Enterprise optimal debt period configuration method, system, device and program product

Abstract

The invention discloses an enterprise optimal debt deadline configuration method, system, device and program product, and belongs to the technical field of enterprise financial management. Market environment data and strategic planning data are introduced into enterprise debt deadline configuration by obtaining multi-type enterprise debt data, and enterprise optimal debt deadline configuration is realized. The influence of a single data source on enterprise debt deadline configuration is avoided, meanwhile, a dynamic interest rate prediction model is utilized, a multi-deadline yield curve is integrated, dynamic interest rate prediction is achieved, strategic adaptation of cash flow is achieved through a strategic adaptation type cash flow prediction model, and the accuracy of enterprise debt deadline configuration is improved. The matching degree of the enterprise debt deadline configuration scheme to the market environment and the enterprise development strategy planning is greatly improved, so that the configuration of the enterprise debt deadline can have multi-industry adaptability and is more reasonably suitable for actual enterprises; and through the debt configuration linear programming model, an optimal debt deadline configuration scheme for the enterprise can be efficiently and accurately generated.

Description

Technical Field

[0001] This invention belongs to the field of enterprise financial management technology, specifically relating to a method, system, equipment, and program product for configuring the optimal debt maturity of an enterprise. Background Technology

[0002] Optimizing the debt maturity structure is a core issue in corporate financial management, especially for large, asset-heavy, long-cycle enterprises (such as those in the power, infrastructure, and energy sectors). The allocation of debt maturity is crucial to funding costs, liquidity security, and the smooth implementation of major strategic projects. Currently, mainstream debt maturity allocation techniques in the industry primarily utilize traditional capital structure theories and rely mainly on two methods: first, subjective judgment and decision-making based on the experience of financial managers; and second, analysis using general quantitative models (e.g., using the ARIMA model for univariate time series forecasting of market interest rates) or traditional linear regression methods to predict cash flows based on historical financial data. While these existing methods can provide some reference for corporate debt maturity decisions, with the increasing complexity of the market environment and the deepening of refined corporate management, they often rely on a single, lagging interest rate data source when addressing the actual needs of asset-heavy, long-cycle enterprises. They fail to effectively integrate multi-dimensional market environment data, such as yield curves across multiple maturities, yields to maturity of corporate bonds with different credit ratings, and direct discount rates for bills reflecting short-term funding supply and demand. This narrowness of data sources prevents existing methods from accurately capturing the dynamic changes in interest rate and credit cycles, leading to a disconnect between corporate debt decisions and the market. This has led to companies potentially relying excessively on short-term debt rollover financing during economic upturns and rising interest rates, forcing them to bear ever-increasing refinancing costs; or, during downturns, excessively allocating long-term debt due to future uncertainties, resulting in a large amount of low-cost funds being idle, asset returns being diluted, and the scale of interest-bearing liabilities growing irrationally.

[0003] Furthermore, existing methods for allocating corporate debt maturities lack industry adaptability. Asset-heavy industries such as power and rail transportation exhibit distinct operational characteristics, including significant seasonal cash flows (peak electricity revenue from summer cooling and winter heating) and regular, large, fixed expenditures (such as power grid companies paying substantial electricity purchase fees on fixed dates each month and concentrated fixed asset investments at mid-year and year-end). However, existing cash flow forecasting models in these methods primarily use generic models and fail to embed these specific variables as core factors, resulting in smoothed cash flow curves that significantly deviate from the actual financial situation of the companies.

[0004] As mentioned above, how to provide a method, system, equipment, and program product for optimizing corporate debt maturity that can improve the matching degree between corporate debt maturity allocation schemes and corporate strategic development plans, and has multi-industry adaptability, has become an urgent problem to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, device, and program product for configuring the optimal debt term for an enterprise, in order to solve the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for configuring the optimal debt maturity for an enterprise, comprising: The process involves acquiring raw corporate debt data, classifying and storing the raw corporate debt data to obtain multiple types of raw corporate debt data, and then cleaning and standardizing the multiple types of raw corporate debt data to obtain multiple types of corporate debt data, including corporate operation data, strategic planning data, and market environment data. Acquire historical debt data of various types of enterprises, construct a dynamic interest rate forecasting model and a strategically adapted cash flow forecasting model based on the historical debt data of various types of enterprises, and use the debt data of various types of enterprises as the input of the dynamic interest rate forecasting model and the strategically adapted cash flow forecasting model. The dynamic interest rate forecasting model outputs the interest rate forecast value at the target time, and the strategically adapted cash flow forecasting model outputs the cash flow forecast value at the target time. A preset debt allocation linear programming model is obtained. The predicted interest rate and the predicted cash flow at the target time are input into the debt allocation linear programming model to solve the debt allocation plan and output the optimal debt allocation scheme for the enterprise. The debt allocation linear programming model takes minimizing the comprehensive financing cost as the objective function. The optimal debt allocation scheme for the enterprise includes the financing term and the comprehensive financing interest rate at the target time.

