Method and device for determining capital cost of automatic teller machine, and electronic equipment

Abstract

The invention discloses an automatic teller machine fund cost determination method and device and electronic equipment, and relates to the field of financial science and technology, and the determination method comprises the steps: for a plurality of automatic teller machines, obtaining current transaction data on the automatic teller machines in a first preset time period, and inputting the current transaction data into a preset fund usage prediction model to obtain the fund usage amount of the automatic teller machine in a second preset time period, determining the fund inventory of each automatic teller machine based on the fund usage amount, and using a preset multiple regression analysis model to analyze the fund usage amount of each automatic teller machine based on all the fund inventory amounts. And the fund cost of each automatic teller machine is determined. The technical problem that the fund cost of the automatic teller machine is difficult to accurately determine in the related art is solved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a method for determining the capital cost of a self-service teller machine, a device thereof, and an electronic device. Background Art

[0002] ATMs (such as ATMs (Automated Teller Machines), CDMs (Cash Deposit Machines), etc.) are self-service terminals for financial institutions facing customers. They undertake the core function of depositing and withdrawing cash. The cash stored in the cash boxes of ATMs is not only a necessity for daily business activities, but also an important part of the total inventory of financial institutions. When managing ATMs, financial institutions need to ensure that customers can obtain cash at any time, while minimizing the cost of cash occupation.

[0003] However, the current management of ATMs has the following problems: (1) Since the public's cash usage behavior is affected by factors such as the location of the ATM, the consumption habits of the surrounding population, seasonal factors, and emergencies, it is difficult to accurately predict the future cash usage of ATMs; (2) In the process of calculating the minimum cash cost of ATMs, it is necessary to comprehensively consider the interaction of multiple variables. Due to the large number of variables and the complex relationships, manual calculation is difficult to achieve the global optimal solution, which requires a lot of time and effort and has low accuracy.

[0004] Therefore, there is an urgent need for a method for determining the capital cost of a self-service teller machine to accurately determine the capital cost of the self-service teller machine.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiment of the present invention provides a method and device for determining the capital cost of a self-service teller machine, and an electronic device thereof, so as to at least solve the technical problem in the related art that it is difficult to accurately determine the capital cost of a self-service teller machine.

[0007] According to one aspect of an embodiment of the present application, a method for determining the capital cost of an ATM is provided, comprising: for multiple ATMs, obtaining current transaction data on the ATMs within a first preset time period, and inputting the current transaction data into a preset capital usage prediction model to obtain the capital usage of the ATMs within a second preset time period; based on the capital usage, determining the capital inventory of each of the ATMs; based on all the capital inventory amounts, using a preset multivariate regression analysis model to determine the capital cost of each of the ATMs.

[0008] Furthermore, before the current transaction data is input into the preset fund usage prediction model to obtain the fund usage of the self-service teller machine in the second preset time period, it also includes: collecting historical transaction data of multiple self-service teller machines in the historical preset time period, wherein the historical transaction data at least includes: the beginning balance, the total withdrawal amount, the amount of banknote addition, the total deposit amount, the transfer amount, and the recovery amount. The beginning balance refers to the fund balance at the beginning of the historical preset time period. The transfer amount refers to the total amount of funds transferred from the fund point to the self-service teller machine. The fund point is a node where a financial institution manages funds. The recovered amount refers to the amount of funds recovered from the ATM; based on the beginning balance, the total withdrawal amount, the additional amount, the total deposit amount, the transfer amount and the recovered amount, the ending balance is determined, wherein the ending balance refers to the balance of funds at the end of the historical preset time period; the historical transaction data, the ending balance and the preset label are added to the training data set, wherein the preset label includes the actual historical funds usage within the historical preset time period; based on the training data set, the initial funds usage prediction model is trained to obtain the preset funds usage prediction model.

[0009] Furthermore, based on the training data set, the initial funds usage prediction model is trained to obtain the preset funds usage prediction model, including: drawing a curve trend graph based on the total withdrawal amount and the total deposit amount in the training data set, and analyzing the curve trend graph to obtain trend characteristics of the total withdrawal amount and the total deposit amount; based on the curve trend graph, determining the peak node of the curve trend graph and the valley node of the curve trend graph; based on the training data set, the trend characteristics, the peak node and the valley node, adjusting the parameters of the initial funds usage prediction model until the absolute difference between the predicted funds usage and the actual historical funds usage is less than a preset difference threshold, thereby obtaining the preset funds usage prediction model, wherein the predicted funds usage is the funds usage output by the initial funds usage prediction model.

[0010] Furthermore, after the current transaction data is input into a preset fund usage prediction model to obtain the fund usage of the ATM in the second preset time period, it also includes: for each of the ATMs, based on the amount of added banknotes, the initial cash amount, the preset fund safety lower limit value and the fund usage, determining the number of times banknotes are added, wherein the amount of added banknotes is the amount of funds added to the ATM each time, the initial cash amount is the amount of cash in the ATM at the beginning of the first preset time period, and the preset fund safety lower limit value is the minimum safe fund amount of the ATM; based on the amount of added banknotes and the number of times banknotes are added, determining the initial parameter value of the total amount of funds in transit parameter of each of the ATMs; based on each of the initial parameter values, determining the parameter range of the total amount of funds in transit parameter.

[0011] Furthermore, before determining the capital cost of each of the ATMs based on the capital inventory of all the ATMs using a preset multiple regression analysis model, it also includes: constructing the preset multiple regression analysis model based on the capital cost data consumed by the ATMs, capital inventory parameters, cash cart cost parameters, total capital in transit parameters, cash cart number coefficient, ATM inventory interest rate coefficient, in-transit capital interest rate coefficient and interference coefficient.

