Data processing device, data processing method, and program

Abstract

A data processing device, a data processing method, and a program are provided. [Solution] A data processing device that acquires business data and accounting data from the communication terminals of multiple business operators from an accounting data management device via a network comprises: an identification unit that identifies the cash balance for each month from the beginning of a period based on the business operator's past beginning balance; a data storage unit that stores a dataset including the cash balance for each of the multiple months identified by the identification unit and an amount corresponding to one or more account items for each of the multiple months; and a learning model generation unit that uses the multiple datasets to generate a learning model in which the cash balance for each of the multiple months prior to a base month and the amount corresponding to one or more account items for the month prior to the base month are at least explanatory variables, and the cash balance for each of the multiple future months is the objective variable.

Description

[Technical field]

[0001] The present invention relates to a data processing device, a data processing method, and a program. [Background technology]

[0002] 2. Description of the Related Art Accounting management systems that support financial accounting operations of business operators are known (see, for example, Patent Document 1). [Prior art document] [Patent documents] [Patent Document 1] JP 2001-014384 A Summary of the Invention

[0003] According to one embodiment of the present invention, there is provided a data processing device. The data processing device may include an identification unit that identifies the cash balance for each month from the beginning of a period based on the business entity's past beginning balance. The data processing device may include a data storage unit that stores a data set including the cash balance for each of the multiple months identified by the identification unit and an amount corresponding to one or more account items for the multiple months. The data processing device may include a learning model generation unit that uses the multiple data sets to generate a learning model in which the cash balance for each of the multiple months prior to a base month and the amount corresponding to one or more account items for the month prior to the base month are at least explanatory variables, and the cash balance for each of the multiple future months is an objective variable,

[0004] The above summary of the invention does not list all of the necessary features of the present invention. Also, subcombinations of these features may also be inventions. [Brief description of the drawings]

[0005] [Figure 1] An example of a data processing device 100 is shown diagrammatically. [Diagram 2] FIG. 11 is an explanatory diagram for explaining a process for creating a data mart 390 by the data processing device 100. [Diagram 3]FIG. 11 is an explanatory diagram for explaining a process for creating a data mart 390 by the data processing device 100. [Figure 4] FIG. 11 is an explanatory diagram for explaining a process for creating a data mart 390 by the data processing device 100. [Diagram 5] 4 shows a schematic diagram of an example of a cash balance graph 400. [Figure 6] 4 is a schematic diagram of another example of a cash balance graph 400. [Figure 7] 1 illustrates an example of a functional configuration of a data processing device 100. [Figure 8] 1 illustrates an example of a processing flow by the data processing device 100. [Figure 9] 1 illustrates an example of a processing flow by the data processing device 100. [Figure 10] An example of a hardware configuration of a computer 1200 functioning as the data processing device 100 is shown in schematic form. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0006] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0007] FIG. 1 shows an example of a data processing device 100. The data processing device 100 according to the present embodiment provides a technique that contributes to predicting the timing of fund raising. The data processing device 100 has a function of predicting the future cash balance of a target business from the cash balance of the target business for multiple months, for example, by using accounting data of multiple businesses. The data processing device may use AI (Artificial Intelligence) or ML (Machine Learning).

[0008] The data processing device 100 stores business data and accounting data of a plurality of business operators. The data processing device 100 acquires and stores the business data and accounting data of a plurality of business operators from, for example, an accounting data management device 200 that manages the business data and accounting data of a plurality of business operators.

[0009] The data processing device 100 may acquire business data and accounting data of multiple businesses from the accounting data management device 200 via the network 50. The network 50 may include a cloud network. The network 50 may include the Internet. The network 50 may include a mobile communication network. The network 50 may include a dedicated network such as a LAN (Local Area Network). The data processing device 100 and the accounting data management device 200 may communicate directly without going through the network 50.

[0010] The accounting data management device 200 may manage accounting data input by businesses, accounting firms, etc., using so-called accounting software, so-called cloud-based accounting software, and related software. The accounting data management device 200 may manage accounting data provided by businesses, accounting firms, etc., without using accounting software, cloud-based accounting software, and related software.

[0011] The accounting data management device 200 may receive and manage business data and accounting data of a business from a communication terminal 80 used by a user 82. The user 82 may be a business. The user 82 may be an accounting firm or the like used by the business. The accounting data management device 200 may communicate with the communication terminal 80 via a network 50. The communication terminal 80 may be any terminal capable of communication. For example, the communication terminal 80 is a mobile phone such as a smartphone, a tablet terminal, a PC (Personal Computer), etc.