[0007] In one possible design, raw corporate debt data is acquired, and the raw corporate debt data undergoes data cleaning and standardization to obtain corporate debt data. This corporate debt data is then categorized and stored to form multiple types of corporate debt data, including: Multiple types of original internal corporate debt data are collected through various data interfaces of the corporate financial database, and original external market environment data are collected through external data interfaces. The original internal corporate debt data and the original external market environment data are time-aligned, and the time-aligned original internal corporate debt data and the original external market environment data are integrated into original corporate debt data. The original internal corporate debt data includes original corporate operation data and original strategic planning data. Based on each data interface, the original corporate debt data is classified and processed to obtain multiple types of original corporate debt data; The forward imputation method is used to fill missing values ​​in the original corporate debt data of the various types, and outliers in the original corporate debt data of the various types are removed based on the 3σ principle to obtain pre-corporate debt data of various types. Obtain a preset data format standard to standardize the data format of the multi-type pre-corporate debt data, and use the multi-type pre-corporate debt data that has been standardized as multi-type corporate debt data.

[0008] In one possible design, historical debt data for various types of enterprises is acquired, and a dynamic interest rate forecasting model and a strategically adapted cash flow forecasting model are constructed based on this historical debt data, including: Historical raw corporate debt data is acquired, classified and stored to obtain historical multi-type raw corporate debt data, and the historical multi-type raw corporate debt data is cleaned and standardized to obtain historical multi-type corporate debt data, wherein the historical multi-type corporate debt data includes historical corporate operation data, historical strategic planning data and historical market environment data; Using the DNSS model as the first base model, a state model is established based on the state equation in the Kalman filter algorithm. The first base model is then embedded into the state model to build an initial dynamic interest rate prediction model. Historical enterprise operation data is extracted from the historical multi-type enterprise debt data, and the historical enterprise operation data is integrated into a first pre-training dataset; The first pre-training dataset is input into the initial dynamic interest rate prediction model. The interest rate prediction values ​​at each selected time and for each selected debt term are used as outputs to update the parameters of the interest rate prediction algorithm of the initial dynamic interest rate prediction model in order to train the dynamic interest rate prediction model. The Prophet model is used as the second base model, and strategic variables are introduced into the second base model to form an initial strategic-adaptive cash flow forecasting model. Historical strategic planning data and historical market environment data are extracted from the historical multi-type corporate debt data, and the historical strategic planning data and historical market environment data are integrated into a second pre-training dataset. The second pre-trained dataset is input into the initial strategic-adaptive cash flow forecasting model, and the cash flow forecast values ​​at each selected time point are used as outputs to update the parameters of the cash flow forecasting algorithm of the initial strategic-adaptive cash flow forecasting model in order to train the strategic-adaptive cash flow forecasting model.

[0009] In one possible design, the interest rate prediction algorithm of the dynamic interest rate prediction model is expressed by the following formula (1): (1) in, Indicates at the selected time The debt term is Interest rate forecasts Indicates at the selected time interest rate level, Indicates at the selected time The rate of change in short-term interest rates, Indicates at the selected time The medium-term interest rate curvature, Indicates at the selected time Additional interest rate curvature, This is the parameter for the curvature decay of the medium-term interest rate. For additional interest rate curvature decay parameters, is the base of the natural logarithm; The cash flow forecasting algorithm of the strategically adapted cash flow forecasting model is expressed by the following formula (2): (2) in, Indicates at the selected time Cash flow forecasts Indicates about the selected time The cash flow trend change function, Indicates about the selected time The seasonal cyclical variation function of cash flow. Indicates about the selected time The cash flow holiday variation function, Represents the matrix of corporate strategic variables. This represents the regression coefficient of the corporate strategy variable. This is the error term for the normal distribution.

[0010] In one possible design, the multi-type corporate debt data is used as input to the dynamic interest rate forecasting model and the strategically adapted cash flow forecasting model. The dynamic interest rate forecasting model outputs the interest rate forecast at the target time, and the strategically adapted cash flow forecasting model outputs the cash flow forecast at the target time, including: A preset target time is obtained, and the enterprise operation data in the multi-type enterprise debt data is used as input to the dynamic interest rate prediction model so as to calculate the enterprise's interest rate prediction value for each financing period at the target time through the dynamic interest rate prediction model. The strategic planning data and market environment data from the various types of corporate debt data are used as inputs to the strategic-adaptive cash flow forecasting model, so as to calculate the cash flow forecast value at the target time.

