CN117273723B - Settlement prediction method, settlement prediction device, computer device and storage medium - Google Patents
Settlement prediction method, settlement prediction device, computer device and storage medium Download PDFInfo
- Publication number
- CN117273723B CN117273723B CN202311130331.2A CN202311130331A CN117273723B CN 117273723 B CN117273723 B CN 117273723B CN 202311130331 A CN202311130331 A CN 202311130331A CN 117273723 B CN117273723 B CN 117273723B
- Authority
- CN
- China
- Prior art keywords
- amount
- settlement
- calculated
- calculation
- preparation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/22—Payment schemes or models
- G06Q20/24—Credit schemes, i.e. "pay after"
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present application relates to the field of data processing technologies, and in particular, to a settlement prediction method, apparatus, computer device, and storage medium. The settlement prediction method comprises the following steps: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest; substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error. The settlement mechanism of each target mechanism can be predicted by adopting the method, and the corresponding preparation model is selected from a plurality of preparation modes for each target mechanism to be used as a prediction mode for predicting the settlement amount, so that the reliability of settlement amount prediction is improved.
Description
Technical Field
The present application relates to the field of data processing technology, and in particular, to a settlement prediction method, a settlement prediction apparatus, a computer device, and a computer-readable storage medium.
Background
With the rapid development of the internet financial industry, frequent settlement transactions exist between lending institutions, loan bodies, and the like, and financial institutions. In the current settlement link, financial institutions often take initiative, and the settlement amount is typically provided by the financial institutions. Once the settlement amount provided by the financial institution is wrong, there is a risk that the parties participating in the settlement scene cannot find the settlement amount wrong.
Disclosure of Invention
In view of the above, it is desirable to provide a settlement prediction method, a settlement prediction device, a computer device, and a computer-readable storage medium, which are capable of predicting settlement mechanisms of respective target institutions and selecting a preliminary model to which each target institution is applied from a plurality of preliminary models as a prediction model for predicting a settlement amount, and which are advantageous in improving reliability of settlement amount prediction.
In one aspect, a settlement prediction method is provided, the settlement prediction method including: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest; substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In one embodiment of the application, the preliminary model includes a structuring module and a floating module; substituting the basic amount into a plurality of preparation models for calculation respectively, and outputting an estimated amount each time comprises: substituting the basic amount into each preparation model to respectively calculate a plurality of times, wherein each preparation model calculates a plurality of calculated amounts based on the basic amount; the method comprises the steps that a structuring module calculates fixed amount in each calculation process, and a floating module calculates floating amount with strong correlation with a settlement scene based on time information; and fusing the results output by the structuring module and the floating module to obtain the calculated amount.
In one embodiment of the present application, the settlement scenario includes an overdue scenario; the method is applied to a preparation model of a overdue scene, a structured model calculates the superposition amount of principal and interest as fixed amount, and a floating module calculates the product of the overdue amount, overdue days and overdue interest rate to obtain overdue penalty information as floating amount; the method is applied to a plurality of preparation models of overdue scenes, and at least one of overdue amount, overdue days and overdue interest rate is calculated in different manners.
In one embodiment of the present application, the settlement scene includes a pre-settlement scene; the method is applied to a preparation model of an advanced settlement scene, and a structuring module calculates the remaining principal to be settled; the floating module calculates additional cost; the method is applied to a plurality of preparation models of a settlement scene in advance, and at least two additional cost calculation modes exist; the at least two additional cost calculation modes include: the remaining principal to be returned, the calculated time length and the initial daily interest rate are multiplied and added to form a commission; all interest to be returned is superimposed.
In an embodiment of the present application, the preliminary model includes a derivation formula for deriving the settlement amount, the derivation formula including a rule factor to be derived; the preparation model carries out calculation respectively, and each calculation output a calculation amount comprises: substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation.
In one embodiment of the present application, a settlement prediction method includes: acquiring a standard value range of the rule factors; determining a possible maximum value and a possible minimum value of the rule factors based on the canonical value range; selecting a plurality of possible values between the possible maximum value and the possible minimum value; calculating the calculated amount corresponding to each possible value respectively; comparing each calculated amount with the settlement amount, and updating a possible maximum value and a possible minimum value based on the comparison result; and taking the possible value of the calculated amount matched with the settlement amount as the value of the rule factor until the calculated amount of the possible value is matched with the settlement amount.
In one embodiment of the present application, a settlement prediction method includes: acquiring a target mechanism and a basic amount to which a bill to be predicted belongs; invoking a prediction mode matched with a target mechanism to which the bill to be predicted belongs; and inputting the basic amount of the bill to be predicted into the called prediction model to obtain the predicted amount of the bill to be predicted.
