Bill staging scheme determination method and device, equipment, medium and product

Abstract

The embodiment of the invention discloses a bill installment scheme determination method and device, equipment and a medium, and the method comprises the steps: obtaining the bill information of a to-be-repaid bill, and obtaining the account feature attribute information and historical bill installment record information of a credit card account corresponding to the to-be-repaid bill; inputting the bill information, the account feature attribute information and the historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result of the to-be-repaid bill; and when the staging prediction result indicates that the bill to be repaid is a staging bill, inputting the bill information and the account feature attribute information into a pre-constructed Monte Carlo search tree to obtain a target bill staging scheme output by the Monte Carlo search tree. According to the technical scheme of the embodiment of the invention, the problem is solved, the possibility that the credit card bill is staging can be identified in advance, and an appropriate staging scheme is formulated for the bill which needs to be staging in a large probability in advance, so that a bank is helped to carry out credit turnover planning.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of artificial intelligence technology, and in particular, to a method, device, equipment, medium and product for determining a bill installment plan. Background Art

[0002] Bank credit card customers can choose to repay in installments or not. Currently, the number of users who choose to repay in installments is increasing. The behavior of credit card customers to repay bills in installments has affected the bank's credit turnover.

[0003] If the possibility of installment payments for each credit card bill can be predicted, it will help banks to formulate bill installment plans in advance and reduce the impact on bank credit turnover. Summary of the invention

[0004] Embodiments of the present invention provide a method, apparatus, device, medium and product for determining a bill installment plan, which can pre-identify the possibility of a credit card bill being divided into installments and pre-formulate a suitable installment plan for bills that are likely to be divided into installments.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a bill installment plan, the method comprising:

[0006] Obtaining bill information of the bill to be repaid, and obtaining account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid;

[0007] Input bill information, account feature attribute information, and historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result for the bill to be repaid;

[0008] When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

[0009] In a second aspect, an embodiment of the present invention further provides a device for determining a bill installment plan, the device comprising:

[0010] The bill information acquisition module is used to obtain the bill information of the bill to be repaid, and obtain the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid;

[0011] The installment prediction module is used to input bill information, account feature attribute information and historical bill installment record information into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid;

[0012] The installment plan determination module is used to input the bill information and account characteristic attribute information into a pre-built Monte Carlo search tree when the installment prediction result indicates that the bill to be repaid is an installment bill, and obtain the target bill installment plan output by the Monte Carlo search tree.

[0013] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0014] one or more processors;

[0015] A memory for storing one or more programs;

[0016] When one or more programs are executed by one or more processors, the one or more processors implement the bill installment plan determination method provided by any embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining a bill installment plan as provided in any embodiment of the present invention.

[0018] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements a method for determining a bill installment plan as provided in any embodiment of the present invention.

[0019] The embodiments of the above invention have the following advantages or beneficial effects:

[0020] The embodiment of the present invention obtains the bill information of the bill to be repaid, and obtains the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; the bill information, account characteristic attribute information and historical bill installment record information are input into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; when the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-built Monte Carlo search tree to obtain the target bill installment plan output by the Monte Carlo search tree. The technical solution of the embodiment of the present disclosure solves the problem that it is impossible to recommend a suitable installment plan for the bill to be repaid in advance, and can pre-identify the possibility of credit card bills being in installments, and pre-formulate suitable installment plans for bills that are likely to be in installments, so as to help banks with credit turnover planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a method for determining a bill installment plan provided by an embodiment of the present invention;

[0022] Figure 2is a flow chart of a method for determining a bill installment plan provided by an embodiment of the present invention;

[0023] Figure 3 is a schematic diagram of a network structure provided by an embodiment of the present invention;

[0024] Figure 4 is a flow chart of a method for determining a bill installment plan provided by an embodiment of the present invention;

[0025] Figure 5 It is a structural schematic diagram of a device for determining a bill installment plan provided by an embodiment of the present invention;

[0026] Figure 6 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0028] Figure 1 This is a flow chart of a method for determining a bill installment plan provided in an embodiment of the present invention. This embodiment can be applied to the scenario of managing credit card bills, especially the situation of managing credit card bill installment services. The method can be executed by a bill installment plan determination device, which can be implemented in software and / or hardware and integrated into a computer device with application development functions.

[0029] like Figure 1 As shown, the method for determining a bill installment plan in this embodiment includes the following steps:

[0030] S110. Obtain bill information of the bill to be repaid, and obtain account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid.

