Financial product supply and demand matching list generation method and device, equipment and storage medium

Abstract

The invention relates to the field of data request processing, and discloses a financial product supply and demand matching list generation method, which comprises the following steps: calculating financial product demand data of a target user, and generating a risk value corresponding to each supplier mechanism; obtaining a priority sequence value of each supplier mechanism according to the financial product expected supply data of each supplier mechanism; classifying the supplier institutions to obtain qualification type label values corresponding to the supplier institutions; and substituting the capital type label value, the priority sequence value and the risk value into a calculation formula to calculate a matching value, performing comprehensive sorting on the supplier mechanism according to the matching value, and generating a financial product supply and demand matching list according to a comprehensive sorting result. According to the method, the demand amount and the demand deadline of the target user only need to be acquired and matched with the data of each supplier mechanism to obtain the financial product supply and demand matching list, so that the problem of low recommendation accuracy caused by new users or data-deficient users is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of data request processing, and in particular to a method, apparatus, device and storage medium for generating a financial product supply and demand matching list. Background Art

[0002] In the FinTech sector, financial product supply and demand matching systems (e.g., loan products) are crucial tools for connecting users with suppliers. Their core goal is to accurately allocate users' financial needs to appropriate suppliers based on their financial needs and their business objectives, thereby achieving efficient financial supply and demand matching and business growth. However, existing financial product supply and demand matching systems often face a critical issue when dealing with new users or users with limited data: the "cold start problem."

[0003] For example, existing financial product supply and demand matching systems typically rely on users' historical financial supply and demand data and preference data, achieving precise matching through collaborative filtering or content recommendation algorithms. However, for newly registered users or those with insufficient historical data, these systems struggle to obtain sufficient information to accurately predict their financial needs and risk preferences. In these cases, the accuracy of these systems decreases significantly, resulting in a high error rate in recommendation results, which severely impacts the normal operation of financial services.

[0004] While machine learning and deep learning models excel at data-driven predictions, they also rely on extensive historical data for training. When faced with new users, the lack of sufficient training samples prevents the models from effectively learning their characteristics and behavior patterns, and thus from providing reliable recommendations. This "cold start problem" severely impacts the accuracy of financial product supply and demand matching systems.

[0005] Therefore, when dealing with new users or users with scarce data, how to improve the accuracy of matching supply and demand of financial products is a technical problem that needs to be solved urgently. Summary of the Invention

[0006] In view of the above, it is necessary to provide a method for generating a financial product supply and demand matching list, the purpose of which is to obtain only the target user's demand amount and demand period, match them with the data of various supply institutions, and obtain a financial product supply and demand matching list, which effectively solves the problem of low recommendation accuracy caused by new users or users with insufficient data.

[0007] The present invention provides a method for generating a financial product supply and demand matching list, the method comprising: Periodically obtaining historical supply data of financial products of multiple supplier institutions in a preset historical time period from a database, wherein the historical supply data of financial products includes the historical expected target profit value and the historical actual profit value obtained by each supplier institution in the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supplier institution in the preset historical time period; Numerical calculations are performed on the historical actual transaction values ​​and the historical expected target transaction values, and a preset attenuation factor of a penalty function algorithm is adjusted based on the numerical calculation results; a first profit variable weight coefficient of each supplier institution is calculated based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value; a second profit variable weight coefficient of each supplier institution is calculated based on the historical actual profit value and the first profit variable weight coefficient; and a priority scoring formula for each supplier institution is updated based on the first profit variable weight coefficient and the second profit variable weight coefficient; Receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution, wherein the financial product demand data includes the target user's demand amount and demand term; Obtaining expected supply data of financial products for each supplier institution in a preset expected time period, wherein the expected supply data of financial products includes an expected target profit value and an expected target transaction value for each supplier institution in the preset expected time period; Substituting the expected target profit value and the expected target transaction value of each supplier organization in the preset expected time period into the priority scoring formula corresponding to each supplier organization, calculating the priority score corresponding to each supplier organization, and prioritizing each supplier organization according to the calculated priority score to obtain the priority order value of each supplier organization; Classify each supplier institution according to the expected supply data of the financial product, and obtain a capital type label value corresponding to each supplier institution; Substituting the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate a matching value, comprehensively ranking the supplier institutions according to the matching value, and generating a financial product supply and demand matching list for the target user based on the comprehensive ranking result.

[0008] In order to solve the above problem, the present invention further provides a device for generating a financial product supply and demand matching list, the device comprising: an acquisition module, configured to periodically acquire from a database historical supply data of financial products by multiple supply institutions during a preset historical time period, the historical supply data comprising the historical expected target profit value and the historical actual profit value obtained by each supply institution during the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supply institution during the preset historical time period; an adjustment module, configured to perform numerical calculations on the historical actual transaction values ​​and the historical expected target transaction values, adjust the attenuation factor of a preset penalty function algorithm based on the numerical calculation results, calculate a first profit variable weight coefficient for each supplier institution based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value, calculate a second profit variable weight coefficient for each supplier institution based on the historical actual profit value and the first profit variable weight coefficient, and update a priority scoring formula for each supplier institution based on the first profit variable weight coefficient and the second profit variable weight coefficient; a calculation module configured to receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution, wherein the financial product demand data includes the target user's demand amount and demand term; a ranking module for obtaining expected supply data of financial products from each supplier institution during a preset expected time period, the expected supply data including the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period; substituting the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period into a priority scoring formula corresponding to each supplier institution, calculating a priority score corresponding to each supplier institution, and ranking each supplier institution according to the calculated priority score to obtain a priority order value for each supplier institution; A classification module is used to classify each supplier institution according to the expected supply data of the financial product and obtain a capital type label value corresponding to each supplier institution; The comprehensive module is used to substitute the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate the matching value, comprehensively sort the supply institutions according to the matching value, and generate a financial product supply and demand matching list for the target user based on the comprehensive sorting result.