In another aspect, there is provided a settlement prediction apparatus including: the device comprises an acquisition module and a control module; the acquisition module is used for acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest; the control module is connected with the acquisition module and is used for substituting the basic amount into a plurality of preparation models respectively to calculate, and each calculation outputs a calculated amount; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In yet another aspect, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest; substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In yet another aspect, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the steps of obtaining a base amount, a settlement amount, and time information for historical settlement of a plurality of target institutions in a settlement scenario; wherein the base amount includes principal and interest; substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
The settlement prediction method, settlement prediction device, computer device, and computer-readable storage medium acquire relevant information of historical settlement of each target institution in a settlement scene, namely, a base amount, a settlement amount, time information, and the like. Calculating the amount of possible settlement by using the basic amount and a plurality of pre-designed preparation models respectively to obtain calculated amount, wherein the preparation models are the calculated amount obtained by using a preset target institution possible settlement mechanism, and comparing the calculated amount with the actual settlement amount to determine the preparation model applicable to the target institution as a prediction mode for predicting the settlement amount. If so, the settlement mechanism of each target organization predicts, and selects the preparation model applicable to each target organization from a plurality of preparation modes as the prediction mode for predicting the settlement amount, thereby being beneficial to improving the reliability of settlement amount prediction.
Drawings
FIG. 1 is a flow chart of an embodiment of a settlement prediction method of the present application;
FIG. 2 is a flow chart of an embodiment of a method for obtaining a predictive model according to the present application;
FIG. 3 is a flow chart of another embodiment of the settlement prediction method of the present application;
FIG. 4 is a window diagram of one embodiment of the pre-settlement scene visualization of the present application;
FIG. 5 is a window diagram of an embodiment of the overdue scene visualization of the present application;
FIG. 6 is a schematic diagram showing the construction of an embodiment of the settlement prediction apparatus according to the present application;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In order to solve the technical problems that the method for acquiring the settlement amount is passive and lacks verification measures in the prior art, the application provides a settlement prediction method, a settlement prediction device, computer equipment and a computer readable storage medium. The settlement prediction method comprises the following steps: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest; substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time; calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error. The following exemplifies the detailed embodiments of the present application.
In one embodiment, as shown in fig. 1, a settlement prediction method is provided, and fig. 1 is a flow chart of an embodiment of the settlement prediction method of the present application.
S101: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest.
In this embodiment, the target institution may be a financial institution whose settlement mechanism is to be predicted.
Historical settlement refers to a settlement transaction that has occurred or completed, with explicit base amount, settlement amount, and time information.
The settlement amount is the amount actually settled. The time information may be used to identify whether the historical settlement is on-time settlement, such as on-time settlement, overdue settlement, advanced settlement, etc., without limitation.
Historical settlement data of each target institution under the settlement scene is obtained, and the settlement mechanism of each target institution is deduced by using the real historical settlement data, so that the authenticity and reliability of the deduction process are improved.
S102: and substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time.
In the present embodiment, a plurality of preliminary models are previously established. The calculation method comprises the steps that a plurality of preparation models calculate calculated amount by utilizing different calculation mechanisms respectively, namely the calculation mechanisms of the preparation models are different, and the calculation mechanisms correspond to the calculation mechanisms of a target mechanism for calculating a settlement scene.
In the process of selecting the corresponding preparation model for each target organization, the basic amount of one-time historical settlement can be substituted into each preparation model, each preparation model is calculated based on the basic amount, and the calculated amount related to the basic amount obtained by calculating each preparation model is obtained.
S103: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In this embodiment, when a prediction model is selected for each target institution, at least one historical settlement of the target institution is calculated through a plurality of preliminary models, each of the base amounts of the historical settlement obtains a plurality of estimated amounts associated with the base amounts, and a difference between the estimated amount associated with each of the base amounts and the actual settlement amount is calculated as an estimated error of each of the preliminary models for the historical settlement estimation.
And synthesizing at least one calculation error of each preparation model aiming at least one historical settlement of a target mechanism, considering that the preparation model with the minimum overall error is applicable to the settlement mechanism of the current target mechanism, and selecting the preparation model with the minimum overall error as a prediction model of the current target mechanism. The overall error may be a weighted fusion, average, variance, etc. of at least one of the estimated errors, which is not limited herein.
Similarly, a preliminary model to which the settlement mechanism is applied is selected as a prediction model for predicting the settlement amount for each target institution.
Therefore, in this embodiment, a plurality of preliminary models of possible settlement mechanisms are prepared for each target institution, the calculated amount is calculated based on the basic amount of settlement through each preliminary model, the calculated amount is compared with the real settlement amount, and the overall error of at least one historical settlement calculation for each target institution is calculated through the global calculation preliminary model, so that the preliminary model applicable to the settlement mechanism of each target institution is selected as the prediction model, and the reliability of the prediction model is improved. If so, the target institutions can be predicted, so that the settlement amount can be predicted in the settlement period, the problem that the settlement amount provided by the financial institutions cannot be checked can be solved, meanwhile, the financial institutions can obtain the predicted amount by the method, and the accuracy of the settlement amount is considered by taking the predicted amount as a reference in advance. Therefore, in this embodiment, the settlement mechanism of each target mechanism can be predicted, and the corresponding preparation model is selected from the plurality of preparation modes as the prediction mode for predicting the settlement amount, which is beneficial to improving the reliability of settlement amount prediction.
In an embodiment, as shown in fig. 2, a settlement prediction method is provided, and fig. 2 is a flow chart of an embodiment of a method for obtaining a prediction model according to the present application. It should be noted that, this embodiment may be an extension of the foregoing embodiment, and this embodiment includes all the contents in the foregoing embodiment, and some of the same contents are not described herein again.
S201: and acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene.
In this embodiment, the base amount includes principal and interest.
