Asset screening and management method and system based on automation rule

Abstract

The invention discloses an asset screening and management method and system based on an automation rule. Value evaluation and resource management are performed on an asset management project by using a Monte Carlo simulation algorithm. The method comprises the following steps: firstly, acquiring asset management list data and historical data, performing value evaluation on the historical data by adopting Monte Carlo simulation, and acquiring a resource consumption condition; the management difficulty is evaluated according to the resource load, if the load is too high, a value influence probability distribution model is constructed, and the influence weight of historical data features on the asset value is determined; and establishing a value path simulation decision tree, determining simulation times according to tolerance, performing simulation analysis on each asset management project, and finally generating an asset screening and management strategy. The asset management decision making efficiency and accuracy can be improved, resource allocation is optimized, and the method has high practical value and popularization prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of asset management, and in particular to an asset screening and management method and system based on automated rules. Background Art

[0002] In modern asset management, the accuracy and efficiency of asset screening and management decisions play a vital role in improving asset allocation and risk control. To this end, the Monte Carlo simulation algorithm, as a powerful numerical calculation tool, has been widely used in asset valuation, risk assessment, and decision-making optimization. The Monte Carlo algorithm generates a probability distribution of asset value by performing multiple random simulations on the historical data of asset management projects, and optimizes asset management strategies based on this.

[0003] However, the Monte Carlo simulation algorithm faces the problem of excessive resource consumption when performing path simulation. Since Monte Carlo simulation requires a large number of computational iterations to generate simulation paths and calculate valuations, its consumption of computing resources (such as CPU, memory, network bandwidth, etc.) is extremely significant. In traditional asset management systems, especially when the scale of managed assets is large and the historical data is complex, Monte Carlo simulation may require tens of thousands of simulation paths and simulation times, resulting in reduced system performance, low computational efficiency, and even computational interruptions or delays when resources are limited.

[0004] At present, although some studies have tried to reduce resource consumption by reducing the number of simulation paths or simplifying simulation models, these methods often sacrifice the precision and accuracy of the simulation. Especially in the complex environment of asset management, how to optimize resource consumption while ensuring simulation accuracy is still a technical problem that needs to be solved urgently.

[0005] Therefore, how to effectively optimize the resource consumption in the Monte Carlo simulation process, especially in determining the simulation path and the number of simulations, has become a key issue in improving the performance of the asset management system. By rationally optimizing the simulation path and the number of simulations, the demand for computing resources can be significantly reduced, the efficiency of asset screening and management can be improved, and high-precision asset evaluation results can be maintained. This is also the core problem to be solved by the present invention. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes an asset screening and management method and system based on automated rules.

[0007] The first aspect of the present invention provides an asset screening and management method based on automated rules, comprising:

[0008] Obtain asset management list data, obtain historical data of each asset management project based on the asset management list data, introduce a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtain resource consumption data during the value assessment process;

[0009] Evaluate the resource load of the asset management list based on the resource consumption data; if the resource load is greater than a preset value, obtain data features of historical data and construct a value impact probability distribution model;

[0010] Determine the value impact weights of historical data features on asset management projects according to the value impact probability distribution model, construct a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm, analyze the decision tree according to the value impact weights, and determine several simulation paths for valuing asset management projects using a Monte Carlo simulation algorithm;

[0011] Obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance;

[0012] The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project. The asset management projects are screened and managed based on the value path simulation to obtain an asset management strategy.

[0013] In this solution, the asset management list data is obtained, and the historical data of each asset management project is obtained according to the asset management list data. The Monte Carlo simulation algorithm is introduced to evaluate the value of the historical data of each asset management project, and the resource consumption data in the value evaluation process is obtained, specifically:

[0014] Acquire asset management list data of the target asset management system, and acquire historical data of each asset management project according to the asset management list data, wherein the historical data includes asset value data, loan data, borrower credit data, early repayment data, default and recovery rate data;

[0015] Introducing a Monte Carlo simulation algorithm, importing the Monte Carlo simulation algorithm into the target asset management system, and continuously updating the historical data, performing calculations based on the historical data continuously updated by the Monte Carlo simulation algorithm, and continuously conducting real-time value evaluation on each asset management project in the asset management project list data;

[0016] Obtaining the call status data of historical data in the process of the Monte Carlo simulation algorithm in the target asset management system performing value assessment on the asset management project, obtaining the call timestamp of each data item in the historical data by the Monte Carlo simulation algorithm according to the call status data, and constructing a data access path according to the call timestamp;

[0017] Perform statistics on the data access path, determine the initial price simulation path and the initial number of simulations in the process of the Monte Carlo simulation algorithm performing value assessment on the asset management project, and obtain the single resource consumption of a single initial price simulation path of the Monte Carlo simulation algorithm for a single simulation;

[0018] The resource consumption data of the Monte Carlo simulation algorithm in the process of value assessment of each asset management project is determined based on the single resource consumption situation. The resource consumption data includes CPU usage, memory occupancy, database interaction frequency, and network bandwidth occupancy.