[0012] The data processing device 100 and the accounting data management device 200 may be integrated. In other words, the data processing device 100 may be configured to have the functions of the accounting data management device 200.

[0013] The business data may be data indicating the attributes of the business. The business data may include the business name. The business data may include settlement date information indicating the settlement date. The business data may include business content. The business data may include the number of employees. The business data may include the establishment date. The business data may include the period since establishment. The business data may include the location area. The business data may include an industry code indicating the industry of the company. The industry code may be a code defined by the country. For example, the industry code may be the Japan Standard Industrial Classification Code. The industry code may be a securities code defined by the Japan Exchange Group. The industry code is not limited to this, and may be any other code indicating the industry of the company. The business data may include a company type indicating whether the business is a joint stock company or a limited liability company. The business data may include data indicating whether the company is a listed company or an unlisted company.

[0014] The accounting data may be data related to the accounting of a business. The accounting data may include so-called journal entry data. In other words, the accounting data may include data on transactions recorded and classified by account item.

[0015] The accounting data may include capital. The accounting data may include capital reserves. The accounting data may include advance payments. The accounting data may include time deposits. The accounting data may include accounts receivable. The accounting data may include long-term loans payable. The accounting data may include interest received. The accounting data may include sales. The accounting data may include sales amount. The accounting data may include ending inventory. The accounting data may include gains on sales of securities. The accounting data may include accounts receivable. The accounting data may include miscellaneous income. The accounting data may include beginning balance. The accounting data may include accounts payable. The accounting data may include cost of sales. The accounting data may include accounts receivable. The accounting data may include operating profit. The accounting data may include total assets. The accounting data may include cash and deposits. The accounting data may include trade receivables. The accounting data may include securities. The accounting data may include inventory. The accounting data may include accounts payable. The accounting data may include tangible fixed assets. The accounting data may include intangible fixed assets. The accounting data may include interest-bearing liabilities. The accounting data may include equity capital. The accounting data may include trade payables. The accounting data may include depreciation expenses. The accounting data may include amortization of goodwill. The accounting data may include selling and general administrative expenses. The accounting data may include an effective tax rate. The accounting data may include changes in working capital. The accounting data may include capital investment amounts. The accounting data may include debt financing costs. The accounting data may include shareholder's equity ratios. The accounting data may include average accounts receivable balances. The accounting data may include average inventory balances. The accounting data may include average payables balances. The accounting data may include retirement benefit obligations. The accounting data may include minority interests. The accounting data may include dividend amounts. The accounting data may include annual profit amounts. The accounting data may include net assets. The accounting data may include net income for the current period. The accounting data may include the number of issued shares. The accounting data may include total assets. The accounting data may include the days' accounts receivable turnover. The accounting data may include the days' inventory turnover. The accounting data may not include some of these. The accounting data may include other data.

[0016] The data processing device 100 may generate data for learning using business data and accounting data of a plurality of businesses. The data processing device 100 may create a data mart that tracks the monthly cash balance for each of the plurality of businesses. Generally, accounting data does not include the monthly cash balance. The data processing device 100 may create a data mart that tracks the monthly cash balance by processing the business data and accounting data of the businesses.

[0017] 2, 3, and 4 are explanatory diagrams for explaining an example of a method for creating a data mart by the data processing device 100. The data processing device 100 may create a data mart using accounting data of a business and business data. The accounting data and business data may be managed in various data configurations. In particular, the accounting data and business data may have different data configurations depending on the management entity. The data processing device 100 may create a data mart by a method according to the data configuration of the target accounting data and business data.

[0018] Here, we will explain an example of creating a data mart using transaction details table 330, which contains information on one transaction per record, accounting settings table 340, which contains business operator data, and account balance table 350, which contains the opening balance for each account item. In this example, one record in transaction details table 330 contains information such as the business operator ID, account item ID, and transaction amount.

[0019] The account title ID is a string of mechanically generated letters and numbers, and does not have a logical structure by itself. The data processing device 100 uses the account title table 310 and the auxiliary title table 320 to convert the account title ID into account title information with a logical structure. The account title table 310 and the auxiliary title table 320 may be tables showing the correspondence between the account title ID and the account title information. The account title information may have a hierarchical logical structure for each digit. As a specific example, the data processing device 100 converts the account title ID: XXXX-XXXX-0001 into 6-digit account title information: 1-1-0-0-0-0. The first level of the account title information may represent the major items of the account title, and the second level and subsequent levels may represent the more detailed items. The format of the account title ID and the format of the account title information are not limited to these, and may be other formats. The data processing device 100 combines the account title information with the transaction details table 330. In addition, the account item information may be originally combined with the transaction details table 330, in which case the data processing device 100 does not need to perform conversion using the account item table 310 and the auxiliary item table 320.