[0009] In order to solve the above problem, the present invention further provides an electronic device, comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a financial product supply and demand matching list generation program that can be executed by the at least one processor. The financial product supply and demand matching list generation program is executed by the at least one processor so that the at least one processor can perform the above-mentioned financial product supply and demand matching list generation method.

[0010] In order to solve the above problems, the present invention also provides a computer-readable storage medium, on which a financial product supply and demand matching list generation program is stored. The financial product supply and demand matching list generation program can be executed by one or more processors to implement the above-mentioned financial product supply and demand matching list generation method.

[0011] Compared to existing technologies, this invention achieves precise matching of financial product supply and demand by comprehensively analyzing historical data from supplier organizations and target user demand data. Specifically, by regularly acquiring historical financial product supply data from supplier organizations, including historical expected target profit values, historical actual profit values, historical expected target transaction values, and historical actual transaction values, it calculates the profit variable weight coefficient for each supplier organization and updates the priority scoring formula accordingly. Simultaneously, it receives financial product service applications from target users, extracts key information such as the requested amount and requested period, and calculates the corresponding risk value for each supplier organization. Furthermore, it obtains the supplier organization's expected supply data for financial products during the expected time period and calculates the priority score for each supplier organization. Finally, it substitutes the capital type tag value, priority order value, and risk value into the matching value calculation formula to obtain the matching value, which is then comprehensively ranked to generate a matching list of financial product supply and demand. This process only obtains the target user's requested amount and requested period, matches them with the data of each supplier organization, and generates a matching list of financial product supply and demand. This effectively solves the problem of low recommendation accuracy caused by new users or users with insufficient data, and improves the accuracy and efficiency of financial product supply and demand matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of a method for generating a financial product supply and demand matching list according to an embodiment of the present invention; Figure 2 A schematic diagram of modules of a device for generating a financial product supply and demand matching list according to an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing a method for generating a financial product supply and demand matching list according to an embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0014] It should be noted that the descriptions of "first", "second", etc. in the present invention are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0015] Reference Figure 1 The figure shows a flow chart of a method for generating a financial product supply and demand matching list according to an embodiment of the present invention. The method is based on a computer program stored and executed in an electronic device, and is capable of analyzing and processing a user's financial product demand data and a supplier's financial product supply data to generate a corresponding financial product supply and demand matching list for the user to select. When executed by the electronic device, the computer program controls the electronic device to perform the following steps of the method for generating a financial product supply and demand matching list: S1. Periodically obtain historical supply data of financial products from a database for multiple supply institutions during a preset historical time period. The historical supply data includes the historical expected target profit value and the historical actual profit value obtained by each supply institution during the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supply institution during the preset historical time period. In this embodiment, historical financial product supply data for multiple suppliers within a preset historical time period is automatically retrieved from the database at preset intervals (e.g., hourly, daily, weekly, or monthly). This regular data acquisition mechanism ensures the timeliness and accuracy of the data, providing a foundation for subsequent analysis and matching.

[0016] In the financial product supply and demand matching system, databases play a core role, storing not only historical financial product supply data from suppliers but also demand data from demanders and related business records. In the financial sector, suppliers refer to those providing financial products or services.

[0017] Each supplier organization sets a historical target profit value for a pre-set historical time period. This value reflects the profit target the supplier organization hopes to achieve within that time period. The actual profit value a supplier organization actually achieved during that time period reflects its actual profitability during that time period and is a key indicator for evaluating its business performance.

[0018] Each supplier organization sets a historical target transaction value for a pre-set historical time period. This target value reflects the transaction volume the supplier organization plans to complete within that time period and is typically determined based on business development plans and market forecasts. The actual transaction value a supplier organization actually completed within that pre-set historical time period reflects the supplier organization's actual transaction volume within that time period and is a key indicator for evaluating its business performance and market adaptability.

[0019] By comparing historical expected target profits with historical actual profits, we can assess whether the supplier organization's profitability has met expectations. Similarly, by comparing historical expected target transaction values ​​with historical actual transaction values, we can assess the supplier organization's market expansion and transaction completion performance.

[0020] S2. Numerical calculation is performed on the historical actual transaction value and the historical expected target transaction value, and the attenuation factor of the preset penalty function algorithm is adjusted according to the numerical calculation result; a first profit variable weight coefficient of each supplier institution is calculated according to the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value; a second profit variable weight coefficient of each supplier institution is calculated according to the historical actual profit value and the first profit variable weight coefficient; and a priority scoring formula of each supplier institution is updated according to the first profit variable weight coefficient and the second profit variable weight coefficient; In one embodiment, the performing of numerical calculations on the historical actual transaction value and the historical expected target transaction value, and adjusting the attenuation factor of a preset penalty function algorithm according to the numerical calculation results, includes: Calculating a ratio between the historical actual transaction value and the historical expected target transaction value; Adjust the attenuation factor of the penalty function algorithm according to the size of the ratio value, and the range of the ratio value is [0,1]; If the difference between the ratio value and 1 is less than a first threshold, the value of the attenuation factor is reduced to a first value, and the attenuation speed value of the weight coefficient of the first profit variable is reduced to a second value using the first value; If the difference between the ratio value and 0 is greater than or equal to the first threshold, the value of the attenuation factor is increased to a third value, and the attenuation speed value of the first profit variable weight coefficient is increased to a fourth value using the third value.

[0021] Calculating the ratio between historical actual transaction value and historical expected target transaction value is a key step in evaluating the completion of target transactions by a supplier organization. This ratio reflects the relative relationship between the supplier organization's actual transaction value and the expected target transaction value over the historical time period. The specific calculation formula is: Ratio value = historical actual transaction value / historical expected target transaction value The ratio value ranges from [0, 1]. The closer the ratio value is to 1, the closer the supplier's actual transaction value is to its expected target transaction value, indicating better target completion. Conversely, the smaller the ratio value, the worse the target completion.

[0022] In the context of matching supply and demand for financial products, penalty function algorithms incorporate constraints into the objective function by introducing a penalty term, thereby transforming a constrained optimization problem into an unconstrained one. The core idea is that when there is a gap between the actual performance of a supplier institution and the desired target, a penalty is imposed on this gap. This penalty is then minimized through an optimization algorithm, thereby achieving optimal matching.