[0011] In one possible design, the pre-defined method for the debt allocation linear programming model includes: Taking the minimization of the overall corporate financing interest rate as the debt allocation objective, the debt allocation objective function is constructed using the following formula (3). : (3) in, Total number of financing transactions for enterprises Indicates the first Corporate financing, Indicates the first The principal amount of corporate financing, For the first The annualized interest rate for corporate financing. For the first The financing term for this corporate financing. For the company's overall financing interest rate, This represents the minimum value operation; Obtain the preset fixed constraints for debt allocation, based on the debt allocation objective function. A linear programming model for debt allocation is constructed based on the fixed constraints of the debt allocation, wherein the fixed constraints of the debt allocation include maturity matching constraints, maturity diversification constraints, and market timing constraints.

[0012] In one possible design, the predicted interest rate and the predicted cash flow at the target time are input into the debt allocation linear programming model to solve for the debt allocation plan, thereby outputting the optimal debt allocation scheme for the enterprise, including: Based on the cash flow forecasts at the target time, the company's projected total financing needs and projected net cash flow are calculated. Based on the enterprise's projected total financing needs, a total financing constraint is formed. Based on the projected net cash flow, a cash flow matching constraint is formed. The total financing constraint and the cash flow matching constraint are used as dynamic constraints for debt allocation and input into the debt allocation linear programming model to update the debt allocation linear programming model. Based on the interest rate forecast at the target time, multiple candidate corporate financing schemes are generated, wherein each candidate corporate financing scheme includes an interest rate forecast and a financing product term; Each of the candidate enterprise financing schemes is input into the updated debt allocation linear programming model, so as to use the debt allocation linear programming model to calculate the comprehensive financing interest rate of each of the candidate enterprise financing schemes respectively; Using the debt allocation objective function in the aforementioned debt allocation linear programming model The candidate corporate financing scheme with the lowest comprehensive corporate financing interest rate among all the candidate corporate financing schemes is selected as the optimal debt allocation scheme.

[0013] Secondly, the present invention provides a system for configuring the optimal debt maturity for an enterprise, comprising: The corporate debt data acquisition unit is used to acquire raw corporate debt data, classify and store the raw corporate debt data to obtain multiple types of raw corporate debt data, and perform data cleaning and standardization processing on the multiple types of raw corporate debt data to obtain multiple types of corporate debt data, wherein the multiple types of corporate debt data include corporate operation data, strategic planning data and market environment data; The prediction model building and running unit is used to acquire historical debt data of various types of enterprises, construct a dynamic interest rate prediction model and a strategically adapted cash flow prediction model based on the historical debt data of various types of enterprises, and use the debt data of various types of enterprises as the input of the dynamic interest rate prediction model and the strategically adapted cash flow prediction model. The dynamic interest rate prediction model outputs the interest rate prediction value at the target time, and the strategically adapted cash flow prediction model outputs the cash flow prediction value at the target time. The optimal debt allocation scheme generation unit is used to obtain a preset debt allocation linear programming model, input the predicted interest rate and the predicted cash flow at the target time into the debt allocation linear programming model, perform debt allocation planning and solution, and output the optimal debt allocation scheme for the enterprise. The debt allocation linear programming model takes minimizing the comprehensive financing cost as the objective function, and the optimal debt allocation scheme for the enterprise includes the financing term and the comprehensive financing interest rate at the target time.

[0014] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the configuration method for the optimal debt term of an enterprise as described in the first aspect or any possible design of the first aspect.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the configuration method for the optimal debt term of an enterprise as described in the first aspect or any possible design of the first aspect.

[0016] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform a configuration method for the optimal debt maturity of an enterprise as described in the first aspect or any possible design of the first aspect.