[0020] The data processing device 100 identifies the beginning year / month and the beginning balance from the settlement date information recorded in the accounting setting table 340 and the balance in the item balance table 350.

[0021] The data processing device 100 calculates the monthly income and expenditure for each account item for each of the multiple businesses by grouping and aggregating the records in the transaction details table 330 by business, account item, and month. The data processing device 100 also calculates the overall monthly income and expenditure for each of the multiple businesses. At this time, the data processing device 100 may refer to the credit and debit flags and make the transaction amount negative for the credit side. This allows reconciliation to be expressed.

[0022] The data processing device 100 calculates the monthly cash balance 360 ​​by adding the calculated overall monthly income and expenditure, starting from the specified beginning year and month and beginning balance. FIG. 3 shows a specific example. In FIG. 3, an example is described in which the beginning year and month of the target business is January 2020, the beginning balance 352 is 1,000,000 yen, the income and expenditure 332 for January 2020 is -100,000 yen, and the income and expenditure 334 for February 2020 is +300,000 yen. The data processing device 100 calculates the cash balance for February 2020 (900,000 yen) by adding the income and expenditure 332 for January to the beginning balance 352 of the target business. Moreover, data processing device 100 calculates the cash balance for March 2020 (1,200,000 yen) by adding February income / expenses 334 to the calculated cash balance for February 2020. By performing such a calculation for each month, data processing device 100 calculates cash balances 360 for multiple months.

[0023] The data processing device 100 generates a data mart 390 combining the explanatory variable 370 and the objective variable 380 by combining the income and expenditure for each account item and the monthly cash balance 360. The data processing device 100 may set the cash balances for multiple months in the past from the base month (year and month for which prediction is performed) as the explanatory variable 370, and the cash balances for multiple months in the future from the base month as the objective variable 380. As a specific example, the data processing device 100 calculates the cash balances for 15 months, sets the three months in the latter chronological order as the objective variable 380, and sets the twelve months in the former chronological order as the explanatory variable 370. The data processing device 100 adds the amount corresponding to one or more account items for one or more months in the past from the base month to the explanatory variable 370. The amount corresponding to the account item for each month is the income and expenditure of the account item for each month. For example, the data processing device 100 groups and aggregates the records of the transaction details table 330 by business operator, account item, and month, and outputs the result as a feature table when calculating the monthly income and expenditure for each account item for each of the multiple business operators. The data processing device 100 may set the unique keys of the feature table to the business operator ID and the predicted year and month, and each record may have the income and expenditure for each account item as a column. The data processing device 100 may generate a data mart 390 by combining the monthly cash balance 360 ​​with the feature table. The data mart 390 includes multiple monthly cash balances and one or multiple monthly income and expenditures for each account item for each of the multiple business operators.

[0024] Fig. 4 shows an example of explanatory variables 370 and objective variables 380. In the example shown in Fig. 4, explanatory variables 370 include the cash balance from one month before the base month to 12 months before, and objective variable 380 includes the cash balance from one month after the base month to three months after the base month. If the base month is April, explanatory variable 370 includes the cash balance from April to December of the previous year and the cash balance from January to March of the same year, and objective variable 380 includes the cash balances for April, May, and June.

[0025] The data processing device 100 may include a cash statistic in the explanatory variable 370 as illustrated in FIG. 4. Examples of the cash statistic include, as illustrated in FIG. 4, an average value for the past n months and a median value for the past n months, but are not limited thereto, and may include a variance for the past n months, a monthly difference for the past n months, and the like. The data processing device 100 may include some of these in the explanatory variable 370, or may include other statistics. The data processing device 100 may include the income and expenditure of each account item in the previous month in the explanatory variable 370 as illustrated in FIG. 4. Examples of account items include, as illustrated in FIG. 4, sales and accounts receivable for the previous month, but are not limited thereto, and may include capital, capital reserve, advance payment, time deposit, accounts receivable, long-term borrowing, interest received, sales, end-of-period inventory, profit on sale of securities, and miscellaneous income. The data processing device 100 may include some of these in the explanatory variable 370, or may include income and expenditure of account items other than these.