[0012] Furthermore, before determining the capital cost of each of the ATMs based on all the capital inventory levels using a preset multiple regression analysis model, it also includes: based on the parameter range, using a preset optimization algorithm, iterating the preset multiple regression analysis model until the value of the capital cost data remains unchanged in a preset number of iterations, thereby obtaining a target capital cost and a target parameter value of the preset multiple regression analysis model, wherein the target parameter value includes: a target parameter value of the capital inventory level parameter, a target parameter value of the cash cart expense parameter, and a target parameter value of the total amount of funds in transit parameter; adding the target parameter value of the capital inventory level parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter to the target parameter value set.

[0013] Furthermore, after determining the capital cost of each of the self-service teller machines by using a preset multivariate regression analysis model based on all the capital inventory amounts, it also includes: obtaining the current capital cost of the self-service teller machine; when the current capital cost of multiple self-service teller machines is higher than the target capital cost, re-iteratively calculating each of the target parameter values ​​in the target parameter value set.

[0014] According to another aspect of an embodiment of the present application, a device for determining the capital cost of a self-service teller machine is also provided, comprising: an input unit, for obtaining current transaction data on a plurality of self-service teller machines within a first preset time period, and inputting the current transaction data into a preset capital usage prediction model to obtain the capital usage of the self-service teller machines within a second preset time period; a first determination unit, for determining the capital inventory of each of the self-service teller machines based on the capital usage; and a second determination unit, for determining the capital cost of each of the self-service teller machines based on all the capital inventories using a preset multivariate regression analysis model.

[0015] Furthermore, the determination device includes: a first collection module, which is used to collect historical transaction data of multiple self-service teller machines within a historical preset time period before inputting the current transaction data into a preset fund usage prediction model to obtain the fund usage of the self-service teller machine in a second preset time period, wherein the historical transaction data at least includes: an opening balance, a total withdrawal amount, a note addition amount, a total deposit amount, an allocation amount, and a recovery amount, wherein the opening balance refers to the fund balance at the beginning of the historical preset time period, the allocation amount refers to the total amount of funds allocated from a fund point to the self-service teller machine, and the fund point is a node for a financial institution to manage funds, and the recovery amount refers to the amount of funds from The amount of funds recovered at the ATM; a first determination module, used to determine the ending balance based on the beginning balance, the total withdrawal amount, the additional amount, the total deposit amount, the transfer amount and the recovered amount, wherein the ending balance refers to the fund balance at the end of the historical preset time period; a first adding module, used to add the historical transaction data, the ending balance and the preset label to the training data set, wherein the preset label includes the actual historical fund usage within the historical preset time period; a first training module, used to train the initial fund usage prediction model based on the training data set to obtain the preset fund usage prediction model.

[0016] Furthermore, the first training module includes: a first analysis submodule, used to draw a curve trend graph based on the total withdrawal amount and the total deposit amount in the training data set, and analyze the curve trend graph to obtain the trend characteristics of the total withdrawal amount and the total deposit amount; a first determination submodule, used to determine the peak node of the curve trend graph and the valley node of the curve trend graph based on the curve trend graph; a first adjustment submodule, used to adjust the parameters of the initial funds usage prediction model based on the training data set, the trend characteristics, the peak node and the valley node, until the absolute difference between the predicted funds usage and the actual historical funds usage is less than a preset difference threshold, thereby obtaining the preset funds usage prediction model, wherein the predicted funds usage is the funds usage output by the initial funds usage prediction model.

[0017] Furthermore, the determination device also includes: a second determination module, which is used to determine the number of times of adding banknotes for each self-service teller machine based on the amount of banknotes added, the initial cash amount, the preset lower limit value of fund safety and the amount of fund usage after inputting the current transaction data into a preset fund usage prediction model to obtain the amount of fund usage of the self-service teller machine in a second preset time period, wherein the amount of banknotes added is the amount of funds added to the self-service teller machine each time, the initial cash amount is the amount of cash in the self-service teller machine at the beginning of the first preset time period, and the preset lower limit value of fund safety is the minimum safe amount of funds of the self-service teller machine; a third determination module, which is used to determine the initial parameter value of the total amount of funds in transit parameter of each self-service teller machine based on the amount of banknotes added and the number of banknotes added; and a fourth determination module, which is used to determine the parameter range of the total amount of funds in transit parameter based on each of the initial parameter values.

[0018] Furthermore, the determination device also includes: a first construction module, which is used to construct the preset multiple regression analysis model based on the capital cost data consumed by the self-service teller machine, capital inventory parameters, cash car cost parameters, total funds in transit parameters, cash car number coefficient, self-service teller machine inventory interest rate coefficient, in-transit funds interest rate coefficient and interference coefficient before determining the capital cost of each self-service teller machine based on all the capital inventory levels using a preset multiple regression analysis model.

[0019] Furthermore, the determination device also includes: a first iteration module, which is used to iterate the preset multiple regression analysis model based on the parameter range and using a preset optimization algorithm before determining the capital cost of each of the self-service teller machines based on all the capital inventory levels and using a preset multiple regression analysis model, until the value of the capital cost data remains unchanged in the preset number of iterations, thereby obtaining the target capital cost and target parameter value of the preset multiple regression analysis model, wherein the target parameter value includes: the target parameter value of the capital inventory level parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter; a second adding module, which is used to add the target parameter value of the capital inventory level parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter to the target parameter value set.

[0020] Furthermore, the determination device also includes: a first acquisition module, which is used to obtain the current capital cost of the self-service teller machine after determining the capital cost of each of the self-service teller machines based on all the capital inventory amounts using a preset multivariate regression analysis model; and a second iteration module, which is used to re-iterate and calculate each of the target parameter values ​​in the target parameter value set when the current capital cost of multiple self-service teller machines is higher than the target capital cost.

[0021] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for determining the capital cost of an ATM.

[0022] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned methods for determining the capital cost of an ATM.