[0023] The attenuation factor in the penalty function algorithm is dynamically adjusted based on the size of the ratio. This adjustment mechanism enables the profit variable weight coefficient to better reflect the actual business performance and target completion progress of the supplier organization. The specific adjustment rules are as follows: When the difference between the ratio and 1 is less than the first threshold, this indicates that the supplier's actual transaction value is very close to or even reaches its target transaction value, indicating successful target achievement. At this point, the decay factor is reduced to the first value, and the decay rate of the first profit variable's weight coefficient is reduced to the second value using the first value, slowing the decay rate of the first profit variable's weight coefficient. In this way, the supplier's weight is appropriately increased, encouraging it to maintain its strong performance.

[0024] If the difference between the ratio and 0 is greater than or equal to the first threshold, this indicates that the supplier's actual transaction value is far below its target transaction value, indicating poor performance. In this case, the decay factor is increased to a third value, and the decay rate of the first profit variable's weight coefficient is increased to a fourth value using the third value, accelerating the decay rate of the first profit variable's weight coefficient. This can appropriately reduce the supplier's weight, encouraging them to take measures to improve their performance.

[0025] The first to fourth values ​​are parameters used to adjust the attenuation rate of the attenuation factor and the profit variable weight coefficient in the penalty function algorithm. The specific sizes of these values ​​need to be set and adjusted according to actual conditions and business needs, and are not limited in any way.

[0026] In one embodiment, the first profit variable weight coefficient of each supplier organization is obtained by calculating according to the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value, including: Calculating the difference between the historical expected target profit value and the historical actual transaction value; The proportion of the difference to the historical expected target profit value is calculated, and the proportion is multiplied by the attenuation factor to obtain the first profit variable weight coefficient of each supplier organization.

[0027] Multiplying the percentage by the attenuation factor yields the weight coefficient for each supplier's primary profit variable. The formula is: Primary Profit Variable Weight Coefficient = Percentage × Attenuation Factor. By introducing the attenuation factor, the weight coefficient dynamically reflects the supplier's progress toward achieving its goals.

[0028] Based on the calculated weight coefficients for the first and second profit variables, the priority scoring formula for each supplier institution is updated. This formula comprehensively considers the supplier institution's profit performance and business goal achievement, providing a more accurate basis for prioritization for subsequent matching of financial product supply and demand. This update can be implemented by incorporating the first and second profit variable weight coefficients as new variables into the priority scoring formula, or by adjusting and optimizing the correlation coefficients in the existing formula based on business needs.

[0029] The first profit variable weighting coefficient is calculated based on the ratio of the supplier's historical actual transaction value to its target transaction value and is dynamically optimized using an adjusted penalty function algorithm. This coefficient reflects the supplier's performance in achieving its transaction volume target. The second profit variable weighting coefficient combines the supplier's historical actual profit value with the first profit variable weighting coefficient to further quantify the supplier's profitability. Together, these two coefficients provide a dynamic and comprehensive quantitative indicator of the supplier's business performance.

[0030] By incorporating the weight coefficient of the first profit variable and the weight coefficient of the second profit variable into the priority scoring formula, the priority score of the supplier organization can be dynamically adjusted. This dynamic adjustment mechanism enables the priority scoring formula to better reflect the actual business performance and goal completion progress of the supplier organization under current market conditions. The priority scoring formula can be automatically updated according to market changes and the real-time performance of the supplier organization to ensure the accuracy and timeliness of the score. For new users or supplier organizations with scarce data, traditional recommendation systems often find it difficult to accurately assess their priority. By introducing the weight coefficient of the first profit variable and the weight coefficient of the second profit variable, the system can provide a reasonable initial priority score for the supplier organization based on its business goals and real-time performance when data is insufficient. This dynamic evaluation mechanism based on real-time business data effectively alleviates the "cold start problem" and improves the accuracy and adaptability of the recommendation system.

[0031] S3. Receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution. The financial product demand data includes the target user's demand amount and demand term. In this embodiment, a financial product service application is received from a target user. A financial product service application is a formal request submitted by a demander user (such as an individual or enterprise) to a provider institution (such as a bank, insurance company, etc.) to express their demand for a specific financial product or service.

[0032] Extract key financial product demand data from service applications, including but not limited to the requested amount and term. The requested amount and term are the basis for risk assessment and directly reflect the user's basic requirements and usage plans for financial products. Traditional recommendation systems often struggle to accurately predict the needs and risk preferences of new users or those with limited data. As the most basic user demand information, the requested amount and term provide a reasonable initial basis for matching when data is insufficient. This matching strategy, based on limited but critical information, helps alleviate the "cold start problem," namely, how to provide personalized recommendations to target users in the absence of sufficient historical data.

[0033] Using the supplier institution's corresponding risk calculation formula, the extracted financial product demand data is calculated to obtain the risk value corresponding to each supplier institution. This process generally includes the following aspects: calculation of default probability value, order risk score value, and risk exposure value.

[0034] In one embodiment, the step of calling the risk value calculation formula corresponding to each supplier institution to calculate the financial product demand data and generate the risk value corresponding to each supplier institution includes: The default risk calculation formula, order risk scoring formula and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data respectively to obtain the risk value of each supplier institution for the service application.

[0035] In one embodiment, the default risk calculation formula, order risk scoring formula, and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data respectively to obtain the risk value of each supplier institution for the service application, including: Obtaining the target user's credit score, calculating the credit score, the required amount, and the required term using the default risk calculation formula to obtain a default probability value for the target user; Substituting the required amount and the required term into the order risk scoring formula, using the order risk scoring formula to divide the product of the required amount and the required term by the credit score, and then multiplying the product by a preset risk coefficient to obtain an order risk score value for the service application of each supplier institution; Calculate the demand amount and the current cumulative risk exposure of each supplier organization using the risk exposure calculation formula to obtain the risk exposure value of each supplier organization after the new order is added; The risk value of each supplier organization for the service application is obtained according to the default probability value, the order risk score value and the risk exposure value.