[0017] Beneficial Effects: This invention provides a method for configuring the optimal debt maturity for enterprises, including: First, acquiring raw enterprise debt data, classifying and storing the raw enterprise debt data to obtain multiple types of raw enterprise debt data, and performing data cleaning and standardization on the multiple types of raw enterprise debt data to obtain multiple types of enterprise debt data, wherein the multiple types of enterprise debt data include enterprise operation data, strategic planning data, and market environment data; Second, acquiring historical multiple types of enterprise debt data, constructing a dynamic interest rate prediction model and a strategically adapted cash flow prediction model based on the historical multiple types of enterprise debt data, and using the multiple types of enterprise debt data as the basis for the configuration. The inputs to the dynamic interest rate forecasting model and the strategically adapted cash flow forecasting model are used to output the target time's interest rate forecast value through the dynamic interest rate forecasting model and the target time's cash flow forecast value through the strategically adapted cash flow forecasting model. Finally, a preset debt allocation linear programming model is obtained, and the target time's interest rate forecast value and cash flow forecast value are input into the debt allocation linear programming model to solve the debt allocation planning problem, so as to output the optimal debt allocation scheme for the enterprise. The debt allocation linear programming model uses minimizing the comprehensive financing cost as the objective function, and the optimal debt allocation scheme for the enterprise includes the financing term and the comprehensive financing interest rate for the enterprise at the target time. By acquiring debt data from multiple types of enterprises, market environment data and strategic planning data are incorporated into the allocation of corporate debt maturities, avoiding the influence of a single data source on debt maturity allocation. Simultaneously, a dynamic interest rate forecasting model integrates yield curves from multiple maturities, enabling dynamic interest rate forecasting. A strategically adapted cash flow forecasting model achieves strategic adaptation of cash flow, significantly improving the matching degree of corporate debt maturity allocation schemes with the market environment and corporate development strategic planning. This makes the allocation of corporate debt maturities adaptable to multiple industries and more rationally applicable to actual enterprises. Furthermore, a linear programming model for debt allocation can efficiently and accurately generate the optimal debt maturity allocation scheme for enterprises. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the method for configuring the optimal debt maturity for an enterprise, as provided in an embodiment of the present invention; Figure 2 A functional structure diagram of the enterprise optimal debt maturity configuration system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0020] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0021] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0022] Example: like Figure 1 As shown, the first aspect of this embodiment provides a method for configuring the optimal debt maturity for an enterprise, which may include, but is not limited to, the following steps: S1. Obtain raw corporate debt data, classify and store the raw corporate debt data to obtain multiple types of raw corporate debt data, and perform data cleaning and standardization processing on the multiple types of raw corporate debt data to obtain multiple types of corporate debt data, wherein the multiple types of corporate debt data include corporate operation data, strategic planning data and market environment data; In one possible implementation, step S1 involves acquiring raw corporate debt data, cleaning and standardizing the raw corporate debt data to obtain corporate debt data, and classifying and storing the corporate debt data to form multi-type corporate debt data. This can be broken down into steps S11-S14, specifically including: S11. Collect various types of original internal corporate debt data through multiple data interfaces of the corporate financial database, collect original external market environment data through external data interfaces, perform time alignment on the original internal corporate debt data and the original external market environment data, and integrate the time-aligned original internal corporate debt data and the original external market environment data into original corporate debt data, wherein the original internal corporate debt data includes original corporate operation data and original strategic planning data; S12. Based on each data interface, the original corporate debt data is classified to obtain multiple types of original corporate debt data; S13. The missing values ​​of the original corporate debt data of the multiple types are filled by the forward filling method, and the outliers in the original corporate debt data of the multiple types are removed based on the 3σ principle to obtain the pre-corporate debt data of the multiple types. S14. Obtain a preset data format standard, and perform data format standardization processing on the multi-type pre-corporate debt data through the data format standard, and use the multi-type pre-corporate debt data that has been processed by data format standardization as multi-type corporate debt data.

[0023] It should be noted that the method for configuring the optimal debt term for enterprises provided in this embodiment ensures the reliability of the prediction and optimization results by systematically integrating three-dimensional data of operations, strategy, and market. In particular, industry-specific variables (such as peak electricity revenue days and electricity purchase expenditure days) are introduced for market environment data, so that the input information of the subsequent model can truly reflect the real and complex operating scenarios of enterprises in various industries. This overcomes the impact of a single data source on debt term configuration, making the generated configuration scheme meet the actual needs of enterprises in various industries, and laying a comprehensive, structured, and high-quality data foundation for the subsequent prediction model.

[0024] Specifically, the classification and processing of raw corporate debt data is achieved by using data interfaces that collect data from different sources.

[0025] S2. Obtain historical debt data of various types of enterprises, construct a dynamic interest rate prediction model and a strategically adapted cash flow prediction model based on the historical debt data of various types of enterprises, and use the debt data of various types of enterprises as the input of the dynamic interest rate prediction model and the strategically adapted cash flow prediction model. Output the interest rate prediction value at the target time through the dynamic interest rate prediction model, and output the cash flow prediction value at the target time through the strategically adapted cash flow prediction model. In one possible implementation, step S2 involves acquiring historical multi-type corporate debt data and constructing a dynamic interest rate forecasting model and a strategically adapted cash flow forecasting model based on the historical multi-type corporate debt data. This can be broken down into, but is not limited to, the following steps S21-S2, specifically including: S21. Obtain historical original corporate debt data, classify and store the historical original corporate debt data to obtain historical multi-type original corporate debt data, and perform data cleaning and standardization processing on the historical multi-type original corporate debt data to obtain historical multi-type corporate debt data, wherein the historical multi-type corporate debt data includes historical corporate operation data, historical strategic planning data and historical market environment data; S22. Using the DNSS model as the first base model, a state model is established based on the state equation in the Kalman filter algorithm, and the first base model is embedded into the state model to build an initial dynamic interest rate prediction model. S23. Extract historical enterprise operation data from the historical multi-type enterprise debt data, and integrate the historical enterprise operation data into a first pre-training dataset; S24. Input the first pre-training dataset into the initial dynamic interest rate prediction model, and use the interest rate prediction values ​​at each selected time and selected debt maturity as outputs to update the parameters of the interest rate prediction algorithm of the initial dynamic interest rate prediction model in order to train the dynamic interest rate prediction model. S25. Use the Prophet model as the second base model and introduce strategic variables into the second base model to form an initial strategic-adaptive cash flow forecasting model; S26. Extract historical strategic planning data and historical market environment data from the historical multi-type corporate debt data, and integrate the historical strategic planning data and the historical market environment data into a second pre-training dataset; S27. Input the second pre-trained dataset into the initial strategic-adaptive cash flow forecasting model, use the cash flow forecast values ​​at each selected time as the output, update the parameters of the cash flow forecasting algorithm of the initial strategic-adaptive cash flow forecasting model, and train the strategic-adaptive cash flow forecasting model.