[0019] In this solution, the resource load of the asset management list is evaluated according to the resource consumption data. If the resource load is greater than the preset value, the data features of the historical data are obtained to construct a value impact probability distribution model, specifically:

[0020] Obtaining operation load weight information of each resource consumption data on the target asset management system according to the resource consumption data, performing resource load evaluation on the resource consumption data according to the operation load weight information, and obtaining the resource load of the target asset management system for managing the asset management list;

[0021] Compare the resource load with a preset value. If the resource load is greater than the preset value, construct a data matrix with the historical data, standardize the data matrix, calculate the covariance matrix of the standardized data matrix, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues ​​and eigenvectors.

[0022] Sort the eigenvalues ​​from large to small, select the eigenvectors corresponding to the first k eigenvalues ​​to construct a projection matrix, and multiply the standardized data matrix by the projection matrix to obtain data features of the historical data;

[0023] Calculating the mean and variance of each data feature according to the historical data, and constructing a probability density function of the data feature according to the mean and variance;

[0024] A probability distribution model of the impact of each data feature on the asset value is constructed based on the probability density function.

[0025] In this solution, the weight of the value impact of historical data features on the asset management project is determined according to the value impact probability distribution model, and a value simulation path decision tree for the asset management project valuation using the Monte Carlo simulation algorithm is constructed. The decision tree is analyzed according to the value impact weight to determine several simulation paths for the asset management project valuation using the Monte Carlo simulation algorithm, specifically:

[0026] Integrating the probability density function of each data feature according to the value impact probability distribution model to calculate the probability value of each data feature at different values;

[0027] Calculate the conditional entropy of each data feature based on the Bayesian formula, calculate the value probability value and the conditional entropy based on the information entropy weight method, obtain the information entropy of each data feature, determine the information gain of each data feature based on the information entropy, and determine the value impact weight of each historical data feature on the asset management project based on the information gain;

[0028] Constructing a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm based on the initial price simulation path, limiting the impact weight of each node in the decision tree based on the value impact weight, and calculating the comprehensive weight information of each branch path of the decision tree after the impact weight is limited;

[0029] Calculating the Euclidean distance between each branch path in the decision tree based on the K-means clustering algorithm, evaluating the similarity between the branch paths according to the Euclidean distance, and performing a clustering operation on each branch path according to the similarity to obtain a clustering result;

[0030] According to the comprehensive weight information, the branch path with the highest comprehensive weight of each clustering result is taken as the preferred value simulation path, and several simulation paths for valuing the asset management project using the Monte Carlo simulation algorithm are determined according to the preferred value simulation path.

[0031] In this solution, the tolerance of the target asset management system to the accuracy of asset value assessment is obtained, and the number of simulations of the simulation path by the Monte Carlo simulation algorithm is determined according to the tolerance, specifically:

[0032] Determine the impact of each historical data feature on the price fluctuation of the asset management project according to the weight of the impact of the historical data feature on the value of the asset management project, and obtain the risk impact data of the price fluctuation impact on asset management;

[0033] Determine the target asset management system's tolerance for the accuracy of asset value assessment based on the risk impact data;

[0034] Obtaining the relationship data of the simulation number of the simulation path of the Monte Carlo simulation algorithm and the value assessment accuracy, and constructing a simulation number-simulation accuracy relationship model according to the relationship data;

[0035] The tolerance is introduced into the simulation number-simulation accuracy relationship model to determine the number of simulations of the simulation path by the Monte Carlo simulation algorithm under the tolerance of the current target asset management system to the accuracy of asset value assessment.

[0036] In this solution, the simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to simulate the value path of each asset management project, and the asset management projects are screened and managed according to the value path simulation to obtain an asset management strategy, which is specifically:

[0037] The simulation path and the number of simulations are used as the automated optimization rules of the Monte Carlo simulation algorithm to perform a value path simulation operation on each asset management project, and output the asset value probability distribution of each asset management project;

[0038] Obtaining expected return and risk level control data of asset management projects, and using the expected return and risk level control data as screening conditions;

[0039] Extracting an asset value simulation sequence according to the asset value probability distribution, calculating the mean value and standard deviation of the asset value simulation sequence, and determining the value change trend and risk change trend of the asset management project according to the mean value and standard deviation;

[0040] Compare the value change trend and risk change trend with the screening conditions, and output the asset management projects that meet the screening conditions within a preset time period and mark them as preferred asset management projects;

[0041] Asset management is performed according to the preferred asset management project, wherein the asset management includes buying, selling, and adjusting asset ratio configuration to obtain an asset management strategy.