[0036] Calculating the probability of default: Obtain the target user's credit score, combine it with the requested amount and term, and apply the default risk calculation formula to assess the likelihood of the user defaulting. The credit score is an important indicator of a user's creditworthiness, reflecting their ability and willingness to repay debts on time. The requested amount and term reflect the scale of the user's demand for funds and the duration of their use. These factors together influence the magnitude of the default risk. The formula for calculating the probability of default is:

[0037] Among them, α, β, and γ are coefficients obtained through training based on historical data.

[0038] Calculation of Order Risk Score: Substitute the requested amount and duration into the order risk score formula to calculate the order risk score. The order risk score formula takes into account factors such as fund size, duration of use, and the user's credit status to quantify the risk level of a single financial product order. The formula for calculating the order risk score is: Order risk score =

[0039] Calculation of risk exposure: Using the risk exposure calculation formula, combined with the demand amount and the current cumulative risk exposure of each supplier organization, the risk exposure value after the new order is calculated. Risk exposure reflects the maximum loss that a supplier organization may suffer if a specific risk event occurs and is an important indicator for risk management. The formula for calculating the risk exposure value after the new order is: Risk exposure value after adding new orders = current cumulative risk exposure + demand amount Based on the default probability, order risk score, and risk exposure, we comprehensively assess the risk of each provider's service application. This comprehensive risk score not only considers the possibility of user default, but also the characteristics of the order itself and the current risk profile of the provider, helping to comprehensively understand and manage risk.

[0040] Through the above steps, a risk value can be generated for each supplier institution. These risk values ​​play a vital role in the subsequent financial product supply and demand matching process, helping the platform to identify and screen financial products with lower risks and more suitable for users to find matches quickly and accurately.

[0041] In one embodiment, after generating the risk value corresponding to each supplier organization, the method further includes: Comparing the risk value with the risk thresholds preset by each supplier organization; If the risk value is less than the risk threshold, determining that the service application meets the risk condition of the current supplier organization, and marking the current supplier organization as a non-risk rejection label; If the risk value is greater than or equal to the risk threshold, it is determined that the service application does not meet the risk condition of the current supplier organization, and the current supplier organization is marked as a risk rejection label.

[0042] Each supplier organization sets a risk threshold based on its own risk tolerance and business strategy. This threshold represents the maximum level of risk the supplier organization is willing to assume. The generated risk value for each supplier organization is then compared against the organization's preset risk threshold.

[0043] If the risk value is less than the risk threshold, it means that the risk of the service application is within the acceptable range of the supplier organization. At this time, the service application is determined to meet the risk conditions of the current supplier organization and the supplier organization is marked as non-risk rejection.

[0044] If the risk value is greater than or equal to the risk threshold, it means that the risk of the service application exceeds the supplier's tolerance. In this case, the service application is determined to not meet the risk conditions of the current supplier and the supplier is marked as risk rejected.

[0045] By marking supplier institutions' risk status, we can quickly screen for suppliers that meet risk criteria. During the matching process of financial product supply and demand, we prioritize suppliers marked as non-risk rejects, thereby reducing overall business risk. Furthermore, by excluding suppliers marked as risk rejects during the matching process, we can reduce unnecessary matching attempts and improve matching efficiency.

[0046] S4. Obtaining expected supply data of financial products for each supplier institution in a preset expected time period, wherein the expected supply data of financial products includes an expected target profit value and an expected target transaction value for each supplier institution in the preset expected time period; Substituting the expected target profit value and the expected target transaction value of each supplier organization in the preset expected time period into the priority scoring formula corresponding to each supplier organization, calculating the priority score corresponding to each supplier organization, and prioritizing each supplier organization according to the calculated priority score to obtain the priority order value of each supplier organization; In this embodiment, the preset expected time period refers to a reasonable expected time period set based on the business planning and market analysis of each supplier organization, such as one month, one quarter, or six months in the future. The expected supply data of financial products refers to data related to the financial products or services that a supplier organization (such as a bank, insurance company, fund management company, etc.) plans to provide within a specific time period.

[0047] Obtain each supplier's target profit value within a pre-set timeframe. This target profit value reflects the supplier's expectations for future business profitability and is typically determined based on market research, business development plans, and historical data. Also collect each supplier's target transaction value within the pre-set timeframe—that is, the size of the transactions they plan to complete. This target transaction value reflects the supplier's business development goals and market share expectations.

[0048] Based on each supplier organization's emphasis on business objectives, weight coefficients are assigned to the expected target profit value and expected target transaction value, respectively. A priority scoring formula is constructed. For example, priority score = w1 × (expected target profit value / industry average profit value) + w2 × (expected target transaction value / industry average transaction value), where w1 and w2 represent the weight coefficients for the expected target profit value and expected target transaction value, respectively, and w1 + w2 = 1. Each supplier organization's expected target profit value and expected target transaction value are substituted into the priority scoring formula to calculate the corresponding priority score. The priority score quantifies the supplier organization's relative performance in meeting business objectives.

[0049] When calculating the priority score, fine-tuning the weighting coefficients based on benchmark data such as industry average profit and industry average transaction value can make the priority score more objective and comparable. These benchmark data can be obtained through industry reports, market research, or historical data statistics.

[0050] All suppliers are sorted in descending order based on the calculated priority scores to obtain a priority value for each supplier. This value intuitively demonstrates the supplier's priority in meeting business objectives and provides an important reference for subsequent matching of financial product supply and demand.

[0051] In other embodiments, during business operations, the latest expected target profit value and expected target transaction value are regularly obtained from the supplier organization, and the expected supply data of financial products is updated to ensure the timeliness and accuracy of priority scoring and sorting results.

[0052] S5. Classify each supplier institution according to the expected supply data of the financial product, and obtain a capital provider type label value corresponding to each supplier institution; In one embodiment, the classifying of each supplier institution according to the expected supply data of the financial product to obtain a capital provider type label value corresponding to each supplier institution includes: Extracting the expected target profit value and the expected target transaction value as key features from the expected supply data of the financial product; According to the key features, a preset classification algorithm is called from a preset classification model, and the classification algorithm is used to perform classification prediction on each supplier organization to obtain the capital type label value corresponding to each supplier organization.