[0026] In one possible implementation, in step S24, the interest rate prediction algorithm of the dynamic interest rate prediction model is expressed by the following formula (1): (1) in, Indicates at the selected time The debt term is Interest rate forecasts Indicates at the selected time interest rate level, Indicates at the selected time The rate of change in short-term interest rates, Indicates at the selected time The medium-term interest rate curvature, Indicates at the selected time Additional interest rate curvature, This is the parameter for the curvature decay of the medium-term interest rate. For additional interest rate curvature decay parameters, is the base of the natural logarithm; In step S27, the cash flow forecasting algorithm of the strategically adapted cash flow forecasting model is expressed by the following formula (2): (2) in, Indicates at the selected time Cash flow forecasts Indicates about the selected time The cash flow trend change function, Indicates about the selected time The seasonal cyclical variation function of cash flow. Indicates about the selected time The cash flow holiday variation function, Represents the matrix of corporate strategic variables. This represents the regression coefficient of the corporate strategy variable. This is the error term for the normal distribution.

[0027] In one possible implementation, step S2, using the multi-type corporate debt data as input to the dynamic interest rate forecasting model and the strategically adapted cash flow forecasting model, outputting the target time's interest rate forecast value through the dynamic interest rate forecasting model, and outputting the target time's cash flow forecast value through the strategically adapted cash flow forecasting model, can be decomposed into, but is not limited to, the following steps S28-S29, specifically including: S28. Obtain a preset target time, and input the enterprise operation data in the multi-type enterprise debt data as input to the dynamic interest rate prediction model, so as to calculate the enterprise's interest rate prediction value for each financing period at the target time through the dynamic interest rate prediction model; S29. The strategic planning data and market environment data from the multi-type corporate debt data are used as inputs to the strategic-adaptive cash flow forecasting model, so as to calculate the cash flow forecast value at the target time through the strategic-adaptive cash flow forecasting model.

[0028] It should be noted that the dynamic interest rate forecasting model described in this embodiment is an interest rate forecasting model capable of dynamic parameter calibration, built upon the DNSS model (Dynamic Nelson-Siegel-Svensson model) combined with the Kalman filter algorithm. This DNSS model flexibly fits the yield curve shape, and the Kalman filter absorbs the latest market information in real time to dynamically calibrate parameters, enabling the model to keenly capture interest rate inflection points. Its output interest rate forecast is essentially a multi-term annualized interest rate forecast for enterprises, providing a precise basis for subsequent debt allocation decisions. This ensures that the optimal debt maturity allocation plan helps enterprises lock in long-term, low-cost funds when interest rates are low. This dynamic forecasting achieves a forward-looking, multi-term market cycle response to market interest rates.

[0029] Accordingly, the strategically adapted cash flow forecasting model described in this embodiment incorporates industry seasonal cyclical changes, holiday variations, and strategic investment variables into the Prophet model, enabling the predicted cash flow forecasts to accurately reflect the company's actual revenue and expenditure situation and trends. This allows for the calculation of a precise funding gap (i.e., the company's predicted total financing needs), providing a crucial and dynamic total financing constraint for subsequent corporate debt allocation. This ensures that the debt maturity allocation plan matches industry cash flow changes and corporate strategic planning.

[0030] Specifically, when pre-training a dynamic interest rate forecasting model, it is necessary to use historical data in "days" for pre-training; when training a strategically adapted cash flow forecasting model, it is necessary to add a large amount of enterprise-specific event data (such as industry cycle change data).

[0031] S3. Obtain a preset debt allocation linear programming model, input the predicted interest rate and the predicted cash flow at the target time into the debt allocation linear programming model, perform debt allocation planning and solve, and output the optimal debt allocation scheme for the enterprise. The debt allocation linear programming model takes minimizing the comprehensive financing cost as the objective function, and the optimal debt allocation scheme for the enterprise includes the financing term and the comprehensive financing interest rate at the target time.

[0032] In one possible implementation, the preset method for the debt allocation linear programming model in step S3 may include, but is not limited to, the following steps S301-S302, specifically: S301. Taking the minimization of the overall corporate financing interest rate as the debt allocation objective, the debt allocation objective function is constructed using the following formula (3). : (3) in, Total number of financing transactions for enterprises Indicates the first Corporate financing, Indicates the first The principal amount of corporate financing, For the first The annualized interest rate for corporate financing. For the first The financing term for this corporate financing. For the company's overall financing interest rate, This represents the minimum value operation; S302. Obtain preset fixed constraints on debt allocation, based on the debt allocation objective function. A linear programming model for debt allocation is constructed based on the fixed constraints of the debt allocation, wherein the fixed constraints of the debt allocation include maturity matching constraints, maturity diversification constraints, and market timing constraints.