[0026] The data processing device 100 executes machine learning using the explanatory variables 370 and the objective variables 380 illustrated in FIG. 4, and can generate a learning model that inputs the cash balance for the past 12 months, the cash statistics, and the income and expenditure of each account item for the previous month, and outputs the cash balance for the future three months. The data processing device 100 may use the generated learning model to predict the future cash balance for multiple months of the target business. The data processing device 100 may output the predicted future cash balance for multiple months of the target business. The data processing device 100 displays and outputs, for example, a graph showing the predicted future cash balance for multiple months of the target business.

[0027] FIG. 5 shows an example of a cash balance graph 400. The vertical axis of the cash balance graph 400 indicates the cash balance in units of one million yen. The horizontal axis of the cash balance graph 400 indicates the year and month. Here, an example of a cash balance graph 400 is shown in which the cash balances for April 2025, May 2025, and June 2025 are predicted from data prior to March 2025 at the end of the month of March 2025.

[0028] The data processing device 100 may generate a cash balance graph 400 that shows the past transition of the cash balance and the predicted future transition of the cash balance in different ways, as exemplified in Fig. 5. In Fig. 5, the past transition of the cash balance is shown by a solid line, and the predicted future transition of the cash balance is shown by a dashed line.

[0029] By the data processing device 100 outputting the cash balance graph 400 illustrated in FIG. 5, the effort required for the business operator to plan cash flow can be reduced, and the business operator can understand the time and amount of cash shortage, enabling the business operator to raise funds with ample time.

[0030] Fig. 6 is a schematic diagram of another example of a cash balance graph 400. Here, differences from the cash balance graph 400 in Fig. 5 will be mainly described.

[0031] In the example shown in FIG. 6, the data processing device 100 outputs a reference trend 410, which is a trend of predicted balance for multiple future months, a large balance trend 420 in which the cash balance is higher for multiple months than the reference trend 410, and a small balance trend in which the cash balance is lower for multiple months than the reference trend.

[0032] For example, the data processing device 100 generates a reference trend 410 by predicting the cash balance for multiple future months from past data, generates a large balance trend 420 by multiplying the predicted cash balance for multiple months by a predetermined value greater than 1, and generates a small balance trend 430 by multiplying the predicted cash balance for multiple months by a predetermined value smaller than 1. As a specific example, the data processing device 100 generates a large balance trend 420 by multiplying the predicted cash balance for multiple months by 1.1, and generates a small balance trend 430 by multiplying the predicted cash balance for multiple months by 0.9.

[0033] The data processing device 100 may generate a learning model for generating the reference transition 410, a learning model for generating the large-balance transition 420, and a learning model for generating the small-balance transition 430. For example, the data processing device 100 generates a learning model for generating the reference transition 410 using past data as is, generates a learning model for generating the large-balance transition 420 using data from the past data in which the cash balance of the objective variable has been increased, and generates a learning model for generating the small-balance transition 430 using data from the past data in which the cash balance of the objective variable has been decreased.

[0034] By the data processing device 100 outputting the cash balance graph 400 illustrated in FIG. 6, the trends in the cash balance in both a good case scenario and a bad case scenario can be understood, making it possible to implement a more multifaceted fund raising plan.

[0035] 7 illustrates an example of a functional configuration of the data processing device 100. The data processing device 100 includes a data storage unit 102, a data acquisition unit 104, an identification unit 106, a data management unit 108, a learning model generation unit 110, a target data acquisition unit 112, a prediction unit 114, and an output control unit 116.

[0036] The data storage unit 102 stores various data. The data storage unit 102 stores the data acquired by the data acquisition unit 104.

[0037] The data acquiring unit 104 acquires various data. The data acquiring unit 104 acquires business data and accounting data of a plurality of business operators. The data acquiring unit 104 may acquire the business data and accounting data of a plurality of business operators from the data management device 200.

[0038] The identification unit 106 identifies the monthly cash balance of the business operator. The identification unit 106 may identify the monthly cash balance of the business operator by using the business operator data and accounting data of the business operator. If the business operator data and accounting data of the business operator include the monthly cash balance of the business operator, the identification unit 106 identifies the monthly cash balance of the business operator by referring to the business operator data and accounting data. If the business operator data and accounting data of the business operator do not include the monthly cash balance of the business operator, the identification unit 106 identifies the monthly cash balance of the business operator by using the data included in the business operator data and accounting data.