[0042] The second aspect of the present invention further provides an asset screening and management system based on automated rules, the system comprising: a memory, a processor, the memory comprising an asset screening and management method program based on automated rules, and when the asset screening and management method program based on automated rules is executed by the processor, the following steps are implemented:

[0043] Obtain asset management list data, obtain historical data of each asset management project based on the asset management list data, introduce a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtain resource consumption data during the value assessment process;

[0044] Evaluate the resource load of the asset management list based on the resource consumption data; if the resource load is greater than a preset value, obtain data features of historical data and construct a value impact probability distribution model;

[0045] Determine the value impact weights of historical data features on asset management projects according to the value impact probability distribution model, construct a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm, analyze the decision tree according to the value impact weights, and determine several simulation paths for valuing asset management projects using a Monte Carlo simulation algorithm;

[0046] Obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance;

[0047] The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project. The asset management projects are screened and managed based on the value path simulation to obtain an asset management strategy.

[0048] The present invention discloses an asset screening and management method and system based on automated rules, which uses a Monte Carlo simulation algorithm to perform value assessment and resource management on asset management projects. The method first obtains asset management list data and historical data, uses Monte Carlo simulation to perform value assessment on historical data, and obtains resource consumption. The management difficulty is assessed according to the resource load. If the load is too high, a value impact probability distribution model is constructed, and the impact weight of historical data characteristics on asset value is determined. By constructing a value path simulation decision tree and determining the number of simulations according to tolerance, each asset management project is simulated and analyzed, and finally an asset screening and management strategy is generated. The present invention can improve the efficiency and accuracy of asset management decisions, optimize resource allocation, and has high practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of an asset screening and management method based on automated rules of the present invention is shown;

[0050] Figure 2 A flow chart showing the construction of a value impact probability distribution model according to the present invention is shown;

[0051] Figure 3 A flow chart of determining the number of simulations for a simulation path according to the present invention is shown;

[0052] Figure 4 A block diagram of an automated rule-based asset screening and management system of the present invention is shown. DETAILED DESCRIPTION

[0053] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0055] Figure 1 A flow chart of an asset screening and management method based on automated rules of the present invention is shown.

[0056] like Figure 1 As shown, the first aspect of the present invention provides an asset screening and management method based on automated rules, comprising:

[0057] S102, obtaining asset management list data, obtaining historical data of each asset management project according to the asset management list data, introducing a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtaining resource consumption data during the value assessment process;

[0058] S104, evaluating the resource load of the asset management list according to the resource consumption data, and if the resource load is greater than a preset value, obtaining data features of historical data and constructing a value impact probability distribution model;

[0059] S106, determining the value impact weight of the historical data characteristics on the asset management project according to the value impact probability distribution model, constructing a value simulation path decision tree for the asset management project valuation using the Monte Carlo simulation algorithm, analyzing the decision tree according to the value impact weight, and determining several simulation paths for the asset management project valuation using the Monte Carlo simulation algorithm;

[0060] S108, obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance;

[0061] S110, using the simulation path and the number of simulations as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project, screening and managing the asset management projects according to the value path simulation, and obtaining an asset management strategy.

[0062] It should be noted that since the target asset management system needs to continuously value and monitor each asset management project based on the accumulated historical data of each asset management project, and the Monte Carlo simulation algorithm will greatly consume system resources during the value assessment process, the historical data of the asset management project of the target asset management system is valued through the Monte Carlo simulation algorithm, and the resource consumption data is obtained in real time, and the resource load in the asset management process is monitored and evaluated in real time. When the resource load is too high, the data features of the historical data are extracted, and the impact of different data features on the asset value assessment can be analyzed by constructing a value simulation path decision tree, analyzing the decision tree according to the value impact weight, and selecting several simulation paths for the Monte Carlo simulation algorithm to value the asset management project. Monte Carlo simulation usually requires a lot of computing resources, especially when the number of simulation paths and the number of simulations are large, the system burden will increase sharply. By selecting an appropriate simulation path, the computational complexity can be effectively controlled, unnecessary computation can be reduced, and the consumption of system resources can be optimized. It can avoid repeated calculations of unimportant or redundant paths; in the asset evaluation process, the more simulations, the higher the accuracy of the calculation results, but it will also be accompanied by an increase in resource consumption. By dynamically adjusting the number of simulations according to the system's tolerance (i.e., the requirement for evaluation accuracy), an optimal balance can be achieved between accuracy and efficiency. For example, when the evaluation tolerance is high, the number of simulations can be appropriately reduced to save computing resources; when the accuracy requirement is high, the number of simulations can be increased to improve the accuracy of the simulation results. This flexible adjustment mechanism helps ensure that the asset management system can operate efficiently and stably in different environments; ultimately, the Monte Carlo simulation algorithm values ​​and manages asset management projects based on the optimized value simulation path and number of simulations, which can effectively reduce the load on the asset management system and avoid performance bottlenecks or crashes in the system due to excessive consumption of computing resources. When conducting large-scale asset management, the system can dynamically adjust simulation parameters according to the load conditions to ensure that the system always operates within a reasonable load range, thereby improving the stability and responsiveness of the system.