[0033] In one possible implementation, step S3 involves inputting the predicted interest rate and the predicted cash flow at the target time into the debt allocation linear programming model to solve for the debt allocation plan and output the optimal debt allocation scheme for the enterprise. This can be decomposed into, but is not limited to, the following steps S31-S3, specifically including: S31. Based on the cash flow forecast at the target time, calculate the company's projected total financing needs and projected net cash flow; S32. Based on the enterprise's predicted total financing needs, a total financing constraint is formed, and based on the predicted net cash flow, a cash flow matching constraint is formed. The total financing constraint and the cash flow matching constraint are used as dynamic constraints for debt allocation and input into the debt allocation linear programming model to update the debt allocation linear programming model. S33. Based on the interest rate forecast at the target time, generate multiple candidate corporate financing schemes, wherein each candidate corporate financing scheme includes an interest rate forecast and a financing product term; S34. Input each of the candidate enterprise financing schemes into the updated debt allocation linear programming model, so as to use the debt allocation linear programming model to calculate the comprehensive financing interest rate of each of the candidate enterprise financing schemes respectively; S35. Utilize the debt allocation objective function in the aforementioned linear programming model for debt allocation. The candidate corporate financing scheme with the lowest comprehensive corporate financing interest rate among all the candidate corporate financing schemes is selected as the optimal debt allocation scheme.

[0034] It should be noted that the optimal debt maturity allocation method provided in this embodiment uses the company's predicted total financing needs and predicted net cash flow as dynamic constraints for debt allocation, establishing a dynamic linear programming model for debt allocation. Using the predicted interest rate values, multiple candidate corporate financing schemes are generated as inputs to the linear programming model. This accurately identifies the debt allocation scheme group with the lowest overall financing cost. This realizes the execution process from data analysis to executable decision-making, significantly improving decision-making efficiency. Furthermore, through the clearly defined objectives and boundary constraints in the linear programming model for debt allocation, accurate selection of corporate debt maturity allocation schemes is achieved.

[0035] like Figure 2 As shown, the second aspect of this embodiment provides a hardware system for implementing the configuration method for the optimal debt maturity of an enterprise as described in the first aspect of the embodiment, including: The corporate debt data acquisition unit is used to acquire raw corporate debt data, classify and store the raw corporate debt data to obtain multiple types of raw corporate debt data, and perform data cleaning and standardization processing on the multiple types of raw corporate debt data to obtain multiple types of corporate debt data, wherein the multiple types of corporate debt data include corporate operation data, strategic planning data and market environment data; The prediction model building and running unit is used to acquire historical debt data of various types of enterprises, construct a dynamic interest rate prediction model and a strategically adapted cash flow prediction model based on the historical debt data of various types of enterprises, and use the debt data of various types of enterprises as the input of the dynamic interest rate prediction model and the strategically adapted cash flow prediction model. The dynamic interest rate prediction model outputs the interest rate prediction value at the target time, and the strategically adapted cash flow prediction model outputs the cash flow prediction value at the target time. The optimal debt allocation scheme generation unit is used to obtain a preset debt allocation linear programming model, input the predicted interest rate and the predicted cash flow at the target time into the debt allocation linear programming model, perform debt allocation planning and solution, and output the optimal debt allocation scheme for the enterprise. The debt allocation linear programming model takes minimizing the comprehensive financing cost as the objective function, and the optimal debt allocation scheme for the enterprise includes the financing term and the comprehensive financing interest rate at the target time.

[0036] The working process, working details and technical effects of the system provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0037] like Figure 3As shown, the third aspect of this embodiment provides an electronic device, including: a memory, a processor, and a transceiver that are sequentially and communicatively connected, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the configuration method for the optimal debt term of an enterprise as described in the first aspect of the embodiment.

[0038] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0039] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee transceiver (a low-power LAN protocol based on the IEEE 802.15.4 standard), a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0040] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0041] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the configuration method for the optimal debt term of an enterprise as described in the first aspect of the embodiment. That is, the storage medium stores instructions that, when executed on a computer, perform the configuration method for the optimal debt term of an enterprise as described in the first aspect of the embodiment.