The settlement scene generally comprises a conventional settlement scene, and can further comprise a overdue scene and/or an advanced settlement scene and the like. That is, the settlement scene in the present application may be a single settlement scene or may include a plurality of settlement scenes. And the settlement amount of the multi-settlement scene is predicted, so that the functionality of the settlement prediction method is improved, and the applicable settlement scene is enriched. The calculation scenario including the overdue scenario and the advanced settlement scenario will be exemplified later.
S202: the basic amount is substituted into the plurality of preliminary models, respectively.
In this embodiment, the preparation model may calculate the calculation transaction based on the base amount, and obtain the calculated amount.
Further, the preliminary model includes a structuring module and a floating module. The structuring module may be used to calculate a relatively fixed amount of money, such as based on principal, interest, etc. settled in the contracted contract. The floating module is used for calculating the relative individuation parts of each target mechanism, such as different overdue interest, late gold and the like.
Optionally, the preliminary model comprises a derivation formula for deriving the settlement amount, the derivation formula comprising a rule factor to be derived. The rule factors to be deduced are parameter factors which are set by each target organization in the standard value range and are ambiguous by other institutions/persons, such as overdue interest rate, commission fee and the like.
S203: and respectively estimating in each preparation model, and outputting an estimated amount for each estimation.
In this embodiment, the basic amount is substituted into each of the preliminary models to estimate a plurality of times, and each of the preliminary models estimates a plurality of estimated amounts based on the basic amount.
The floating module calculates floating amount with strong correlation with settlement scenes based on time information. And fusing the results output by the structuring module and the floating module to obtain the calculated amount.
Optionally, substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation. In other words, when each preparation model performs calculation based on a basic amount, a plurality of calculation amounts can be calculated for a plurality of times, and rule factors to be predicted are continuously changed in each calculation process, so that a prediction model applicable to a target mechanism is selected from a plurality of preparation models using the most applicable specification factors after finding the rule factors most applicable to the target mechanism by each preparation model. And if so, the reliability of the prediction model is further facilitated, and the accuracy of the predicted amount is improved.
Alternatively, in selecting the most applicable rule factor, a canonical value range of the rule factor may be obtained. The possible maximum and possible minimum values of the rule factors are determined based on the canonical value range. And selecting a plurality of possible values between the possible maximum value and the possible minimum value. Calculating the estimated amount corresponding to each possible value. And comparing each calculated amount with the settlement amount, and updating the possible maximum value and the possible minimum value based on the comparison result. And until the calculated amount of a possible value is matched with the settlement amount, taking the possible value of the calculated amount matched with the settlement amount as the value of the rule factor, thereby realizing the rapid positioning of the rule factor, improving the efficiency of selecting the rule factor, and further improving the efficiency of selecting the prediction model.
S204: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount.
In this embodiment, the calculation error may be a difference between the calculated amount and the settlement amount, or may be a value obtained by performing data processing such as weighting on the difference between them, and is not limited herein.
S205: and respectively selecting a preparation model for each target mechanism as a prediction model based on the calculation errors.
In this embodiment, the specific implementation of step S204 and step S205 is similar to the implementation of S103 in the above embodiment, and is not limited herein.
The following illustrates various settlement scenarios:
the settlement scenario may include an overdue scenario. The settlement amount of the overdue scene is equal to the superposition amount of principal, interest and overdue penalty.
Specifically, the method is applied to a preparation model of a overdue scene, a structured model calculates the superposition amount of principal and interest as a fixed amount, and a floating module calculates the product of the overdue amount, the overdue days and the overdue interest rate to obtain overdue penalty as a floating amount; the method is applied to a plurality of preparation models of overdue scenes, and at least one of overdue amount, overdue days and overdue interest rate is calculated in different manners.
For example, the overdue default interest may be the product of the overdue amount, the overdue number of days, and the overdue interest rate.
The overdue amount may be calculated as the amount of overdue principal or the sum of overdue principal and overdue interest.
The overdue days may be calculated by a number of days exceeding the overdue payoff day, or by a number of days exceeding the overdue payoff day superimposed on the floating number of days. The number of days exceeding the overdue repayment date is the number of days of the interval between the overdue repayment date and the due repayment date.
The penalty rate may be calculated either at the original capital cost or by adding a float percentage to the original capital cost.
When the method is applied to the overdue scene to calculate the overdue penalty, the calculation modes of overdue amount, overdue days and default interest interest can be selected from the calculation modes respectively for combination to form each preparation model of the overdue scene.
For example, in the derivation formula of the first preliminary model applied to the overdue scene, the floating model is calculated as: overdue penalty = overdue principal > exceeds the number of days of overdue payoff days. In the derivation formula of the second preparation model applied to the overdue scene, the calculation of the floating model is as follows: the overdue penalty = overdue principal x exceeds the number of days of overdue payoff days by an increase in float percentage over the original capital cost. And so on, a plurality of preparation models applied to overdue scenes are formed, and will not be described herein.
The settlement scenario may include an advanced settlement scenario. The settlement amount of the preset advanced settlement scene can be the rest principal daily accounting or the rest repayment amount.