[0031] The outstanding bill may be a credit card account payment bill generated on the credit card account's billing date and not yet paid. Each credit card user will generate an outstanding bill on the corresponding billing date after using the credit limit to make a payment.

[0032] The bill information of the bill to be repaid includes the bill amount information, bill identification information and other contents. The account characteristic attribute information of the credit card account corresponding to the bill to be repaid may include: account limit, age, gender, region and other characteristic information of the customer corresponding to the account that can reflect the consumption capacity or repayment capacity of the credit card account. The historical bill installment record information may include the customer's consumption behavior and historical installment behavior data, such as transaction records, bill details, special installment records and other data. In addition, it may also include: whether the credit card is expired, whether it is in a frozen state, and data related to customer feedback after bill installment promotion for customers, such as telephone promotion records and SMS promotion records.

[0033] S120: Input the bill information, account feature attribute information and historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid.

[0034] The bill installment prediction model is a pre-trained neural network model, which can be a binary classification model for classification prediction. The training input samples of the bill installment prediction model can be feature information in bill information, account feature attribute information, and historical bill installment record information. After training, the prediction results of installment repayment corresponding to the bill to be repaid can be output, including the probability value of installment repayment corresponding to the bill to be repaid.

[0035] S130. When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and the account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

[0036] Monte Carlo Tree Search (MCTS) is an algorithm used to search for optimal strategies in the decision-making process. Monte Carlo Search Tree continuously simulates and explores in the decision tree, evaluates the pros and cons of each decision branch based on the simulation results, and then guides the search to expand in the direction that is more likely to produce the optimal solution, and gradually builds a search tree that can reflect the value of each decision path. It cleverly combines the advantages of random simulation (Monte Carlo method) and tree search, and can effectively find better action strategies when facing complex and uncertain decision-making environments.

[0037] The bill information and account feature attribute information are used as the initial state of the root node of the Monte Carlo search tree. Starting from the root node, the child nodes are recursively selected according to a specific strategy (usually based on the number of node visits and value information to calculate the score), and the selection continues downward until a node that is not fully expanded is reached (that is, the node has an action branch that has not been added to the tree). This selection process is a bit like looking for potential directions along the branches of the tree, giving priority to those branches that seem more valuable but not over-explored. Among them, the action of selecting the child node branch path is the selection of the installment period.

[0038] When an incompletely expanded node is found, one of the possible actions corresponding to the node is selected and added as a new child node of the node, thus expanding the structure of the search tree and increasing the scope of exploration. Starting from the newly expanded node, the game process is simulated using a random strategy (Monte Carlo simulation part) until the game ends (such as determining the winner or reaching the preset maximum number of steps, etc.), and a simulated result (such as win, lose, draw) is obtained. This is like playing the game randomly without following the precise optimal strategy to see what the final result is.

[0039] The simulation results are propagated back along the node paths previously selected and expanded, and the statistical information related to these nodes is updated, such as the analysis interest corresponding to the installment period and the analysis results of the user's repayment pressure, so that the strategy value corresponding to each node can be evaluated more accurately in the future. Finally, the target bill installment plan output by the Monte Carlo search tree can be obtained.

[0040] The technical solution of this embodiment obtains the bill information of the bill to be repaid, and obtains the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; the bill information, account characteristic attribute information and historical bill installment record information are input into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; when the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-built Monte Carlo search tree to obtain the target bill installment plan output by the Monte Carlo search tree. The technical solution of the disclosed embodiment solves the problem that it is impossible to recommend a suitable installment plan for the bill to be repaid in advance, and can pre-identify the possibility of credit card bills being in installments, and pre-formulate suitable installment plans for bills that are likely to be in installments, so as to help banks with credit turnover planning.

[0041] Figure 2This is a flowchart of a method for determining a bill installment plan provided in an embodiment of the present invention. This embodiment and the method for determining a bill installment plan in the above embodiment belong to the same inventive concept. The method can be executed by a bill installment plan determination device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0042] like Figure 2 As shown, the method for determining a bill installment plan in this embodiment includes the following steps:

[0043] S210: Obtain bill information of the bill to be repaid, and obtain account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid.

[0044] S220: Perform feature processing on the bill information, account feature attribute information and historical bill installment record information respectively to obtain feature data corresponding to preset feature items.

[0045] The preset feature items may be feature data obtained after feature engineering processing is performed on the model training samples of the bill installment prediction model, which may be feature data that affects whether the bill to be repaid will be repaid in installments.