[0023] In the present invention, for multiple self-service teller machines, current transaction data on the self-service teller machines within a first preset time period is obtained, and the current transaction data is input into a preset fund usage prediction model to obtain the fund usage of the self-service teller machines in a second preset time period. Based on the fund usage, the fund inventory of each self-service teller machine is determined, and based on all fund inventories, a preset multivariate regression analysis model is used to determine the fund cost of each self-service teller machine, thereby solving the technical problem in the related art that it is difficult to accurately determine the fund cost of a self-service teller machine.

[0024] In the present invention, current transaction data on multiple ATMs within a first preset time period is obtained, and the current transaction data is input into a preset fund usage prediction model, so that the fund usage of the ATMs in a second preset time period can be obtained, and then the fund inventory of each ATM can be calculated based on the fund usage, and based on all fund inventories, the preset multivariate regression analysis model can be used to determine the fund cost of each ATM, and through automated and intelligent strategy adjustments, the fund cost of each ATM can be accurately calculated, effectively reducing the total operating cost, thereby achieving the technical effect of accurately calculating the fund cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0026] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining the capital cost of a self-service teller machine is shown;

[0027] Figure 2 is a flow chart of a method for determining the capital cost of an ATM according to Embodiment 1 of the present application;

[0028] Figure 3 is a schematic diagram of an optional device for determining the capital cost of a self-service teller machine according to an embodiment of the present application;

[0029] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) collected and involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set between the system and the relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0033] In the present invention, when the cash balance of the ATM drops to a certain level, the ATM needs to be replenished. By using a preset fund usage prediction model to predict the future cash usage of the ATM, the total inventory of the ATM can be calculated every day, and then the relationship between the total amount of funds in transit, the number of times the cash needs to be replenished and the total operating cost is formed. The fund cost of the ATM is calculated using a multivariate regression algorithm, which improves the efficiency and accuracy of fund management.

[0034] The present invention is described in detail below in conjunction with various embodiments.

[0035] Example 1

[0036] According to an embodiment of the present application, an embodiment of a method for determining the capital cost of an ATM is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining the capital cost of an ATM is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more ( Figure 1 102a, 102b, ..., 102n are used to illustrate) processor 102 (processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera, wherein the network interface may be connected to a wired and / or wireless network. A person of ordinary skill in the art will understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0038] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0039] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the capital cost of the self-service teller machine in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for determining the capital cost of the self-service teller machine is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0040] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0042] Under the above operating environment, this application provides Figure 2 The method for determining the capital cost of ATMs is shown. Figure 2 is a flow chart of a method for determining the capital cost of an ATM according to Example 1 of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0043] Step S201, for multiple ATMs, obtain current transaction data on the ATMs within a first preset time period, and input the current transaction data into a preset fund usage prediction model to obtain the fund usage of the ATMs in a second preset time period.

[0044] Optionally, current transaction data of each ATM within a first preset time period (such as a week, a month or a quarter, etc.) can be obtained. The current transaction data includes but is not limited to: beginning balance, total withdrawal amount, amount of added cash, total deposit amount, transferred amount, recovered amount, number of withdrawals, number of deposits, ending balance, transferred amount and recovered amount, etc.

[0045] In an embodiment of the present invention, the current transaction data of each ATM is input into a preset fund usage prediction model (such as a trained BP (Backpropagation Neural Network Model) neural network model), and the fund usage of the ATM in a second preset time period (i.e., a future period after the end of the first preset time period, such as the second day after the end of the first preset time period) can be output.

[0046] Step S202, based on the amount of funds used, determine the amount of funds in stock at each ATM.

[0047] Optionally, the fund inventory is the fund inventory that each ATM needs to maintain in order to meet the predicted fund usage. The fund inventory of each ATM can be calculated based on the fund usage and the safety inventory strategy.

[0048] For example, assuming that you want the cash in the ATM to be able to meet the cash usage for the next N days (i.e., safety stock strategy), then the cash inventory = future cash usage × N + buffer inventory (the amount of additional cash prepared to deal with emergencies, which can be determined based on risk assessment).

[0049] Step S203, based on the total capital inventory, a preset multiple regression analysis model is used to determine the capital cost of each ATM.

[0050] Optionally, for each ATM, the operating cost factors can be determined (including the interest rate of the ATM inventory and the capital inventory of a single ATM, the amount of banknotes added each time, the number of banknotes added and the interest rate of funds in transit, the coefficient of the number of money carts and the annual money cart expenses), and then the operating cost factors of all single devices can be added together to obtain the total operating cost of all devices, that is, the total operating cost R of all devices is calculated using a preset multiple regression analysis model, wherein the formula of the preset multiple regression analysis model is: R=k1X+k2Y+k3Z+ε, wherein k1 is the coefficient of the number of money carts, k2 is the interest rate coefficient of the ATM inventory, k3 is the interest rate coefficient of funds in transit, X is the parameter of the money cart expense, Y is the parameter of the ATM capital inventory, Z is the parameter of the total amount of funds in transit, and ε is the interference factor (i.e., the interference coefficient).

[0051] In an embodiment of the present invention, the capital cost is taken as the multivariate regression target and multiple regression calculations are performed to adjust the optimal parameters, find the optimal balance point of the preset multivariate regression analysis model, and generate the optimal preset multivariate regression analysis model. In this way, the capital cost of the ATM can be minimized.

[0052] In summary, by obtaining current transaction data on multiple ATMs within a first preset time period and inputting the current transaction data into a preset funds usage prediction model, the funds usage of the ATMs in the second preset time period can be obtained, and then the funds inventory of each ATM can be calculated based on the funds usage, and based on all funds inventory, the preset multiple regression analysis model can be used to determine the funds cost of each ATM, thereby solving the technical problem in the related technology that it is difficult to accurately determine the funds cost of the ATMs.