[0063] According to an embodiment of the present invention, the asset management list data is obtained, the historical data of each asset management project is obtained according to the asset management list data, a Monte Carlo simulation algorithm is introduced to perform value assessment on the historical data of each asset management project, and resource consumption data in the value assessment process is obtained, specifically:

[0064] Acquire asset management list data of the target asset management system, and acquire historical data of each asset management project according to the asset management list data, wherein the historical data includes asset value data, loan data, borrower credit data, early repayment data, default and recovery rate data;

[0065] Introducing a Monte Carlo simulation algorithm, importing the Monte Carlo simulation algorithm into the target asset management system, and continuously updating the historical data, performing calculations based on the historical data continuously updated by the Monte Carlo simulation algorithm, and continuously conducting real-time value evaluation on each asset management project in the asset management project list data;

[0066] Obtaining the call status data of historical data in the process of the Monte Carlo simulation algorithm in the target asset management system performing value assessment on the asset management project, obtaining the call timestamp of each data item in the historical data by the Monte Carlo simulation algorithm according to the call status data, and constructing a data access path according to the call timestamp;

[0067] Perform statistics on the data access path, determine the initial price simulation path and the initial number of simulations in the process of the Monte Carlo simulation algorithm performing value assessment on the asset management project, and obtain the single resource consumption of a single initial price simulation path of the Monte Carlo simulation algorithm for a single simulation;

[0068] The resource consumption data of the Monte Carlo simulation algorithm in the process of value assessment of each asset management project is determined based on the single resource consumption situation. The resource consumption data includes CPU usage, memory occupancy, database interaction frequency, and network bandwidth occupancy.

[0069] It should be noted that the asset management project data is an ABS asset pool, including housing mortgages, auto loans, credit card receivables, rental rents, etc. These underlying assets will generate a series of cash flows. For example, in residential mortgage-backed securities (RMBS), the asset pool is composed of many personal housing mortgages. The principal and interest repaid by the borrower each month constitute the cash flow of the asset pool. The loan data includes the loan amount, loan term, repayment method, interest rate type and interest rate level; the borrower credit data includes credit score, debt-to-income ratio, credit history, including the number of overdue times and overdue duration; the early repayment data includes early repayment rate; the default and recovery rate data includes historical data on default probability, historical data on default rate, and recovery rate data. The simulation path is to use the Monte Carlo simulation algorithm to perform a large number of random sampling simulation calculations. In each simulation, the estimated value of the asset management project in the corresponding scenario is calculated based on the randomly generated variable values ​​and the preset asset value evaluation model (such as the cash flow discount model, etc.). After multiple simulations (usually thousands or even tens of thousands of times), a series of value estimates are obtained, thereby constructing the probability distribution of the value of the asset management project, and then determining its value assessment results (such as mean, median, confidence interval, etc.). Determine the initial price through the data access path. The simulation path is the Monte Carlo simulation algorithm. When performing the asset management project value assessment, different data items in the historical data (such as asset value data, loan data, borrower credit data, etc.) will be called multiple times, and multiple simulation calculations will be performed based on the changes in these data items. By tracking and recording the access to historical data, the call timestamps and access order of the data items in each simulation process can be obtained, and then the data access path can be constructed.

[0070] Figure 2 A flow chart of constructing a value impact probability distribution model according to the present invention is shown.

[0071] According to an embodiment of the present invention, the resource load of the asset management list is evaluated according to the resource consumption data. If the resource load is greater than a preset value, the data features of the historical data are obtained and a value impact probability distribution model is constructed, specifically:

[0072] S202, obtaining operation load weight information of each resource consumption data on the target asset management system according to the resource consumption data, performing resource load evaluation on the resource consumption data according to the operation load weight information, and obtaining the resource load of the target asset management system for managing the asset management list;

[0073] S204, comparing the resource load with a preset value, if the resource load is greater than the preset value, constructing a data matrix with the historical data, standardizing the data matrix, calculating the covariance matrix of the standardized data matrix, and performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0074] S206, sorting the eigenvalues ​​from large to small, selecting the eigenvectors corresponding to the first k eigenvalues ​​to construct a projection matrix, and multiplying the standardized data matrix by the projection matrix to obtain data features of the historical data;

[0075] S208, calculating the mean and variance of each data feature according to the historical data, and constructing a probability density function of the data feature according to the mean and variance;

[0076] S210, constructing a probability distribution model of the impact of each data feature on the asset value according to the probability density function.

[0077] It should be noted that in asset management systems, historical data often contains a large number of variables and dimensions. Direct calculations on these data may lead to high computational complexity and excessive resource consumption. Through feature extraction, especially through methods such as eigenvalue decomposition and principal component analysis (PCA), high-dimensional data can be reduced in dimension, the core features that have the greatest impact on asset value can be extracted, and the data structure can be simplified. By calculating the mean and variance of historical data features, the probability density function (PDF) of each data feature can be constructed to achieve quantitative analysis of asset value fluctuations. First, the mean represents the central tendency of the data, and the variance measures the fluctuation range of the data. Based on these two statistics, the distribution of data features can be inferred, and it is usually assumed that these features conform to the normal distribution. The probability density function of the normal distribution is determined by the mean and variance, and the probability of occurrence of a certain feature value can be calculated through this function. In asset management, these probability density functions can help quantify the range of changes in asset value and then evaluate the risk and return potential of assets. Through this method, each data feature (such as asset value, loan default rate, etc.) can be converted into a probability model. In a multi-feature scenario, the mean and variance of each feature can be calculated separately, and multiple independent probability density functions can be constructed. These functions can be integrated through the Bayesian formula to form a value impact probability distribution model of asset value. This model can not only accurately describe the impact of each data feature on the asset value, thereby improving the efficiency and accuracy of asset management, but also reducing uncertainty and risk in decision-making. The shape of the data matrix is ​​m*n, where m is the number of samples and n is the number of features; the standardization process makes each feature have the same scale to avoid the impact of different feature dimensions on subsequent analysis.