[0053] Expected target profit and expected target transaction value are extracted from the expected supply data of financial products. These two indicators reflect the supplier's business objectives and expected performance over the next period of time. Expected target profit represents the profit the supplier hopes to earn from supplying financial products, while expected target transaction value indicates the scale of transactions it plans to complete.

[0054] The system has a pre-set classification model, which includes various algorithms such as decision trees, logistic regression, and the K-nearest neighbor algorithm. The most appropriate classification algorithm is dynamically selected based on business needs and data characteristics. For example, the decision tree algorithm, due to its excellent interpretability and ability to clearly display classification rules and decision paths, is suitable for scenarios requiring high-level classification logic. The logistic regression algorithm, on the other hand, is well-suited for binary classification problems and can output classification probabilities, providing a reference for subsequent matching decisions.

[0055] The classification model training process includes collecting historical data, including the provider's expected target profit, expected target transaction value, actual profit, actual transaction value, and risk assessment results. The provider's classification labels (e.g., guaranteed volume, profit-sharing, loan assistance, and risk control) are also collected. Data preprocessing (data cleaning and data conversion) is performed on the historical data and classification labels to obtain a preprocessed dataset. This dataset is then divided into a training set, a validation set, and a test set, typically with a ratio of 70%, 15%, and 15%. An appropriate classification algorithm is selected, such as decision tree, logistic regression, K-nearest neighbor (KNN), support vector machine (SVM), or random forest. The selected classification algorithm is trained on the training set, and model parameters are adjusted to optimize performance. The trained model is validated on the validation set to evaluate its accuracy and stability. Based on the validation results, model parameters can be adjusted or a different algorithm can be selected. The final model is tested on the test set to obtain the classification model and ensure good performance on unseen data.

[0056] The extracted expected target profit value and expected target transaction value are input as key features into the selected classification algorithm. The classification algorithm analyzes the relationship between these key features and pre-set investor type labels to categorize and predict each supplier. During the prediction process, the algorithm references historical data and existing classification labels to continuously optimize classification boundaries and improve classification accuracy and reliability. After processing by the classification algorithm, each supplier is assigned a investor type label value, such as "volume-guaranteed investor," "profit-sharing investor," "loan-facilitating investor," or "risk-control investor." These investor type labels intuitively reflect the supplier's business model and core competitiveness, providing an important reference for subsequent matching of supply and demand for financial products.

[0057] By categorizing suppliers, we can more accurately match target users' financial product needs. For example, for users who prioritize stable transaction volumes, we can prioritize volume-guaranteed suppliers; for users seeking profit sharing, we can prioritize profit-sharing suppliers. Using supplier type tags can help quickly identify suppliers that meet user needs, reducing unnecessary matching attempts and improving matching efficiency.

[0058] At the same time, traditional recommendation systems often struggle to accurately predict the needs and risk preferences of new users or those with limited data. The introduction of investor type tags, combined with priority and risk values, can provide clear matching criteria for these users without relying on large amounts of historical data, effectively solving the "cold start problem."

[0059] S6. Substitute the capital provider type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate a matching value, comprehensively rank the supplier institutions according to the matching value, and generate a financial product supply and demand matching list for the target user based on the comprehensive ranking result.

[0060] In this embodiment, in order to provide target users with more diversified and accurate financial product choices while ensuring that the matching results meet the business objectives and risk preferences of the provider institution, factors such as the funder type tag value, priority order, and risk value need to be comprehensively considered. The specific steps are as follows: The predetermined matching value calculation formula is a weighted summation: Matching Value = w1 × Provider Type Tag Value + w2 × Priority Order Value + w3 × Risk Value, where w1, w2, and w3 represent the weighting coefficients for the Provider Type Tag Value, Priority Order Value, and Risk Value, respectively, and w1 + w2 + w3 = 1. Weighting coefficients should be determined based on business objectives and the emphasis placed on different factors. For example, if the business prioritizes risk control, the risk value weighting coefficient can be set relatively high; if the business priority of the provider organization is emphasized, the priority order value weighting coefficient can be set relatively high.

[0061] Substitute each provider's capital type tag value, priority order value, and risk value into the matching value calculation formula to calculate the matching value for each provider. The matching value comprehensively reflects the degree of compatibility between the provider and the target user's financial product needs, with higher matching values ​​indicating better compatibility. All providers are sorted in descending order based on the calculated matching values, placing providers with higher matching values ​​at the top. The sorting results intuitively demonstrate the degree of compatibility between the provider and the target user's needs, providing a foundation for subsequently generating a matching list of financial product supply and demand.

[0062] Based on the comprehensive ranking results, determine the content of the financial product supply and demand matching list. This matching list should include key information such as the supplier institution name, matching value, financial product information (such as product name, interest rate, and term), funder type tag value, priority order value, and risk value, so that users can fully understand the characteristics and matching status of each supplier institution. The ranked supplier information is organized into a financial product supply and demand matching list and presented to users in an appropriate format. Common presentation formats include tables, lists, or charts. Ensure that the matching list is clear, easy to understand, browse, and compare.

[0063] In other embodiments, the generated financial product supply and demand matching list is manually reviewed and verified to ensure the rationality and accuracy of the matching results, and to identify and correct erroneous matches caused by data anomalies or algorithmic deviations.

[0064] In other embodiments, after the risk value is generated, the "non-risk rejection label" and "risk rejection label" of each supplier organization are collected. These labels indicate whether the service application meets the risk conditions of the supplier organization. The "non-risk rejection label" and "risk rejection label" are converted into numerical form, for example, the "non-risk rejection label" is 1 and the "risk rejection label" is 0. Ensure that all data are on the same order of magnitude. The "non-risk rejection label" and "risk rejection label" are added to the matching value calculation formula. For example, use the weighted summation formula: matching value = w1×capital type label value + w2×priority order value + w3×risk value + w4×non-risk rejection label + w5×risk rejection label, where w1, w2, w3, w4, w5 represent the weight coefficients of each factor respectively, and w1+w2+w3+w4+w5=1.