[0053] In order to accurately obtain the preset fund usage prediction model, in the method for determining the fund cost of the self-service teller machine provided in Example 1 of the present application, historical transaction data of multiple self-service teller machines within a historical preset time period are collected, wherein the historical transaction data at least includes: an opening balance, a total withdrawal amount, an amount of banknotes added, a total deposit amount, an allocation amount, and a recovery amount, wherein the opening balance refers to the fund balance at the beginning of the historical preset time period, the allocation amount refers to the total amount of funds transferred from the fund point to the self-service teller machine, the fund point is a node for financial institutions to manage funds, and the recovery amount refers to the amount of funds recovered from the self-service teller machine; based on the opening balance, the total withdrawal amount, the amount of banknotes added, the total deposit amount, the allocation amount and the recovery amount, the ending balance is determined, wherein the ending balance refers to the fund balance at the end of the historical preset time period; the historical transaction data, the ending balance and the preset label are added to the training data set, wherein the preset label includes the actual historical fund usage within the historical preset time period; based on the training data set, the initial fund usage prediction model is trained to obtain the preset fund usage prediction model.

[0054] Optionally, historical transaction data of multiple ATMs within a historical preset time period (such as one week, one month or any preset period) are collected, and the historical transaction data include but are not limited to: all cash transaction records of the ATMs within the historical preset time period (such as the beginning balance (the balance of funds at the beginning of the historical preset time period), the total withdrawal amount, the amount of added banknotes, the total deposit amount, the transfer amount (the total amount of funds transferred from the funding point (the node where the financial institution manages funds) to the ATM), the recovery amount (the amount of funds recovered from the ATM), the ATM number, the ATM type, the transaction currency, the transaction date, the number of withdrawals, and the number of deposits).

[0055] In the embodiment of the present invention, the ending balance (i.e., the fund balance at the end of the historical preset time period) can be determined based on the beginning balance, total withdrawal amount, additional note amount, total deposit amount, transfer amount, and recovery amount.

[0056] Exemplarily, the ending balance = the beginning balance - the total withdrawal amount + the total deposit amount + the amount of additional notes + the amount of transfer - the amount of recovery.

[0057] In an embodiment of the present invention, historical transaction data, end-of-period balances, and preset labels (i.e., actual historical funds usage within a preset historical time period) are added to a training data set, and an initial funds usage prediction model is trained based on the training data set to obtain a preset funds usage prediction model.

[0058] In order to improve the accuracy of the preset funds usage prediction model, in the method for determining the funds cost of an ATM machine provided in Example 1 of the present application, a curve trend graph is drawn based on the total withdrawal amount and the total deposit amount in the training data set, and the curve trend graph is analyzed to obtain the trend characteristics of the total withdrawal amount and the total deposit amount; based on the curve trend graph, the peak node of the curve trend graph and the valley node of the curve trend graph are determined; based on the training data set, trend characteristics, peak nodes and valley nodes, the parameters of the initial funds usage prediction model are adjusted until the absolute difference between the predicted funds usage and the actual historical funds usage is less than the preset difference threshold, so as to obtain the preset funds usage prediction model, wherein the predicted funds usage is the funds usage output by the initial funds usage prediction model.

[0059] In an embodiment of the present invention, a curve trend graph (used to show the trend of capital flow (such as seasonal changes, cyclical fluctuations, etc.)) can be drawn based on the total amount of withdrawals and deposits of the ATM, and the curve trend graph can be analyzed to obtain the trend characteristics of the total amount of withdrawals and the total amount of deposits, and the peak nodes and valley nodes of the capital transaction volume can be extracted. The trend characteristics, peak nodes and valley nodes can be used as part of the characteristics. According to the training data set, trend characteristics, peak nodes and valley nodes, the parameters of the initial capital usage prediction model (such as the BP neural network model) are adjusted until the absolute difference between the predicted capital usage and the actual historical capital usage is less than a preset difference threshold (such as 0), and a preset capital usage prediction model is obtained. By adjusting the model parameters, the prediction model can more accurately reflect the trends and characteristics in the historical transaction data, reduce the prediction error, and improve the prediction accuracy.

[0060] In order to accurately determine the parameter range of the total amount of funds in transit parameter, in the method for determining the capital cost of the self-service teller machine provided in Example 1 of the present application, for each self-service teller machine, the number of times of adding money is determined based on the amount of money added, the initial cash amount, the preset lower limit value of funds safety and the amount of funds used, wherein the amount of money added is the amount of funds added to the self-service teller machine each time, the initial cash amount is the amount of cash in the self-service teller machine at the beginning of the first preset time period, and the preset lower limit value of funds safety is the minimum safe amount of funds of the self-service teller machine; based on the amount of money added and the number of times of money added, the initial parameter value of the total amount of funds in transit parameter of each self-service teller machine is determined; based on each initial parameter value, the parameter range of the total amount of funds in transit parameter is determined.

[0061] Optionally, the amount of added cash is the amount of funds replenished each time the ATM is operated to add cash, the initial cash amount is the amount of cash in the ATM at the beginning of the first preset time period, and the preset fund safety lower limit is the minimum safe fund amount that the ATM must maintain to ensure normal operation. Based on the amount of added cash, the initial cash amount, the preset fund safety lower limit and the fund usage, the number of times the ATM is added can be calculated (i.e., the number of times the ATM needs to be added within a certain time period (such as one year) to maintain the fund supply of the ATM).

[0062] For example, if the future fund usage of an ATM in one day is C, the amount of banknotes added is Q, the initial cash amount is S, and the preset fund safety lower limit is L, then the number of banknote additions = (SL) ÷ (QC).

[0063] In an embodiment of the present invention, the initial parameter value of the total amount of funds in transit (i.e., the total amount of funds in transit) parameter of each ATM can be determined based on the amount of added banknotes and the number of times banknotes are added, and the parameter range of the total amount of funds in transit parameter can be determined based on each initial parameter value.

[0064] For example, the amount of cash added is Q, and the number of times of adding cash is M, then the total amount of funds in transit Z is a ratio of the amount of cash added multiplied by the number of times of adding cash (because the funds are not always in transit, assuming that the funds are in transit for an average of P% of the time during each cash addition process, then Z = Q×M×P%).

