part of the national economy, covering a variety of business areas such as banking, insurance, securities, and trust. This industry involves a large amount of data processing and complex business logic, and has high requirements for risk control and decision support. The characteristics of high business complexity, high regulatory pressure, and diversified customer needs require financial insurance institutions to use advanced data analysis technology to optimize business processes, improve risk control capabilities, optimize product design, and provide customers with more personalized services.

[0003] With the rapid development of technologies such as big data, cloud computing, and artificial intelligence, data analysis is increasingly being used in the financial and insurance industries. These technologies provide financial and insurance institutions with powerful data processing and analysis capabilities, enabling them to more deeply tap into the value of data, discover potential market trends and investment opportunities, and make more informed decisions. Summary of the invention

[0004] The purpose of the present invention is to provide an economic management data analysis device and method, which can make full use of existing data, explore the correlation between data, optimize premium strategies and investment strategies, and thus maximize the benefits of enterprises. At the same time, through continuous monitoring and adjustment of strategies, enterprises can adapt to the ever-changing market environment and maintain their competitive advantages.

[0005] To achieve the above object, the present invention provides an economic management data analysis method, comprising the following steps:

[0006] Based on the existing enterprise insurance management system and crawler engine, the original data is obtained and pre-processed. The original data includes premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction;

[0007] Analysis of investment and asset data based on pre-processing of raw data;

[0008] This application combines the Boolean rule with a multi-objective optimization algorithm to maximize the benefits of the enterprise as the objective function, and uses premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction to optimize the NSGA-II algorithm and make decisions.

[0009] Preferably, preprocessing the raw data includes:

[0010] Remove missing values, outliers or duplicate data from premium-related data, payment and claims data, and investment and asset data;

[0011] Standardize customer satisfaction and employee satisfaction data to ensure data consistency and comparability.

[0012] Preferably, K-means and hierarchical clustering algorithms are used to cluster premium-related data, payment and claims data, business scale and market share, customer satisfaction and employee satisfaction;

[0013] Determine the number of clusters to be 4, and obtain the first centroid, the second centroid, the third centroid, and the fourth centroid;

[0014] Calculate the influence factors between the centroids, which are defined based on the intrinsic relevance of the data and business logic;

[0015] Use a convolutional neural network (CNN) to adjust the distance between centroids. CNN handles complex nonlinear relationships and captures patterns in the data.

[0016] Store and analyze changes in centroid distances to reveal correlations between data.

[0017] Preferably, the investment and asset data analysis is performed based on the preprocessing of the raw data to obtain national policies and market trends using a crawler engine;

[0018] The information is re-encoded and decoded into symbol sequences and time series;

[0019] Based on the first symbol sequence and the first time series, use linear regression, time series analysis and other methods to predict the development trend of future market industries;

[0020] Establish VAR model to analyze the relationship between investment and asset data such as total investment, investment income, investment rate of return, debt-to-asset ratio, and symbolic series and time series;

[0021] By setting lag terms, the investment situation at different time nodes and lag term lengths can be analyzed.

[0022] Preferably, the NSGA-II algorithm optimization includes:

[0023] Initialize the population, where each individual represents a potential solution;

[0024] Calculate the fitness of each individual, which can be defined based on the enterprise's goal of maximizing benefits;

[0025] Use non-dominated sorting and crowding distance calculation to maintain population diversity and convergence;

[0026] Generate new individuals through operations such as selection, crossover, and mutation to form a parent population;

[0027] Apply the elite strategy to merge the parent and child generations and retain the optimal solution;

[0028] The above steps are iterated until the stopping condition is met.

[0029] Preferably, the optimal premium strategy and investment strategy are selected according to the output results of the NSGA-II algorithm;

[0030] According to the cluster analysis results, adjust the premiums, promotional activities, and marketing strategies to expand the market size and market share while ensuring the maximum benefits of the enterprise;

[0031] When the predicted investment return is lower than the set threshold, the investment and insurance ratio will be adjusted according to current national policies and market trends.

[0032] An economic management data analysis device, comprising

[0033] The data processing module is used to obtain raw data based on the original enterprise insurance management system and crawler engine, and pre-process the raw data. The raw data includes premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction;

[0034] The data analysis module is used to analyze investment and asset data based on the preprocessing of raw data;

[0035] The optimization module is used to combine the Boolean rule with the multi-objective optimization algorithm to maximize the company's benefits as the objective function, and use premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction to optimize the NSGA-II algorithm and make decisions.

[0036] A terminal device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the method when executing the computer program.