[0065] Substitute the capital type label value, priority order value, risk value, "non-risk rejection label" and "risk rejection label" of each supplier organization into the expanded matching value calculation formula to calculate the corresponding matching value of each supplier organization. By adding "non-risk rejection label" and "risk rejection label" to the matching value calculation formula, the adaptability of the supplier organization to user needs can be more comprehensively evaluated, further improving the accuracy and rationality of the matching.

[0066] In one embodiment, after generating the financial product supply and demand matching list for the target user, the method further includes: Feedback the financial product supply and demand matching list to the terminal device of the target user; receiving feedback information from the target user on the financial product supply and demand matching list; The matching value calculation formula and the classification model are optimized and updated according to the feedback information.

[0067] The generated financial product supply and demand matching list is pushed to the target user's terminal device, and detailed information about each supplier institution, including financial product characteristics, interest rates, maturities, and risk levels, is displayed through the user interface to assist users in decision-making. Feedback from target users on the financial product supply and demand matching list is collected, such as user click-through rates, selection preferences, and satisfaction ratings. Based on this feedback, the matching value calculation formula and classification model are continuously optimized and updated to improve matching accuracy and user experience.

[0068] like Figure 2, which is a schematic diagram of a module of a device for generating a financial product supply and demand matching list according to an embodiment of the present invention. The device 100 for generating a financial product supply and demand matching list according to the present invention can be installed in an electronic device. Depending on the functions implemented, the device 100 can include an acquisition module 110, an adjustment module 120, a calculation module 130, a sorting module 140, a classification module 150, and an integration module 160. A module according to the present invention, also referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and is stored in the memory of the electronic device.

[0069] In this embodiment, the functions of each module / unit are as follows: An acquisition module 110 is configured to periodically acquire from a database historical supply data of financial products by multiple supply institutions during a preset historical time period. The historical supply data includes the historical expected target profit value and the historical actual profit value achieved by each supply institution during the preset historical time period, as well as the historical expected target transaction value and the historical actual transaction value completed by each supply institution during the preset historical time period. An adjustment module 120 is configured to perform numerical calculations on the historical actual transaction values ​​and the historical expected target transaction values, adjust the attenuation factor of a preset penalty function algorithm based on the numerical calculation results, calculate a first profit variable weight coefficient for each supplier institution based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value, calculate a second profit variable weight coefficient for each supplier institution based on the historical actual profit value and the first profit variable weight coefficient, and update a priority scoring formula for each supplier institution based on the first profit variable weight coefficient and the second profit variable weight coefficient; Calculation module 130 is configured to receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution. The financial product demand data includes the target user's demand amount and demand term. The ranking module 140 is configured to obtain the expected supply data of financial products from each supplier institution during a preset expected time period, the expected supply data including the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period; substitute the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period into the priority scoring formula corresponding to each supplier institution, calculate the priority score corresponding to each supplier institution, and prioritize each supplier institution according to the calculated priority score to obtain a priority order value for each supplier institution; A classification module 150 is configured to classify each supplier institution according to the expected supply data of the financial product, and obtain a capital type label value corresponding to each supplier institution; The comprehensive module 160 is used to substitute the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate a matching value, comprehensively sort the supplier institutions according to the matching value, and generate a financial product supply and demand matching list for the target user based on the comprehensive sorting result.

[0070] In one embodiment, the performing of numerical calculations on the historical actual transaction value and the historical expected target transaction value, and adjusting the attenuation factor of a preset penalty function algorithm according to the numerical calculation results, includes: Calculating a ratio between the historical actual transaction value and the historical expected target transaction value; Adjust the attenuation factor of the penalty function algorithm according to the size of the ratio value, and the range of the ratio value is [0,1]; If the difference between the ratio value and 1 is less than a first threshold, the value of the attenuation factor is reduced to a first value, and the attenuation speed value of the weight coefficient of the first profit variable is reduced to a second value using the first value; If the difference between the ratio value and 0 is greater than or equal to the first threshold, the value of the attenuation factor is increased to a third value, and the attenuation speed value of the first profit variable weight coefficient is increased to a fourth value using the third value.

[0071] In one embodiment, the first profit variable weight coefficient of each supplier organization is obtained by calculating according to the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value, including: Calculating the difference between the historical expected target profit value and the historical actual transaction value; The proportion of the difference to the historical expected target profit value is calculated, and the proportion is multiplied by the attenuation factor to obtain the first profit variable weight coefficient of each supplier organization.

[0072] In one embodiment, the step of calling the risk value calculation formula corresponding to each supplier institution to calculate the financial product demand data and generate the risk value corresponding to each supplier institution includes: The default risk calculation formula, order risk scoring formula and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data respectively to obtain the risk value of each supplier institution for the service application.

[0073] In one embodiment, the default risk calculation formula, order risk scoring formula, and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data respectively to obtain the risk value of each supplier institution for the service application, including: Obtaining the target user's credit score, calculating the credit score, the required amount, and the required term using the default risk calculation formula to obtain a default probability value for the target user; Substituting the required amount and the required term into the order risk scoring formula, using the order risk scoring formula to divide the product of the required amount and the required term by the credit score, and then multiplying the product by a preset risk coefficient to obtain an order risk score value for the service application of each supplier institution; Calculate the demand amount and the current cumulative risk exposure of each supplier organization using the risk exposure calculation formula to obtain the risk exposure value of each supplier organization after the new order is added; The risk value of each supplier organization for the service application is obtained according to the default probability value, the order risk score value and the risk exposure value.

[0074] In one embodiment, the classifying of each supplier institution according to the expected supply data of the financial product to obtain a capital provider type label value corresponding to each supplier institution includes: Extracting the expected target profit value and the expected target transaction value as key features from the expected supply data of the financial product; According to the key features, a preset classification algorithm is called from a preset classification model, and the classification algorithm is used to perform classification prediction on each supplier organization to obtain the capital type label value corresponding to each supplier organization.