[0065] In order to accurately construct a preset multiple regression analysis model, in the method for determining the capital cost of an ATM provided in Example 1 of the present application, a preset multiple regression analysis model is constructed based on the capital cost data consumed by the ATM, capital inventory parameters, cash cart cost parameters, total capital in transit parameters, cash cart number coefficient, interest rate coefficient of the ATM inventory, interest rate coefficient of funds in transit and interference coefficient.

[0066] Optionally, the ATM inventory interest rate coefficient (i.e., funds occupied by the ATM will incur relevant costs, such as k2) is related to the opportunity cost of funds and can be determined based on factors such as the interest rate level of the financial market. The ATM inventory interest rate coefficient and funds inventory parameters (such as Y) can generate inventory cash costs (such as k2Y).

[0067] In an embodiment of the present invention, the parameter value of the cash cart cost parameter (such as X) is a fixed value, which can be obtained by statistics according to a certain calculation period (such as one year) based on all the costs related to the operation of the cash cart, such as the purchase cost, maintenance cost, employee wages, fuel costs, etc. of the cash cart. The number coefficient of the cash cart (such as k1) can be determined by analyzing the operating cost structure. For example, if a cash cart is added, the cost related to the cash cart in the operating cost increases by ΔR, and there is a certain proportional relationship between ΔR and the parameter value of the cash cart cost parameter (i.e., the number coefficient of the cash cart).

[0068] In the embodiment of the present invention, the cash cart number coefficient and the cash cart fee parameter can determine the transportation cost (such as k1X).

[0069] In an embodiment of the present invention, the total amount parameter of funds in transit (such as Z) can be determined according to the amount of banknotes added and the number of times banknotes are added. The interest rate coefficient of funds in transit (such as k3) mainly considers the costs such as the time value loss of funds in the transportation process, and can be determined according to factors such as transportation time, financial market interest rate, and fund risk. For example, the average transportation time of funds in transit is T days, and the market daily interest rate is d. The interest rate coefficient of funds in transit can be set to a value slightly higher than T×d.

[0070] In the embodiment of the present invention, the in-transit funds interest rate coefficient and the in-transit funds total amount parameter can determine the in-transit funds cost (such as k3Z).

[0071] In an embodiment of the present invention, there are other cost factors, such as equipment maintenance costs, labor management costs, etc. (i.e., the interference coefficient ε). A preset multivariate regression analysis model can be constructed based on the capital cost data consumed by the ATM, capital inventory parameters, cash car cost parameters, total capital in transit parameters, cash car number coefficient, ATM inventory interest rate coefficient, in-transit capital interest rate coefficient, and interference coefficient.

[0072] In order to accurately obtain a set of target parameter values, in the method for determining the capital cost of an ATM provided in Example 1 of the present application, based on the parameter range, a preset optimization algorithm is used to iterate the preset multiple regression analysis model until the value of the capital cost data remains unchanged in the preset number of iterations, thereby obtaining the target capital cost and target parameter values ​​of the preset multiple regression analysis model, wherein the target parameter values ​​include: the target parameter values ​​of the capital inventory quantity parameters, the target parameter values ​​of the cash cart expense parameters, and the target parameter values ​​of the total amount of funds in transit parameters; the target parameter values ​​of the capital inventory quantity parameters, the target parameter values ​​of the cash cart expense parameters, and the target parameter values ​​of the total amount of funds in transit parameters are added to the target parameter value set.

[0073] Optionally, by iteratively optimizing the preset multiple regression analysis model and gradually adjusting the model parameters, a set of target parameter values ​​that minimizes the capital cost data (ie, the target capital cost) and is stable can be obtained.

[0074] In an embodiment of the present invention, according to the parameter range, a preset optimization algorithm (such as a gradient descent algorithm) can be used to iterate the preset multiple regression analysis model until the value of the capital cost data consumed by the ATM remains unchanged within a preset number of iterations (to avoid infinite iterations, the pre-set iteration termination condition refers to the maximum number of iterations), and the target capital cost of the preset multiple regression analysis model and the target parameter values ​​of the capital inventory parameters, the target parameter values ​​of the cash car cost parameters, and the target parameter values ​​of the total amount of funds in transit parameters can be obtained.

[0075] In order to improve the accuracy of determining the target parameter value, in the method for determining the capital cost of an ATM provided in Example 1 of the present application, the current capital cost of the ATM is obtained; when the current capital costs of multiple ATMs are higher than the target capital cost, each target parameter value in the target parameter value set is re-iteratively calculated.

[0076] In an embodiment of the present invention, by dynamically acquiring the current capital cost of the ATM, and when the current capital cost is higher than the target capital cost, a preset multivariate regression analysis model is selected, and the preset optimization algorithm is used again to iteratively calculate the target parameter value set. After the iterative calculation is completed, the target parameter value set can be re-determined to ensure that the new set can reflect the new cost optimization strategy while meeting operational needs.

[0077] The method for determining the capital cost of a self-service teller machine provided in the embodiment of the present application can predict the future cash usage through a preset capital usage prediction model to determine a reasonable cash inventory and cash replenishment strategy, and then analyze the periodicity of withdrawals and deposits by drawing a trend chart, determine the peak and valley nodes, and finely adjust the prediction model parameters to ensure the accurate prediction of the preset capital usage prediction model, and then construct a preset multivariate regression analysis model, and through an iterative optimization algorithm, iterate repeatedly within the parameter range until the value of the capital cost data remains unchanged within the preset number of iterations, so as to obtain the target capital cost and target parameter value, and when the current capital cost exceeds the target cost, the preset multivariate regression analysis model can be re-iterated to dynamically adjust the parameters to minimize the cost, thereby realizing intelligent prediction and dynamic optimization of the operating cost of the self-service teller machine, reducing the cost caused by cash inventory and cash replenishment, and improving the efficiency of capital use.

[0078] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0079] Example 2

[0080] The embodiment of the present application also provides a self-service ATM capital cost determination device. It should be noted that the self-service ATM capital cost determination device of the embodiment of the present application can be used to execute the self-service ATM capital cost determination method provided in the embodiment of the present application. The following introduces the self-service ATM capital cost determination device provided in the embodiment of the present application.

[0081] According to an embodiment of the present application, a device for implementing the above-mentioned method for determining the capital cost of an ATM is also provided. Figure 3 is a schematic diagram of an optional device for determining the capital cost of a self-service teller machine according to an embodiment of the present application, such as Figure 3 As shown, the device for determining the capital cost of an ATM machine may include: an input unit 30 , a first determining unit 31 , and a second determining unit 32 .

[0082] The input unit 30 is used to obtain current transaction data on the self-service teller machines within a first preset time period for multiple self-service teller machines, and input the current transaction data into a preset fund usage prediction model to obtain the fund usage of the self-service teller machines in a second preset time period;

[0083] A first determining unit 31 is used to determine the fund inventory of each ATM based on the fund usage;

[0084] The second determining unit 32 is used to determine the capital cost of each ATM machine based on the total capital inventory using a preset multiple regression analysis model.

[0085] The device for determining the capital cost of an ATM provided in the embodiment of the present application can obtain current transaction data on the ATMs within a first preset time period for multiple ATMs through an input unit 30, and input the current transaction data into a preset capital usage prediction model to obtain the capital usage of the ATMs in a second preset time period. The first determination unit 31 can be used to determine the capital inventory of each ATM based on the capital usage. The second determination unit 32 can be used to determine the capital cost of each ATM based on all capital inventories by using a preset multiple regression analysis model.

[0086] Optionally, the determination device includes: a first collection module, which is used to collect historical transaction data of multiple self-service teller machines within a historical preset time period before inputting current transaction data into a preset fund usage prediction model to obtain the fund usage of the self-service teller machine in a second preset time period, wherein the historical transaction data at least includes: an opening balance, a total withdrawal amount, a banknote addition amount, a total deposit amount, a transfer amount, and a recovery amount, wherein the opening balance refers to the fund balance at the beginning of the historical preset time period, the transfer amount refers to the total amount of funds transferred from the fund point to the self-service teller machine, the fund point is a node for financial institutions to manage funds, and the recovery amount The amount refers to the amount of funds recovered from the ATM; the first determination module is used to determine the ending balance based on the beginning balance, the total withdrawal amount, the amount of banknote addition, the total deposit amount, the transfer amount and the recovery amount, wherein the ending balance refers to the fund balance at the end of the historical preset time period; the first adding module is used to add the historical transaction data, the ending balance and the preset label to the training data set, wherein the preset label includes the actual historical fund usage within the historical preset time period; the first training module is used to train the initial fund usage prediction model based on the training data set to obtain the preset fund usage prediction model.

[0087] Optionally, the first training module includes: a first analysis submodule, which is used to draw a curve trend graph based on the total withdrawal amount and the total deposit amount in the training data set, and analyze the curve trend graph to obtain trend characteristics of the total withdrawal amount and the total deposit amount; a first determination submodule, which is used to determine the peak node and the valley node of the curve trend graph based on the curve trend graph; a first adjustment submodule, which is used to adjust the parameters of the initial funds usage prediction model based on the training data set, trend characteristics, peak nodes and valley nodes, until the absolute difference between the predicted funds usage and the actual historical funds usage is less than a preset difference threshold, so as to obtain a preset funds usage prediction model, wherein the predicted funds usage is the funds usage output by the initial funds usage prediction model.

[0088] Optionally, the determination device also includes: a second determination module, which is used to determine the number of times of adding banknotes for each self-service teller machine based on the amount of banknotes added, the initial cash amount, the preset lower limit value of fund safety and the amount of funds used, after inputting the current transaction data into a preset fund usage prediction model to obtain the amount of funds used by the self-service teller machine in the second preset time period, wherein the amount of banknotes added is the amount of funds added to the self-service teller machine each time, the initial cash amount is the amount of cash in the self-service teller machine at the beginning of the first preset time period, and the preset lower limit value of fund safety is the minimum safe amount of funds of the self-service teller machine; a third determination module, which is used to determine the initial parameter value of the total amount of funds in transit parameter of each self-service teller machine based on the amount of banknotes added and the number of banknotes added; and a fourth determination module, which is used to determine the parameter range of the total amount of funds in transit parameter based on each initial parameter value.

[0089] Optionally, the determination device also includes: a first construction module, which is used to construct a preset multiple regression analysis model based on the capital cost data consumed by the self-service ATM, capital inventory parameters, cash car cost parameters, total funds in transit parameters, cash car number coefficient, self-service ATM inventory interest rate coefficient, in-transit funds interest rate coefficient and interference coefficient before determining the capital cost of each ATM based on all capital inventory levels using a preset multiple regression analysis model.

[0090] Optionally, the determination device also includes: a first iteration module, which is used to iterate the preset multiple regression analysis model based on the parameter range and using a preset optimization algorithm before determining the capital cost of each ATM machine based on all cash inventory levels using a preset multiple regression analysis model, until the value of the capital cost data remains unchanged in the preset number of iterations, thereby obtaining the target capital cost and target parameter value of the preset multiple regression analysis model, wherein the target parameter value includes: the target parameter value of the cash inventory level parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter; a second adding module, which is used to add the target parameter value of the cash inventory level parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter to the target parameter value set.

[0091] Optionally, the determination device also includes: a first acquisition module, which is used to obtain the current capital cost of the self-service teller machine after determining the capital cost of each self-service teller machine based on all capital inventory amounts using a preset multivariate regression analysis model; and a second iteration module, which is used to re-iterate and calculate each target parameter value in the target parameter value set when the current capital cost of multiple self-service teller machines is higher than the target capital cost.

[0092] The above-mentioned device for determining the capital cost of an ATM machine may also include a processor and a memory. The above-mentioned input unit 30, the first determination unit 31, the second determination unit 32, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0093] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the capital cost of each self-service teller machine is determined based on the total capital inventory by adjusting the kernel parameters and using a preset multiple regression analysis model.

[0094] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0095] It should be noted that the above-mentioned input unit 30, the first determination unit 31, and the second determination unit 32 correspond to steps S201 to S203 in Embodiment 1, and the above-mentioned units and the corresponding steps implement the same instances and application scenarios, but are not limited to the contents disclosed in the above-mentioned Embodiment 1. It should be noted that the above-mentioned units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned units may also be part of the device and may be run in the computer terminal 10 provided in Embodiment 1.

[0096] Example 3

[0097] The embodiment of the present application may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal or an electronic device.

[0098] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0099] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the method for determining the capital cost of an ATM: for multiple ATMs, obtain the current transaction data on the ATM within a first preset time period, and input the current transaction data into a preset capital usage prediction model to obtain the capital usage of the ATM in a second preset time period; based on the capital usage, determine the capital inventory of each ATM; based on all capital inventories, use a preset multiple regression analysis model to determine the capital cost of each ATM.

[0100] Optionally, the computer terminal can execute the following steps of the method for determining the capital cost of an ATM: collecting historical transaction data of multiple ATMs within a historical preset time period, wherein the historical transaction data at least includes: an opening balance, a total withdrawal amount, an amount of cash added, a total deposit amount, an allocation amount, and a recovery amount, wherein the opening balance refers to the capital balance at the beginning of the historical preset time period, the allocation amount refers to the total amount of funds transferred from a capital point to the ATM, the capital point is a node where a financial institution manages funds, and the recovery amount refers to the amount of funds recovered from the ATM; based on the opening balance, the total withdrawal amount, the amount of cash added, the total deposit amount, the allocation amount, and the recovery amount, determining the ending balance, wherein the ending balance refers to the capital balance at the end of the historical preset time period; adding the historical transaction data, the ending balance, and the preset label to a training data set, wherein the preset label includes the actual historical capital usage within the historical preset time period; based on the training data set, training an initial capital usage prediction model to obtain a preset capital usage prediction model.

[0101] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for determining the capital cost of an ATM: based on the total amount of withdrawals and the total amount of deposits in the training data set, draw a curve trend graph, and analyze the curve trend graph to obtain the trend characteristics of the total amount of withdrawals and the total amount of deposits; based on the curve trend graph, determine the peak node of the curve trend graph and the valley node of the curve trend graph; based on the training data set, trend characteristics, peak nodes and valley nodes, adjust the parameters of the initial capital usage prediction model until the absolute difference between the predicted capital usage and the actual historical capital usage is less than a preset difference threshold, and obtain a preset capital usage prediction model, wherein the predicted capital usage is the capital usage output by the initial capital usage prediction model.

[0102] Optionally, the computer terminal may execute the following program codes of the method for determining the capital cost of an ATM: for each ATM, determining the number of times that cash is added based on the amount of cash added, the initial cash amount, the preset lower limit value for capital safety, and the amount of capital used, wherein the amount of cash added is the amount of capital that is added to the ATM each time, the initial cash amount is the amount of cash in the ATM at the beginning of the first preset time period, and the preset lower limit value for capital safety is the minimum safe amount of capital in the ATM; determining the initial parameter value of the total amount of capital in transit parameter of each ATM based on the amount of cash added and the number of times that cash is added; and determining the parameter range of the total amount of capital in transit parameter based on each initial parameter value.

[0103] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for determining the capital cost of the self-service ATM: based on the capital cost data consumed by the self-service ATM, the capital inventory parameters, the cash car cost parameters, the total amount of funds in transit parameters, the cash car number coefficient, the interest rate coefficient of the self-service ATM inventory, the interest rate coefficient of funds in transit and the interference coefficient, a preset multivariate regression analysis model is constructed.

[0104] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for determining the capital cost of an ATM: based on the parameter range, using a preset optimization algorithm, iterate the preset multiple regression analysis model until the value of the capital cost data remains unchanged in the preset number of iterations, and obtain the target capital cost and target parameter value of the preset multiple regression analysis model, wherein the target parameter value includes: the target parameter value of the capital inventory parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter; the target parameter value of the capital inventory parameter, the target parameter value of the cash cart expense parameter, and the target parameter value of the total amount of funds in transit parameter are added to the target parameter value set.

[0105] Optionally, the above-mentioned computer terminal can execute the program code of the following steps in the method for determining the capital cost of an ATM: obtaining the current capital cost of the ATM; when the current capital costs of multiple ATMs are higher than the target capital cost, re-iteratively calculating each target parameter value in the target parameter value set.

[0106] Optionally, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 402, memory 404, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0107] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for determining the capital cost of the self-service teller machine in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method for determining the capital cost of the self-service teller machine. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0108] The processor can call the information and application programs stored in the memory through the transmission device to execute the above steps in the above method for determining the capital cost of the self-service teller machine.

[0109] By adopting the embodiment of the present application, a solution is provided for determining the capital cost of self-service teller machines. The capital usage is predicted by inputting the transaction data of a first preset time period into a preset capital usage prediction model, and then the capital inventory is determined. Finally, with the help of a preset multivariate regression analysis model, the capital cost of each self-service teller machine is accurately calculated, which effectively reduces operating costs and improves the efficiency and refinement of capital management, thereby solving the technical problem in related technologies that it is difficult to accurately determine the capital cost of self-service teller machines.

[0110] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a terminal device such as a smart phone, a tablet computer, a PDA, and a mobile Internet device (Mobile Internet Devices, MID). Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0111] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0112] Example 4

[0113] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the capital cost of an ATM provided in the first embodiment.

[0114] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0115] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the method for determining the capital cost of an ATM.

[0116] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0117] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining the capital cost of a self-service teller machine, characterized in that: include: For multiple self-service teller machines, current transaction data on the self-service teller machines in a first preset time period is obtained, and the current transaction data is input into a preset fund usage prediction model to obtain the fund usage of the self-service teller machines in a second preset time period; Based on the amount of funds used, determining the amount of funds in stock at each of the self-service teller machines; Based on all the fund inventories, a preset multiple regression analysis model is used to determine the fund cost of each of the ATMs.

2. The method for determining the capital cost of an ATM according to claim 1, characterized in that: Before inputting the current transaction data into a preset fund usage prediction model to obtain the fund usage of the ATM in a second preset time period, the method further includes: Collecting historical transaction data of the plurality of self-service teller machines within a historical preset time period, wherein the historical transaction data at least includes: an opening balance, a total withdrawal amount, a cash addition amount, a total deposit amount, a transfer amount, and a recovery amount, wherein the opening balance refers to the fund balance at the beginning of the historical preset time period, the transfer amount refers to the total amount of funds transferred from a funding point to the self-service teller machine, the funding point is a node where a financial institution manages funds, and the recovery amount refers to the amount of funds recovered from the self-service teller machine; Based on the opening balance, the total withdrawal amount, the additional amount, the total deposit amount, the transfer amount and the recovery amount, determine the ending balance, wherein the ending balance refers to the fund balance at the end of the historical preset time period; Adding the historical transaction data, the ending balance and the preset label to the training data set, wherein the preset label includes the actual historical fund usage within the historical preset time period; Based on the training data set, the initial funds usage prediction model is trained to obtain the preset funds usage prediction model.

3. The method for determining the capital cost of an ATM according to claim 2, characterized in that: The step of training the initial funds usage prediction model based on the training data set to obtain the preset funds usage prediction model includes: Based on the total withdrawal amount and the total deposit amount in the training data set, a curve trend graph is drawn, and the curve trend graph is analyzed to obtain trend characteristics of the total withdrawal amount and the total deposit amount; Based on the curve trend graph, determining a peak node of the curve trend graph and a valley node of the curve trend graph; Based on the training data set, the trend characteristics, the peak nodes and the valley nodes, the parameters of the initial funds usage prediction model are adjusted until the absolute difference between the predicted funds usage and the actual historical funds usage is less than a preset difference threshold, thereby obtaining the preset funds usage prediction model, wherein the predicted funds usage is the funds usage output by the initial funds usage prediction model.

4. The method for determining the capital cost of a self-service teller machine according to claim 1, characterized in that: After inputting the current transaction data into a preset fund usage prediction model to obtain the fund usage of the ATM in a second preset time period, the method further includes: For each of the self-service teller machines, the number of times of adding banknotes is determined based on the amount of banknotes added, the initial amount of cash, the preset lower limit value of fund safety, and the amount of funds used, wherein the amount of banknotes added is the amount of funds added to the self-service teller machine each time, the initial amount of cash is the amount of cash in the self-service teller machine at the beginning of the first preset time period, and the preset lower limit value of fund safety is the minimum safe amount of funds in the self-service teller machine; Based on the amount of banknotes added and the number of times of banknotes added, determining an initial parameter value of a total amount of funds in transit parameter of each of the self-service teller machines; Based on each of the initial parameter values, a parameter range of the total amount of funds in transit parameter is determined.

5. The method for determining the capital cost of a self-service teller machine according to claim 4, characterized in that: Before determining the capital cost of each of the self-service teller machines based on all the capital inventories by using a preset multiple regression analysis model, the method further includes: The preset multiple regression analysis model is constructed based on the capital cost data consumed by the ATM, capital inventory parameters, cash cart cost parameters, total capital in transit parameters, cash cart number coefficient, ATM inventory interest rate coefficient, capital in transit interest rate coefficient and interference coefficient.

6. The method for determining the capital cost of a self-service teller machine according to claim 5, characterized in that: Before determining the capital cost of each of the self-service teller machines based on all the capital inventories by using a preset multiple regression analysis model, the method further includes: Based on the parameter range, the preset optimization algorithm is used to iterate the preset multiple regression analysis model until the value of the capital cost data remains unchanged in the preset number of iterations, thereby obtaining the target capital cost and target parameter values ​​of the preset multiple regression analysis model, wherein the target parameter values ​​include: the target parameter value of the capital inventory parameter, the target parameter value of the cash vehicle cost parameter, and the target parameter value of the total amount of funds in transit parameter; The target parameter value of the fund inventory parameter, the target parameter value of the cash vehicle cost parameter, and the target parameter value of the total amount of funds in transit parameter are added to the target parameter value set.

7. The method for determining the capital cost of a self-service teller machine according to claim 6, characterized in that: After determining the capital cost of each of the self-service teller machines based on all the capital inventories by using a preset multiple regression analysis model, the method further includes: Obtaining the current capital cost of the ATM; When the current capital cost of the plurality of self-service teller machines is higher than the target capital cost, each target parameter value in the target parameter value set is re-iteratively calculated.

8. A device for determining the capital cost of a self-service teller machine, characterized in that: include: An input unit, for obtaining, for a plurality of self-service teller machines, current transaction data on the self-service teller machines within a first preset time period, and inputting the current transaction data into a preset fund usage prediction model to obtain the fund usage of the self-service teller machines within a second preset time period; A first determining unit, configured to determine the fund inventory of each of the self-service teller machines based on the fund usage; The second determination unit is used to determine the capital cost of each of the self-service teller machines based on all the capital inventory amounts by using a preset multivariate regression analysis model.

9. A computer program product, characterized in that It comprises a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for determining the capital cost of a self-service teller machine as claimed in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the capital cost of a self-service teller machine as described in any one of claims 1 to 7.

Images