[0037] A computer-readable storage medium stores a computer program, and the steps of the method are performed when the computer program is executed by a processor.

[0038] Therefore, the present invention adopts the above-mentioned economic management data analysis device and method, and the technical effects are as follows:

[0039] Through regression forecasting, we can predict the development trend of future market industries based on historical data and provide a basis for investment decisions.

[0040] Time series analysis can capture trends, seasonality, and cyclicality in data and improve forecasting accuracy.

[0041] The vector autoregression (VAR) model can analyze the relationship between total investment, investment returns, and investment and asset data, and evaluate the effectiveness of different investment strategies.

[0042] By setting lag terms, we can analyze the investment situation at different time points and lag term lengths, and provide support for dynamic adjustment of investment strategies.

[0043] The NSGA-II algorithm can find a balance between multiple objectives and optimize multiple objectives such as premium strategy and investment strategy.

[0044] Through non-dominated sorting and crowding distance calculation, the diversity and convergence of the population are maintained to avoid falling into the local optimal solution.

[0045] The decision-making process based on data analysis is more scientific and objective, and can reduce decision-making errors caused by human factors.

[0046] By combining the cluster analysis results with the output of the NSGA-II algorithm, a strategy that is more in line with market demand and maximizes corporate benefits can be developed. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The present invention is a flow chart of an economic management data analysis device and method. DETAILED DESCRIPTION

[0048] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0049] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0050] Embodiment 1

[0051] like Figure 1 As shown, the present invention provides an economic management data analysis method, comprising the following steps:

[0052] The original data is obtained based on the existing enterprise insurance management system and crawler engine. The original data includes premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction.

[0053] Premium-related data, payment and claims data, business scale and market share can be obtained from the QiTe Insurance Management System. Among them, customer satisfaction and employee satisfaction can be comprehensively evaluated from customer satisfaction with transactions during actual transactions and crawling of relevant satisfaction content within the enterprise through crawler engines. Investment and asset data include the original assets of the enterprise and the investment situation of the enterprise in the market.

[0054] In addition, it is necessary to understand national policies and market information in order to timely evaluate market development trends and adjust investment shares.

[0055] Premium income: This is an important indicator to measure the business scale and market share of insurance companies. Premium income reflects the total amount of insurance premiums collected by insurance companies from customers and is one of the main sources of funds for insurance companies.

[0056] Premium growth rate: reflects the business growth rate of an insurance company and is an important reference for evaluating an insurance company's market expansion capabilities and sustainable business development potential.

[0057] First-year premium and renewal premium: First-year premium reflects the new output value created by a company in the current year, while renewal premium is the continuation of previous business. Together, the two reflect the business stability and customer retention rate of an insurance company.

[0058] Claims expenses: The amount of compensation paid by an insurance company to its customers due to an insurance contract directly reflects the insurance company's claims payment ability and risk management level.

[0059] Claims ratio: The ratio of claims expenditure to premium income is an important indicator to measure the risk management ability of an insurance company. The lower the claims ratio, the stronger the risk management ability of the insurance company.

[0060] Claim settlement ratio: The ratio of the number of successfully settled claims to the total number of cases, reflecting the insurance company's customer service level and claims settlement efficiency.

[0061] Total investment: The total investment of an insurance company in stocks, bonds, real estate and other fields, reflecting the insurance company's ability to use funds and investment risk preference.

[0062] Investment income: The income that insurance companies obtain through investment is one of the important sources of profit for insurance companies.

[0063] Investment return rate: The ratio of investment income to total investment amount, which measures the investment efficiency and profitability of the insurance company.

[0064] Debt-to-asset ratio: reflects the proportional relationship between an insurance company's assets and liabilities and is an important indicator for measuring the financial stability of an insurance company.

[0065] Number of insurance contracts: reflects the business scale and risk management capabilities of an insurance company. The more insurance contracts there are, the larger the business scale and the stronger the risk management capabilities of the insurance company.

[0066] The number of policies: reflects the number of customers and service level of the insurance company. The more policies, the broader the customer base of the insurance company and the higher the service level.

[0067] Market share: The share of an insurance company in a specific market or for a specific product is an important indicator to measure the competitiveness and market position of an insurance company.

[0068] Customer satisfaction: reflects the customer service level of an insurance company. The higher the customer satisfaction, the better the customer service quality of the insurance company. Customer satisfaction surveys are an important basis for insurance companies to improve services and enhance customer experience.