[0042] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0043] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0044] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the configuration method for the optimal debt term of an enterprise as described in the first aspect of this embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0045] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for configuring the optimal debt maturity of an enterprise, characterized in that, The method comprises the following steps: obtaining original enterprise debt data, classifying and storing the original enterprise debt data to obtain multi-type original enterprise debt data, and performing data cleaning and standardization processing on the multi-type original enterprise debt data to obtain multi-type enterprise debt data, wherein the multi-type enterprise debt data comprises enterprise operation data, strategic planning data and market environment data; obtaining historical multi-type enterprise debt data, constructing a dynamic interest rate prediction model and a strategic adaptive cash flow prediction model based on the historical multi-type enterprise debt data, taking the multi-type enterprise debt data as input of the dynamic interest rate prediction model and the strategic adaptive cash flow prediction model, outputting a predicted value of an interest rate at a target time through the dynamic interest rate prediction model, and outputting a predicted value of a cash flow at the target time through the strategic adaptive cash flow prediction model; obtaining a preset debt configuration linear programming model, inputting the predicted value of the interest rate at the target time and the predicted value of the cash flow at the target time into the debt configuration linear programming model, performing debt configuration programming solving, and outputting an optimal debt configuration scheme of an enterprise, wherein the debt configuration linear programming model takes minimizing comprehensive financing cost as an objective function, and the optimal debt configuration scheme of the enterprise comprises a financing period and a comprehensive financing interest rate of the enterprise at the target time.

2. The method for configuring the optimal debt maturity of an enterprise according to claim 1, wherein, obtaining original enterprise debt data, performing data cleaning and standardization processing on the original enterprise debt data to obtain enterprise debt data, and classifying and storing the enterprise debt data to form multi-type enterprise debt data, comprising: collecting multi-type original internal enterprise debt data through a plurality of data interfaces of an enterprise financial database, collecting original external market environment data through an external data interface, time-aligning the original internal enterprise debt data and the original external market environment data, and integrating the original internal enterprise debt data and the original external market environment data that have completed time alignment into original enterprise debt data, wherein the original internal enterprise debt data comprises original enterprise operation data and original strategic planning data; performing data classification processing on the original enterprise debt data based on each data interface to obtain multi-type original enterprise debt data; The missing values of the multi-type original enterprise debt data are filled by using a forward filling method, and the multi-type original enterprise debt data is pruned based on The abnormal values in the multi-type original enterprise debt data are pruned according to the principle, and multi-type pre-enterprise debt data is obtained. obtaining a preset data format standard, performing data format standardization processing on the multi-type original enterprise debt data through the data format standard, and taking the multi-type original enterprise debt data that has completed data format standardization processing as multi-type enterprise debt data.

3. The method for configuring the optimal debt maturity of an enterprise according to claim 1, wherein, obtaining historical multi-type enterprise debt data, constructing a dynamic interest rate prediction model and a strategic adaptive cash flow prediction model based on the historical multi-type enterprise debt data, comprising: obtaining historical original enterprise debt data, classifying and storing the historical original enterprise debt data to obtain historical multi-type original enterprise debt data, and performing data cleaning and standardization processing on the historical multi-type original enterprise debt data to obtain historical multi-type enterprise debt data, wherein the historical multi-type enterprise debt data comprises historical enterprise operation data, historical strategic planning data and historical market environment data; The DNSS model is taken as a first base model, a state model is established based on a state equation in a Kalman filtering algorithm, and the first base model is embedded into the state model to build an initial dynamic interest rate prediction model; The historical enterprise operation data is extracted from the historical multi-type enterprise debt data, and the historical enterprise operation data is integrated into a first pre-training data set; The first pre-training data set is input into the initial dynamic interest rate prediction model, the interest rate prediction value of each selected time and selected debt period is taken as an output, the interest rate prediction algorithm of the initial dynamic interest rate prediction model is updated in parameters, and a dynamic interest rate prediction model is trained; The Prophet model is taken as a second base model, and a strategic variable term is introduced into the second base model to form an initial strategic adaptive cash flow prediction model; The historical strategic planning data and historical market environment data are extracted from the historical multi-type enterprise debt data, and the historical strategic planning data and the historical market environment data are integrated into a second pre-training data set; The second pre-training data set is input into the initial strategic adaptive cash flow prediction model, the cash flow prediction value of each selected time is taken as an output, the cash flow prediction algorithm of the initial strategic adaptive cash flow prediction model is updated in parameters, and a strategic adaptive cash flow prediction model is trained.