The method is applied to a preparation model of an advanced settlement scene, and a structuring module calculates the remaining principal to be settled; the floating module calculates additional cost; the method is applied to a plurality of preparation models of a settlement scene in advance, and at least two additional cost calculation modes exist; the at least two additional cost calculation modes include: the remaining principal to be returned, the calculated time length and the initial daily interest rate are multiplied and added to form a commission; all interest to be returned is superimposed. Further, the additional cost may also include first-term interest, etc., which is not limited herein.
For example, in the third preparation model applied to the advanced settlement scene, the estimated amount is the superposition of the remaining principal and the original due interest. The original interest is the superposition of all the interest to be reduced.
And the calculation amount is the superposition of the product of the remaining principal to be restored, the calculated time length and the initial daily interest rate and the remaining principal to be restored and the commission fee in the fourth preparation model applied to the advanced settlement scene. The fee is a personalized part of each target organization, and may be additionally charged under the scene of clearing in advance, namely, the fee belongs to one of the rule factors.
Of course, the target institution can also be considered to not charge the commission, namely, the method is applied to the fourth preparation model of the advanced settlement scene, and the calculated amount is the superposition of the product of the remaining principal to be restored, the calculated time length and the initial daily interest rate and the remaining principal to be restored.
Further, the settlement scene may include a regular settlement scene, an overdue scene, and an advanced settlement scene. The conventional settlement scene is equivalent to the settlement of an expired repayment order, and the settlement amount is the superposition of principal and interest.
In one embodiment, as shown in fig. 3, a settlement prediction method is provided, and fig. 3 is a flow chart of another embodiment of the settlement prediction method of the present application.
S301: and obtaining a target organization and a basic amount to which the bill to be predicted belongs.
In this embodiment, the document to be predicted is a document to be predicted for the settlement amount, and may be an ongoing settlement transaction, a future settlement transaction, or a historical settlement transaction, which is not limited herein.
S302: and calling a prediction mode matched with a target mechanism to which the bill to be predicted belongs.
In the present embodiment, the prediction mode is a preliminary model selected from the plurality of preliminary models and applied to the settlement mechanism of the current target institution as the prediction model in the embodiment set forth above.
Alternatively, when the preliminary model is selected as the prediction model, the preliminary model is given an identifier carrying the applicable target institution, so that when the amount of the calculation is predicted, the corresponding prediction model can be invoked. Alternatively, after confirming the prediction model of the target institution, a mapping relationship between the target institution and the prediction model is formed, and when the settlement amount needs to be predicted, the prediction model matched with the target institution is called, which is not limited herein.
S303: and inputting the basic amount of the bill to be predicted into the called prediction model to obtain the predicted amount of the bill to be predicted.
In this embodiment, the basic amount of the bill to be predicted is used as the input of the prediction model, the prediction model performs prediction calculation, and the output of the prediction model can be used as the predicted amount of the bill to be predicted.
Optionally, the time information of the bill to be predicted can also be input into the prediction model to obtain the predicted amount.
The settlement amount of the bill to be predicted can be compared with the predicted amount, and whether the difference value of the settlement amount and the predicted amount is within the tolerance range is judged. If the difference value of the two is within the tolerance range, judging that the settlement amount is correct; if the difference value of the two is within the tolerance range, the settlement amount is judged to be in doubt, so that the settlement amount can be found out in time when the settlement amount is in doubt, and the settlement amount can be confirmed and checked with a financial institution.
In summary, the present application selects a prediction model for each target institution under each settlement scenario, so as to calculate whether the settlement amount provided by the financial institution is within the tolerance range. The deduction formula is used for reversing the settlement mechanism of the target institution aiming at the settlement amount of different scene historic settlement. For example, the components of the settlement amount of the conventional settlement scene are principal and interest; the overdue scene settlement amount comprises principal, interest and penalty; the components for clearing the scene settlement amount in advance include the remaining principal, first-stage interest and the like. The calculation modes of default interest amount, first-period interest and the like of each target institution can be considered to be different; meanwhile, the number of decimal accurate digits in settlement amount calculation is different. That is, the application can also learn the decimal accuracy of the settlement amount, and superimpose the decimal accuracy in the process of obtaining the estimated amount and/or the predicted amount, thereby being beneficial to improving the accuracy of the estimated amount and/or the predicted amount.
The application can reversely calculate the differential calculation logic of each financial institution according to the settlement amount of the historical settlement of the financial institution, and finally extract the calculation formula applicable to each financial institution, namely the derivation formula. Furthermore, the application can also carry out visual and configurable processing on parameters required by calculation of the deduction formula, thereby facilitating users to intuitively and accurately know. The visualization window may be applicable to a process of selecting a prediction model, or may be applicable to a process of predicting a settlement amount to obtain a predicted amount, which is not limited herein.
As illustrated in fig. 4 and 5, fig. 4 is a window diagram of an embodiment of the early settlement scene visualization of the present application, and fig. 5 is a window diagram of an embodiment of the overdue scene visualization of the present application.
A visual window in the advanced settlement scene can be used for checking the calculation mode of settlement amount, the advanced settlement number of days whether to adjust the number of days of interest in the first period, whether to collect the fee of advance clearing, the proportion of the fee of advance clearing, etc.
The visual window in the overdue scene can be used for checking a calculation formula of the settlement amount, overdue grace period (such as floating days), whether to collect penalty, default interest years' interest rate, default interest collection technology, penalty and number of days.
