Fund party loan amount estimation method, device and equipment and storage medium

Abstract

The invention discloses a fund party loan amount estimation method and device, equipment and a storage medium, and the method comprises the steps: receiving a loan amount determination request, obtaining the historical loan data of an asset party based on the loan amount determination request, and obtaining the expected loan amount of each customer group corresponding to the asset party in a target period based on the historical loan data; historical loan data of the fund party for each customer group is determined, and the expected loan amount of the fund party for each customer group in the target period is acquired based on the historical loan data; and obtaining a change factor, determining a target fund party and a target loan quota corresponding to each customer group in the target period based on the expected loan quota, the expected loan quota and the change factor, and feeding back the target fund party and the target loan quota to a requester of the quota determination request. According to the method, the loan expectation and the loan expectation are estimated based on a large amount of historical data, the change value of the change factor is acquired in real time, and the estimated value is dynamically corrected, so that the estimation of the actual loan amount of the fund party is more accurately completed in real time.

Description

Technical Field

[0001] The present invention relates to the field of electronic financial technology, and in particular to a method, device, equipment and storage medium for estimating a funding party's loan amount. Background Art

[0002] Fintech companies connect with funding parties and provide funds to customers with loan needs. Customers with loan needs are called assets, and the institutions that provide funds are called funding parties. As the types and numbers of funding parties increase, such as consumer finance, small loans, local banks, trusts, etc., each funding party has a loan limit requirement for the fintech platform. As assets change, the appropriate loan limit for each funding party is an urgent problem that needs to be solved.

[0003] The current common practice is to manually calculate the loan quota of each funding party based on the loan quota requirements of historical assets, and make loans based on the calculation results. When the assets change, manual calculation is performed again.

[0004] The manual method of estimating the funding party's loan amount has a low ability to process large amounts of data and takes relatively few factors into consideration. The final actual loan amount is significantly different from the estimated result. Moreover, as the funding party and the asset party change in real time, manual work cannot meet the real-time changes in loan amounts and loan amount needs. Summary of the invention

[0005] The present invention provides a method, device, equipment and storage medium for estimating the loan amount of a funding party. By analyzing historical data to estimate loan demand and loan amount, and making corrections based on variable factors, the timeliness and accuracy of the funding party's loan amount estimation can be improved.

[0006] According to one aspect of the present invention, a method for estimating a funding party's loan amount is provided, comprising:

[0007] receiving a loan limit determination request, obtaining historical loan data of the asset party based on the loan limit determination request, and obtaining expected loan limit amounts of each customer group corresponding to the asset party within a target period based on the historical loan data;

[0008] Determine the historical loan data of the funding party for each of the customer groups, and obtain the expected loan amount of the funding party for each of the customer groups within the target period based on the historical loan data;

[0009] Obtaining a variation factor, and determining a target funding source and a target loan amount corresponding to each customer group within a target period based on the expected loan amount, the expected loan amount, and the variation factor, wherein the variation factor includes at least one of a loan amount variation factor and a loan amount variation factor;

[0010] The target funding party and the target loan amount are fed back to the requester of the amount determination request.

[0011] According to another aspect of the present invention, a funding party loan amount estimation device is provided, comprising:

[0012] A loan amount expected amount acquisition module, used to receive a loan amount determination request, acquire historical loan data of the asset party based on the loan amount determination request, and acquire the loan amount expected amount of each customer group corresponding to the asset party within a target period based on the historical loan data;

[0013] A module for obtaining an expected amount of loan quota, used to determine the historical loan data of the funding party for each of the customer groups, and to obtain the expected amount of loan quota of the funding party for each of the customer groups within the target period based on the historical loan data;

[0014] A target loan information determination module is used to obtain a variation factor, and determine the target funding party and target loan amount corresponding to each customer group within a target period based on the expected amount of the loan amount, the expected amount of the loan amount, and the variation factor, wherein the variation factor includes at least one of a loan amount variation factor and a loan amount variation factor;

[0015] The target loan information feedback module is used to feed back the target funding party and the target loan amount to the requester of the amount determination request.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor;

[0018] and a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for estimating the loan amount of the funding party described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for estimating the loan amount of a funding party described in any embodiment of the present invention when executed.