[0039] The identification unit 106 may identify the cash balance for each month after the beginning of the term based on the business's past beginning balance. For example, the identification unit 106 identifies the beginning month and year and the beginning balance from the business data and accounting data. For example, the identification unit 106 identifies the beginning month and year based on the settlement date information included in the business data, refers to an item balance table included in the accounting data, identifies the beginning balance for each account item, and adds these together to identify the beginning balance. The identification unit 106 also refers to the accounting data and calculates the monthly income and expenditure for each account item by aggregating the transaction amount for each month, and calculates the overall monthly income and expenditure by aggregating the monthly income and expenditure. The identification unit 106 may determine whether the transaction is a debit or credit, and execute a process of making the transaction amount a negative value for the credit side.

[0040] The identification unit 106 calculates the monthly cash balance by adding the calculated overall monthly income and expenditure to the identified beginning year and month of the term and beginning balance. This makes it possible to calculate the monthly cash balance for the period in which accounting data is included in the data storage unit 102. For example, if the data storage unit 102 includes accounting data for 10 years, the monthly cash balance for the 10 years can be calculated. The identification unit 106 identifies the monthly cash balance for each of the multiple businesses. The data storage unit 102 stores the monthly cash balance for each of the multiple businesses identified by the identification unit 106.

[0041] The data management unit 108 manages the data stored in the data storage unit 102. The data management unit 108 may generate learning data using the data stored in the data storage unit 102. The data management unit 108 may generate a data set including the cash balance for the multiple months identified by the identification unit 106 and the amount corresponding to one or multiple account items for each of the multiple months for each of the multiple businesses. The data storage unit 102 stores the multiple data sets generated by the data management unit 108.

[0042] The data management unit 108 may generate data for learning after performing preprocessing on the data stored in the data storage unit 102. For example, the data management unit 108 targets only data in which the stock of cash is less than a predetermined threshold in all of the multiple months. That is, the data management unit 108 excludes data in which the stock of cash is greater than a threshold in any of the multiple months from the data stored in the data storage unit 102. For example, the threshold is set to 100 million yen. Also, for example, the data management unit 108 may remove data that has not changed in the past 12 months from the data stored in the data storage unit 102. Also, for example, the data management unit 108 may exclude data that is at the beginning of the month from the data stored in the data storage unit 102 in which the settlement date is not at the end of the month.

[0043] The data management unit 108 may include capital in the data set. The data management unit 108 may include advance payments in the data set. The data management unit 108 may include accounts receivable in the data set. The data management unit 108 may include long-term borrowings in the data set. The data management unit 108 may include interest received in the data set. The data management unit 108 may include sales in the data set. The data management unit 108 may include end-of-period inventory in the data set. The data management unit 108 may include gains on sales of securities in the data set. The data management unit 108 may include accounts receivable in the data set. The data management unit 108 may include miscellaneous income in the data set. Of the many account items that exist, these account items have a large impact on the cash balance, so including at least one of these in the data set can contribute to generating a learning model with high prediction accuracy of the future cash balance. The data management unit 108 may include amounts corresponding to account items other than these in the data set.

[0044] The learning model generation unit 110 uses multiple data sets stored in the data storage unit 102 to generate a learning model in which the cash balance for multiple months prior to a base month and the amount corresponding to one or multiple account items for the month before the base month are at least explanatory variables, and the cash balance for multiple future months is the objective variable. The data storage unit 102 stores the learning model generated by the learning model generation unit 110.

[0045] The dataset includes actual cash balances for multiple months in the past, and when the cash balance shows a certain trend during a certain period, it shows how the cash balance actually changed after that. Therefore, by generating a learning model using multiple datasets from multiple businesses, it is possible to generate a learning model that can predict future changes in cash fluctuations from changes in cash fluctuations during a certain period in the past.

[0046] The learning model generation unit 110 may generate a learning model that further uses statistical information on the cash balance for multiple past months as an explanatory variable. For example, the learning model generation unit 110 generates a learning model that uses the cash balance for multiple months prior to a base month, statistical information on the cash balance for multiple months, and the amount corresponding to one or multiple account items for the month before the base month as explanatory variables, and uses the cash balance for multiple future months as an objective variable.

[0047] The learning model generation unit 110 may use statistical information on the cash balance for the same multiple months as the multiple months including the cash balance. For example, when using the monthly cash balance for the past year of the base month, the learning model generation unit 110 may use statistical information on the cash balance for the past year of the base month.

[0048] The learning model generation unit 110 may use statistical information on the cash balance for multiple months that are different from multiple months that include the cash balance. For example, when using the monthly cash balance for the past year of the base month, the learning model generation unit 110 may use statistical information on the cash balance for the past three months of the base month.