It is easy to understand that the content available for viewing in the visualization window can be adjusted according to actual requirements, for example, adding detailed deduction formulas, reducing part of parameters in the figure, and the like, which is not limited herein. Further, the user-defined permission can be opened to the user, so that the user can conveniently define the display content and the arrangement mode of the visual window according to the self requirement, the functionality of the visual window can be improved, the user requirement of the user can be met, and the user experience of the user can be improved.
Meanwhile, the orders to be settled can be fetched periodically, such as daily, weekly, monthly, etc., the amounts to be settled of each order are calculated and accumulated to obtain the total amount, and the total amount is compared with the total settlement amount provided by the financial institution for reference comparison. Thus, the settlement logic of the financial institution does not need to be confirmed by the financial institution, and the communication cost is reduced.
It should be understood that, although the steps in the flowcharts of fig. 1-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, a settlement prediction device is provided, and fig. 6 is a schematic structural diagram of an embodiment of the settlement prediction device of the present application.
The settlement prediction device includes an acquisition module 41 and a control module 42.
The obtaining module 41 is configured to obtain a base amount, a settlement amount, and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest.
The control module 42 is connected to the obtaining module 41, and is configured to substitute the basic amount into a plurality of preliminary models, calculate each preliminary model, and output a calculated amount each time; calculating an estimated error between the estimated amount and the settled amount associated with the same basic amount, and selecting one preparation model for each target institution as a prediction model based on the estimated error.
For specific limitations on the settlement prediction apparatus, reference may be made to the above limitations on the settlement prediction method, and the details are not repeated here. The respective modules in the settlement prediction apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, as shown in fig. 7, a computer device is provided, and fig. 7 is a schematic structural diagram of an embodiment of the computer device according to the present application.
In this embodiment, the computer device may be a server, or may be a mobile terminal device such as a mobile phone, a computer, a tablet, etc., which is not limited herein.
Alternatively, the computer device may be a server, and the computer device includes a processor, memory, and a network interface connected by a system bus.
Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a settlement prediction method.
Alternatively, the computer device may be a terminal, and the computer device may include a processor, a memory, a network interface, a display screen, and an input device connected by a system bus.
Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a settlement prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by persons skilled in the art that the structures described above are merely block diagrams of partial structures associated with the aspects of the application and do not constitute a limitation of the computer apparatus to which the aspects of the application may be applied, and that a particular computer apparatus may include more or less components than those shown in the figures, or may combine some of the components, or have a different arrangement of components.
Further, the computer device may comprise a processor 51, a memory 52 and a computer program stored on the memory 52 and executable on the processor 51, the processor 51 implementing the following steps when executing the computer program:
s101: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest.
S102: and substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time.
S103: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In an embodiment, the processor when executing the computer program further performs the steps of:
s201: and acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene.
In this embodiment, the base amount includes principal and interest.
S202: the basic amount is substituted into the plurality of preliminary models, respectively.
In this embodiment, the preliminary model includes a structuring module and a floating module.
Optionally, the preliminary model comprises a derivation formula for deriving the settlement amount, the derivation formula comprising a rule factor to be derived.
S203: and respectively estimating in each preparation model, and outputting an estimated amount for each estimation.
In this embodiment, the basic amount is substituted into each of the preliminary models to estimate a plurality of times, and each of the preliminary models estimates a plurality of estimated amounts based on the basic amount.
Optionally, substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation.
Optionally, acquiring a specification value range of the rule factors; determining a possible maximum value and a possible minimum value of the rule factors based on the canonical value range; selecting a plurality of possible values between the possible maximum value and the possible minimum value; calculating the estimated amount corresponding to each possible value. And comparing the calculated amount corresponding to each possible value with the settlement amount. And taking the calculated amount corresponding to each possible value, the possible maximum value and the possible minimum value as an amount node, confirming the amount node closest to both sides of the settlement amount, namely, confirming the amount node which is larger than the settlement amount and closest to the settlement amount and the amount node which is smaller than the settlement amount and closest to the settlement amount, and taking the possible value/the possible maximum value/the possible minimum value corresponding to the two closest amount nodes as new possible maximum values and possible minimum values, wherein the possible maximum values and the possible minimum values are updated based on the comparison result. And taking the possible value of the calculated amount matched with the settlement amount as the value of the rule factor until the calculated amount of the possible value is matched with the settlement amount.
Alternatively, the number of possible values may be one, two, three, four, etc., without limitation.
In an alternative embodiment, when calculating the rule factor, the likelihood value of the rule factor may be substituted into the derivation formula to calculate, and the obtained likelihood value closest to the calculated amount and the rule factor is selected as the value of the rule factor.
The method comprises the steps that a structuring module calculates fixed amount in each calculation process, and a floating module calculates floating amount with strong correlation with a settlement scene based on time information; and fusing the results output by the structuring module and the floating module to obtain the calculated amount.
The settlement scenario includes a overdue scenario. The method is applied to a preparation model of a overdue scene, a structured model calculates the superposition amount of principal and interest as fixed amount, and a floating module calculates the product of the overdue amount, overdue days and overdue interest rate to obtain overdue penalty information as floating amount; the method is applied to a plurality of preparation models of overdue scenes, and at least one of overdue amount, overdue days and overdue interest rate is calculated in different manners.