[0021] The technical solution of the embodiment of the present invention includes: receiving a credit limit determination request, obtaining the asset party's historical loan data based on the credit limit determination request, and obtaining the expected loan limit amount of each customer group corresponding to the asset party within the target period based on the historical loan data; determining the historical loan data of the funding party for each of the customer groups, and obtaining the expected loan limit amount of the funding party for each customer group within the target period based on the historical loan data; obtaining a variation factor, and determining the target funding party and target loan limit corresponding to each customer group within the target period based on the expected loan limit amount, the expected loan limit amount and the variation factor, wherein the variation factor includes at least one of a loan limit variation factor and a loan limit variation factor; and feeding back the target funding party and the target loan limit to the requester of the credit limit determination request. In the embodiment of the present invention, the loan amount demand of the asset party and the loan amount of the capital party are estimated based on a large amount of historical data, and the change value of the variable factor is obtained in real time, and the estimated value is dynamically corrected, which solves the problem that the manual estimation of the loan amount of the capital party has low processing capacity for a large amount of data, relatively few factors are considered, and the final actual loan amount is quite different from the calculated result. In addition, as the capital party and the asset party change in real time, the manual labor cannot meet the technical problem of the real-time changing loan amount and loan amount demand. It realizes the more real-time and accurate estimation of the loan amount of the capital party, which can not only reduce the labor cost of the enterprise, but also improve the refined operation efficiency of the loan amount of the capital party.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a method for estimating a loan amount of a funding party provided in the first embodiment of the present invention;

[0025] Figure 2 A flowchart of a method for estimating a funding party's loan amount provided in Embodiment 2 of the present invention;

[0026] Figure 3 A schematic diagram of the structure of a device for estimating the loan amount of a funding party provided in Embodiment 3 of the present invention;

[0027] Figure 4This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] Figure 1 This is a flowchart of a funding party loan amount estimation method provided in the first embodiment of the present invention. This embodiment can be applied to estimate the funding party loan amount so as to better recommend the funding party's situation to the asset party. The method can be executed by a funding party loan amount estimation device, which can be implemented in the form of hardware and / or software, and the device can be configured in a computer device. Figure 1 As shown, the method includes:

[0032] S110, receiving a loan limit determination request, obtaining historical loan data of an asset party based on the loan limit determination request, and obtaining expected loan limit amounts of each customer group corresponding to the asset party within a target period based on the historical loan data.

[0033] Among them, the credit limit determination request refers to a request to determine the loan limit of the funding party. For example, when a financial technology company recommends a suitable funding party to a customer with loan needs, a credit limit determination request can be generated through the account manager's terminal device.

[0034] Historical loan data can be loan-related data generated by the asset side in the historical time period. The target period can be a pre-set time range, for example, the target period can be the next hour, day, week, month, quarter or year. The customer group can be a customer group divided according to a certain attribute dimension of the asset side. The expected loan amount is used to indicate the expected demand for loan amount of each customer group. For example, if the expected demand for loan amount of customer group A in the next week is 50,000, then the expected loan amount is 50,000.

[0035] It is understandable that financial technology companies connect with funding parties. In order to provide services to customers with loan needs, they can estimate the expected loan amount of the asset party in the future target period based on the asset party’s historical loan data, so as to match the appropriate funding party in advance according to the expected loan amount, so as to meet the expected loan amount needs of each customer group.

[0036] In an embodiment of the present invention, historical loan data includes historical loan time, customer attribute information and loan amount. The method of obtaining the expected loan amount of each customer group corresponding to the asset party within the target period based on the historical loan data includes: determining at least two customer groups based on the customer attribute information; for each of the customer groups, determining the expected loan amount of the customer group through a trend analysis method according to the historical loan time and the loan amount corresponding to the customer group.

[0037] The historical loan time may be the application time, issuance time or repayment time of each loan of the asset party before the target cycle, and the loan amount may be the specific amount of each loan.

[0038] Customer attribute information includes at least one of customer acquisition channel, age range, loan amount range, region, risk level, product term and product pricing. Customer acquisition channel may refer to how customers establish contact with the fintech platform. Age range may be the age group of customers, such as 18-25 years old, 26-35 years old, etc. Loan amount range may be the range of loan amounts previously obtained by customers, such as 1,000-5,000 yuan, 5,000-10,000 yuan, etc. Region may be the geographical location of the customer, such as a city, province or region. Risk level may be an assessment of the customer's credit risk and repayment ability. Product term may be the repayment period of the loan product, and product pricing may be the interest rate of the loan product, etc.

[0039] Specifically, customers can be classified according to their attribute information to form different customer groups. The number of customer groups can be more than two, or can be set according to actual needs. When dividing customer groups, customers can be divided into different customer groups according to different business situations. The division of customer groups can be based on a single or multiple dimensions. For example, a customer group can be customers aged 18-25 with a loan amount of 1,000-5,000 yuan.

[0040] For each customer group, the historical loan time and loan amount of the customers corresponding to the customer group can be obtained, and trend analysis methods such as linear regression and time series analysis can be selected to establish a loan amount expectation model for the customer group, so as to predict the expected loan amount of the customer group in the target period through the loan amount expectation model. For example, for each customer group, a trend line is fitted using the historical loan time and loan amount corresponding to the customer group. The trend line can show the changing trend of the customer group's loan amount, and the expected loan amount of the customer group in the target period can be estimated through the trend line.

[0041] S120, determining the historical loan data of the funding source for each of the customer groups, and obtaining the expected loan amount of the funding source for each of the customer groups within the target period based on the historical loan data.