[0049] The learning model generation unit 110 may use at least one of the average value, median value, variance, and difference of the cash balances of multiple months as the statistical information of the cash balances of multiple months. The inventor's verification using actual data has demonstrated that there is a high correlation between the statistical information of the cash balances of multiple past months of a reference month and the cash balances of multiple future months of the reference month. The inventor created a learning model using actual data, verified the input and output to the learning model, verified the SHAP (SHapley Additive exPlanations) value at that time, and identified the average value, median value, variance, and difference as statistical information highly correlated with the future cash balance from his experience in managing accounting data. In this way, by adding statistical information of the past cash balances that is highly correlated with the future cash balance to explanatory variables and learning it, the prediction accuracy of the future cash balance can be improved.

[0050] The data set further includes the amount of one or more account items for multiple actual months in the past. The inventor's verification using actual data has demonstrated that there is a high correlation between the amount of one or more account items for the month before the base month and the cash balance for multiple future months before the base month. The inventor created a learning model using actual data, verified the input and output to the learning model, verified the SHAP (SHapley Additive exPlanations) value at that time, and from his experience in accounting data management, identified the following account items as having a particularly high correlation with the future cash balance: capital, advance payment, accounts receivable, long-term loan, interest received, sales, end-of-period inventory, profit on sale of securities, accounts receivable, and miscellaneous income. The learning model generation unit 110 may generate a learning model using the cash balance for multiple months in the past than the base month and at least one of the following items as explanatory variables: capital, advance payment, accounts receivable, long-term loan, interest received, sales, end-of-period inventory, profit on sale of securities, accounts receivable, and miscellaneous income for the month before the base month. The learning model generation unit 110 may add account items other than these to the explanatory variables. In this way, by adding account items that are highly correlated with future cash balances to explanatory variables and learning them, the prediction accuracy of future cash balances can be improved.

[0051] The target data acquisition unit 112 acquires data of a target business entity for which a future cash balance is to be predicted. The target data acquisition unit 112 acquires, for example, the cash balance for each of a number of months prior to a base month, and the amount corresponding to one or more account items for the month prior to the base month. The target data acquisition unit 112 may acquire these data from data stored in the data storage unit 102.

[0052] The prediction unit 114 predicts the future cash balance of the target business operator. The prediction unit 114 inputs the data acquired by the target data acquisition unit 112 into the learning model stored in the data storage unit 102, and acquires the future monthly cash balance output from the learning model as the predicted cash balances of the target business operator for each of the multiple future months.

[0053] The output control unit 116 outputs the predicted cash balance for each of the target company in the future for multiple months acquired by the prediction unit 114. The output control unit 116 displays the predicted cache balance on, for example, a display provided in the data processing device 100. The output control unit 116 transmits the predicted cache balance to, for example, the communication terminal 80 or the like.

[0054] The output control unit 116 may output the future projected cash balance of the target business operator as a numerical value. The output control unit 116 may output a cash balance graph as shown in FIG. 5, which shows the transition of the target business operator's cash balance over the past several months and the transition of the target business operator's projected cash balance in the future.

[0055] The output control unit 116 may control to output a reference trend, which is a trend of the predicted cash balance for multiple months of the target business acquired by the prediction unit 114, a large-balance trend in which the cash balance for multiple months is larger than the reference trend, and a small-balance trend in which the cash balance for multiple months is smaller than the reference trend. The output control unit 116 may output a cash balance graph as illustrated in FIG. 6, for example. The output control unit 116 may acquire the predicted cash balance for multiple months of the target business from the prediction unit 114, generate a reference trend from the predicted cash balance for the multiple months, generate a large-balance trend by multiplying the predicted cash balance for the multiple months by a predetermined value greater than 1, and generate a small-balance trend by multiplying the predicted cash balance for the multiple months by a predetermined value smaller than 1.

[0056] Alternatively, the learning model generation unit 110 may generate a learning model for generating a reference trend, a learning model for generating a large-balance trend, and a learning model for generating a small-balance trend. For example, the learning model generation unit 110 generates a learning model for generating a reference trend using past data as is, generates a learning model for generating a large-balance trend using data from the past data in which the cash balance of the objective variable has been increased, and generates a learning model for generating a small-balance trend using data from the past data in which the cash balance of the objective variable has been decreased.

[0057] By the data processing device 100 outputting the cash balance graph 400 illustrated in FIG. 6, the trends in the cash balance when things go well and when things do not go well can be understood, making it possible to implement a more multifaceted fundraising plan.