The settlement scene includes an advanced settlement scene. The method is applied to a preparation model of an advanced settlement scene, and a structuring module calculates the remaining principal to be settled; the floating module calculates additional cost; the method is applied to a plurality of preparation models of a settlement scene in advance, and at least two additional cost calculation modes exist; the at least two additional cost calculation modes include: the remaining principal to be returned, the calculated time length and the initial daily interest rate are multiplied and added to form a commission; all interest to be returned is superimposed.
S204: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount.
S205: and respectively selecting a preparation model for each target mechanism as a prediction model based on the calculation errors.
In an embodiment, the processor when executing the computer program further performs the steps of:
S301: and obtaining a target organization and a basic amount to which the bill to be predicted belongs.
S302: and calling a prediction mode matched with a target mechanism to which the bill to be predicted belongs.
S303: and inputting the basic amount of the bill to be predicted into the called prediction model to obtain the predicted amount of the bill to be predicted.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
s101: acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest.
S102: and substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time.
S103: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount, and selecting a preparation model for each target institution as a prediction model based on the calculation error.
In an embodiment, the computer program when executed by the processor further performs the steps of:
s201: and acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene.
In this embodiment, the base amount includes principal and interest.
S202: the basic amount is substituted into the plurality of preliminary models, respectively.
In this embodiment, the preliminary model includes a structuring module and a floating module.
Optionally, the preliminary model comprises a derivation formula for deriving the settlement amount, the derivation formula comprising a rule factor to be derived.
S203: and respectively estimating in each preparation model, and outputting an estimated amount for each estimation.
In this embodiment, the basic amount is substituted into each preliminary model to calculate a plurality of times, and each preliminary model calculates a plurality of calculated amounts based on the basic amount;
Optionally, substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation.
Optionally, acquiring a specification value range of the rule factors; determining a possible maximum value and a possible minimum value of the rule factors based on the canonical value range; selecting a plurality of possible values between the possible maximum value and the possible minimum value; calculating the calculated amount corresponding to each possible value respectively; comparing each calculated amount with the settlement amount, and updating a possible maximum value and a possible minimum value based on the comparison result; and taking the possible value of the calculated amount matched with the settlement amount as the value of the rule factor until the calculated amount of the possible value is matched with the settlement amount.
The method comprises the steps that a structuring module calculates fixed amount in each calculation process, and a floating module calculates floating amount with strong correlation with a settlement scene based on time information; and fusing the results output by the structuring module and the floating module to obtain the calculated amount.
The settlement scenario includes a overdue scenario. The method is applied to a preparation model of a overdue scene, a structured model calculates the superposition amount of principal and interest as fixed amount, and a floating module calculates the product of the overdue amount, overdue days and overdue interest rate to obtain overdue penalty information as floating amount; the method is applied to a plurality of preparation models of overdue scenes, and at least one of overdue amount, overdue days and overdue interest rate is calculated in different manners.
The settlement scene includes an advanced settlement scene. The method is applied to a preparation model of an advanced settlement scene, and a structuring module calculates the remaining principal to be settled; the floating module calculates additional cost; the method is applied to a plurality of preparation models of a settlement scene in advance, and at least two additional cost calculation modes exist; the at least two additional cost calculation modes include: the remaining principal to be returned, the calculated time length and the initial daily interest rate are multiplied and added to form a commission; all interest to be returned is superimposed.
S204: calculating the calculation error between the calculation amount and the settlement amount associated with the same basic amount.
S205: and respectively selecting a preparation model for each target mechanism as a prediction model based on the calculation errors.
In an embodiment, the computer program when executed by the processor further performs the steps of:
S301: and obtaining a target organization and a basic amount to which the bill to be predicted belongs.
S302: and calling a prediction mode matched with a target mechanism to which the bill to be predicted belongs.
S303: and inputting the basic amount of the bill to be predicted into the called prediction model to obtain the predicted amount of the bill to be predicted.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (8)
1. A settlement prediction method, comprising:
acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest;
Substituting the basic amount into a plurality of preparation models to calculate respectively, and outputting a calculated amount each time;
Calculating an estimated error between the estimated amount and the settlement amount associated with the same basic amount, and selecting one preparation model for each target institution as a prediction model based on the estimated error;
The calculated amount merges fixed amount and floating amount, and the floating amount is calculated based on time information and is related to the settlement scene;
The preparation model comprises a structuring module and a floating module;
Substituting the basic amount into a plurality of preparation models for calculation respectively, and outputting an estimated amount each time comprises:
substituting the basic amount into each preparation model to respectively calculate a plurality of times, wherein each preparation model calculates a plurality of calculated amounts based on the basic amount;
Wherein, the structuring module calculates a fixed amount in each calculation process, the floating module calculates a floating amount having a strong correlation with the settlement scene based on the time information; fusing the results output by the structuring module and the floating module to obtain the calculated amount;
the calculated amount is used for checking the settlement amount in the settlement period;
The preparation model comprises a deduction formula for deducting the settlement amount, wherein the deduction formula comprises rule factors to be deducted;
The preparation model carries out calculation respectively, and each calculation output one calculation amount comprises the following steps:
substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation.