[0042] Among them, the historical loan data can be the data related to loans for each customer group by the funding party within a historical time period; the expected loan amount can be the estimated loan amount that the funding party can provide.

[0043] Specifically, there are loan records of the funding party to each customer group within the historical time period, and the loan records may include the customer's attributes, loan amount, loan time, etc. The loan records can be analyzed and processed, for example, divided according to different customer groups, and the loan records corresponding to each customer group are determined as the historical loan data corresponding to the customer group. Further, the historical loan data is analyzed and processed in time series, and specifically the historical loan data corresponding to different time points can be input into the long short-term memory network, and the long short-term memory network can output the expected loan amount. It should also be noted that the number of funding parties can be one or more. If there are multiple funding parties, the expected loan amount of each funding party to each customer group can be determined.

[0044] In an embodiment of the present invention, the expected loan amount of the funding party for each of the customer groups within the target period is obtained based on the historical loan data, including: according to the funding party type, the funding party's business model, the historical loan amount and the historical loan time, a combined forecasting method is used to determine the expected loan amount corresponding to each of the customer groups within the target period by the funding party.

[0045] Among them, historical loan data includes the type of funding party, the funding party's business model, the historical loan amount and the historical loan time. According to the historical loan data, the lending behavior of the funding party in the historical time period can be determined. The funding party type can be different types of loan funds, such as banks, consumer finance companies, microfinance companies, trusts, insurance, etc. Different types of funding parties can correspond to different lending strategies and risk preferences. The funding party business model can be the different operating models adopted by the funding party in the loan business, such as loan assistance, trust, joint loan, own funds, etc. The historical loan amount can be the loan amount that the funding party has issued to customers in the past, and the historical loan time can be the time record of the funding party issuing loans to customers in the past. According to the historical loan data, it is helpful to analyze the changing trend and periodicity of the loan amount.

[0046] Specifically, the combined forecasting method can be used to predict the loan amount to be used by the funding party for each customer group based on the funding party type, funding party business model, historical loan amount and historical loan time. For each customer group, you can first find some historical loan data that matches the current customer group from the historical loan data, and then perform time series analysis or regression analysis based on the historical loan time, historical loan amount, funding party type and funding party business model in this part of the historical loan data to predict the expected loan amount corresponding to each customer group by the funding party within the target period.

[0047] It should also be noted that when using the combined forecasting method, the expected amount of the loan amount can be estimated according to the time dimension, and the expected amount of the loan amount can also be estimated by combining the time dimension with other dimensions.

[0048] S130, obtaining a variation factor, and determining a target funding source and a target loan amount corresponding to each customer group within a target period based on the expected loan amount, the expected loan amount and the variation factor.

[0049] Among them, the variable factors include at least one of the asset side demand variable factors and the funding side quota variable factors, and the variable factors can affect the specific values ​​of the expected loan amount and the expected loan amount.

[0050] Specifically, the expected loan amount is the estimated loan demand of the customer group, and the expected loan amount can be the estimated loan amount of the funding party. The number of funding parties is one or more. In order to meet the loan demand of the customer, the expected loan amount can be matched with the expected loan amount, and the funding party or funding party combination that meets the expected loan amount can be determined as the target funding party, and the actual loan amount required by the target funding party is used as the target loan amount. This makes it easier to recommend the target funding party and target loan amount to the asset party more accurately.

[0051] It is understandable that in the loan business, various factors such as market environment, customer demand, and funding party strategy may change over time. The variable factors can be determined based on various factors. The variable factors have a direct impact on the expected loan amount and the expected amount of loan disbursement. Therefore, these expected values ​​need to be updated in a timely manner to reflect the actual situation.

[0052] In an embodiment of the present invention, obtaining the variation factor includes: inputting the historical loan data and the historical loan disbursement data into a large model to obtain the factor to be monitored inferred by the large model; when a change in the value corresponding to the factor to be monitored is detected, determining the factor to be monitored as the variation factor.

[0053] Among them, the factors to be monitored can be understood as indicators or variables that need to be monitored. For example, the factors to be monitored can be loan limits. Changes in the specific values ​​corresponding to the factors to be monitored will affect the expected amount of the loan amount or the expected amount of the loan amount.

[0054] Specifically, historical loan data and historical loan disbursement data can be input into the big model, and the big model can be used to analyze multiple features contained in the historical loan disbursement data and historical loan data, and determine some features that can affect the expected amount of loan amount or the expected amount of loan disbursement as factors to be monitored. Then, the specific data of the factors to be monitored is obtained in real time to monitor the factors to be monitored. As the market changes, when the specific value of at least one factor to be monitored changes, at least one factor to be monitored can be determined as a variable factor.

[0055] In an embodiment of the present invention, the historical loan data and the historical loan data are input into a large model to obtain the factors to be monitored inferred by the large model, including: performing reasoning and analysis on the historical loan data and the historical loan data through the large model to obtain multiple features to be selected and importance scores of the features to be selected; sorting the features to be selected based on the importance scores, and determining the factors to be monitored based on the sorting results of the features to be selected.

[0056] Among them, the candidate features can be one or more features inferred by the large model that may affect the expected amount of loan amount or the expected amount of loan disbursement. Different candidate features have different degrees of influence. The degree of influence of the candidate features on the expected amount of loan amount or the expected amount of loan disbursement can be quantified by the importance score.

[0057] Specifically, historical loan data and historical loan data are input into the big model. Since the data covers multiple dimensions such as the customer's loan record, repayment record, loan amount, loan term, etc., it can provide a rich source of information for the model. Then the big model uses its own reasoning and analysis capabilities to conduct in-depth analysis and feature mining of historical loan data and historical loan data, identify multiple candidate features related to the expected amount of loan amount or the expected amount of loan amount, and output importance scores. Furthermore, the candidate features are sorted based on the importance scores. In order to give priority to the candidate features that have the greatest impact on the expected amount of loan amount or the expected amount of loan amount as the factors to be monitored, the candidate features with the highest ranking can be used as the factors to be monitored.

[0058] In the embodiment of the present invention, the factors to be monitored that affect loans and loan issuance are automatically screened out from a large amount of data through intelligent analysis and reasoning of historical loan data and historical loan issuance data by a large model, without the need for financial operation service personnel to manually set the factors to be monitored after analyzing historical data, thus solving the problem of low manual processing capacity for a large amount of data, realizing automatic analysis and determination of the factors to be monitored, and improving the accuracy and timeliness of the final estimate of the loan amount of the funding party. By scoring and ranking the importance of the selected features, the factors to be monitored with great influence can be selected more accurately, and the value changes of the factors to be monitored can be monitored in real time and determined as change factors, thus realizing dynamic adjustment and optimization of the estimate of the loan amount of the funding party.

[0059] In an embodiment of the present invention, the target funding party and target loan amount corresponding to each customer group within the target period are determined, including: if the expected loan amount is less than or equal to the expected loan amount, the funding party corresponding to the expected loan amount is used as the target funding party, and the expected loan amount is used as the target loan amount.

[0060] It is understandable that the aforementioned steps have estimated the expected loan amount of each customer group in the target period based on historical loan data, which reflects the loan demand of each customer group in the future. The expected loan amount of each funding party in the target period has also been estimated based on historical loan data, which reflects the amount of funds available for loan by each funding party in the future.

[0061] The expected amount of loan quota and the expected amount of loan disbursement can be compared. For each customer group, the expected amount of loan quota of at least one funding party corresponding to the customer group is predicted to be compared with the expected amount of loan disbursement of the customer group. If the loan quota requirement can be met, the funding party can be used as the target funding party, and the expected amount of loan quota of the customer group can be used as the target loan disbursement amount of the funding party. Of course, if there are more than two funding parties, the two funding parties can jointly provide the corresponding target loan disbursement amount for the expected amount of loan quota.

[0062] S140: Feedback the target funding party and the target loan amount to the requester of the amount determination request.

[0063] Specifically, the target funding party and the target loan amount may be fed back to the terminal device corresponding to the amount determination request.

[0064] The technical solution of the embodiment of the present invention includes: receiving a credit limit determination request, obtaining the asset party's historical loan data based on the credit limit determination request, and obtaining the expected loan limit amount of each customer group corresponding to the asset party within the target period based on the historical loan data; determining the historical loan data of the funding party for each customer group, and obtaining the expected loan limit amount of the funding party for each customer group within the target period based on the historical loan data; obtaining a variation factor, and determining the target funding party and target loan limit corresponding to each customer group within the target period based on the expected loan limit amount, the expected loan limit amount and the variation factor, wherein the variation factor includes at least one of a loan limit variation factor and a loan limit variation factor; and feeding back the target funding party and the target loan limit to the requester of the credit limit determination request. In the embodiment of the present invention, the loan amount demand of the asset party and the loan amount of the capital party are estimated based on a large amount of historical data, and the change value of the variable factor is obtained in real time, and the estimated value is dynamically corrected, which solves the problem that the manual estimation of the loan amount of the capital party has low processing capacity for a large amount of data, relatively few factors are considered, and the final actual loan amount is quite different from the calculated result. In addition, as the capital party and the asset party change in real time, the manual labor cannot meet the technical problem of the real-time changing loan amount and loan amount demand. It realizes the more real-time and accurate estimation of the loan amount of the capital party, which can not only reduce the labor cost of the enterprise, but also improve the refined operation efficiency of the loan amount of the capital party.