[0058] The data processing device 100 may execute a prediction using the monthly cash balance of the target business in any period in the past. The data processing device 100 may use the cash balance of the target business in consecutive months in the past, or may use the cash balance of the target business in non-consecutive months in the past. As a specific example, the target data acquisition unit 112 acquires the monthly cash balance of the target business in the past year before the base month and the amount corresponding to one or more account items in the month before the base month, and the prediction unit 114 inputs these into the learning model. There is a high possibility that the transition of the cash balance will show periodic characteristics from year to year. Therefore, by performing a prediction using the monthly cash balance in the past year, it may be possible to improve the prediction accuracy of the future cash balance.

[0059] The data processing device 100 may predict the monthly cash balance of the target business for any future period. The data processing device 100 may predict the future cash balance of the target business for multiple consecutive months, or may predict the future cash balance of the target business for multiple non-consecutive months. As a specific example, the learning model generation unit 110 generates a learning model with the monthly cash balance of the future three months from the reference month as the objective variable. This allows the business to know the predicted cash balance one month, two months, and three months from the timing of executing the prediction, for example, and allows the business to raise funds in plenty of time as necessary.

[0060] It is not essential that the data processing device 100 includes all of the data storage unit 102, the data acquisition unit 104, the identification unit 106, the data management unit 108, the learning model generation unit 110, the target data acquisition unit 112, the prediction unit 114, and the output control unit 116. For example, the data processing device 100 may have a function of generating a learning model, but may not have a function of executing prediction using the learning model. In this case, the data processing device 100 includes the data storage unit 102, the data acquisition unit 104, the identification unit 106, the data management unit 108, and the learning model generation unit 110. For example, the data processing device 100 does not have a function of generating a learning model, but has a function of executing prediction using the learning model. In this case, the data processing device 100 includes the data storage unit 102, the target data acquisition unit 112, the prediction unit 114, and the output control unit 116. In this case, another device generates a learning model, and the data processing device 100 acquires and uses the learning model from the other device.

[0061] 8 shows an example of a flow of processing by the data processing device 100. Here, an example of a flow is shown in which the output control unit 116 performs control processing to output a warning when the predicted cash balance for each of a plurality of future months of the target business acquired by the prediction unit 114 is less than a predetermined threshold.

[0062] In step (sometimes abbreviated to S) 102, the target data acquisition unit 112 acquires data on the target business. In S104, the prediction unit 114 inputs the data on the target business acquired by the target data acquisition unit 112 in S102 into a learning model stored in the data storage unit 102, thereby predicting the future cash balance of the target business.

[0063] In S106, the output control unit 116 judges whether the predicted cash balance for each of the target business in the future for multiple months predicted by the prediction unit 114 in S104 is equal to or less than a predetermined threshold. The threshold may be arbitrarily settable and may be changeable. For example, the output control unit 116 may judge YES when at least any of the predicted cash balances for multiple months is equal to or less than the threshold, and may judge NO when all of the predicted cash balances for multiple months are greater than the threshold. The output control unit 116 may judge YES when the predicted cash balance for the last month of the multiple months is equal to or less than the threshold, and may judge NO when the predicted cash balance for the last month is not equal to or less than the threshold. If YES is judged, the process proceeds to S108, and if NO is judged, the process proceeds to S110.

[0064] In S108, the output control unit 116 outputs the prediction result predicted by the prediction unit 114 in S104 and a warning. The output control unit 116 may output the prediction result and the warning to, for example, the communication terminal 80 of the target business operator. The warning may include content encouraging fund raising. The warning may include content notifying of a shortage of funds. In S110, the output control unit 116 outputs the prediction result predicted by the prediction unit 114 in S104. The output control unit 116 may output the prediction result to, for example, the communication terminal 80 of the target business operator.

[0065] In this way, by issuing a warning to encourage fundraising when the predicted cash balance falls below a threshold, the risk of the target business going bankrupt despite being profitable due to a cash shortage can be reduced, and support can be provided for the stabilization and further growth of the target business's business.

[0066] Fig. 9 shows an example of a flow of processing by the data processing device 100. Here, an example of a flow is shown in which the output control unit 116 performs control to output a warning when the balance after applying the corresponding monthly accounts receivable and accounts payable to each of the multiple future monthly projected cash balances of the target company acquired by the prediction unit 114 is less than a predetermined threshold. Note that here, differences from Fig. 8 will be mainly described.