2. The settlement prediction method according to claim 1, wherein the settlement scene includes an overdue scene;
The method comprises the steps that in a preparation model applied to the overdue scene, the structural model calculates the superposition amount of principal and interest as the fixed amount, and the floating module calculates the product of overdue amount, overdue days and overdue interest rate to obtain overdue default interest as the floating amount;
The method is applied to a plurality of the preparation models of the overdue scene, wherein at least one of the overdue amount, the overdue days and the overdue interest rate is calculated in different manners.
3. The settlement prediction method according to claim 1, wherein the settlement scene comprises an advanced settlement scene;
The structuring module is applied to a preparation model of the advanced settlement scene and calculates the remaining principal to be settled; the floating module calculates additional cost; in a plurality of the preparation models applied to the pre-settlement scene, at least two calculation modes of the additional cost exist;
The at least two additional cost calculation modes include: the remaining principal to be returned, the calculated time length and the initial daily interest rate are multiplied and added to form a commission; all interest to be returned is superimposed.
4. The settlement prediction method according to claim 1, wherein the settlement prediction method comprises:
Acquiring a standard value range of the rule factors;
determining a possible maximum value and a possible minimum value of the rule factors based on the specification value range;
selecting a plurality of possible values between the possible maximum value and the possible minimum value; calculating the calculated amount corresponding to each possible value respectively; comparing each calculated amount with the settlement amount, and updating a possible maximum value and a possible minimum value based on the comparison result; and taking the possible value of the calculated amount matched with the settlement amount as the value of the rule factor until the calculated amount of the possible value is matched with the settlement amount.
5. The settlement prediction method according to claim 1, wherein the settlement prediction method comprises:
Acquiring a target mechanism and a basic amount to which a bill to be predicted belongs;
invoking a prediction mode matched with a target mechanism to which the bill to be predicted belongs;
and inputting the basic amount of the bill to be predicted into the called prediction model to obtain the predicted amount of the bill to be predicted.
6. A settlement prediction device, characterized by comprising:
The acquisition module is used for acquiring the basic amount, settlement amount and time information of historical settlement of a plurality of target institutions in a settlement scene; wherein the base amount includes principal and interest;
The control module is connected with the acquisition module and is used for substituting the basic amount into a plurality of preparation models respectively, calculating the basic amount in each preparation model respectively and outputting an estimated amount in each calculation; calculating an estimated error between the estimated amount and the settlement amount associated with the same basic amount, and selecting one preparation model for each target institution as a prediction model based on the estimated error; the calculated amount merges fixed amount and floating amount, and the floating amount is calculated based on time information and is related to the settlement scene;
The preparation model comprises a structuring module and a floating module;
Substituting the basic amount into a plurality of preparation models for calculation respectively, and outputting an estimated amount each time comprises:
substituting the basic amount into each preparation model to respectively calculate a plurality of times, wherein each preparation model calculates a plurality of calculated amounts based on the basic amount;
Wherein, the structuring module calculates a fixed amount in each calculation process, the floating module calculates a floating amount having a strong correlation with the settlement scene based on the time information; fusing the results output by the structuring module and the floating module to obtain the calculated amount;
the calculated amount is used for checking the settlement amount in the settlement period;
The preparation model comprises a deduction formula for deducting the settlement amount, wherein the deduction formula comprises rule factors to be deducted;
The preparation model carries out calculation respectively, and each calculation output one calculation amount comprises the following steps:
substituting the basic amount and the time information into the deduction formula for a plurality of times, and calculating for a plurality of times to obtain a plurality of calculated amounts belonging to the same deduction formula; wherein the rule factor is different in each calculation.
7. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the settlement prediction method as claimed in any one of claims 1 to 5 when the computer program is executed.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the settlement prediction method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311130331.2A CN117273723B (en) | 2023-09-04 | 2023-09-04 | Settlement prediction method, settlement prediction device, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311130331.2A CN117273723B (en) | 2023-09-04 | 2023-09-04 | Settlement prediction method, settlement prediction device, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117273723A CN117273723A (en) | 2023-12-22 |
| CN117273723B true CN117273723B (en) | 2024-10-18 |
Family
ID=89205363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311130331.2A Active CN117273723B (en) | 2023-09-04 | 2023-09-04 | Settlement prediction method, settlement prediction device, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273723B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639798A (en) * | 2020-05-26 | 2020-09-08 | 华青融天(北京)软件股份有限公司 | Intelligent prediction model selection method and device |