[0065] Embodiment 2

[0066] Figure 2 This is a flowchart of a funding party loan amount estimation method provided in the second embodiment of the present invention. Based on the above embodiment, this embodiment further explains the process of adjusting the expected amount of loan amount and the expected amount of loan amount according to the variable factor. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or corresponding to the above embodiment are not repeated here. Figure 2 As shown, the method includes:

[0067] S210: receiving a loan limit determination request, obtaining historical loan data of an asset party based on the loan limit determination request, and obtaining expected loan limit amounts of each customer group corresponding to the asset party within a target period based on the historical loan data.

[0068] S220, determining the historical loan data of the funding party for each of the customer groups, and obtaining the expected loan amount of the funding party for each of the customer groups within the target period based on the historical loan data.

[0069] S230. Obtain a variation factor, and update the expected loan amount and / or the expected loan amount based on the variation factor.

[0070] In an embodiment of the present invention, updating the expected loan amount and / or the expected loan amount based on the change factor includes: determining a customer group division method and a waiting period based on the asset side change factor, and re-dividing the customer groups on the asset side based on the customer group division method to obtain each customer group to be updated; determining the expected loan amount to be updated and the expected loan amount to be updated corresponding to each customer group to be updated within the waiting period based on the waiting period and each customer group to be updated; updating the expected loan amount based on the expected loan amount to be updated, and updating the expected loan amount based on the expected loan amount to be updated.

[0071] The period to be updated may be a re-determined estimated period.

[0072] Specifically, a new customer group division method and a period to be updated are determined based on the asset side change factor. According to the new customer group division method, it can be more adaptable to the current business situation. The new customer group obtained after the customer group division method is re-divided is the customer group to be updated. Further, based on the new period to be updated and the customer group to be updated, the estimation process of the expected loan amount and / or the expected loan amount is re-executed. This process is the same as steps S210 and S220 and will not be repeated. Accordingly, the obtained new expected loan amount and expected loan amount are used as the expected loan amount to be updated and the expected loan amount to be updated, and then the original expected loan amount is updated based on the expected loan amount to be updated, and the original expected loan amount is updated based on the expected loan amount to be updated.

[0073] The embodiment of the present invention realizes the dynamic update of the expected loan amount and the expected loan amount through the above process, ensures the accuracy and timeliness of the predicted value, helps the funding party to better respond to customer needs and improve business efficiency, and for the asset party, it can also obtain more timely and accurate loan services.

[0074] In an embodiment of the present invention, updating the expected loan amount based on the variation factor includes: determining the remaining total credit limit, loan limit and additional limit of the funding party and the new funding party based on the funding party variation factor; updating the expected loan amount based on the remaining total credit limit, the loan limit and the additional limit.

[0075] Among them, the funding party change factors may include the current remaining total credit limit of each funding party, the current loan limit of each funding party, whether each current funding party supports additional credit limits (additional credit limits refer to whether it can continue to lend after the lending limit of the funding party is met), additional loan limits, types of new funding parties (consumer finance, trusts, banks, micro-loans, insurance), business models of new funding parties (assisted loans, trusts, joint loans, own funds), total credit limits of new funding parties, loan limits of new funding parties, whether new funding parties support additional credit limits, and additional loan limits of new funding parties.

[0076] Among them, the remaining total credit limit of the funding party = the total credit limit of the funding party - the loan limit already issued. The total credit limit of the funding party and the loan limit of the funding party are set to different values ​​according to the type and business model of the funding party. For example, the total credit limit of the trust and loan assistance model is 100 million, and the loan limit is 1 million / day. For the consumer finance and loan assistance model, the total credit limit is 1 billion, and the loan limit is 1 million / day. The loan limit already issued is collected regularly according to the selected estimation period, and the accumulated value of each funding party's loan limit is calculated and updated dynamically.

[0077] Specifically, the expected amount of the loan amount can be updated according to the change factor of the funding party, that is, the previously estimated expected amount of the loan amount can be adjusted in time according to the change factor.

[0078] In an embodiment of the present invention, the updating of the expected loan amount based on the remaining total credit limit, the loan limit and the additional credit limit includes: determining candidate funding parties from the funding parties and the newly added funding parties based on their priorities; and updating the expected loan amount based on the remaining total credit limit, loan limit and additional credit limit corresponding to the candidate funding parties.

[0079] Specifically, after obtaining the expected amount of loan quota, the remaining total credit limit of each funding party can be determined according to the change factor of the funding party, and the expected amount of loan quota can be adjusted in time based on the remaining total credit limit. If the remaining total credit limit is insufficient, that is, after adjusting the expected amount of loan quota according to the remaining credit limit, it does not meet the expected amount of loan quota of the asset party, the insufficient part needs to be supplemented. The specific supplementation method can be: if the priority of the current funding party is higher than that of the newly added funding party, it is preferred to find other funding parties with sufficient remaining total credit limit from the current funding party to supplement, and then select from the newly added funding party.