4. The method for configuring the optimal debt maturity of an enterprise according to claim 3, wherein, The interest rate prediction algorithm of the dynamic interest rate prediction model is represented by the following formula (1): （1） in, Indicates at the selected time The debt term is Interest rate forecasts Indicates at the selected time interest rate level, Indicates at the selected time The rate of change in short-term interest rates, Indicates at the selected time The medium-term interest rate curvature, Indicates at the selected time Additional interest rate curvature, This is the parameter for the curvature decay of the medium-term interest rate. For additional interest rate curvature decay parameters, is the base of the natural logarithm; The cash flow prediction algorithm of the strategic adaptive cash flow prediction model is represented by the following formula (2): （2） wherein, represents a cash flow prediction value at a selected time represents a cash flow trend change function with respect to a selected time represents a cash flow seasonal periodicity change function with respect to a selected time represents a cash flow holiday change function with respect to a selected time represents a matrix of firm strategy variables, represents regression coefficients of firm strategy variables, is a normally distributed error term.​​​​ 5. The method for configuring the optimal debt maturity of an enterprise according to claim 3, wherein, The multi-type enterprise debt data is taken as an input of the dynamic interest rate prediction model and the strategic adaptive cash flow prediction model, the interest rate prediction value of a target time is output by the dynamic interest rate prediction model, and the cash flow prediction value of the target time is output by the strategic adaptive cash flow prediction model, including: A preset target time is acquired, enterprise operation data in the multi-type enterprise debt data is taken as an input, and is input into the dynamic interest rate prediction model, so that the interest rate prediction value of each financing period of the enterprise at the target time is calculated by the dynamic interest rate prediction model; Strategic planning data and market environment data in the multi-type enterprise debt data are taken as inputs, and are input into the strategic adaptive cash flow prediction model, so that the cash flow prediction value at the target time is calculated by the strategic adaptive cash flow prediction model.

6. The method for configuring optimal maturity of enterprise debt according to claim 1, wherein, The preset method of the debt configuration linear programming model includes: The debt allocation target is to minimize the interest rate of the enterprise comprehensive financing, and the debt allocation target function is constructed by formula (3) as follows : （3） wherein, is the total number of enterprise financings, represents the enterprise financing, represents the financing capital of the enterprise financing, is the financing annual interest rate of the enterprise financing, is the financing term of the enterprise financing, is the comprehensive financing interest rate of the enterprise, represents the minimum operation; Obtain the preset fixed constraints for debt allocation, based on the debt allocation objective function. A linear programming model for debt allocation is constructed based on the fixed constraints of the debt allocation, wherein the fixed constraints of the debt allocation include maturity matching constraints, maturity diversification constraints, and market timing constraints.

7. The method for configuring the optimal debt maturity of an enterprise according to claim 6, wherein, The interest rate prediction value and the cash flow prediction value of the target time are input into the debt configuration linear programming model, debt configuration planning is solved, and an optimal debt configuration scheme of the enterprise is output, including: Based on the cash flow prediction value at the target time, the predicted total financing demand and the predicted net cash flow of the enterprise are calculated; forming a total financing constraint based on the predicted total financing demand of the enterprise, forming a cash flow matching constraint based on the predicted net cash flow, inputting the total financing constraint and the cash flow matching constraint as dynamic constraint conditions of debt configuration into the debt configuration linear programming model, and updating the debt configuration linear programming model; generating a plurality of candidate enterprise financing schemes based on the interest rate prediction value at the target time, wherein each candidate enterprise financing scheme includes an interest rate prediction value and a financing product term; inputting each candidate enterprise financing scheme into the updated debt configuration linear programming model to calculate an enterprise comprehensive financing interest rate of each candidate enterprise financing scheme by using the debt configuration linear programming model; Utilizing the debt allocation objective function in a debt allocation linear programming model Selecting, from the enterprise comprehensive financing interest rates of the respective candidate enterprise financing schemes, a candidate enterprise financing scheme with the lowest enterprise comprehensive financing interest rate as an optimal debt allocation scheme.

8. A system for optimal debt maturity profile of an enterprise, characterized by, The application is applied to the method for configuring the optimal debt term of an enterprise according to any one of claims 1-7, and comprises: An enterprise debt data acquisition unit is configured to acquire original enterprise debt data, store the original enterprise debt data in a classified manner to obtain multi-type original enterprise debt data, and perform data cleaning and standardization processing on the multi-type original enterprise debt data to obtain multi-type enterprise debt data, wherein the multi-type enterprise debt data includes enterprise operation data, strategic planning data and market environment data. A prediction model building and running unit is configured to acquire historical multi-type enterprise debt data, build a dynamic interest rate prediction model and a strategic adaptive cash flow prediction model based on the historical multi-type enterprise debt data, and use the multi-type enterprise debt data as input of the dynamic interest rate prediction model and the strategic adaptive cash flow prediction model, output an interest rate prediction value at a target time through the dynamic interest rate prediction model, and output a cash flow prediction value at the target time through the strategic adaptive cash flow prediction model. An optimal debt configuration scheme generation unit is configured to acquire a preset debt configuration linear programming model, input the interest rate prediction value and the cash flow prediction value at the target time into the debt configuration linear programming model, perform debt configuration programming solving, and output an optimal debt configuration scheme of an enterprise, wherein the debt configuration linear programming model takes minimization of comprehensive financing cost as a target function, and the optimal debt configuration scheme of the enterprise includes a financing term at the target time and an enterprise comprehensive financing interest rate.

9. An electronic device, comprising: The computer program or the instructions realize the method for configuring the optimal debt term of an enterprise according to any one of claims 1-7 when executed by a computer.

10. A computer program product comprising computer programs or instructions, characterized in that, ​

Images