[0046] The feature engineering processing of the model training samples of the bill installment prediction model may include preprocessing such as data cleaning, missing value processing, format conversion, normalization and continuous value discretization of the original sample data to obtain the target features as preset feature items.

[0047] S230: Input the feature data into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid.

[0048] Among them, the bill installment prediction model is a convolutional neural network, including an input layer, a hidden layer and an output layer.

[0049] In a specific example, the bill installment prediction model can be Figure 3 The structure shown in Figure 1 is composed of 8 network layers, namely the input layer, 6 hidden layers and the output layer. The input layer and the output layer each contain 20 neurons. The structure of the hidden layer has both vector and matrix forms. However, the basic mathematical expressions between layers are: y=Vσ(Wx+b).

[0050] It includes the input vector x, the output vector y, the weight matrices W and V, and the bias vector b. The activation function σ is a nonlinear function, and commonly used ones include relu, sigmoid, and tanh. Based on this shallow neural network model, it can be naturally extended to a deep neural network model, where the expression of an L-layer neural network includes L-1 hidden layers, and its expression is as follows:

[0051] y=A L σ(A L-1 σ(A L-2 ...σ(A 1 x+b 1 ))+b L-1 )+b L .

[0052] S240. When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and the account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

[0053] The technical solution of this embodiment is to obtain the bill information of the bill to be repaid, and obtain the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; perform feature processing on the bill information, account characteristic attribute information and historical bill installment record information respectively to obtain feature data corresponding to the preset feature items; input the feature data into the pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; when the installment prediction result indicates that the bill to be repaid is an installment bill, input the bill information and account characteristic attribute information into the pre-built Monte Carlo search tree to obtain the target bill installment plan output by the Monte Carlo search tree. The technical solution of the disclosed embodiment solves the problem that it is impossible to recommend a suitable installment plan for the bill to be repaid in advance, and can pre-identify the possibility of credit card bills being in installments, and pre-formulate suitable installment plans for bills with a high probability of being in installments, so as to help banks with credit turnover planning.

[0054] Figure 4 This is a flowchart of a method for determining a bill installment plan provided in an embodiment of the present invention. This embodiment and the method for determining a bill installment plan in the above embodiment belong to the same inventive concept. The method can be executed by a bill installment plan determination device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0055] like Figure 4 As shown, the method for determining a bill installment plan in this embodiment includes the following steps:

[0056] S310: Obtain bill information of the bill to be repaid, and obtain account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid.

[0057] S320: Input the bill information, account feature attribute information and historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result for the bill to be repaid.

[0058] S330. When the installment prediction result indicates that the bill to be repaid is an installment bill, the state space of the Monte Carlo search tree corresponding to the bill to be repaid is determined based on the credit card bill amount corresponding to the bill information and the account credit characteristics in the account characteristic attribute information.

[0059] The state space also includes optional installment periods and installment interest.

[0060] The state space of the Monte Carlo search tree can be defined as variables in the state space by integrating factors such as the credit card bill amount, the number of available installments, the current interest rate level, and the cardholder's repayment ability. For example, a state space can be the bill amount, the optional number of installments (3 installments, 6 installments, 9 installments, 12 installments, etc.), the corresponding handling fee rate for each installment (0.7%, 0.6%, 0.55%, 0.5%), and the monthly disposable income amount. All possible state combinations constitute the entire state space.

[0061] When the bill to be paid is a confirmed bill, the state space of the Monte Carlo search tree corresponding to the bill to be paid can be determined based on the credit card bill amount corresponding to the bill information and the account credit characteristics in the account characteristic attribute information.

[0062] In addition, the actions in the action space can also be predefined, and can be selectable installment periods, namely, 3 periods, 6 periods, 9 periods, and 12 periods.

[0063] S340: Initialize the root node of the Monte Carlo search tree with the bill information of the bill to be repaid, and use the selection of the installment period as the action of expanding the child node.

[0064] The bill information and account attribute information of the bill to be repaid can be used as the root node of the Monte Carlo search tree, which represents the initial state before any installment selection is made. The selection of the installment period is used as the action of expanding the child node, and the appropriate child node is selected to go down.

[0065] S350, respectively calculate the action benefit corresponding to each child node, and perform back propagation and optimization based on the action benefit to obtain the target bill installment plan.

[0066] When reaching a child node, if there are installment periods (actions) that have not been tried, expand and add new child nodes. Then start the simulation from the new child node. The simulation can calculate the repayment amount of each period, total interest, etc. according to the set rules, and combine a virtual "action benefit" evaluation (for example, you can consider comprehensive interest costs, repayment pressure and other factors, set a comprehensive score as the benefit, low interest costs, low repayment pressure, high scores), simulate multiple times (for example, 100 times or more, the more times the more accurate the result but the greater the calculation) to obtain a relatively stable average benefit.

[0067] In an optional implementation, the action benefit corresponding to each subnode is calculated by calculating the installment interest cost based on the number of installments corresponding to each subnode, the installment amount in the bill information, and the installment interest; based on the installment interest cost and the account credit characteristics, determine the installment plan score corresponding to the bill installment according to the installment number corresponding to the subnode, and use the installment plan score as the corresponding action benefit.

[0068] In an optional implementation, the action benefit corresponding to each child node can be calculated by: inputting the installment period corresponding to the child node, the installment amount in the bill information, the installment interest, and the account credit characteristics into a pre-trained installment plan evaluation model, obtaining the installment plan score corresponding to the installment period, and using the installment plan score as the corresponding action benefit. That is, the action benefit of the installment plan corresponding to the action of the child node is calculated by the pre-trained analysis plan scoring model.

[0069] The technical solution of this embodiment is to obtain the bill information of the bill to be repaid, and obtain the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; input the bill information, account characteristic attribute information and historical bill installment record information into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; when the installment prediction result indicates that the bill to be repaid is an installment bill, determine the state space of the Monte Carlo search tree corresponding to the bill to be repaid based on the credit card bill amount corresponding to the bill information and the account credit characteristics in the account characteristic attribute information; initialize the root node of the Monte Carlo search tree with the bill information of the bill to be repaid, and use the selection of the installment number as the action of expanding the child node; calculate the action benefit corresponding to each child node respectively, and perform back propagation and optimization based on the action benefit to obtain the target bill installment plan.

[0070] In a specific application example, assume that account A has a bill to be repaid, and the current bill amount is 15,000 yuan. The bank provides credit card bill installment options of 3, 6, 9, and 12 installments, and the corresponding monthly handling fee rates are 0.7%, 0.6%, 0.55%, and 0.5%, respectively. Account A hopes to reduce the repayment pressure through a reasonable installment plan, while trying to control the total handling fee expenditure, so it decides to use the Monte Carlo search tree to explore the best installment plan.

[0071] First, construct the state space and action space

[0072] State space: The current bill amount (15,000 yuan), the corresponding fee rates for each period (0.7%, 0.6%, 0.55%, 0.5%), and Xiao Li's monthly disposable income (8,000-3,000 = 5,000 yuan) are defined as state space variables, and each possible situation constitutes a state space. For example, the state can be expressed as (bill amount 15,000 yuan, 3-period fee rate 0.7%, 6-period fee rate 0.6%, 9-period fee rate 0.55%, 12-period fee rate 0.5%, monthly disposable income and / or credit rating or consumption capacity rating, etc.).

[0073] Action space: the number of installments that can be selected, namely 3 installments, 6 installments, 9 installments, and 12 installments.

[0074] Initialize the search tree: Use the bill information of the bill to be repaid and the characteristic information of account A as the root node. This root node represents the initial state where no installment selection has been made.

[0075] Selection process: Starting from the root node, select subnodes for in-depth exploration according to the confidence upper limit strategy. For example, at the beginning, the number of visits to each subnode (corresponding to different installment periods) is 0. As the simulation progresses, assuming that after several iterations, the cumulative income evaluation value of the node corresponding to the 3rd period is currently high, but the number of visits is relatively small, it may be selected first according to the confidence upper limit calculation, and continue to explore the branch corresponding to the node.

[0076] Extension and simulation: When the selection reaches a certain child node, if there are installment periods (actions) that have not been tried, the expansion operation is performed. For example, when the node corresponding to the selection of 3 periods is reached for the first time, if the other 6 periods, 9 periods, and 12 periods have not been explored under this path, new child nodes will be created to correspond to these unexplored installment period options. Start simulating the repayment process from the newly expanded child node. Taking the selection of 6 periods as an example, the monthly handling fee = 15,000 × 0.6% = 90 yuan, and the principal repayment per period = 15,000 ÷ 6 = 2,500 yuan, then the repayment amount per period is 2,500 + 90 = 2,590 yuan. This amount is within Xiao Li's monthly disposable income or the corresponding consumption capacity level, and the repayment pressure is relatively controllable. Simulate this repayment process multiple times (assuming 100 simulations), record the total handling fee expenditure for each simulation, repayment pressure (which can be simply measured by the ratio of each repayment amount to monthly disposable income, for example, the lower the ratio, the smaller the repayment pressure), and other information, and comprehensively evaluate a "benefit" value based on pre-set rules (for example, you can set the benefit value = 100-(total handling fee as a percentage of the bill amount × 100 + each repayment amount as a percentage of monthly disposable income × 100). This is just an example rule and can be adjusted based on actual conditions).

[0077] Back propagation and iterative optimization: The simulated benefit value is back propagated along the search path back to the root node, and the statistical information such as the number of visits and cumulative benefits of each node on the path (including the selected node, the intermediate nodes passed, etc.) is updated. After hundreds of such iterative processes of selection, expansion, simulation, and back propagation, the search tree is constantly improved.

[0078] Final result and decision basis: After 500 iterations, for example, check the statistical information of the nodes corresponding to each installment period:

[0079] Phase 3: 150 visits, with an average revenue value (calculated according to pre-set rules or the corresponding neural network model) of 60 points.

[0080] Issue 6: 180 visits, average revenue value is 70 points.

[0081] Issue 9: 120 visits, average profit value is 65 points.

[0082] Issue 12: 50 visits, average profit value is 55 points.

[0083] According to these statistical results, the average return value corresponding to 6 installments is the highest, which means that after comprehensively considering factors such as total handling fee expenditure and repayment pressure, choosing a 6-installment credit card bill installment plan may be relatively optimal for Account A.

[0084] Figure 5 A structural schematic diagram of a device for determining a bill installment plan provided in an embodiment of the present invention. This embodiment can be applied to scenarios of credit card bill installment plan analysis. The device for determining a bill installment plan can be implemented by software and / or hardware and integrated into a computer terminal device with application development capabilities.

[0085] like Figure 5 The bill installment plan determination device shown includes: a bill information acquisition module 410, an installment prediction module 420 and an installment plan determination module 430.

[0086] Among them, the bill information acquisition module 410 is used to obtain the bill information of the bill to be repaid, and obtain the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; the installment prediction module 420 is used to input the bill information, account characteristic attribute information and historical bill installment record information into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; the installment plan determination module 430 is used to input the bill information and account characteristic attribute information into a pre-constructed Monte Carlo search tree when the installment prediction result indicates that the bill to be repaid is an installment bill, so as to obtain the target bill installment plan output by the Monte Carlo search tree.

[0087] The technical solution of this embodiment obtains the bill information of the bill to be repaid, and obtains the account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; the bill information, account characteristic attribute information and historical bill installment record information are input into a pre-trained bill installment prediction model to obtain the installment prediction result of the bill to be repaid; when the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-built Monte Carlo search tree to obtain the target bill installment plan output by the Monte Carlo search tree. The technical solution of the disclosed embodiment solves the problem that it is impossible to recommend a suitable installment plan for the bill to be repaid in advance, and can pre-identify the possibility of credit card bills being in installments, and pre-formulate suitable installment plans for bills that are likely to be in installments, so as to help banks with credit turnover planning.

[0088] In an optional implementation, the stage prediction module 420 is specifically used for:

[0089] Perform feature processing on bill information, account feature attribute information and historical bill installment record information respectively to obtain feature data corresponding to preset feature items;

[0090] Input the feature data into the pre-trained bill installment prediction model to obtain the installment prediction results of the bill to be repaid;

[0091] Among them, the bill installment prediction model is a convolutional neural network, including an input layer, a hidden layer and an output layer.

[0092] In an optional implementation, the staging scheme determination module 430 may be specifically used to:

[0093] Based on the credit card bill amount corresponding to the bill information and the account credit characteristics in the account characteristic attribute information, determine the state space of the Monte Carlo search tree corresponding to the bill to be repaid; wherein the state space also includes the optional installment period and the installment interest;

[0094] Initialize the root node of the Monte Carlo search tree with the bill information of the bill to be repaid, and use the selection of the installment period as the action of expanding the child node;

[0095] The action benefit corresponding to each child node is calculated separately, and backpropagation and optimization are performed based on the action benefit to obtain the target bill installment plan.

[0096] In an optional implementation, the staging scheme determination module 430 may be specifically used to:

[0097] Calculate the installment interest cost based on the number of installments corresponding to each child node, the installment amount in the bill information, and the installment interest;

[0098] According to the installment interest cost and account credit characteristics, determine the installment plan score corresponding to the bill installment according to the installment period corresponding to the sub-node, and use the installment plan score as the corresponding action benefit.

[0099] In an optional implementation, the staging scheme determination module 430 may be specifically used to:

[0100] The installment period corresponding to the child node, the installment amount in the bill information, the installment interest and the account credit features are input into the pre-trained installment plan evaluation model to obtain the installment plan score corresponding to the installment period, and the installment plan score is used as the corresponding action benefit.

[0101] In an optional implementation, the account characteristic attribute information includes account credit rating characteristic information.

[0102] The bill installment plan determination device provided in the embodiment of the present invention can execute the bill installment plan determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0103] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 6 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 6 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller and server, a mobile phone and other terminal devices.

[0104] like Figure 6 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0105] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0106] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0107] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0108] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0109] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 6Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0110] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing the bill installment plan determination method provided in the embodiment of the present invention, the method comprising:

[0111] Obtaining bill information of the bill to be repaid, and obtaining account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid;

[0112] Input bill information, account feature attribute information, and historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result for the bill to be repaid;

[0113] When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

[0114] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for determining a bill installment plan provided in any embodiment of the present invention is implemented. The method includes:

[0115] Obtaining bill information of the bill to be repaid, and obtaining account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid;

[0116] Input bill information, account feature attribute information, and historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result for the bill to be repaid;

[0117] When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

[0118] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0119] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0120] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0121] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0122] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0123] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements a method for determining a bill installment plan as provided in any one of the embodiments of the present disclosure.

[0124] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0125] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a bill installment plan, characterized in that: include: Obtaining bill information of the bill to be repaid, and obtaining account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; Inputting the bill information, the account characteristic attribute information and the historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid; When the installment prediction result indicates that the bill to be repaid is an installment bill, the bill information and the account characteristic attribute information are input into a pre-constructed Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree.

2. The method according to claim 1, characterized in that The step of inputting the bill information, the account characteristic attribute information and the historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid includes: Performing feature processing on the bill information, the account feature attribute information and the historical bill installment record information respectively to obtain feature data corresponding to preset feature items; Inputting the feature data into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid; Among them, the bill installment prediction model is a convolutional neural network, including an input layer, a hidden layer and an output layer.

3. The method according to claim 1, characterized in that The step of inputting the bill information and the account characteristic attribute information into a pre-built Monte Carlo search tree to obtain a target bill installment plan output by the Monte Carlo search tree includes: Based on the credit card bill amount corresponding to the bill information and the account credit characteristics in the account characteristic attribute information, determine the state space of the Monte Carlo search tree corresponding to the bill to be repaid; wherein the state space also includes the optional installment number and installment interest; Initializing the root node of the Monte Carlo search tree with the bill information of the bill to be repaid, and taking the selection of the installment period as the action of expanding the child node; The action benefit corresponding to each child node is calculated respectively, and back propagation and optimization are performed based on the action benefits to obtain the target bill installment plan.

4. The method according to claim 3, characterized in that The calculation of the action benefit corresponding to each child node includes: Calculate the installment interest cost according to the number of installments corresponding to each of the subnodes, the installment amount in the bill information, and the installment interest; According to the installment interest cost and the account credit characteristics, determine the installment plan score corresponding to the bill installment according to the installment period corresponding to the sub-node, and use the installment plan score as the corresponding action benefit.

5. The method according to claim 3, characterized in that: The calculation of the action benefit corresponding to each child node includes: The installment number corresponding to the subnode, the installment amount in the bill information, the installment interest and the account credit feature are input into a pre-trained installment plan evaluation model to obtain an installment plan score corresponding to the installment number, and the installment plan score is used as the corresponding action benefit.

6. The method according to any one of claims 1 to 5, characterized in that: The account characteristic attribute information includes account credit rating characteristic information.

7. A device for determining a bill installment plan, characterized in that: include: A bill information acquisition module is used to acquire bill information of the bill to be repaid, and acquire account characteristic attribute information and historical bill installment record information of the credit card account corresponding to the bill to be repaid; An installment prediction module, used to input the bill information, the account characteristic attribute information and the historical bill installment record information into a pre-trained bill installment prediction model to obtain an installment prediction result of the bill to be repaid; The installment plan determination module is used to input the bill information and the account characteristic attribute information into a pre-constructed Monte Carlo search tree when the installment prediction result indicates that the bill to be repaid is an installment bill, so as to obtain a target bill installment plan output by the Monte Carlo search tree.

8. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the bill installment plan determination method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining a bill installment plan as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the bill installment plan determination method according to any one of claims 1 to 6.

Images