[0080] For example, if the expected loan amount is 1 million, the predicted expected loan amount of funding party A is 1 million, and the expected loan amount of funding party B is 200,000. However, according to statistics, funding party A has made more loans in the past, and its remaining total credit limit is only 800,000, which means that funding party A alone cannot meet the loan demand. At this time, if there is a new funding party, and the remaining total credit limit of the new funding party F is 200,000, and the current funding party B has a higher priority than the new funding party F, then the 800,000 limit of funding party A and the 200,000 limit of funding party B can be used to meet the expected loan amount. That is, the expected loan amount is 800,000 of funding party A and 200,000 of funding party B.

[0081] If the new funding party F's excellent grade is higher than the current funding party A, it is preferred to find a funding party with sufficient total credit limit from the new funding party to make up the difference, and then choose from the current funding party. That is, the 800,000 credit limit of funding party A and the 200,000 credit limit of the new funding party F are used to meet the loan demand. In other words, the expected loan amount is the 800,000 credit limit of funding party A and the 200,000 credit limit of the new funding party F.

[0082] If the loan quota is still insufficient, check whether each funding party supports additional quota and how much the additional quota is. If the current funding party has a higher priority than the new funding party, prioritize finding a funding party with sufficient additional quota among the current funding party to make up the difference, and then look for it from the new funding party. If the new funding party has a higher priority than the current funding party, prioritize finding a funding party with sufficient additional quota among the new funding party to make up the difference, and then look for it from the current funding party.

[0083] In the embodiment of the present invention, when the assets change, the expected amount of the loan amount estimated for the first time can be updated (re-dividing the customer group, reselecting the estimation period), and when the funding party changes, the change factor is updated (updating the remaining total credit limit of the current funding party and the newly added funding party, the loan limit, and the additional limit), and the historical data is updated regularly according to the estimation period. Repeating the above steps can automatically estimate the loan limits of all funding parties.

[0084] S240. Based on the updated expected loan amount and / or expected loan amount, determine the target funding party and target loan amount corresponding to each customer group within the target period.

[0085] S250: Feedback the target funding party and the target loan amount to the requester of the amount determination request.

[0086] The technical solution of the embodiment of the present invention includes: receiving a credit limit determination request, obtaining the asset party's historical loan data based on the credit limit determination request, and obtaining the expected loan limit amount of each customer group corresponding to the asset party within the target period based on the historical loan data. Determining the historical loan data of the funding party for each of the customer groups, and obtaining the expected loan limit amount of the funding party for each of the customer groups within the target period based on the historical loan data. Obtaining a variation factor, and updating the expected loan limit amount and / or the expected loan limit amount based on the variation factor. Based on the updated expected loan limit amount and / or the expected loan limit amount, determining the target funding party and target loan limit corresponding to each of the customer groups within the target period. In the embodiment of the present invention, the loan amount demand of the asset party and the loan amount of the capital party are estimated based on a large amount of historical data, and the change value of the variable factor is obtained in real time, and the estimated value is dynamically corrected, which solves the problem that the manual estimation of the loan amount of the capital party has low processing capacity for a large amount of data, relatively few factors are considered, and the final actual loan amount is quite different from the calculated result. In addition, as the capital party and the asset party change in real time, the manual labor cannot meet the technical problem of the real-time changing loan amount and loan amount demand. It realizes the more real-time and accurate estimation of the loan amount of the capital party, which can not only reduce the labor cost of the enterprise, but also improve the refined operation efficiency of the loan amount of the capital party.

[0087] Embodiment 3

[0088] Figure 3 This is a schematic diagram of the structure of a funding party loan amount estimation device provided in the third embodiment of the present invention. Figure 3 As shown, the device comprises:

[0089] The expected loan amount acquisition module 310 is used to receive a loan amount determination request, obtain historical loan data of the asset party based on the loan amount determination request, and obtain the expected loan amount of each customer group corresponding to the asset party within a target period based on the historical loan data;

[0090] The expected amount of loan amount acquisition module 320 is used to determine the historical loan data of the funding party for each of the customer groups, and obtain the expected amount of loan amount of the funding party for each of the customer groups within the target period based on the historical loan data;

[0091] The target loan information determination module 330 is used to obtain a variation factor, and determine the target funding party and target loan amount corresponding to each customer group within the target period based on the expected amount of the loan amount, the expected amount of the loan amount, and the variation factor, wherein the variation factor includes at least one of a loan amount variation factor and a loan amount variation factor;