[0078] According to an embodiment of the present invention, the value impact weight of the historical data feature on the asset management project is determined according to the value impact probability distribution model, and a value simulation path decision tree for valuing the asset management project using the Monte Carlo simulation algorithm is constructed. The decision tree is analyzed according to the value impact weight to determine several simulation paths for valuing the asset management project using the Monte Carlo simulation algorithm, specifically:

[0079] Integrating the probability density function of each data feature according to the value impact probability distribution model to calculate the probability value of each data feature at different values;

[0080] Calculate the conditional entropy of each data feature based on the Bayesian formula, calculate the value probability value and the conditional entropy based on the information entropy weight method, obtain the information entropy of each data feature, determine the information gain of each data feature based on the information entropy, and determine the value impact weight of each historical data feature on the asset management project based on the information gain;

[0081] Constructing a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm based on the initial price simulation path, limiting the impact weight of each node in the decision tree based on the value impact weight, and calculating the comprehensive weight information of each branch path of the decision tree after the impact weight is limited;

[0082] Calculating the Euclidean distance between each branch path in the decision tree based on the K-means clustering algorithm, evaluating the similarity between the branch paths according to the Euclidean distance, and performing a clustering operation on each branch path according to the similarity to obtain a clustering result;

[0083] According to the comprehensive weight information, the branch path with the highest comprehensive weight of each clustering result is taken as the preferred value simulation path, and several simulation paths for valuing the asset management project using the Monte Carlo simulation algorithm are determined according to the preferred value simulation path.

[0084] It should be noted that by taking the branch path with the highest comprehensive weight of each clustering result as the preferred value simulation path according to the comprehensive weight information, the efficiency and accuracy of the Monte Carlo simulation algorithm in the valuation process of asset management projects can be significantly improved. First, the K-means clustering algorithm is used to cluster the branch paths in the decision tree, evaluate the similarity between the paths, and classify the paths with higher similarity into one category. This clustering process can effectively reduce unnecessary calculations, and reduce redundant calculations in the simulation process by aggregating multiple similar paths into a group. Then, according to the comprehensive weight of each clustering result, the path with the highest weight is selected as the preferred simulation path. In this way, the system can focus on the most valuable simulation paths and avoid calculating those paths with less impact or redundant paths, thereby improving calculation efficiency and ensuring more accurate simulation results. Finally, these preferred simulation paths are the valuation simulation paths of asset management projects, which greatly reduces the system resource consumption of the target asset management system for calculating a large number of simulation paths.

[0085] Figure 3 A flow chart of determining the number of simulations of a simulation path according to the present invention is shown.

[0086] According to an embodiment of the present invention, the tolerance of the target asset management system to the accuracy of asset value assessment is obtained, and the number of simulations of the simulation path by the Monte Carlo simulation algorithm is determined according to the tolerance, specifically:

[0087] S302, determining the influence degree of each historical data feature on the price fluctuation of the asset management project according to the weight of the influence of the historical data feature on the value of the asset management project, and obtaining the risk influence data of the influence degree of price fluctuation on asset management;

[0088] S304, determining the tolerance of the target asset management system to the accuracy of asset value assessment according to the risk impact data;

[0089] S306, obtaining the relationship data between the simulation times of the simulation path and the value assessment accuracy of the Monte Carlo simulation algorithm, and constructing a simulation times-simulation accuracy relationship model according to the relationship data;

[0090] S308, importing the tolerance into the simulation times-simulation accuracy relationship model to determine the simulation times of the simulation path by the Monte Carlo simulation algorithm under the tolerance of the current target asset management system to the accuracy of asset value assessment.

[0091] It should be noted that by determining the number of simulations of the Monte Carlo simulation algorithm according to the tolerance of the target asset management system to the accuracy of asset value assessment, the relationship between computing resource consumption and assessment accuracy can be effectively balanced. First, according to the weight of the impact of historical data features on asset value, the degree of influence of each data feature on price fluctuations is determined, and further data on the impact of these fluctuations on asset management risks are obtained. These data are helpful in assessing the risk level of asset management projects, thereby determining the accuracy tolerance that the system can accept in asset value assessment. Next, a relationship model between the number of simulations and simulation accuracy is constructed to quantify the impact of the number of simulations on the accuracy of the assessment results. By inputting tolerance information into the relationship model, the system can automatically adjust the number of simulations to ensure that the use of computing resources is optimized within the limited accuracy range. In this way, by reasonably determining the number of simulations, the accuracy of asset value assessment can be guaranteed, and the waste of resources caused by excessive calculation can be avoided, which improves the computing efficiency and resource utilization of the system and ensures the accuracy of asset management decisions. The higher the impact of price fluctuations on the risk of asset management, the lower the tolerance of the target asset management system to the accuracy of asset value assessment. Conversely, the lower the risk impact, the higher the tolerance of the target asset management system to the accuracy of asset value assessment.

[0092] According to an embodiment of the present invention, the simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project, and the asset management projects are screened and managed according to the value path simulation to obtain an asset management strategy, which is specifically:

[0093] The simulation path and the number of simulations are used as the automated optimization rules of the Monte Carlo simulation algorithm to perform a value path simulation operation on each asset management project, and output the asset value probability distribution of each asset management project;

[0094] Obtaining expected return and risk level control data of asset management projects, and using the expected return and risk level control data as screening conditions;

[0095] Extracting an asset value simulation sequence according to the asset value probability distribution, calculating the mean value and standard deviation of the asset value simulation sequence, and determining the value change trend and risk change trend of the asset management project according to the mean value and standard deviation;

[0096] Compare the value change trend and risk change trend with the screening conditions, and output the asset management projects that meet the screening conditions within a preset time period and mark them as preferred asset management projects;

[0097] Asset management is performed according to the preferred asset management project, wherein the asset management includes buying, selling, and adjusting asset ratio configuration to obtain an asset management strategy.

[0098] It should be noted that by using the simulation path and the number of simulations as the automated optimization rules of the Monte Carlo simulation algorithm, the accuracy and efficiency of asset management decisions can be greatly improved. In each asset management project, the system outputs the probability distribution of asset value through value path simulation, thereby providing a quantitative basis for subsequent decisions. Combined with the expected returns and risk control data of the asset management project, the system can extract the asset value simulation sequence based on probability distribution analysis and calculate its average and standard deviation. These statistical indicators help to determine the value change trend and risk change trend of the asset, and provide scientific risk assessment and return forecasting for asset management. By comparing these trends with the preset screening conditions, the system can screen out qualified preferred asset management projects within a predetermined time period to ensure that the selected projects achieve the best balance between returns and risks. Finally, the system performs specific operations such as buying, selling or adjusting asset allocation according to the preferred asset management projects to form an optimized asset management strategy. This process can improve the accuracy of asset management, reduce the uncertainty in manual decision-making, and at the same time improve the efficiency and economic benefits of overall asset management through automated optimization and resource allocation. The asset value simulation sequence is a series of prediction results on the future value of assets generated by the Monte Carlo simulation algorithm. It reflects the possible change paths of asset value under different scenarios under given initial conditions. These paths are generated through random sampling and simulation based on historical data, market conditions, asset characteristics, etc. Each simulated path represents a possible future situation, and the collection of all simulated paths constitutes the overall picture of asset value.

[0099] According to an embodiment of the present invention, it also includes:

[0100] Construct a resource consumption monitoring data interface and a data interaction interface of the target asset management system, and obtain real-time resource consumption data and incremental information of historical data of the target system in real time according to the resource consumption monitoring data interface and the data interaction interface;

[0101] Determine the data transmission packet loss rate and data transmission delay of the target resource management system based on the real-time resource consumption data, and determine the data damage of the target asset management system receiving historical data based on the data transmission packet loss rate, data transmission delay and the incremental information;

[0102] Constructing a data buffer of the target resource management system. If the damage to the historical data received by the target asset management system is greater than a preset damage level, the historical data received in real time is imported into the data buffer for temporary storage to construct temporary data;

[0103] According to the resource consumption monitoring data interface and the data interaction interface, real-time monitoring is performed on the data damage of the historical data received by the target asset management system. When the data damage is less than the preset damage degree, the transmission priority of the temporary data is determined according to the acquisition time of the temporary data;

[0104] The temporary data is transmitted and analyzed according to the priority.

[0105] It should be noted that with the high frequency of financial market transactions and the explosive growth of data volume, the target asset management system faces many challenges in processing large amounts of historical data and interacting with real-time data. For example, network fluctuations may cause packet loss and delays in the data transmission process, which will not only affect the integrity of historical data, but also may cause deviations in the value assessment process such as the Monte Carlo simulation algorithm based on these data, thereby misleading asset screening and management decisions. By constructing the resource consumption monitoring data interface and data interaction interface of the target asset management system, it is possible to obtain the real-time resource consumption data of the system and the incremental information of historical data in real time, so as to accurately judge the packet loss rate and delay of data transmission, and then determine the degree of damage to the reception of historical data. When the damage is greater than the preset damage level, the historical data received in real time is imported into the data buffer to construct temporary data, avoiding direct discarding or incorrect use of these data due to data damage, and ensuring the integrity backup of the data. At the same time, through continuous monitoring, when the data damage situation improves, the transmission priority of the temporary data is determined according to the acquisition time of the temporary data, and the data with strong timeliness and greater impact on the current asset value assessment is processed first, thereby ensuring the timeliness and accuracy of the historical data used by the Monte Carlo simulation algorithm, and effectively improving the reliability of asset screening and management strategies.

[0106] Figure 4 A block diagram of an automated rule-based asset screening and management system of the present invention is shown.

[0107] The second aspect of the present invention further provides an asset screening and management system 4 based on automated rules, the system comprising: a memory 41, a processor 42, the memory comprising an asset screening and management method program based on automated rules, the asset screening and management method program based on automated rules being executed by the processor to implement the following steps:

[0108] Obtain asset management list data, obtain historical data of each asset management project based on the asset management list data, introduce a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtain resource consumption data during the value assessment process;

[0109] Evaluate the resource load of the asset management list based on the resource consumption data; if the resource load is greater than a preset value, obtain data features of historical data and construct a value impact probability distribution model;

[0110] Determine the value impact weights of historical data features on asset management projects according to the value impact probability distribution model, construct a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm, analyze the decision tree according to the value impact weights, and determine several simulation paths for valuing asset management projects using a Monte Carlo simulation algorithm;

[0111] Obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance;

[0112] The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project. The asset management projects are screened and managed based on the value path simulation to obtain an asset management strategy.

[0113] The present invention discloses an asset screening and management method and system based on automated rules, which uses a Monte Carlo simulation algorithm to perform value assessment and resource management on asset management projects. The method first obtains asset management list data and historical data, uses Monte Carlo simulation to perform value assessment on historical data, and obtains resource consumption. The management difficulty is assessed according to the resource load. If the load is too high, a value impact probability distribution model is constructed, and the impact weight of historical data characteristics on asset value is determined. By constructing a value path simulation decision tree and determining the number of simulations according to tolerance, each asset management project is simulated and analyzed, and finally an asset screening and management strategy is generated. The present invention can improve the efficiency and accuracy of asset management decisions, optimize resource allocation, and has high practical value and promotion prospects.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0115] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0116] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0117] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0118] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0119] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An asset screening and management method based on automated rules, characterized in that: The following steps are involved: Obtain asset management list data, obtain historical data of each asset management project based on the asset management list data, introduce a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtain resource consumption data during the value assessment process; Evaluate the resource load of the asset management list based on the resource consumption data; if the resource load is greater than a preset value, obtain data features of historical data and construct a value impact probability distribution model; Determine the value impact weights of historical data features on asset management projects according to the value impact probability distribution model, construct a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm, analyze the decision tree according to the value impact weights, and determine several simulation paths for valuing asset management projects using a Monte Carlo simulation algorithm; Obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance; The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project. The asset management projects are screened and managed based on the value path simulation to obtain an asset management strategy.

2. The method for asset screening and management based on automated rules according to claim 1, characterized in that: The asset management list data is obtained, and the historical data of each asset management project is obtained according to the asset management list data, and the Monte Carlo simulation algorithm is introduced to perform value assessment on the historical data of each asset management project, and the resource consumption data in the value assessment process is obtained, specifically: Acquire asset management list data of the target asset management system, and acquire historical data of each asset management project according to the asset management list data, wherein the historical data includes asset value data, loan data, borrower credit data, early repayment data, default and recovery rate data; Introducing a Monte Carlo simulation algorithm, importing the Monte Carlo simulation algorithm into the target asset management system, and continuously updating the historical data, performing calculations based on the historical data continuously updated by the Monte Carlo simulation algorithm, and continuously conducting real-time value evaluation on each asset management project in the asset management project list data; Obtain the call status data of historical data in the process of the Monte Carlo simulation algorithm in the target asset management system performing value assessment on the asset management project, obtain the call timestamp of each data item in the historical data by the Monte Carlo simulation algorithm according to the call status data, and construct a data access path according to the call timestamp; Perform statistics on the data access path, determine the initial price simulation path and the initial number of simulations in the process of the Monte Carlo simulation algorithm performing value assessment on the asset management project, and obtain the single resource consumption of a single initial price simulation path of the Monte Carlo simulation algorithm for a single simulation; The resource consumption data of the Monte Carlo simulation algorithm in the process of value assessment of each asset management project is determined based on the single resource consumption situation. The resource consumption data includes CPU usage, memory occupancy, database interaction frequency, and network bandwidth occupancy.

3. The asset screening and management method based on automated rules according to claim 1, characterized in that: The resource load of the asset management list is evaluated according to the resource consumption data. If the resource load is greater than a preset value, the data features of the historical data are obtained to construct a value impact probability distribution model, specifically: Obtaining operation load weight information of each resource consumption data on the target asset management system according to the resource consumption data, performing resource load evaluation on the resource consumption data according to the operation load weight information, and obtaining the resource load of the target asset management system for managing the asset management list; Compare the resource load with a preset value. If the resource load is greater than the preset value, construct a data matrix with the historical data, standardize the data matrix, calculate the covariance matrix of the standardized data matrix, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues ​​and eigenvectors. Sort the eigenvalues ​​from large to small, select the eigenvectors corresponding to the first k eigenvalues ​​to construct a projection matrix, and multiply the standardized data matrix by the projection matrix to obtain data features of the historical data; Calculating the mean and variance of each data feature according to the historical data, and constructing a probability density function of the data feature according to the mean and variance; A probability distribution model of the impact of each data feature on the asset value is constructed based on the probability density function.

4. The asset screening and management method based on automated rules according to claim 1, characterized in that: The value impact weights of historical data features on asset management projects are determined according to the value impact probability distribution model, a value simulation path decision tree for asset management project valuation using a Monte Carlo simulation algorithm is constructed, and the decision tree is analyzed according to the value impact weights to determine several simulation paths for asset management project valuation using a Monte Carlo simulation algorithm, specifically: Integrating the probability density function of each data feature according to the value impact probability distribution model to calculate the probability value of each data feature at different values; Calculate the conditional entropy of each data feature based on the Bayesian formula, calculate the value probability value and the conditional entropy based on the information entropy weight method, obtain the information entropy of each data feature, determine the information gain of each data feature based on the information entropy, and determine the value impact weight of each historical data feature on the asset management project based on the information gain; Constructing a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm based on the initial price simulation path, limiting the impact weight of each node in the decision tree based on the value impact weight, and calculating the comprehensive weight information of each branch path of the decision tree after the impact weight is limited; Calculating the Euclidean distance between each branch path in the decision tree based on the K-means clustering algorithm, evaluating the similarity between the branch paths according to the Euclidean distance, and performing a clustering operation on each branch path according to the similarity to obtain a clustering result; According to the comprehensive weight information, the branch path with the highest comprehensive weight of each clustering result is taken as the preferred value simulation path, and several simulation paths for valuing the asset management project using the Monte Carlo simulation algorithm are determined according to the preferred value simulation path.

5. The asset screening and management method based on automated rules according to claim 1, characterized in that: The method of obtaining the tolerance of the target asset management system to the accuracy of asset value assessment and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance is specifically as follows: Determine the impact of each historical data feature on the price fluctuation of the asset management project according to the weight of the impact of the historical data feature on the value of the asset management project, and obtain the risk impact data of the price fluctuation impact on asset management; Determine the target asset management system's tolerance for the accuracy of asset value assessment based on the risk impact data; Obtaining the relationship data of the simulation number of the simulation path of the Monte Carlo simulation algorithm and the value assessment accuracy, and constructing a simulation number-simulation accuracy relationship model according to the relationship data; The tolerance is introduced into the simulation number-simulation accuracy relationship model to determine the number of simulations of the simulation path by the Monte Carlo simulation algorithm under the tolerance of the current target asset management system to the accuracy of asset value assessment.

6. The asset screening and management method based on automated rules according to claim 1, characterized in that: The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project, and the asset management projects are screened and managed according to the value path simulation to obtain an asset management strategy, which is specifically: The simulation path and the number of simulations are used as the automated optimization rules of the Monte Carlo simulation algorithm to perform a value path simulation operation on each asset management project, and output the asset value probability distribution of each asset management project; Obtaining expected return and risk level control data of asset management projects, and using the expected return and risk level control data as screening conditions; Extracting an asset value simulation sequence according to the asset value probability distribution, calculating the mean value and standard deviation of the asset value simulation sequence, and determining the value change trend and risk change trend of the asset management project according to the mean value and standard deviation; Compare the value change trend and risk change trend with the screening conditions, and output the asset management projects that meet the screening conditions within a preset time period and mark them as preferred asset management projects; Asset management is performed according to the preferred asset management project, wherein the asset management includes buying, selling, and adjusting asset ratio configuration to obtain an asset management strategy.

7. An asset screening and management system based on automated rules, characterized in that: The automated rule-based asset screening and management system includes a storage device and a processor. The storage device includes an automated rule-based asset screening and management method program. When the automated rule-based asset screening and management method program is executed by the processor, the following steps are implemented: Obtain asset management list data, obtain historical data of each asset management project based on the asset management list data, introduce a Monte Carlo simulation algorithm to perform value assessment on the historical data of each asset management project, and obtain resource consumption data during the value assessment process; Evaluate the resource load of the asset management list based on the resource consumption data; if the resource load is greater than a preset value, obtain data features of historical data and construct a value impact probability distribution model; Determine the value impact weights of historical data features on asset management projects according to the value impact probability distribution model, construct a value simulation path decision tree for valuing asset management projects using a Monte Carlo simulation algorithm, analyze the decision tree according to the value impact weights, and determine several simulation paths for valuing asset management projects using a Monte Carlo simulation algorithm; Obtaining the tolerance of the target asset management system to the accuracy of asset value assessment, and determining the number of simulations of the simulation path by the Monte Carlo simulation algorithm according to the tolerance; The simulation path and the number of simulations are used as simulation parameters of the Monte Carlo simulation algorithm to perform value path simulation on each asset management project. The asset management projects are screened and managed based on the value path simulation to obtain an asset management strategy.

Images