[0075] In one embodiment, after generating the financial product supply and demand matching list for the target user, the method further includes: Feedback the financial product supply and demand matching list to the terminal device of the target user; receiving feedback information from the target user on the financial product supply and demand matching list; The matching value calculation formula and the classification model are optimized and updated according to the feedback information.

[0076] like Figure 3 , which is a schematic structural diagram of an electronic device for implementing a method for generating a financial product supply and demand matching list provided by an embodiment of the present invention.

[0077] In this embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which can be interconnected via a system bus. The memory 11 stores a financial product supply and demand matching list generation program 10, and the financial product supply and demand matching list generation program 10 can be executed by the processor 12. Figure 3 Only the electronic device 1 having the components 11-13 and the financial product supply and demand matching list generating program 10 is shown. It can be understood by those skilled in the art that Figure 3 The structure shown does not limit the electronic device 1 and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0078] Memory 11 includes internal memory and at least one type of readable storage medium. The internal memory provides cache for the operation of electronic device 1. The readable storage medium may be a non-volatile storage medium such as flash memory, a hard disk, a multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, or an optical disk. In some embodiments, the readable storage medium may be an internal storage unit of electronic device 1. In other embodiments, the non-volatile storage medium may be an external storage device of electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash memory card. In this embodiment, the readable storage medium of memory 11 is typically used to store the operating system and various application software installed on electronic device 1, such as the code of the financial product supply and demand matching list generation program 10 in one embodiment of the present invention. In addition, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.

[0079] In some embodiments, the processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data exchange or communication with other devices. In this embodiment, the processor 12 is used to execute program code stored in the memory 11 or process data, such as executing the financial product supply and demand matching list generation program 10.

[0080] The network interface 13 may include a wireless network interface or a wired network interface, and the network interface 13 is used to establish a communication connection between the electronic device 1 and a terminal (not shown in the figure).

[0081] Optionally, the electronic device 1 may further include a user interface, which may include a display and an input unit such as a keyboard. The optional user interface may also include a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or display unit, and is used to display information processed in the electronic device 1 and to display a visual user interface.

[0082] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0083] The financial product supply and demand matching list generation program 10 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When executed in the processor 12, it can achieve the following: Periodically obtaining historical supply data of financial products of multiple supplier institutions in a preset historical time period from a database, wherein the historical supply data of financial products includes the historical expected target profit value and the historical actual profit value obtained by each supplier institution in the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supplier institution in the preset historical time period; Numerical calculations are performed on the historical actual transaction values ​​and the historical expected target transaction values, and a preset attenuation factor of a penalty function algorithm is adjusted based on the numerical calculation results; a first profit variable weight coefficient of each supplier institution is calculated based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value; a second profit variable weight coefficient of each supplier institution is calculated based on the historical actual profit value and the first profit variable weight coefficient; and a priority scoring formula for each supplier institution is updated based on the first profit variable weight coefficient and the second profit variable weight coefficient; Receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution, wherein the financial product demand data includes the target user's demand amount and demand term; Obtaining expected supply data of financial products for each supplier institution in a preset expected time period, wherein the expected supply data of financial products includes an expected target profit value and an expected target transaction value for each supplier institution in the preset expected time period; Substituting the expected target profit value and the expected target transaction value of each supplier organization in the preset expected time period into the priority scoring formula corresponding to each supplier organization, calculating the priority score corresponding to each supplier organization, and prioritizing each supplier organization according to the calculated priority score to obtain the priority order value of each supplier organization; Classify each supplier institution according to the expected supply data of the financial product, and obtain a capital type label value corresponding to each supplier institution; Substituting the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate a matching value, comprehensively ranking the supplier institutions according to the matching value, and generating a financial product supply and demand matching list for the target user based on the comprehensive ranking result.

[0084] Specifically, the specific implementation method of the processor 12 for the above-mentioned financial product supply and demand matching list generation program 10 can be referred to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0085] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable medium may be either non-volatile or non-volatile. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0086] The computer-readable storage medium stores a financial product supply and demand matching list generation program 10, which can be executed by one or more processors. The specific implementation of the computer-readable storage medium of the present invention is basically the same as the various embodiments of the above-mentioned financial product supply and demand matching list generation method, and will not be repeated here.

[0087] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0088] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0089] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0090] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0091] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0092] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Second-order terms are used to indicate names and do not imply any particular order.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for generating a financial product supply and demand matching list, characterized in that: The method is based on a computer program stored and executed in an electronic device, capable of analyzing and processing a user's financial product demand data and a supplier's financial product supply data to generate a corresponding financial product supply and demand matching list for the user to select. When executed by the electronic device, the computer program controls the electronic device to perform the following steps of the method for generating a financial product supply and demand matching list: Periodically obtaining historical supply data of financial products of multiple supplier institutions in a preset historical time period from a database, wherein the historical supply data of financial products includes the historical expected target profit value and the historical actual profit value obtained by each supplier institution in the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supplier institution in the preset historical time period; Numerical calculations are performed on the historical actual transaction values ​​and the historical expected target transaction values, and a preset attenuation factor of a penalty function algorithm is adjusted based on the numerical calculation results; a first profit variable weight coefficient of each supplier institution is calculated based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value; a second profit variable weight coefficient of each supplier institution is calculated based on the historical actual profit value and the first profit variable weight coefficient; and a priority scoring formula for each supplier institution is updated based on the first profit variable weight coefficient and the second profit variable weight coefficient; Receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution, wherein the financial product demand data includes the target user's demand amount and demand term; Obtaining expected supply data of financial products for each supplier institution in a preset expected time period, wherein the expected supply data of financial products includes an expected target profit value and an expected target transaction value for each supplier institution in the preset expected time period; Substituting the expected target profit value and the expected target transaction value of each supplier organization in the preset expected time period into the priority scoring formula corresponding to each supplier organization, calculating the priority score corresponding to each supplier organization, and prioritizing each supplier organization according to the calculated priority score to obtain the priority order value of each supplier organization; Classify each supplier institution according to the expected supply data of the financial product, and obtain a capital type label value corresponding to each supplier institution; Substituting the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate a matching value, comprehensively ranking the supplier institutions according to the matching value, and generating a financial product supply and demand matching list for the target user based on the comprehensive ranking result.

2. The method for generating a financial product supply and demand matching list according to claim 1, wherein: The performing numerical calculation on the historical actual transaction value and the historical expected target transaction value, and adjusting the attenuation factor of a preset penalty function algorithm according to the numerical calculation result, includes: Calculating a ratio between the historical actual transaction value and the historical expected target transaction value; Adjust the attenuation factor of the penalty function algorithm according to the size of the ratio value, and the range of the ratio value is [0,1]; If the difference between the ratio value and 1 is less than a first threshold, the value of the attenuation factor is reduced to a first value, and the attenuation speed value of the weight coefficient of the first profit variable is reduced to a second value using the first value; If the difference between the ratio value and 0 is greater than or equal to the first threshold, the value of the attenuation factor is increased to a third value, and the attenuation speed value of the first profit variable weight coefficient is increased to a fourth value using the third value.

3. The method for generating a financial product supply and demand matching list according to claim 1, wherein: The first profit variable weight coefficient of each supplier organization is obtained by calculating according to the adjusted penalty function algorithm, the historical expected target profit value and the historical actual transaction value, including: Calculating the difference between the historical expected target profit value and the historical actual transaction value; The proportion of the difference to the historical expected target profit value is calculated, and the proportion is multiplied by the attenuation factor to obtain the first profit variable weight coefficient of each supplier organization.

4. The method for generating a financial product supply and demand matching list according to claim 1, wherein: The step of calculating the financial product demand data by using the risk value calculation formula corresponding to each supplier institution to generate the risk value corresponding to each supplier institution includes: The default risk calculation formula, order risk scoring formula and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data respectively to obtain the risk value of each supplier institution for the service application.

5. The method for generating a financial product supply and demand matching list according to claim 4, wherein: The default risk calculation formula, order risk scoring formula, and risk exposure calculation formula in the risk calculation formula are used to calculate the financial product demand data to obtain the risk value of each supplier institution for the service application, including: Obtaining the target user's credit score, calculating the credit score, the required amount, and the required term using the default risk calculation formula to obtain a default probability value for the target user; Substituting the required amount and the required term into the order risk scoring formula, using the order risk scoring formula to divide the product of the required amount and the required term by the credit score, and then multiplying the product by a preset risk coefficient to obtain an order risk score value for the service application of each supplier institution; Calculate the demand amount and the current cumulative risk exposure of each supplier organization using the risk exposure calculation formula to obtain the risk exposure value of each supplier organization after the new order is added; The risk value of each supplier organization for the service application is obtained according to the default probability value, the order risk score value and the risk exposure value.

6. The method for generating a financial product supply and demand matching list according to claim 1, wherein: The classifying of each supplier institution according to the expected supply data of the financial product to obtain the capital type label value corresponding to each supplier institution includes: Extracting the expected target profit value and the expected target transaction value as key features from the expected supply data of the financial product; According to the key features, a preset classification algorithm is called from a preset classification model, and the classification algorithm is used to perform classification prediction on each supplier organization to obtain the capital type label value corresponding to each supplier organization.

7. The method for generating a financial product supply and demand matching list according to claim 1, wherein: After generating the financial product supply and demand matching list for the target user, the method further includes: Feedback the financial product supply and demand matching list to the terminal device of the target user; receiving feedback information from the target user on the financial product supply and demand matching list; The matching value calculation formula and the classification model are optimized and updated according to the feedback information.

8. A device for generating a financial product supply and demand matching list, characterized in that: The device comprises: an acquisition module, configured to periodically acquire from a database historical supply data of financial products by multiple supply institutions during a preset historical time period, the historical supply data comprising the historical expected target profit value and the historical actual profit value obtained by each supply institution during the preset historical time period, and the historical expected target transaction value and the historical actual transaction value completed by each supply institution during the preset historical time period; an adjustment module, configured to perform numerical calculations on the historical actual transaction values ​​and the historical expected target transaction values, adjust the attenuation factor of a preset penalty function algorithm based on the numerical calculation results, calculate a first profit variable weight coefficient for each supplier institution based on the adjusted penalty function algorithm, the historical expected target profit value, and the historical actual transaction value, calculate a second profit variable weight coefficient for each supplier institution based on the historical actual profit value and the first profit variable weight coefficient, and update a priority scoring formula for each supplier institution based on the first profit variable weight coefficient and the second profit variable weight coefficient; a calculation module configured to receive a financial product service application from a target user, extract financial product demand data from the service application, and calculate the financial product demand data using a risk value calculation formula corresponding to each supplier institution to generate a risk value corresponding to each supplier institution, wherein the financial product demand data includes the target user's demand amount and demand term; a ranking module for obtaining expected supply data of financial products from each supplier institution during a preset expected time period, the expected supply data including the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period; substituting the expected target profit value and expected target transaction value of each supplier institution during the preset expected time period into a priority scoring formula corresponding to each supplier institution, calculating a priority score corresponding to each supplier institution, and ranking each supplier institution according to the calculated priority score to obtain a priority order value for each supplier institution; A classification module is used to classify each supplier institution according to the expected supply data of the financial product and obtain a capital type label value corresponding to each supplier institution; The comprehensive module is used to substitute the capital type tag value, the priority order value, and the risk value into a predetermined matching value calculation formula to calculate the matching value, comprehensively sort the supply institutions according to the matching value, and generate a financial product supply and demand matching list for the target user based on the comprehensive sorting result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a financial product supply and demand matching list generation program that can be executed by the at least one processor, and the financial product supply and demand matching list generation program is executed by the at least one processor so that the at least one processor can execute the financial product supply and demand matching list generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a financial product supply and demand matching list generation program, which can be executed by one or more processors to implement the financial product supply and demand matching list generation method according to any one of claims 1 to 7.

Images