[0069] Employee satisfaction: reflects the level of human resource management of an insurance company. The higher the employee satisfaction, the more effective the insurance company's human resource management is and the higher the employee morale is, which is beneficial to the business development and long-term stability of the insurance company.

[0070] Clean and de-noise the acquired customer behavior data and historical sales data, and return the cleaned and de-noised initial data;

[0071] Pre-process the acquired premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction:

[0072] (1) First, cluster analysis is performed on premium-related data, compensation and claims data, business scale and market share, customer satisfaction and employee satisfaction to obtain the first centroid, the second centroid, the third centroid and the fourth centroid. Then, the influencing factors between the first centroid, the second centroid, the third centroid and the fourth centroid are selected, and the distances between the first centroid, the second centroid, the third centroid and the fourth centroid are adjusted according to the influencing factors. During the adjustment process, a quantitative value can be selected according to demand, and other centroids are used as momentum. The quantitative selection can be the first centroid, the second centroid, the third centroid and the fourth centroid, or the area formed by the first centroid, the second centroid, the third centroid and the fourth centroid. During the adjustment process, a convolutional neural network (CNN) is used for adjustment. The distance changes between the first centroid, the second centroid, the third centroid and the fourth centroid are counted and stored during each adjustment process. The distance changes between the first centroid, the second centroid, the third centroid and the fourth centroid are analyzed to obtain the correlation between premium-related data, compensation and claims data, business scale and market share, customer satisfaction and employee satisfaction.

[0073] (2) Investment and asset data include total investment, investment income, investment rate of return, and debt-to-asset ratio

[0074] When analyzing investment and asset data, it is also necessary to use crawler engines to obtain information such as national policies and market trends that have been made public, convert this information into the first symbol sequence and the first time series through secondary encoding and decoding, and use regression prediction methods to predict based on the first symbol sequence and the first time series to obtain the development trend of the future market industry;

[0075] Likewise, the investment and asset data are re-encoded and decoded to convert into a second symbol sequence and a second time series.

[0076] A vector autoregression (VAR) model is established using the first time series and the second time series, and a symbol node in the first symbol sequence and the second symbol sequence is randomly selected as a lag term. The lengths of multiple lag terms are set with the event node in the first symbol sequence as the center to analyze the investment nodes in the second symbol sequence, and the investment situation results of different lag term lengths at different time nodes are analyzed. Through the analysis results, it is known that the investment benefit can be maximized at the appropriate investment node, which provides a reference for future investment.

[0077] (3) In addition, a regression forecast analysis is performed based on the second time series and the second symbol series to predict the future investment direction based on the current national policies and market trends. When the predicted investment benefit is lower than the set threshold, the investment and insurance ratio is adjusted.

[0078] The insurance adjustment plan can be adjusted according to the analysis results in step (1), specifically:

[0079] Premium-related data, payment and claims data, business scale and market share, customer satisfaction and employee satisfaction are closely related. Expanding the insurance market scale and market share while ensuring the maximum benefits of the company can be achieved through adjusting premiums, related promotional activities and personalized customization. However, the settings of premiums, related promotional activities, marketing and personalized customization can be achieved through the joint efforts of existing market facts and relevant analysis results.

[0080] This application combines the Boolean rule with a multi-objective optimization algorithm to maximize the benefits of the enterprise as the objective function, and uses premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction to optimize the NSGA-II (Non-dominated Sorting Genetic Algorithm II, fast elite non-dominated sorting genetic algorithm II) algorithm:

[0081] Initialize the population: Randomly generate an initial population containing multiple individuals, each of which represents a potential solution.

[0082] Calculate fitness: For each individual, calculate its fitness in the objective function space. The calculation of fitness can be determined according to the specific problem, and generally use evaluation indicators (such as distance, quality, etc.) to indicate the quality of the individual.

[0083] Non-dominated sorting: NSGA-II uses a non-dominated sorting technique to divide the individuals in the population into multiple fronts (or levels). This sorting process determines the non-dominated level of each individual to identify which individuals occupy different positions on the Pareto front. Individuals at higher levels are not dominated by individuals at lower levels.

[0084] Crowding distance calculation: In order to maintain the diversity of the Pareto front, NSGA-II calculates the crowding distance to measure the density of individuals in the target space. The larger the crowding distance, the farther the distance between individuals, which helps to maintain a uniform distribution on the Pareto front.

[0085] Selection operation: NSGA-II uses a binary tournament as the selection operation. In each generation, two individuals are first randomly selected from the current population using the binary tournament selection operation, and then the individual with the higher non-dominated level is selected. If the non-dominated levels of two individuals are the same, the individual with the larger crowding distance is selected.

[0086] Crossover / mutation operation: The selected individuals are used to generate new individuals through crossover and mutation operations to form the parent population.

[0087] Elite strategy: merge the parent and child generations into a larger candidate population. In this way, the optimal solution is usually part of the current population and is not easily missed in the selection operation.

[0088] Iteration: Re-perform non-dominated sorting, crowding distance calculation, selection, crossover, and mutation on the candidate population to generate a new offspring population. Iterate the above steps until the stopping condition is met (such as reaching the maximum number of iterations or converging to a satisfactory Pareto frontier solution).

[0089] Finally, we get a solution that maximizes the enterprise.

[0090] A terminal device is provided in one embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0091] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0092] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0093] The processor may be a central processing unit (CPU), a graphics processing unit (GPU), or other general-purpose processors.

[0094] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0095] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0096] Therefore, the present invention adopts the above-mentioned economic management data analysis device and method to make full use of existing data, explore the correlation between data, optimize premium strategies and investment strategies, and thus maximize the benefits of enterprises. At the same time, through continuous monitoring and adjustment of strategies, enterprises can adapt to the ever-changing market environment and maintain their competitive advantages.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for analyzing economic management data, characterized in that: The following steps are involved: Based on the existing enterprise insurance management system and crawler engine, the original data is obtained and pre-processed. The original data includes premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction; Analysis of investment and asset data based on pre-processing of raw data; The Boolean rule is combined with the multi-objective optimization algorithm to maximize the benefits of the enterprise as the objective function. The premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction are used to optimize the NSGA-II algorithm and make decisions.

2. The economic management data analysis method according to claim 1, characterized in that: Preprocessing of raw data includes: Remove missing values, outliers or duplicate data from premium-related data, payment and claims data, and investment and asset data; Standardize customer satisfaction and employee satisfaction data to ensure data consistency and comparability.

3. The economic management data analysis method according to claim 1, characterized in that: Use K-means and hierarchical clustering algorithms to cluster premium-related data, payment and claims data, business scale and market share, customer satisfaction and employee satisfaction; Determine the number of clusters to be 4, and obtain the first centroid, the second centroid, the third centroid, and the fourth centroid; Calculate the influence factors between the centroids, which are defined based on the intrinsic relevance of the data and business logic; Use a convolutional neural network (CNN) to adjust the distance between centroids. CNN handles complex nonlinear relationships and captures patterns in the data. Store and analyze changes in centroid distances to reveal correlations between data.

4. The economic management data analysis method according to claim 1, characterized in that: Analysis of investment and asset data based on pre-processing of raw data Use crawler engines to obtain national policies and market trends; The information is re-encoded and decoded into symbol sequences and time series; Based on the first symbol sequence and the first time series, use linear regression, time series analysis and other methods to predict the development trend of future market industries; Establish VAR model to analyze the relationship between investment and asset data such as total investment, investment income, investment rate of return, debt-to-asset ratio, and symbolic series and time series; By setting lag terms, the investment situation at different time nodes and lag term lengths can be analyzed.

5. The economic management data analysis method according to claim 1, characterized in that: Optimizations to the NSGA-II algorithm include: Initialize the population, where each individual represents a potential solution; Calculate the fitness of each individual, which can be defined based on the enterprise's goal of maximizing benefits; Use non-dominated sorting and crowding distance calculation to maintain population diversity and convergence; Generate new individuals through operations such as selection, crossover, and mutation to form a parent population; Apply the elite strategy to merge the parent and child generations and retain the optimal solution; The above steps are iterated until the stopping condition is met.

6. The economic management data analysis method according to claim 1, characterized in that: According to the output results of the NSGA-II algorithm, select the optimal premium strategy and investment strategy; According to the cluster analysis results, adjust the premiums, promotional activities, and marketing strategies to expand the market size and market share while ensuring the maximum benefits of the enterprise; When the predicted investment return is lower than the set threshold, the investment and insurance ratio will be adjusted according to current national policies and market trends.

7. An economic management data analysis device, characterized in that: include The data processing module is used to obtain raw data based on the original enterprise insurance management system and crawler engine, and pre-process the raw data. The raw data includes premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction; The data analysis module is used to analyze investment and asset data based on the preprocessing of raw data; The optimization module is used to combine the Boolean rule with the multi-objective optimization algorithm to maximize the company's benefits as the objective function, and use premium-related data, payment and claims data, investment and asset data, business scale and market share, customer satisfaction and employee satisfaction to optimize the NSGA-II algorithm and make decisions.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images