[0092] The target loan information feedback module 340 is used to feed back the target funding party and the target loan amount to the requester of the loan determination request. The technical solution of the embodiment of the present invention includes: receiving a loan determination request, obtaining the historical loan data of the asset party based on the loan determination request, and obtaining the expected loan amount of each customer group corresponding to the asset party in the target period based on the historical loan data; determining the historical loan data of the funding party for each customer group, and obtaining the expected loan amount of the funding party for each customer group in the target period based on the historical loan data; obtaining the variation factor, and determining the target funding party and target loan amount corresponding to each customer group in the target period based on the expected loan amount, the expected loan amount and the variation factor, wherein the variation factor includes at least one of the loan amount variation factor and the loan amount variation factor; feeding back the target funding party and the target loan amount to the requester of the loan determination request. In the embodiment of the present invention, the loan amount demand of the asset party and the loan amount of the capital party are estimated based on a large amount of historical data, and the change value of the variable factor is obtained in real time, and the estimated value is dynamically corrected, which solves the problem that the manual estimation of the loan amount of the capital party has low processing capacity for a large amount of data, relatively few factors are considered, and the final actual loan amount is quite different from the calculated result. In addition, as the capital party and the asset party change in real time, the manual labor cannot meet the technical problem of the real-time changing loan amount and loan amount demand. It realizes the more real-time and accurate estimation of the loan amount of the capital party, which can not only reduce the labor cost of the enterprise, but also improve the refined operation efficiency of the loan amount of the capital party.

[0093] Based on the above technical solution, the historical loan data includes historical loan time, customer attribute information and loan amount, and the expected loan amount acquisition module 310 includes:

[0094] A customer group classification submodule, used to determine at least two customer groups based on the customer attribute information, wherein the customer attribute information includes at least one of customer acquisition channel, age range, loan amount range, region, risk level, product term and product pricing;

[0095] The expected loan amount acquisition submodule is used to determine the expected loan amount of each customer group through trend analysis method according to the historical loan time and loan amount corresponding to the customer group.

[0096] On the basis of the above technical solution, the historical loan data includes the funding party type, funding party business model, historical loan amount and historical loan time, and the expected loan amount acquisition module 320 includes:

[0097] The submodule for obtaining the expected loan amount is used to determine the expected loan amount of the funding party for each customer group within the target period by using a combined forecasting method based on the funding party type, funding party business model, historical loan amounts and historical loan times.

[0098] Based on the above technical solution, the target loan information determination module 330 includes:

[0099] The variation factor acquisition submodule is used to obtain the variation factor;

[0100] An updating submodule, used for updating the expected amount of the loan amount and / or the expected amount of the loan amount based on the change factor;

[0101] A determination submodule is used to determine the target funding party and target loan amount corresponding to each customer group within the target period based on the updated expected loan amount and / or expected loan amount.

[0102] On the basis of the above technical solution, the variation factor acquisition submodule is further used for:

[0103] The historical loan data and the historical loan disbursement data are input into the big model to obtain the factors to be monitored inferred by the big model; when a change in the value corresponding to the factors to be monitored is detected, the factors to be monitored are determined as the change factors.

[0104] On the basis of the above technical solution, the variation factor acquisition submodule further includes an inference unit, which is used to:

[0105] The historical loan data and the historical loan disbursement data are inferred and analyzed by the large model to obtain a plurality of candidate features and importance scores of the candidate features; the candidate features are sorted based on the importance scores, and the factors to be monitored are determined based on the sorting results of the candidate features.

[0106] Based on the above technical solution, the update submodule is specifically used for:

[0107] Determine the customer group division method and the period to be updated based on the asset side's change factor, and re-divide the customer groups on the asset side based on the customer group division method to obtain each customer group to be updated; determine the expected loan amount to be updated and the expected loan amount to be updated corresponding to each customer group to be updated within the period to be updated based on the period to be updated and each customer group to be updated; update the expected loan amount based on the expected loan amount to be updated, and update the expected loan amount based on the expected loan amount to be updated.

[0108] On the basis of the above technical solution, the updating submodule is further used for:

[0109] Based on the funding party change factor, the remaining total credit limit, loan limit and additional credit limit of the funding party and the new funding party are determined; based on the remaining total credit limit, the loan limit and the additional credit limit, the expected loan amount is updated.

[0110] On the basis of the above technical scheme, the update submodule is further specifically used for: determining candidate funding parties from the funding parties and the newly added funding parties based on the priorities of the funding parties and the newly added funding parties; updating the expected loan amount based on the remaining total credit limit, loan limit and additional limit corresponding to the candidate funding parties. The funding party loan amount estimation device provided in the embodiment of the present invention can execute the funding party loan amount estimation method provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0111] Embodiment 4

[0112] Figure 4 A schematic diagram of the structure of an electronic device provided for Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0113] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the funding party loan amount estimation method.

[0116] In some embodiments, the funding party loan amount estimation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the funding party loan amount estimation method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the funding party loan amount estimation method in any other appropriate manner (for example, by means of firmware).

[0117] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0119] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0122] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0123] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0124] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for estimating the loan amount of a funding party, characterized in that: include: receiving a loan limit determination request, obtaining historical loan data of the asset party based on the loan limit determination request, and obtaining expected loan limit amounts of each customer group corresponding to the asset party within a target period based on the historical loan data; Determine the historical loan data of the funding party for each of the customer groups, and obtain the expected loan amount of the funding party for each of the customer groups within the target period based on the historical loan data; Obtaining a variation factor, and determining a target funding source and a target loan amount corresponding to each customer group within a target period based on the expected loan amount, the expected loan amount, and the variation factor, wherein the variation factor includes at least one of a loan amount variation factor and a loan amount variation factor; The target funding party and the target loan amount are fed back to the requester of the amount determination request.

2. The method according to claim 1, characterized in that The historical loan data includes historical loan time, customer attribute information and loan amount. The method of obtaining the expected loan amount of each customer group corresponding to the asset party within the target period based on the historical loan data includes: Determine at least two customer groups based on the customer attribute information, wherein the customer attribute information includes at least one of customer acquisition channel, age range, loan amount range, region, risk level, product term and product pricing; For each of the customer groups, the expected loan amount of the customer group is determined by trend analysis method according to the historical loan time and loan amount corresponding to the customer group.

3. The method according to claim 1, characterized in that The historical loan data includes the funding party type, funding party business model, historical loan amount and historical loan time. The obtaining of the expected loan amount of the funding party for each customer group within the target period based on the historical loan data includes: Based on the funding party type, funding party business model, historical loan amount and historical loan time, a combined forecasting method is used to determine the expected loan amount corresponding to each customer group by the funding party within the target period.

4. The method according to claim 1, characterized in that: The obtaining of the variation factor comprises: Inputting the historical loan data and the historical loan disbursement data into the big model to obtain the factors to be monitored inferred by the big model; When a change in the value corresponding to the factor to be monitored is detected, the factor to be monitored is determined as the change factor.

5. The method according to claim 4, characterized in that The step of inputting the historical loan data and the historical loan disbursement data into a large model to obtain the factors to be monitored inferred by the large model includes: Performing reasoning analysis on the historical loan data and the historical loan disbursement data through the large model to obtain a plurality of candidate features and importance scores of the candidate features; The features to be selected are sorted based on the importance scores, and the factors to be monitored are determined based on the sorting results of the features to be selected.

6. The method according to claim 1, characterized in that The determining, based on the expected amount of loan amount, the expected amount of loan disbursement and the variation factor, the target funding party and the target loan disbursement amount corresponding to each customer group within the target period includes: Updating the expected amount of the loan amount and / or the expected amount of the loan disbursement based on the change factor; Based on the updated expected loan amount and / or expected loan amount, the target funding party and target loan amount corresponding to each customer group within the target period are determined.

7. The method according to claim 6, characterized in that The updating of the expected amount of loan amount and / or the expected amount of loan disbursement based on the variation factor includes: Determine a customer group division method and a waiting-for-update period based on the asset side change factor, and re-divide the customer groups of the asset side based on the customer group division method to obtain customer groups to be updated; Based on the to-be-updated period and each of the to-be-updated customer groups, determining the expected amount of loan quotas to be updated and the expected amount of loan disbursement to be updated corresponding to each of the to-be-updated customer groups within the to-be-updated period; The expected loan amount is updated based on the expected loan amount to be updated, and the expected loan amount is updated based on the expected loan amount to be updated.

8. The method according to claim 6, characterized in that The updating of the expected amount of loan amount based on the variation factor includes: Determine the remaining total credit limit, loan limit and additional credit limit of the funding party and the new funding party based on the funding party change factor; Based on the remaining total credit limit, the loan limit and the additional credit limit, the expected loan amount is updated.

9. The method according to claim 8, characterized in that The updating of the expected amount of loan amount based on the remaining total credit limit, the loan limit and the additional credit limit includes: Determining candidate funding parties from among the funding parties and the newly added funding parties based on the priorities of the funding parties and the newly added funding parties; The expected amount of the loan amount is updated based on the remaining total credit limit, loan limit and additional credit limit corresponding to the candidate funding party.

10. A device for estimating the loan amount of a funding party, characterized in that: include: A loan amount expected amount acquisition module, used to receive a loan amount determination request, acquire historical loan data of the asset party based on the loan amount determination request, and acquire the loan amount expected amount of each customer group corresponding to the asset party within a target period based on the historical loan data; A module for obtaining an expected amount of loan quota, used to determine the historical loan data of the funding party for each of the customer groups, and to obtain the expected amount of loan quota of the funding party for each of the customer groups within the target period based on the historical loan data; A target loan information determination module is used to obtain a variation factor, and determine the target funding party and target loan amount corresponding to each customer group within a target period based on the expected amount of the loan amount, the expected amount of the loan amount, and the variation factor, wherein the variation factor includes at least one of a loan amount variation factor and a loan amount variation factor; The target loan information feedback module is used to feed back the target funding party and the target loan amount to the requester of the amount determination request.

11. 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 computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for estimating the loan amount of the funding party as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the funding party loan amount estimation method described in any one of claims 1-9 when executed.

Images