| CN113723692A (en) * | 2021-09-02 | 2021-11-30 | 深圳前海微众银行股份有限公司 | Data processing method, apparatus, device, medium, and program product |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003006432A (en) * | 2001-06-20 | 2003-01-10 | Bank Of Tokyo-Mitsubishi Ltd | Price calculating method for interest swap including prepayment risk, program, and recording medium |
| AU2005241122B2 (en) * | 2004-05-07 | 2010-02-11 | Etracka Pty Ltd | Loan simulation method and system |
| KR100927146B1 (en) * | 2007-05-07 | 2009-11-18 | 주식회사 국민은행 | Interest rate swap processing method and system derived from fixed interest rate in connection with variable loan |
| KR101187099B1 (en) * | 2010-11-22 | 2012-09-28 | 주식회사 전북은행 | Accounting treatment system for ifrs financial product using database for mass processing |
| CN103985052A (en) * | 2014-05-29 | 2014-08-13 | 中国农业银行股份有限公司 | Interest settlement system and method |
| CN109493214A (en) * | 2018-11-14 | 2019-03-19 | 深圳市数丰科技有限公司 | A kind of dynamic calculates the method and device of refund issue |
| CN110009380B (en) * | 2018-11-29 | 2023-07-11 | 创新先进技术有限公司 | Transaction data prediction method, device, electronic equipment and computer storage medium |
| CN110766202A (en) * | 2019-09-26 | 2020-02-07 | 北京淇瑀信息科技有限公司 | Contract settlement system, method and equipment for predicting channel capacity |
| KR20220048829A (en) * | 2020-10-13 | 2022-04-20 | 한국정보공학 주식회사 | Apparatus and method for providing price adjustment service for open market |
| CN114764412A (en) * | 2021-01-14 | 2022-07-19 | 京东科技控股股份有限公司 | Data processing method and device |
| CN113807943A (en) * | 2021-08-18 | 2021-12-17 | 大箴(杭州)科技有限公司 | A multi-factor valuation method and system, medium and equipment for non-performing assets |
| CN113689289B (en) * | 2021-08-26 | 2024-04-30 | 天元大数据信用管理有限公司 | Bank risk control-based method and equipment |
| CN113988999B (en) * | 2021-09-27 | 2025-01-14 | 上海数禾信息科技有限公司 | Method, device, computer equipment and storage medium for settling business placement fees |
| CN114049196B (en) * | 2021-11-10 | 2024-12-24 | 建信金融科技有限责任公司 | A method, device and computer equipment for settling corporate loan interest |
| CN114240100A (en) * | 2021-12-02 | 2022-03-25 | 中国建设银行股份有限公司 | Loan assessment method, loan assessment device, loan assessment computer equipment and loan assessment storage medium |
| CN114519612A (en) * | 2022-02-14 | 2022-05-20 | 上海数禾信息科技有限公司 | Method and device for sending preferential information, computer equipment and storage medium |
| CN114663079A (en) * | 2022-03-23 | 2022-06-24 | 阿里云计算有限公司 | Settlement method, terminal, storage medium and program product |
| CN114706905A (en) * | 2022-03-24 | 2022-07-05 | 亚信科技（中国）有限公司 | Data prediction method and device, electronic equipment and computer readable storage medium |
| CN114971893B (en) * | 2022-07-28 | 2022-10-25 | 成都运荔枝科技有限公司 | Loan deduction mode flexible configuration method and system |
| CN116629998A (en) * | 2023-05-25 | 2023-08-22 | 杭州一骑轻尘信息技术有限公司 | Automatic information counting method and device, electronic equipment and readable storage medium |
-
2023
- 2023-09-04 CN CN202311130331.2A patent/CN117273723B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639798A (en) * | 2020-05-26 | 2020-09-08 | 华青融天(北京)软件股份有限公司 | Intelligent prediction model selection method and device |
| CN113723692A (en) * | 2021-09-02 | 2021-11-30 | 深圳前海微众银行股份有限公司 | Data processing method, apparatus, device, medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117273723A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8249981B2 (en) | Methods and systems for generating transition probability matrices through an optimization framework | |
| US7516079B2 (en) | Method and apparatus for insurance risk management | |
| Chehrazi et al. | Dynamic valuation of delinquent credit-card accounts | |
| Bardhan et al. | Valuing Mortgage Insurance Contracts in Emerging Market Economies: Bardhan, Karapandža and Urošević | |
| Ballotta et al. | Counterparty credit risk in a multivariate structural model with jumps | |
| Wiener | Introduction to VaR (value-at-risk) | |
| CN117273723B (en) | Settlement prediction method, settlement prediction device, computer device and storage medium | |
| Liu et al. | Option‐Implied Ambiguity and Equity Return Predictability | |
| CN114049196B (en) | A method, device and computer equipment for settling corporate loan interest | |
| US20150088727A1 (en) | Method for determining creditworthiness for exchange of a projected, future asset | |
| CN115204878A (en) | A method, device and equipment for depositing order information | |
| CN119515530A (en) | A repayment risk prediction method and system based on financial credit business | |
| CN113129127A (en) | Early warning method and device | |
| Carmona et al. | Simulation of implied volatility surfaces via tangent Lévy models | |
| CN116862516A (en) | Automatic payment method, device, computer equipment and storage medium | |
| CN114092259A (en) | Processing method, device and equipment for exchange rate data and computer storage medium | |
| CN112967133A (en) | Loan information processing method and electronic device | |
| CN109584070A (en) | Stock certificate data processing method, device, computer equipment and storage medium | |
| CN117575607A (en) | Transaction risk identification method, device, computer equipment and storage medium | |
| CN121327344A (en) | Method, device, equipment, medium and program product for predicting telephone fee paying time sequence | |
| CN121169400A (en) | Multiple payment merging refund method, device and system | |
| CN119648379A (en) | Credit default transfer matrix calibration method, device, equipment and storage medium | |
| CN117314620A (en) | Service data calculation method, device, electronic equipment and storage medium | |
| CN116862487A (en) | Transaction asset processing method, apparatus, device, storage medium and program product | |
| CN121391494A (en) | An insurance policy valuation method, apparatus, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |