JP2019101479A - Balance management system - Google Patents

Abstract

To provide a balance management system capable of improving security of transactions.SOLUTION: A balance management system 100 comprises: a deposit/withdrawal information acquisition part that acquires deposit/withdrawal information on a first account 161 from a business connection system 160 based on registered user information; a deposit/withdrawal pattern creation part that creates a deposit/withdrawal pattern of the first account 161 from the deposit/withdrawal information on the first account 161; and a balance prediction part that calculates a predicted balance of the first account 161 based on the deposit/withdrawal pattern of the first account 161.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a balance management system.

  If there are various withdrawals from your account, such as payment of credit card, rent, loan, etc. in a personal account or settlement in a corporate account, you may run out of balance. If a shortage of balance is neglected, the deduction is not carried out, and the account holder of the account suffers disadvantages such as payment of arrears and loss of credit.

  For example, in Patent Document 1, when it is determined that withdrawal is not possible due to lack of balance of the customer account, the customer is notified of the lack of balance. Financial processing system is disclosed. According to the above-described financial processing system, it is possible to make a customer recognize a shortage of balance and to promote the payment of the shortfall through an ATM (Automatic Teller Machine) of a financial institution or an internet financial service. When the shortage is deposited in the above-mentioned account within business hours of the day and the financial institution attempts to carry out the withdrawal process again, the withdrawal process is executed.

  However, if the customer can not receive a contact or if payment can not be made within business hours, the withdrawal process will not be completed. In addition, even if the financial institution does not try the withdrawal process again, the withdrawal process is not completed. As one of the methods for solving the above problems, Patent Document 2 discloses a withdrawal / settlement system capable of anticipating a shortage of balance before withdrawal and alerting a holder or the like of an account.

Japanese Patent Laid-Open No. 2002-92326 JP, 2010-146487, A

  However, in the system described in Patent Document 2, it is determined whether withdrawal is possible using the received withdrawal amount and the predicted balance calculated from the withdrawal date, and when it is determined that withdrawal is not possible, the account holder Warn Therefore, there is a problem that the warning can not be issued until the withdrawal information is obtained.

  The present invention has been made in view of such circumstances, and it is an object of the present invention to provide a balance management system capable of improving the security of transactions.

  A balance management system according to an aspect of the present invention includes a deposit / withdrawal information acquisition unit for acquiring deposit / withdrawal information on a first account from a customer system based on registered user information, and from the deposit / withdrawal information of the first account A deposit / withdrawal pattern creation unit that creates a deposit / withdrawal pattern of one account, and a balance prediction unit that calculates a predicted balance of the first account based on the first deposit / withdrawal pattern.

  According to the present invention, it is possible to provide a balance management system capable of improving the security of transactions.

It is a figure showing roughly the composition of the balance management system concerning a 1st embodiment. It is a figure which shows roughly the structure of the aggregation part provided in the balance management system which concerns on 1st Embodiment, a simulation part, and a notification part. It is a flowchart which shows an example of the process in the aggregation part which concerns on 1st Embodiment, and a simulation part. It is a flowchart which shows an example of the process in the simulation part which concerns on 1st Embodiment, and a notification part. It is a figure which shows an example of a deposit or withdrawal pattern. It is a figure which shows an example of a deposit or withdrawal schedule. It is a figure which shows an example of a predicted balance. It is a figure which shows an example of a replenishment plan. It is a figure which shows the example of a display in a user terminal. It is a flowchart which shows an example of the process in the simulation part which concerns on 2nd Embodiment, and a notification part. It is a flowchart which shows an example of the process in the simulation part which concerns on 3rd Embodiment, and a notification part. It is a figure which shows roughly the structure of the simulation part in the balance management system which concerns on 4th Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, in the second embodiment and thereafter, the same or similar components as or to those of the first embodiment are denoted by the same or similar reference numerals as those of the first embodiment, and the detailed description will be appropriately omitted. Further, with regard to the effects obtained in the second and subsequent embodiments, the description of the same effects as those of the first embodiment will be appropriately omitted. The drawings of the respective embodiments are exemplifications, and the dimensions and shapes of the respective parts are schematic, and the technical scope of the present invention should not be interpreted as being limited to the embodiments.

First Embodiment
First, the configuration of a balance management system 100 according to the first embodiment of the present invention will be described with reference to FIGS. 1 and 2. FIG. 1 is a diagram schematically showing the configuration of a balance management system according to the first embodiment. FIG. 2 is a diagram schematically showing configurations of an aggregation unit, a simulation unit, and a notification unit provided in the balance management system according to the first embodiment.

  The balance management system 100 is a system that predicts the balance of the user's account and notifies the user of the predicted balance. For example, the balance management system 100 urges the user to deposit into an account that is predicted to run out of balance by notifying the user of the balance shortage prior to the withdrawal date that is predicted to be unable to execute withdrawal processing due to the lack of balance. Prevent a shortage of balance. The balance management system 100 may also prompt the user to deposit into the account by notifying the user when the balance is predicted to fall below a specific amount. Although the user is assumed to be an individual in the present embodiment, the present invention is not limited to this, and the user may be a corporation or an arbitrary group. As an example, a user terminal 151 described later may be a business processing terminal for accessing a corporation's financial management system. In addition, a first account 161, a second account 162, and a third account 163, which will be described later, may be corporate accounts.

  As shown in FIG. 1, the balance management system 100 is communicably connected to the correspondent systems 160, 170, 180 and the user terminal 151 via the Internet. Each of the correspondent systems 160, 170 and 180 is configured using one or more computers. The balance management system 100 is not limited to being communicably connected to the correspondent systems 160, 170, and 180, and may be communicably connected to other systems.

  The correspondent system 160 corresponds to a system that manages an account of a financial institution whose user is the user of the user terminal 151. Supplier system 160 includes a plurality of systems for managing a plurality of accounts including first account 161, second account 162, and third account 163 in the example shown in FIG. 1. In the case where each account is opened at the same financial institution, the correspondent system 160 may be one system.

  The supplier system 170 is an information processing system of a service providing source or a product providing source in which the user of the user terminal 151 designates the supplier system 160 as a withdrawal account. The balance management system 100 may obtain part of the transaction information from the correspondent system 170. According to this, the balance management system 100 can acquire deposit / withdrawal information that has not yet been determined in the correspondent system 160. In FIG. 1, a card company 171, an EC site 172, and an infrastructure provider 173 are listed as an example of the correspondent system 170. The card company 171 is an information processing system in which a credit card company provides transaction information. The EC site 172 is an information processing system that provides information on electronic commerce via the Internet or the like. The infrastructure provider 173 is an information processing system that provides information such as the usage amount and charge of electricity, gas, water, and the like. However, the number and type of correspondent systems 170 are not limited to this.

  The correspondent system 180 corresponds to an information processing system of a lending institution to which the user of the user terminal 151 contracts. The correspondent system 180 is an information processing system capable of processing of withdrawal of repayment from the correspondent system 160 or transfer of borrowing to the correspondent system 160. The correspondent system 180 may be a system that manages a lending department in a financial institution in which any one of the first account 161, the second account 162, and the third account 163 is opened. That is, the correspondent system 160 and the correspondent system 180 may be operated by at least partially overlapping financial institutions.

  The user terminal 151 is a computer used by the user, and is a smartphone, a tablet terminal, a personal computer or the like. The user terminal 151 can acquire account information for accessing the correspondent system 160, 170, 180 by, for example, an input from the user. The account information is, for example, an access ID for accessing the correspondent system 160, 170, 180 by password authentication, a password, or the like. Account information may be obtained from the correspondent system 160, 170, 180. For example, the account information acquired from the correspondent system 160, 170, 180 may include an authentication code, an access token, a refresh token, and the like.

  Based on the account information, the user terminal 151 can access the correspondent system 160, 170, 180 via a dedicated program for access to the correspondent system 160, 170, 180 or a general-purpose program such as a web browser. The user terminal 151 can acquire transaction information from the correspondent system 160, 170, 180 using, for example, web scraping or an API (Application Program Interface). The user terminal 151 provides at least a part of the account information to the balance management system 100, and enables the balance management system 100 to access the customer system 160, 170, 180 by web scraping, API, or the like. As a result, the balance management system 100 can obtain transaction information directly from the correspondent system 160, 170, 180. However, the balance management system 100 can also acquire and record the transaction information input by the user terminal 151.

  The balance management system 100 may be communicably connected to another plurality of user terminals or another plurality of correspondent systems. As the number of connected user terminals and transaction information to be collected increases, the creation accuracy of the deposit and withdrawal pattern to be described later improves.

  As shown in FIG. 1, the balance management system 100 includes a user management unit 101, an aggregation unit 110, a simulation unit 120, and a notification unit 130. The configuration of each of the user management unit 101, the aggregation unit 110, the simulation unit 120, and the notification unit 130 will be described below with reference to FIG. The user management unit 101, the aggregation unit 110, the simulation unit 120, and the notification unit 130 can be realized, for example, by using a storage area or by causing a processor to execute a program stored in the storage area. . Similarly, for each unit constituting the user management unit 101, the aggregation unit 110, the simulation unit 120, and the notification unit 130 described below, the storage area is used, or the processor executes a program stored in the storage area. It can be realized by In the example shown in FIG. 2, the storage area is built in the balance management system 100. However, the storage area may be provided outside the balance management system 100.

  The user management unit 101 manages information of users registered in the balance management system 100. The user management unit 101 includes a user ID registration unit 103 and a user ID storage unit 105. The user ID is information for identifying the user of the balance management system 100. The user ID registration unit 103 stores, for example, the user ID registered by the user in the user ID storage unit 105. The user ID registration unit 103 may generate and register the user ID based on the user information registered by the user. The user ID registration unit 103 may register a part of user information (e.g., a mail address) as a user ID.

  The aggregation unit 110 is an information processing system that collects a plurality of pieces of transaction information from the supplier systems 160, 170, and 180. The aggregation unit 110 includes an account information registration unit 111, an account information storage unit 113, a transaction information acquisition unit 115, and a transaction information storage unit 117.

  The account information registration unit 111 receives account information for accessing the correspondent system 160, 170, 180 from the user terminal 151 and the correspondent system 160, 170, 180 and registers the account information in the account information storage unit 113. For example, the account information registration unit 111 acquires, from the user terminal 151, an access ID, a password, and the like for accessing the correspondent system 160, 170, 180. Further, the account information registration unit 111 accesses the correspondent system 160, 170, 180 based on the access ID, the password, and the like, and acquires an authentication code, an access token, a refresh token, and the like. The account information registration unit 111 may acquire an authentication code, an access token, a refresh token, and the like from the user terminal 151. Note that registration of account information in the account information storage unit 113 is also referred to as “cooperation” of the account information in the aggregation unit 110.

  The account information storage unit 113 stores the account information acquired from the account information registration unit 111. Account information is associated with the user ID. The account information stored in the account information storage unit 113 is information such as an access ID or password for the user to access the correspondent system 160, 170, 180, an authentication code, an access token, a refresh token, or the like.

  The transaction information acquisition unit 115 accesses the correspondent system 160, 170, 180 based on the account information stored in the account information storage unit 113, and acquires a plurality of pieces of transaction information. The transaction information acquisition unit 115 acquires transaction information from the supplier system 160, 170, 180 using, for example, web scraping or an API. The transaction information acquisition unit 115 acquires transaction information automatically, for example, by batch processing. Also, the transaction information acquisition unit 115 periodically accesses the correspondent system 160, 170, 180 to acquire transaction information. The transaction information acquisition unit 115 may acquire transaction information based on an instruction from the user terminal 151.

  The transaction information acquired from the supplier system 160 includes payment information and withdrawal information (hereinafter collectively referred to as deposit / withdrawal information) in the first account 161, the second account 162, and the third account 163. The deposit / withdrawal information includes information such as an account number, transaction details (for example, a transfer item of account transfer), a transaction date, an amount, and the like. The transaction information acquisition unit 115 also acquires information on the account balance of each of the first account 161, the second account 162, and the third account 163 at the time of acquiring the deposit and withdrawal information. The transaction information acquired from the correspondent system 170 includes billing information from the card company 171, the EC site 172, and the infrastructure provider 173. The billing information includes information such as a billing account, a billing date, and a billing amount. The transaction information acquired from the correspondent system 180 includes a repayment account, a repayment amount, a repayment date, and the like, if it has already been borrowed from the correspondent system 180. When borrowing from this, the amount of debt, the deposit date of the debt, the repayment start date, etc. are further included. The transaction information acquisition unit 115 stores the plurality of transaction information in the transaction information storage unit 117, and the transaction information storage unit 117 stores the plurality of transaction information.

  The simulation unit 120 is an information processing system that predicts the balance in the first account 161, the second account 162, and the third account 163. The simulation unit 120 includes a deposit and withdrawal information acquisition unit 121, an extraction model learning unit 123, a deposit and withdrawal pattern creation unit 125, a deposit and withdrawal schedule creation unit 127, and a balance prediction unit 129.

  The deposit and withdrawal information acquisition unit 121 acquires deposit and withdrawal information on each of the first account 161, the second account 162, and the third account 163 from the plurality of pieces of transaction information stored in the transaction information storage unit 117.

  The extraction model learning unit 123 learns an extraction model for extracting a deposit and withdrawal pattern from a plurality of deposit and withdrawal information. The extraction model is a program for extracting periodic payment and withdrawal patterns by text analysis of transaction contents, analysis of the occurrence date and occurrence period of payment and withdrawal, and the like. For example, the extraction model determines that the deposit / withdrawal including words such as “loan”, “rent”, “electricity charge”, etc. is regular deposit / withdrawal by text analysis of the transaction content. The contents of transactions, amount of deposit and withdrawal, principle and exception of deposit and withdrawal date, deposit and withdrawal frequency, etc. are analyzed from history of and extracted as deposit and withdrawal pattern. In addition, for example, the extraction model determines that the same payee or payee with the same payee on a specific day every month is the regular deposit or withdrawal, and the transaction content, deposit or withdrawal from the history of the deposit or withdrawal Analyze the amount of money, the principle and exception of deposit / withdrawal day, the deposit / withdrawal frequency etc, and extract it as the deposit / withdrawal pattern.

  The extraction model is created, for example, by supervised machine learning. That is, the extraction model learning unit 123 learns the extraction model based on the teacher data. The teacher data is a data set including input data and output data. The teacher data relates to, for example, extraction of past deposit and withdrawal patterns of the same user. That is, the input data is past deposit and withdrawal information related to the user of the user terminal 151, and the output data is a past deposit and withdrawal pattern extracted from the past deposit and withdrawal information. Here, the past deposit and withdrawal patterns are, for example, those manually extracted and input from the past deposit and withdrawal information. According to such supervised learning, the extraction model learning unit 123 can create an extraction model capable of automatically extracting a deposit / withdrawal pattern without manual extraction. In addition, teacher data may be related to extraction of deposit and withdrawal patterns of other users. That is, the input data may be deposit / withdrawal information of another user, and the output data may be a deposit / withdrawal pattern of another user extracted from the deposit / withdrawal information of the other user.

  The method of creating the extraction model is not limited to the above. For example, the extraction model may be created by other general machine learning or unsupervised machine learning. The simulation unit 120 may create the deposit and withdrawal pattern without creating the extraction model.

  The teacher data may relate to extraction of deposit and withdrawal patterns of a plurality of users. That is, the input data may be deposit / withdrawal information of a plurality of users, and the output data may be a deposit / withdrawal pattern of a plurality of users extracted from the deposit / withdrawal information of a plurality of users. According to this, the extraction model learning unit 123 can improve the accuracy of the extraction model created by learning.

  The teacher data may use, as input data, the first deposit / withdrawal information related to the user of the user terminal 151, and apply a plurality of extraction models and use the first deposit / withdrawal pattern extracted from the first deposit / withdrawal information as the output data. . For example, the extraction model learning unit 123 uses the second extraction model for extracting the second deposit / withdrawal pattern of the user of the user terminal 152, and generates the second deposit / withdrawal from the first deposit / withdrawal information related to the user of the user terminal 151. Extract the gold pattern. Also, the extraction model learning unit 123 uses the third extraction model for extracting the third deposit / withdrawal model of the user of the user terminal 153 to generate the third deposit / withdrawal from the first deposit / withdrawal information related to the user of the user terminal 151 Extract the gold pattern. Then, the extraction model learning unit 123 integrates the second deposit and withdrawal pattern and the third deposit and withdrawal pattern to create a first deposit and withdrawal pattern. Thereafter, the extraction model learning unit 123 learns the extraction model based on teacher data including a data set in which the first deposit and withdrawal information is input data and the first deposit and withdrawal pattern is output data. According to this, the input of teacher data can be omitted, and the learning of the extraction model in the extraction model learning unit 123 can be automated. Note that the number of deposit and withdrawal patterns integrated to create the first deposit and withdrawal pattern may be three or more. Further, the deposit / withdrawal patterns integrated to create the first deposit / withdrawal pattern may be deposit / withdrawal patterns of a plurality of users each extracted from the deposit / withdrawal information of a plurality of users.

  The extraction model learning unit 123 may correct the extraction model by receiving from the user terminal 151 an instruction such as addition or deletion of a deposit or withdrawal pattern or partial correction of the deposit or withdrawal pattern. According to this, the extraction model learning unit 123 can improve the accuracy of the extraction model.

  The deposit / withdrawal pattern creation unit 125 generates a deposit / withdrawal pattern from the plurality of deposit / withdrawal information based on the extraction model learned by the extraction model learning unit 123. For example, the deposit / withdrawal pattern creation unit 125 extracts all deposit / withdrawal patterns from all the deposit / withdrawal information, and sorts out new deposit / withdrawal patterns not included in the past deposit / withdrawal patterns previously extracted. Then, the past deposit and withdrawal pattern and the new deposit and withdrawal pattern are integrated to update the deposit and withdrawal pattern. As described above, since the extraction model learning unit 123 and the deposit / withdrawal pattern creation unit 125 are provided, the balance management system 100 needs to manually extract and input the deposit / withdrawal pattern every time the deposit / withdrawal pattern is created. There is no That is, the balance management system 100 can quickly create a deposit and withdrawal pattern from the deposit and withdrawal information of many users. The said deposit / withdrawal pattern is information which extracted regularity (a transaction day, the amount of deposit / withdrawal, the amount of change of deposit / withdrawal, etc.) of periodic deposit / withdrawal information. The deposit / withdrawal pattern creation unit 125 may perform addition or deletion of the deposit / withdrawal pattern, partial correction of the deposit / withdrawal pattern, and the like in response to the support from the user terminal 151.

  The deposit / withdrawal pattern creating unit 125 generates a new deposit / withdrawal pattern from the new deposit / withdrawal information except for the past deposit / withdrawal information used once to extract the past deposit / withdrawal pattern in the deposit / withdrawal pattern creating unit 125 previously. May be extracted. At this time, the deposit and withdrawal pattern creating unit 125 integrates the past deposit and withdrawal pattern and the new deposit and withdrawal pattern, and updates the deposit and withdrawal pattern. According to this, the deposit / withdrawal pattern creating unit 125 can reduce the amount of data to be processed to extract the deposit / withdrawal pattern.

  The deposit and withdrawal pattern creation unit 125 may extract all deposit and withdrawal patterns from all deposit and withdrawal information every time the deposit and withdrawal pattern is extracted, and replace the past deposit and withdrawal patterns with all deposit and withdrawal patterns. According to this, the deposit and withdrawal pattern creation unit 125 can suppress duplication and omission of the deposit and withdrawal pattern.

  The deposit / withdrawal schedule creation unit 127 is an information processing system that creates a deposit / withdrawal schedule for each of the first account 161, the second account 162, and the third account 163 based on the deposit / withdrawal pattern. The deposit and withdrawal schedule is a change schedule of account balances arranged in chronological order of deposits and withdrawals expected to be performed in a certain period. Based on the deposit / withdrawal pattern, forecast the estimated date and amount of deposit / withdrawal within the period specifically. The scheduled deposit / withdrawal date considers, for example, irregulars in which financial institutions such as weekends and holidays are closed. In addition, the scheduled amount takes into consideration, for example, temporal fluctuations such as an increase in electricity charges in summer and winter, an increase in credit card payments at the end of the year, and the like.

  The balance prediction unit 129 calculates the predicted balance in each of the first account 161, the second account 162, and the third account 163 based on the balance at the time of creation of the deposit and withdrawal schedule and the deposit and withdrawal schedule. As described above, in order to refer to the deposit and withdrawal schedule created based on the deposit and withdrawal pattern, the balance management system 100 can calculate the predicted balance before the deposit and withdrawal information is determined. The balance prediction unit 129 may obtain the settled deposit and withdrawal information among the estimated deposit and withdrawal information from the customer system, and repredict the balance of each account. The balance management system 100 may periodically carry out such re-prediction multiple times.

  The notification unit 130 is an information processing system that notifies the user terminal 151 of a predicted balance and the like. The notification unit 130 includes a predicted balance notification unit 131, a replenishment plan creation unit 133, a replenishment plan notification unit 135, and a replenishment instruction unit 137.

  The predicted balance notification unit 131 acquires the predicted balance calculated by the balance prediction unit 129, and notifies the user terminal 151 of the predicted balance. The predicted balance notification unit 131 may determine the timing of notification to the user terminal 151. For example, when the predicted balance of the first account 161 runs short, that is, when the predicted balance becomes negative, the predicted balance notification unit 131 notifies the user terminal 151 of the predicted balance. At this time, the predicted balance notification unit 131 notifies of a date on which the predicted balance runs short, details of the transaction, a running amount of money, and the like. Also, for example, the forecasted balance notification unit 131 notifies 10 days before the date when the forecasted balance runs short, and notifies again 5 days before the runout of the forecasted balance, and 1 when the runout of the forecasted balance does not disappear. I will notify again the day before.

  The predicted balance notification unit 131 may notify the user terminal 151 of the predicted balance when the predicted balance of the first account 161 falls below a specific amount (for example, the amount specified by the user). The predicted balance notification unit 131 may periodically notify the user terminal 151 of the predicted balance regardless of the predicted balance. For example, the predicted balance notification unit 131 may notify the user terminal 151 as a table or a graph in which the predicted balances are arranged in time series.

  The replenishment plan creation unit 133 is a replenishment plan for replenishing funds of an account that is expected to require payment due to a lack of balance or the like based on the predicted balances of the first account 161, the second account 162, and the third account 163. Create at least one. The replenishment plan is, for example, a fund transfer plan, a borrowing plan, and the like.

  The replenishment plan creation unit 133 compares the predicted balances of the first account 161, the second account 162, and the third account 163 to determine whether it is possible to move funds, and then the replenishment plan. Create For example, when it is determined that the forecasted balance of the first account 161 is insufficient and the second account 162 and the third account 163 have the forecasted balance capable of replenishing the shortage of the first account 161, the replenishment plan creation unit 133 , A funds transfer plan for transferring funds from at least one of the second account 162 and the third account 163 to the first account 161. In contrast, when it is determined that the predicted balance of the first account 161 is insufficient and the predicted balances of the second account 162 and the third account 163 can not replenish the shortfall of the first account 161, the borrowing of the first account 161 is taken. Create a borrowing plan to be used for replenishment.

  The replenishment plan creation unit 133 creates at least one replenishment plan when the predicted balance of the first account 161 runs short, ie, when the predicted balance becomes negative. The replenishment plan creation unit 133 may create at least one replenishment plan when the predicted balance is predicted to fall below a specific amount. If there is a shortage of forecasted balances, a replenishment plan can be proposed before the actual shortage of balances and withdrawals and withdrawals occur. By creating a replenishment plan when the forecasted balance is less than a specific amount, the balance can be maintained at a desired level by the user.

  The fund transfer plan may be a remittance (transfer or transfer) plan instructing remittance to each account via the Internet. Further, the money transfer plan may be a deposit / withdrawal plan combining a withdrawal for drawing cash by the user's hand and a deposit for depositing cash by the user's hand. In the case of a remittance plan, the user can execute the replenishment plan from the user terminal 151 through the balance management system 100, so that it is possible to save the trouble of the user. In the case of the deposit and withdrawal plan, the user can execute the replenishment plan by his own hand, so it is possible to suppress the occurrence of an economic burden due to a fee for remittance.

  Next, the money transfer plan created by the replenishment plan creation unit 133 will be described with some examples. The remittance plan is described as a fund transfer plan in each example. However, the money transfer plan in each example may be a deposit and withdrawal plan.

(First fund transfer plan)
The money transfer plan may equally transfer money from the second account 162 and the third account 163 to the first account 161. As a specific example, when it is predicted that the forecasted balance of the first account 161 is insufficient for 100,000 yen, the replenishment plan creation unit 133 sets 50 to the first account 161 from each of the second account 162 and the third account 163. Create a fund transfer plan that promotes fund transfer of ¥ 1,000.

(Second fund transfer plan)
The fund transfer plan determines the amount of funds to be transferred from each of the second account 162 and the third account 163 in accordance with the size of the predicted balance of each of the second account 162 and the third account 163 with respect to the first account 161. You may

  In an example of a fund transfer plan created according to the size of the forecasted balance, when the forecasted balance of the second account 162 is larger than the forecasted balance of the third account 163, priority is given to the second account 162 to the first account 161. Move funds in a timely manner. As a specific example, it is assumed that the predicted balance of the first account 161 is about 100,000 yen short and the predicted balance of the second account 162 is predicted to be larger than the predicted balance of the third account 163. At this time, even if there is a surplus in the predicted balance of the third account 163, the replenishment plan creation unit 133 creates a remittance plan prompting a remittance of about 100,000 yen from the second account 162 to the first account 161. . However, if the predicted balance of the second account 162 is 80,000 yen and it is predicted that the shortage of the first account 161 will not be enough to be replenished, the replenishment plan creation unit 133 A remittance plan is created to urge the remittance of approximately 80,000 yen to the account 161 and urge the remittance of approximately 20,000 yen from the third account 163 to the first account 161.

(Third Fund Transfer Plan)
In another example of the fund transfer plan created according to the size of the forecasted balance, the funds amount proportional to the forecasted balances of the second account 162 and the third account 163 is set to the second account 162 and the third account 163 respectively. To the first account 161. As a specific example, the forecast balance of the first account 161 is about 100,000 yen short, the forecast balance of the second account 162 is about 200,000 yen, and the forecast balance of the third account 163 is about 300,000 yen. Suppose that it is predicted. At this time, since the ratio of the predicted balances of the second account 162 and the third account 163 is 2: 3, the replenishment plan creation unit 133 urges a remittance of about 40,000 yen from the second account 162 to the first account 161. And a remittance plan for promoting a remittance of about 60,000 yen from the third account 163 to the first account 161 is created.

(Fourth fund transfer plan)
The fund transfer plan may preferentially transfer funds from accounts of the second account 162 and the third account 163 that are frequently transferred to another account (transfer or transfer). As a specific example, when it is predicted that the forecasted balance of the first account 161 runs short, the replenishment plan creation unit 133 may count the number of remittances from each of the second account 162 and the third account 163 to another account in the last 12 months. Count. Thus, it is assumed that the remittance frequency from the second account 162 is analyzed to be higher than the remittance frequency from the third account 163. At this time, the replenishment plan creation unit 133 creates a remittance plan that prompts remittance from the second account 162 to the first account 161. When it is predicted that the forecasted balance of the second account 162 is insufficient for replenishing the shortfall of the first account 161, the replenishment plan creating unit 133 receives not only the second account 162 but also the third account 163. Create a remittance plan that also encourages remittances. In addition, the period which counts the number of remittances is not limited to 12 months, It can set suitably.

  The replenishment plan creation unit 133 may count only the number of remittances with the first account 161 as a remittance destination from each of the second account 162 and the third account 163 in the analysis of the remittance frequency. That is, based on the comparison result of the remittance frequency from the second account 162 to the first account 161 and the remittance frequency from the third account 163 to the first account 161, the replenishment plan creating unit 133 You may create a remittance plan. According to this, the replenishment plan creation unit 133 analyzes the remittance frequency without limiting the remittance destinations from the second account 162 and the third account 163 to create a fund transfer plan, and the user's behavior pattern is further enhanced. It is possible to create a fund transfer plan adapted to

  In the analysis of the remittance frequency, the replenishment plan creation unit 133 sets the execution date of periodic withdrawals that are predicted to cause the shortage of balance as the reference date, and counts the number of remittances within a certain period from the reference date. Good. For example, when it is predicted that the forecast balance of the first account 161 will run short due to loan repayment, the replenishment plan creation unit 133 determines the second account 162 and the third account 163 from the second account 162 and the third account 163 on the 5 days before the monthly repayment of the loan. The number of remittances to one account 161 is counted. Thus, if it is analyzed that the remittance frequency from the second account 162 is higher than the remittance frequency from the third account 163, the replenishment plan creation unit 133 transfers money from the second account 162 to the first account 161. Create a prompting remittance plan. At this time, the replenishment plan creation unit 133 may count the number of remittances in five days after the monthly repayment date of the loan, and may count the number of remittances in five days before and after the monthly repayment date of the loan. . In addition, the period which counts the frequency | count of remittance is not limited to 5 days, It can set suitably.

(Fifth fund transfer plan)
The fund transfer plan transfers funds preferentially from accounts with a high withdrawal frequency within a fixed period of time from the reference date, of the second account 162 and the third account 163, with the deposit date to the first account 161 as the reference date. May be As a specific example, when it is predicted that the predicted balance of the first account 161 is insufficient, the replenishment plan creation unit 133 determines that the second account 162 for five days prior to the date of deposit to the first account 161 in the last 12 months. And the number of withdrawals from the third account 163 is counted. When the deposit into the first account 161 is performed multiple times, the number of withdrawals from the second account 162 and the third account 163 in the five days preceding each of the plurality of deposit dates is counted. At this time, if the withdrawal frequency from the second account 162 is higher than the withdrawal frequency from the third account 163, the replenishment plan creation unit 133 generates a remittance plan that prompts remittance from the second account 162 to the first account 161. You may create it.

  When the past withdrawal date from the second account 162 and the third account 163 is close to the past deposit date to the first account 161, some or all of the past withdrawals are used for past deposit It is guessed. In this manner, a remittance plan may be created based on the user's actions that can be associated with past deposits into the first account 161.

  As described above, the replenishment plan creation unit 133 uses the remittance (transfer or transfer) history or deposit / withdrawal (deposit and withdrawal) history of each of the first account 161, the second account 162, and the third account 163 to A behavior pattern may be learned, and a fund transfer plan, ie, a remittance plan or a deposit / withdrawal plan, may be created to adapt to the behavior pattern.

(Sixth fund transfer plan)
The replenishment plan creation unit 133 may create a money transfer plan for moving funds out of the selected account based on the priority registered in advance by the user. For example, by the user in advance, when the balance management system 100 runs out of balances in any of the accounts, the priority as a remittance source for replenishing the balances of other accounts by remittance is the first account 161 first. , And the second account 162 is registered as second place and the third account as third place. At this time, if it is predicted that the predicted balance of the first account 161 is insufficient, the replenishment plan creation unit 133 creates a remittance plan that urges remittance from the second account 162 to the first account 161. In addition, the replenishment plan creation unit 133 may create a remittance plan for prompting remittance from the second account 162 and the third account 163 to the first account 161. The sending amount from the second account 162 and the sending amount from the third account are, for example, a ratio registered in advance by the user.

  In the balance management system 100, different priorities may be registered as the remittance source account for each remittance destination account. For example, in the case where the first account 161 is the remittance destination, the priority as the remittance source is to register the second account 162 as the first place and the third account 163 as the second place while remittance the second account 162. In the case of prior consideration, the priority as the remittance source may be registered such that the third account 163 is the first place and the first account 161 is the second place.

(Borrowing plan)
The borrowing plan is a plan for borrowing money from a lending institution and depositing the borrowing into the first account 161. For example, it is assumed that the replenishment plan creation unit 133 determines that the predicted balances of the second account 162 and the third account 163 are insufficient for replenishing the shortfall of the predicted balance of the first account 161. At this time, the replenishment plan creation unit 133 borrows funds from the lending institution (the business partner system 180) owned by the user and has made a contract, and urges to deposit the borrowings from the business partner system 180 to the first account 161. Create a borrowing plan.

  The replenishment plan creation unit 133 creates a replenishment plan suitable for the user from among the above-described money transfer plan, borrowing plan, and the like, based on the past behavior of the user. The replenishment plan creation unit 133 may create a plurality of replenishment plans. At this time, the replenishment plan creation unit 133 may attach a recommendation degree to each of the plurality of replenishment plans. The degree of recommendation may be assigned based on the past behavior of the user. For example, the replenishment plan creating unit 133 compares a plurality of created replenishment plans with each other, gives a high recommendation degree to a replenishment plan close to the user's past behavior, and makes the replenishment plan deviate from the user's past behavior. Give a low degree of recommendation. Also, the recommendation degree may be attached based on the economical burden required of the user. For example, the replenishment plan creation unit 133 compares a plurality of prepared replenishment plans, gives high recommendation to a replenishment plan with low economic burden such as fee, interest rate, etc. A lower recommendation may be attached.

  The replenishment plan notification unit 135 notifies the user terminal 151 of at least one replenishment plan created by the replenishment plan creation unit 133. When the replenishment plan notification unit 135 notifies the user terminal 151 of a plurality of replenishment plans, the replenishment plan notification unit 135 may notify the recommendation levels of the plurality of replenishment plans as well as the plurality of replenishment plans. As an example, the replenishment plan notification unit 135 recommends a replenishment plan with a high degree of recommendation, and also notifies a replenishment plan with a low degree of recommendation together as another option.

  The replenishment instructing unit 137 deposits funds to an account determined to require replenishment of the balance based on the replenishment plan. For example, when it is predicted that the predicted balance of the first account 161 is insufficient, the replenishment instructing unit 137 instructs the deposit to the first account 161 based on any one of the above-described fund transfer plan and the borrowing plan. , The first account 161 balance. The replenishment instructing unit 137 accesses at least one of the second account 162 and the third account 163, and instructs remittance using an API or the like.

  In the case where there is one replenishment plan, the replenishment instructing unit 137 may instruct payment to the first account 161 based on an instruction from the user terminal 151. In the same case, the replenishment instructing unit 137 may instruct payment to the first account 161 based on the replenishment plan after a predetermined period of time has elapsed since the notification of the replenishment plan or the predicted balance to the user terminal 151. When there are a plurality of replenishment plans, the replenishment instructing unit 137 may instruct payment to the first account 161 based on the replenishment plan selected by the user terminal 151. In the same case, the replenishment instructing unit 137 instructs payment to the first account 161 based on the highest priority replenishment plan after a predetermined period has elapsed since notification of a plurality of replenishment plans or predicted balances to the user terminal 151. May be Thus, the replenishment instructing unit 137 can instruct the replenishment plan based on a simple operation of the user terminal 151, for example, one tap, one swipe, or the like. Alternatively, the replenishment instructing unit 137 can instruct execution of the replenishment plan based on biometric authentication such as fingerprint authentication, iris authentication, face authentication, and the like. Alternatively, the replenishment instructing unit 137 can automatically instruct the execution of the replenishment plan without receiving the operation of the user terminal 151.

  As described above, the balance management system 100 acquires a plurality of deposit and withdrawal information from the plurality of accounts in the aggregation unit 110, and determines whether or not each of the plurality of deposit and withdrawal information is periodic deposits and withdrawals in the simulation unit 120. The simulation unit 120 calculates the predicted balance of each account based on the deposit and withdrawal pattern generated from the periodic deposit and withdrawal information. As a result, the balance management system 100 can predict the transition of the balance of each account, and can efficiently manage the balance of each account. That is, the balance management system 100 can suppress the failure of a transaction, the accumulation of surplus funds, and the like, and can improve the security of the transaction.

  By providing the predicted balance notification unit 131, the balance management system 100 can prompt the user to adjust the balance of each account based on the predicted balance before the actual deposit or withdrawal is performed.

  By providing the replenishment plan creation unit 133 and the replenishment plan notification unit 135, the balance management system 100 can notify a user of a preferable replenishment plan and assist the balance adjustment of each account.

  By providing the replenishment instructing unit 137, the balance management system 100 can substitute the instruction for executing the replenishment plan and reduce the effort of the user.

  The balance management system 100 may notify the user terminal 151 of a plan for requesting change of withdrawal date and withdrawal amount by debit or account transfer of each account instead of the replenishment plan. For example, it is assumed that due to withdrawal by the card company 171, the predicted balance of the first account 161 is predicted to be short. The balance management system 100 may create a plan for notifying the card company 171 of an application for postponement of withdrawal date, an application for change to single payment into installments, etc., and may notify the user terminal 151 of the plan.

  Next, an example of a method of processing information in the balance management system 100 will be described with reference to FIGS. 3 to 9. FIG. 3 is a flowchart illustrating an example of processing in the aggregation unit and the simulation unit according to the first embodiment. FIG. 4 is a flowchart illustrating an example of processing in the simulation unit and the notification unit according to the first embodiment. FIG. 5 is a view showing an example of the deposit and withdrawal pattern. FIG. 6 is a diagram showing an example of the deposit and withdrawal schedule. FIG. 7 is a diagram showing an example of the predicted balance. FIG. 8 is a diagram showing an example of the replenishment plan. FIG. 9 is a diagram showing a display example on the user terminal.

  First, the account information registration unit 111 registers the account information acquired from the user terminal 151 (S111). Next, the transaction information acquisition unit 115 acquires a plurality of pieces of transaction information based on the account information registered by the account information registration unit 111 (S115). Next, the deposit and withdrawal information acquisition unit 121 acquires deposit and withdrawal information from among the plurality of pieces of transaction information acquired by the transaction information acquisition unit 115 (S121). The extraction model learning unit 123 learns the extraction model based on the teacher data (S123). The deposit / withdrawal pattern creation unit 125 creates a deposit / withdrawal pattern from the deposit / withdrawal information acquired by the deposit / withdrawal information acquisition unit 121 based on the extraction model learned by the extraction model learning unit 123 (S125).

  As shown in FIG. 5, for example, the deposit / withdrawal pattern is a name of a financial institution in which the account is opened, a store (branch name or head office name), as information for specifying an account in which regular deposit / withdrawal is performed. Includes information such as account number, etc. Further, the deposit / withdrawal pattern includes information such as transaction contents of deposit / withdrawal, types of deposit / withdrawal, transaction date, irregular on trade date, amount of deposit / withdrawal, amount of change of deposit / withdrawal amount, and the like. The calculation method of the amount of money in and out is not particularly limited, and is, for example, an average value or a median value. As an example of the deposit / withdrawal pattern, in the account of the account number 2222222 opened at the B branch of the BBB bank, a payment of 20,000 yen is made as a general management fee each month as a management expense. This withdrawal is performed on the next business day if the beginning of the month is a Saturdays, Sundays and holidays, and there is no change in the amount of withdrawal.

  In addition, from the account with account number 2222222, with a loan of 50,000 yen as a loan on the 5th every month (the next business day for Saturdays and Sundays and public holidays), every month 10th (the next business day for Saturdays, Sundays and public holidays) Withdrawal of 12,000 ± 3,000 yen as electricity fee, withdrawal of 20,000 yen as life insurance fee every month on the 15th (the next business day in case of Saturdays and holidays), 25th every month (in the case of Saturdays, Sundays and holidays) On the next business day, withdrawal of 20,000 yen as a loan and withdrawal of 25,000 yen as a childcare fee at the end of every month (on the next business day in the case of Saturdays and Sundays and public holidays) are recorded as deposit and withdrawal patterns. In addition, with the account number 1111111 opened at the A branch of AAA Bank, withdrawal of 50,000 ± 30,000 yen as a credit card on the 10th of every month (the next business day for Saturdays, Sundays and public holidays) and 25th every month A deposit of 350,000 ± 20,000 yen has been recorded as a deposit / withdrawal pattern as a salary on (Saturdays, Sundays, and public holidays the previous business day).

  Thus, based on the deposit and withdrawal pattern created by the deposit and withdrawal pattern creation unit 125, the deposit and withdrawal schedule creation unit 127 creates a deposit and withdrawal schedule (S127). For example, as shown in FIG. 6, the deposit / withdrawal schedule creating unit 127 creates a deposit / withdrawal schedule of a period of 2017/09/20 to 2017/10/20. The deposit and withdrawal schedule includes a specific estimated date of transaction and an estimated amount. The deposit / withdrawal schedule creation unit 127 calculates a scheduled transaction date on which it is predicted that each deposit / withdrawal will be actually performed within this period, based on the principle transaction date and the irregular of the deposit / withdrawal pattern. For example, the administrative expenses for withdrawal scheduled from the account of the account number 2222222 at the beginning of the month are 2017/10/01 is a Sunday, so 2017/10/02 of the next day is the scheduled transaction date. Further, the deposit / withdrawal schedule creation unit 127 predicts the planned amount of deposit / withdrawal within this period based on the amount of the deposit / withdrawal pattern and the change amount. For example, the electricity bill due to be withdrawn from the account with the account number 2222222 on 2017/10/10 is predicted to be 15,000 yen in consideration of the seasonal fluctuation amount. At this time, the deposit / withdrawal schedule creation unit 127 predicts the withdrawal amount in consideration of the fluctuation of the withdrawal amount of the user during the same period in the past, the fluctuation of withdrawal amounts of other users, and the like.

  Next, the balance prediction unit 129 predicts the balance of each account based on the deposit and withdrawal schedule created by the deposit and withdrawal schedule creation unit 127 (S129). Further, the balance prediction unit 129 acquires updated transaction information (for example, confirmation information of withdrawal amount) from the correspondent system, and predicts the balance of each account again (S129). The predicted balance notification unit 131 notifies the user terminal 151 of the predicted balance predicted by the balance prediction unit 129 (S131).

  As shown in FIG. 7, the predicted balance is calculated based on the actual balance and the deposit / withdrawal schedule during the period when the deposit / withdrawal schedule is created. For example, the account with the account number 1111111 has a balance of 650,000 yen at the start of prediction, and has an allowance of 950,000 yen even in consideration of a payment receipt schedule of a salary and a withdrawal schedule of a credit card. The account with the account number 2222222 has a balance of 60,000 yen at the start of the forecast, and the withdrawal of the management cost of 2017/10/5 will result in a shortage of 5,000 yen, and finally, it will be October 16, 2017. The withdrawal of life insurance premiums is expected to result in a shortage of ¥ 90,000.

  Thus, based on the predicted balance predicted by the balance prediction unit 129, the replenishment plan creation unit 133 creates a replenishment plan (S133). As shown in FIG. 8, the replenishment plan urges remittance to 2017/10/4, which is the day before the withdrawal of the 2017/10/5 management expenses, when the account with the account number 2222222 is expected to run out of balance. The replenishment plan is designed to remit 100,000 yen, which can compensate for the final shortage of the account with the account number 2222222, from the account with the account number 1111111. In order to make room for the predicted balance of the account with the account number 2222222, the remittance amount of the replenishment plan may be increased to 100,000 yen or more. Although the replenishment plan shown in FIG. 8 is designed to make up for the final shortage of the account number 2222222 in a batch, each time the balance of the account number 2222222 runs out, only the deficit is calculated. It may be designed to make up for it. For example, the replenishment plan creation unit 133 compensates 5,000 yen before withdrawal of the management cost in 2017/10/5, and compensates 65,000 yen before withdrawal of the loan and electricity rate in 2017/10/10. Before the withdrawal of life insurance premiums on October 16, 2017, a replenishment plan to supplement 20,000 yen may be formulated.

  Next, the replenishment plan notification unit 135 notifies the user terminal 151 of the replenishment plan created by the replenishment plan creation unit 133 (S135). Next, the replenishment instructing unit 137 instructs each account to execute the replenishment plan based on the replenishment plan selected by the user terminal 151 (S137).

  An example of notification to the user terminal 151 in the flow and an example of display by the notification are summarized in FIG. In the example illustrated in FIG. 9, the balance management system 100 first causes the user terminal 151 to display the advance notification. At this time, the advance notice is limited to the notice of the predicted balance, and the replenishment plan is not presented, since there is a time allowance until the day when the balance shortage is predicted to occur. The balance management system 100 causes the user terminal 151 to display the remittance proposal at the stage when the time margin is lost until the day when it is predicted that the balance shortage will occur. At this time, the balance management system 100 causes the user terminal 151 to display the details of the remittance instruction. A user who agrees to the remittance amount and the fee operates the user terminal 151 to transmit a remittance instruction to the balance management system 100. As described above, the balance management system 100 suppresses the time and economic burden on the user while changing the content of the notification according to the time margin until the day when the balance shortage is predicted to occur, while the balance shortage is suppressed. It is possible to suppress the occurrence of transaction failure due to

Second Embodiment
Next, an example of a method of processing information in the balance management system according to the second embodiment will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of processing in the simulation unit and the notification unit according to the second embodiment.

  The balance management system according to the second embodiment predicts the balance (S229), notifies the predicted balance (S231), and prepares a replenishment plan (S233). Next, the balance management system according to the second embodiment notifies a replenishment plan (S235), and instructs each account to execute the replenishment plan based on the notified replenishment plan (S237). In this way, the balance management system may automatically execute the replenishment plan without waiting for the selection by the user.

Third Embodiment
Next, an example of a method of processing information in the balance management system according to the third embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating an example of processing in the simulation unit and the notification unit according to the third embodiment.

  The balance management system according to the third embodiment is different from the balance management system 100 according to the first embodiment in that the balance management system further includes a deposit and withdrawal schedule notification unit that notifies the user terminal of the deposit and withdrawal schedule. A deposit and withdrawal schedule is created (S327), and the deposit and withdrawal schedule is notified (S330). Next, the balance management system according to the third embodiment predicts the balance based on the deposit and withdrawal schedule (S329), and notifies the predicted balance (S335).

Fourth Embodiment
Next, the configuration of the simulation unit 420 in the balance management system according to the fourth embodiment will be described with reference to FIG. FIG. 12 is a diagram schematically showing a configuration of a simulation unit in the balance management system according to the fourth embodiment.

  The balance management system according to the fourth embodiment differs from the balance management system 100 according to the first embodiment in that the extraction model learning unit is omitted and the deposit / withdrawal information classification unit 424 is provided. The simulation unit 420 includes a deposit and withdrawal information acquisition unit 421, a deposit and withdrawal information classification unit 424, a deposit and withdrawal pattern creation unit 425, a deposit and withdrawal schedule creation unit 427, and a balance prediction unit 429.

  The deposit / withdrawal information classification unit 424 classifies the plurality of deposit / withdrawal information into periodic deposit / withdrawal information and irregular deposit / withdrawal information based on the classification logic. This classification logic is, for example, predetermined. However, the classification logic may be created in the deposit / withdrawal information classification unit 424 by machine learning or the like.

  The classification logic, for example, text-analyzes transaction content, and when the same or similar transaction content appears a plurality of times, classifies deposit / withdrawal information regarding the transaction content into periodic deposit / withdrawal information. The classification logic includes, for example, logic for comparing a plurality of transaction contents, and determining a plurality of transaction contents having a fluctuation in notation not more than a predetermined value as similar transaction contents. The classification logic includes logic for determining a plurality of transaction contents having a specific indication fluctuation given in advance (for example, a portion corresponding to a billing month such as an electricity bill for January, etc.) as similar transaction contents. It may be Also, the classification logic may classify periodic deposit / withdrawal information based on regularity of transaction day, transaction frequency, transaction amount, and the like. For example, if the transaction content includes deposit and withdrawal information including the word "loan", and the amount of payment and withdrawal each month is constant, the classification logic determines whether the payment and withdrawal information is equivalent to regular payment and withdrawal Classified into Similarly, if the monthly withdrawal amount is gradually decreasing, the classification logic categorizes the deposit / withdrawal information into periodic deposit / withdrawal information equivalent to equal payment of principal.

  If the classification logic is created by machine learning, then the credibility of the classification of deposit and withdrawal information using the classification logic may be evaluated based on the teacher data. For example, the regular receipt / withdrawal information classified by using the classification logic is compared with the periodic deposit / withdrawal information correctly classified by hand to obtain the correct answer rate of the former periodical deposit / withdrawal information. By modifying the classification logic so as to improve the correct answer rate, the deposit and withdrawal information classification unit 424 can improve the classification accuracy.

  The deposit / withdrawal pattern creation unit 425 extracts regularity such as transaction content and fluctuation in representation, transaction amount, fluctuation amount, exception of transaction date, exception of transaction date, etc. Create a gold pattern. The deposit / withdrawal pattern creation unit 425 may extract the tendency of the deposit / withdrawal amount from the periodic deposit / withdrawal information with reference to the classification logic. For example, it is assumed that regular deposit / withdrawal information including the word “loan” in the transaction content is classified into equal repayment by the classification logic. At this time, based on the classification logic, the deposit / withdrawal pattern creation unit 425 creates a deposit / withdrawal pattern in which the monthly withdrawal amount is constant, from the periodic deposit / withdrawal information. Similarly, it is assumed that regular deposit / withdrawal information is classified as equal repayment of principal by classification logic. At this time, based on the classification logic, the deposit / withdrawal pattern creating unit 425 creates a deposit / withdrawal pattern in which the monthly withdrawal amount gradually decreases from the periodic deposit / withdrawal information. The monthly withdrawal amount is calculated based on past withdrawal amounts.

  The deposit and withdrawal pattern may be corrected by an external operation. Also, the classification logic may be modified by an external operation, and may be updated by the deposit / withdrawal information classification unit 424 based on the modified deposit / withdrawal pattern.

  The deposit and withdrawal schedule creation unit 427 creates a deposit and withdrawal schedule based on the deposit and withdrawal pattern created by the deposit and withdrawal pattern creation unit 425. The balance prediction unit 429 predicts the balance based on the deposit and withdrawal schedule created by the deposit and withdrawal schedule creation unit 427.

  The classification logic refers to, for example, a library of given deposit and withdrawal patterns, and based on the similarity between the given deposit and withdrawal information and the given deposit and withdrawal pattern, the given deposit and withdrawal information is periodically calculated. It may be classified whether or not it is deposit and withdrawal information. For example, deposit and withdrawal patterns of a plurality of users are stored as a library. Then, it is assumed that the transaction information of a certain deposit and withdrawal information matches a part of the text (for example, the bank name, insurance company name, loan name, etc.) included in the transaction content of the deposit and withdrawal pattern stored in the library. Do. At this time, the classification logic classifies the certain deposit and withdrawal information into periodic deposit and withdrawal information.

  Note that the deposit / withdrawal information classification unit 424 may acquire classified periodic deposit / withdrawal information instead of performing periodic deposit / withdrawal information classification. Specifically, the deposit and withdrawal information classification unit 424 outputs the plurality of deposit and withdrawal information acquired by the deposit and withdrawal information acquisition unit to the outside, and the periodic deposit and withdrawal information classified based on the output plurality of deposit and withdrawal information May be entered. At this time, the regular deposit / withdrawal information input to the deposit / withdrawal information classification unit 424 is manually classified based on, for example, empirical rules, intuition, regularity, and the like.

  As described above, according to one aspect of the present invention, the deposit / withdrawal information acquiring unit 121 that acquires deposit / withdrawal information about the first account 161 from the supplier system 160 based on the registered user information, and the first account 161 Of the first account 161 from the deposit and withdrawal information of the first account 161, and the balance forecasting part 129 of calculating the predicted balance of the first account 161 based on the deposit and withdrawal pattern of the first account 161. And a balance management system 100 is provided.

  According to the above aspect, the balance management system can hold an account with a balance appropriate for future deposits and withdrawals. Therefore, the balance management system can suppress the failure of a transaction, the accumulation of surplus funds, and the like, and can improve the security of the transaction.

  The balance management system 100 further includes an extraction model learning unit 123 that learns an extraction model for extracting the deposit and withdrawal pattern of the first account 161 from the deposit and withdrawal information of the first account 161, and the deposit and withdrawal pattern creating unit 125 extracts the extraction model Based on the above, the deposit and withdrawal pattern of the first account 161 may be created. According to this, the balance management system does not have to manually extract and input the deposit and withdrawal pattern each time the deposit and withdrawal pattern is created. That is, the balance management system can quickly create a deposit and withdrawal pattern from the deposit and withdrawal information of a large number of users.

  The extraction model learning unit 123 may learn an extraction model by machine learning, using a data set including input data and output data as teacher data. According to this, the extraction model learning unit can create an extraction model capable of automatically extracting the deposit and withdrawal pattern without manually extracting the deposit and withdrawal pattern.

  The input data may include past deposit and withdrawal information associated with the user information, and the output data may include a past deposit and withdrawal pattern extracted from the past deposit and withdrawal information. According to this, the extraction model learning unit can create an extraction model that is sufficient for extracting the deposit / withdrawal pattern from the deposit / withdrawal information of the specific user.

  The input data may include deposit and withdrawal information of a plurality of users, and the output data may include deposit and withdrawal patterns of a plurality of users extracted from the deposit and withdrawal information of the plurality of users. According to this, the extraction model learning unit can improve the accuracy of the extraction model created by learning.

  The balance management system 100 creates a replenishment plan creating unit 133 that creates at least one replenishment plan for replenishing the funds of the first account 161 based on the predicted balance of the first account 161, and the at least one replenishment plan to the user terminal 151. And a supplement plan notification unit 135 for notifying the user. According to this, the balance management system can prompt the user to adjust the balance of each account based on the predicted balance before the actual deposit or withdrawal is performed.

  The replenishment plan creation unit 133 may create at least one replenishment plan when the predicted balance of the first account 161 runs short. According to this, the balance management system 100 can propose a replenishment plan before the deposit and withdrawal due to the actual shortage of the balance.

  The replenishment plan creation unit 133 may create at least one replenishment plan when the predicted balance of the first account 161 falls below a specific amount. According to this, the balance management system 100 can maintain the balance at a level desired by the user.

  The deposit and withdrawal information acquisition unit 121 acquires deposit and withdrawal information on the second account 162 from the supplier system 160, and transfers funds from the second account 162 to the first account 161 in at least one replacement plan. May be included. According to this, the balance management system can instruct remittance between accounts via the Internet.

  The deposit / withdrawal pattern creation unit 125 creates the deposit / withdrawal pattern of the second account 162 from the deposit / withdrawal information of the second account 162, and the balance prediction unit 129 generates the second account 162 based on the deposit / withdrawal pattern of the second account 162. Calculation of the estimated balance of the balance, and the replenishment plan creation unit 133 may compare the estimated balances of the first and second accounts 161 and 162 to move funds from the second account 162 to the first account 161 May be determined. According to this, the balance management system can replenish the balance of the first account while maintaining the balance of the second account at a required level.

  The deposit / withdrawal pattern creating unit 125 creates a deposit / withdrawal pattern of the plurality of accounts 162, 163 from the deposit / withdrawal information of the plurality of accounts 162, 163 each corresponding to the second account 162. Based on the deposit and withdrawal pattern of the accounts 162 and 163, the predicted balances of the plurality of accounts 162 and 163 are calculated, and the replenishment plan creation unit 133 transfers funds from at least one of the plurality of accounts 162 and 163 to the first account 161. You may create a fund transfer plan to move. According to this, the balance management system can maintain the balances of multiple accounts at a necessary level. The balance management system can also adjust the balance balance among multiple accounts.

  A fund transfer plan may transfer funds from multiple accounts 162, 163 evenly.

  The money transfer plan may determine the amount of money to be transferred from each of the plurality of accounts 162, 163 in accordance with the size of the predicted balance of each of the plurality of accounts 162, 163.

  The fund transfer plan may transfer funds preferentially from the account with the largest predicted balance among the plurality of accounts 162, 163. According to this, the balance management system can increase the remaining capacity of each account and reduce the economic burden such as the fee for remittance to the first account.

  The fund transfer plan may move funds proportional to the predicted balances of the plurality of accounts 162, 163 from each of the plurality of accounts 162, 163. According to this, the balance management system can maintain the balance balance among multiple accounts.

  The funds transfer plan may preferentially transfer funds from accounts with a high frequency of remittance to another account among the plurality of accounts 162, 163. According to this, the balance management system can reflect the user's behavior pattern in the replenishment plan.

  The remittance frequency may be the frequency of remittance with the first account 161 as a remittance destination. According to this, the balance management system can more accurately reflect the user's behavior pattern in the replenishment plan.

  The fund transfer plan may transfer funds preferentially from accounts with a high frequency of withdrawal within a certain period from the reference date, with the deposit date to the first account 161 as the reference date among the plurality of accounts 162, 163 . According to this, the balance management system can reflect the user's behavior pattern in the replenishment plan.

  The fund transfer plan may move funds out of the selected account based on the registered priorities. According to this, the balance management system can reflect the user's intention in the replenishment plan.

  The at least one replenishment plan may include a borrowing plan for borrowing money from the lending institution (the business partner system 180) and depositing the money into the first account 161. According to this, even if there are no funds remaining to replenish the shortage of the predicted balance of the first account in a plurality of accounts, the balance of the first account is replenished, and stagnation of deposit and withdrawal is suppressed. Can improve the security of the transaction.

  The balance management system 100 may further include a replenishment instructing unit 137 for depositing funds to the first account 161 based on one of the at least one replenishment plans. According to this, the balance management system can substitute instructions for executing the replenishment plan and reduce the effort of the user.

  Balance management system 100 further includes replenishment plan notification unit 135 for notifying the user terminal of at least one replenishment plan, and replenishment instruction unit 137 deposits funds to first account 161 based on an instruction from user terminal 151. May be According to this, the balance management system can instruct execution of the replenishment plan based on the user's selection.

  After calculating the predicted balance of the first account 161, the balance prediction unit 129 may obtain the newly established updated transaction information from the customer system, and may correct the predicted balance of the first account 161. According to this, the balance prediction unit 129 can correct the predicted balance to improve the accuracy of the predicted balance.

  The balance management system 100 may further include a predicted balance notification unit 131 that notifies the user terminal 151 of the predicted balance of the first account 161. According to this, the balance management system can notify the user of the predicted balance of the first account and urge adjustment of the balance. For example, if the balance management system includes both a predicted balance notification unit and a replenishment plan notification unit, the balance management system provides the user with an opportunity to manually replenish the balance of the first account by notifying the predicted balance in advance. It is possible to create a replenishment plan on behalf of the user by notifying the replenishment plan, and to easily replenish the balance of the first account.

  The balance management system 100 creates a deposit / withdrawal schedule based on the deposit / withdrawal pattern, and provides a deposit / withdrawal schedule creating unit 127 provided to the balance predicting unit 129, and a deposit / withdrawal schedule notification unit notifying the user terminal 151 of the deposit / withdrawal schedule. May further be provided. According to this, the balance management system can support the user's cash management.

  The balance management system 100 further includes a deposit / withdrawal information classification unit 424 that classifies the deposit / withdrawal information on a regular basis from the deposit / withdrawal information of the first account 161, and the deposit / withdrawal pattern creation unit 425 Based on it, the deposit and withdrawal pattern of the first account 161 may be created. According to this, the balance management system does not have to manually extract and input the deposit and withdrawal pattern each time the deposit and withdrawal pattern is created. That is, the balance management system can quickly create a deposit and withdrawal pattern from the deposit and withdrawal information of a large number of users.

  As described above, according to one aspect of the present invention, it is possible to provide a balance management system capable of improving the security of transactions.

  The embodiments described above are for the purpose of facilitating the understanding of the present invention, and are not for the purpose of limiting and interpreting the present invention. The present invention can be modified / improved without departing from the gist thereof, and the present invention also includes the equivalents thereof. That is, those in which persons skilled in the art appropriately modify the design of each embodiment are also included in the scope of the present invention as long as they have the features of the present invention. For example, each element included in each embodiment and its arrangement, material, conditions, shape, size, and the like are not limited to those illustrated, and can be appropriately changed. Further, the elements included in each embodiment can be combined as much as technically possible, and combinations of these are included in the scope of the present invention as long as they include the features of the present invention.

100 ... Balance management system aggregation unit ... 110
111 ... account information registration unit 113 ... account information storage unit 115 ... transaction information acquisition unit 117 ... transaction information storage unit 120 ... simulation unit 121 ... deposit and withdrawal information acquisition unit 123 ... extraction model learning unit 125 ... deposit and withdrawal pattern creation unit 127 ... Deposit / withdrawal schedule creation unit 129 ... balance prediction unit 130 ... notification unit 131 ... predicted balance notification unit 133 ... replenishment plan creation unit 135 ... replenishment plan notification unit 137 ... replenishment instruction unit

Claims (26)

A deposit / withdrawal information acquisition unit that acquires deposit / withdrawal information about the first account from the supplier system based on the registered user information;
A deposit / withdrawal pattern creation unit that creates a deposit / withdrawal pattern of the first account from the deposit / withdrawal information of the first account;
A balance prediction unit that calculates a predicted balance of the first account based on the deposit and withdrawal pattern of the first account;
, Balance management system. It further comprises an extraction model learning unit that learns an extraction model for extracting the deposit and withdrawal pattern of the first account from the deposit and withdrawal information of the first account,
The deposit / withdrawal pattern creation unit creates a deposit / withdrawal pattern of the first account based on the extraction model.
The balance management system according to claim 1. The extraction model learning unit learns the extraction model by machine learning using a data set including input data and output data as teacher data.
The balance management system according to claim 2. The input data includes past deposit and withdrawal information related to the user information,
The output data includes past deposit and withdrawal patterns extracted from the past deposit and withdrawal information.
The balance management system according to claim 3. The input data includes deposit and withdrawal information of a plurality of users,
The output data includes a plurality of user deposit and withdrawal patterns extracted from the plurality of user deposit and withdrawal information.
The balance management system according to claim 3 or 4. A replenishment plan creation unit for creating at least one replenishment plan for replenishing the funds of the first account based on the predicted balance of the first account;
A replenishment plan notification unit that notifies the user terminal of the at least one replenishment plan;
Further comprising
The balance management system according to any one of claims 1 to 5. The replenishment plan creation unit creates the at least one replenishment plan when the predicted balance of the first account runs short.
The balance management system according to claim 6. The replenishment plan creation unit creates the at least one replenishment plan when the predicted balance of the first account falls below a specific amount.
The balance management system according to claim 6. The deposit and withdrawal information acquiring unit acquires deposit and withdrawal information on the second account from the supplier system,
The at least one replacement plan includes a funds transfer plan for transferring funds from the second account to the first account.
The balance management system according to any one of claims 6 to 8. The deposit / withdrawal pattern creation unit creates the deposit / withdrawal pattern of the second account from the deposit / withdrawal information of the second account,
The balance prediction unit calculates a predicted balance of the second account based on the deposit and withdrawal pattern of the second account,
The replenishment plan creation unit compares predicted balances of the first and second accounts to determine whether it is possible to move funds from the second account to the first account.
The balance management system according to claim 9. The deposit / withdrawal pattern creating unit creates deposit / withdrawal patterns of the plurality of accounts from deposit / withdrawal information of a plurality of accounts each corresponding to the second account,
The balance prediction unit calculates predicted balances of the plurality of accounts based on the deposit and withdrawal patterns of the plurality of accounts,
The replenishment plan creation unit creates a funds transfer plan for transferring funds from at least one of the plurality of accounts to the first account.
The balance management system according to claim 9 or 10. The funds transfer plan transfers funds from the plurality of accounts equally.
The balance management system according to claim 11. The money transfer plan determines the amount of money to be transferred from each of the plurality of accounts according to the size of each of the predicted balances of the plurality of accounts.
The balance management system according to claim 11. The funds transfer plan preferentially transfers funds from the account with the largest predicted balance among the plurality of accounts.
The balance management system according to claim 13. The funds transfer plan transfers funds from each of the plurality of accounts proportional to the expected balance of the plurality of accounts.
The balance management system according to claim 13. The funds transfer plan preferentially transfers funds from accounts with a high frequency of remittance to another account among the plurality of accounts.
The balance management system according to claim 11. The remittance frequency is the frequency of remittance with the first account as the remittance destination.
The balance management system according to claim 16. Among the plurality of accounts, the fund transfer plan transfers funds preferentially from accounts with high withdrawal frequency within a certain period from the reference date, with the deposit date to the first account as the reference date,
The balance management system according to claim 11. The funds transfer plan transfers funds from the selected account based on the registered priorities.
The balance management system according to claim 11. The at least one replacement plan includes a borrowing plan for borrowing money from a lending institution and depositing money into the first account.
The balance management system according to any one of claims 6 to 19. The system further comprises a replenishment instructing unit for depositing funds to the first account based on one of the at least one replenishment plan.
The balance management system according to any one of claims 6 to 20. The system further comprises a replenishment plan notification unit that notifies the user terminal of the at least one replenishment plan,
The replenishment instructing unit deposits the funds to the first account based on an instruction from the user terminal.
A balance management system according to claim 21. After calculating the predicted balance of the first account, the balance prediction unit acquires newly determined updated transaction information from the customer system, and corrects the predicted balance of the first account.
The balance management system according to any one of claims 1 to 22. The system further comprises a predicted balance notification unit for notifying the user terminal of the predicted balance of the first account.
The balance management system according to any one of claims 1 to 23. A deposit / withdrawal schedule creation unit that creates a deposit / withdrawal schedule based on the deposit / withdrawal pattern and provides the balance forecasting unit with the deposit / withdrawal schedule;
And a deposit and withdrawal schedule notification unit that notifies the user terminal of the deposit and withdrawal schedule.
The balance management system according to any one of claims 1 to 24. The system further comprises a deposit / withdrawal information classification unit that classifies periodic deposit / withdrawal information from the deposit / withdrawal information of the first account,
The deposit / withdrawal pattern creation unit creates the deposit / withdrawal pattern of the first account based on the periodic deposit / withdrawal information.
The balance management system according to claim 1.