[0067] In S202, the target data acquisition unit 112 acquires data of the target business. In S204, the prediction unit 114 inputs the data of the target business acquired by the target data acquisition unit 112 in S202 into a learning model stored in the data storage unit 102, thereby predicting the future cash balance of the target business.

[0068] In S206, the output control unit 116 adds the accounts receivable of the target business to each of the multiple future monthly predicted cash balances of the target business predicted by the prediction unit 114 in S204, subtracts the accounts payable of the target business from the multiple future monthly predicted cash balances, and compares the results with a predetermined threshold value. The threshold value may be arbitrarily set and may be changeable. For example, the threshold value is set to 0. The output control unit 116 may determine YES when at least one of the multiple months of "cash balance + accounts receivable - accounts payable" is equal to or less than the threshold value, and may determine NO when both are greater than the threshold value. The output control unit 116 may determine YES when the "cash balance + accounts receivable - accounts payable" of the last month of the multiple months is equal to or less than the threshold value, and may determine NO when the "cash balance + accounts receivable - accounts payable" of the last month is not equal to or less than the threshold value. If the determination is YES, the process proceeds to S208, and if the determination is NO, the process proceeds to S210.

[0069] In S208, the output control unit 116 outputs a warning and the prediction result predicted by the prediction unit 114 in S204. In S210, the output control unit 116 outputs the prediction result predicted by the prediction unit 114 in S204.

[0070] In order to prevent bankruptcy even if the business is profitable, it is necessary to take into account accounts payable and accounts receivable in addition to the cash balance. By executing the process shown in Figure 9, the data processing device 100 can determine whether or not there is a cash shortage after taking into account accounts payable and accounts receivable. This reduces the risk of the target business going bankrupt even if the business is profitable due to a cash shortage and supports the stabilization and further growth of the target business's business.

[0071] 10 is a schematic diagram showing an example of a hardware configuration of a computer 1200 functioning as the data processing device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the device according to the present embodiment, and / or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0072] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes a legacy input / output unit such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0073] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data created by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

[0074] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides the programs or data to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0075] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0076] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing operations or processing of information according to the use of the computer 1200.

[0077] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, the DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to a network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0078] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive 1226 (DVD-ROM 1227), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0079] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0080] The above-described programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0081] The blocks in the flowcharts and block diagrams in the present embodiment may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as, for example, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like, including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0082] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

[0083] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0084] Computer readable instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., to cause the processor of the general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, to execute the computer readable instructions to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0085] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.

[0086] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and that the process may be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," and the like for convenience, this does not mean that the process must be performed in this order. [Explanation of symbols]

[0087] 50 network, 80 communication terminal, 82 user, 100 data processing device, 102 data storage unit, 104 data acquisition unit, 106 identification unit, 108 data management unit, 110 learning model generation unit, 112 target data acquisition unit, 114 prediction unit, 116 output control unit, 200 data management device, 310 account subject table, 320 auxiliary subject table, 330 transaction details table, 332 January balance, 334 February balance, 340 accounting setting table, 350 subject balance table, 352 beginning balance, 360 monthly cash balance, 370 explanatory variable, 380 objective variable, 390 data mart, 400 cash balance graph, 410 benchmark trend, 420 large balance trend, 430 small balance trend, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 input / output controller, 1222 communication interface, 1224 storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 input / output chip

Claims

1. An identification unit that identifies the cash balance of each month of the business operator after the beginning of a fiscal year by adding the monthly income and expenditure of the business operator to the past beginning balance of the business operator; a data storage unit that stores a data set including the cash balance for each of the multiple months identified by the identification unit and the amount corresponding to one or more account items for each of the multiple months; a learning model generation unit that generates a learning model in which the multiple monthly cash balances in the past before a reference month and the amounts corresponding to one or more account items in the month preceding the reference month are at least explanatory variables and the multiple future monthly cash balances are objective variables by performing supervised learning using as training data the multiple monthly cash balances in the past before a reference month among the multiple monthly cash balances included in the data set, the multiple monthly cash balances in the past before the reference month among the multiple monthly cash balances included in the data set, and the amounts corresponding to one or more account items in the month preceding the reference month among the multiple monthly cash balances included in the data set; A data processing device comprising:

2. a prediction unit that inputs into the learning model the target business's cash balances for multiple months prior to a base month and amounts corresponding to one or multiple account items for the month prior to the base month, and obtains the future cash balances for multiple months output from the learning model as the target business's future predicted cash balances for multiple months; an output control unit that controls the prediction unit to output the predicted cash balances for the target company for each of a plurality of future months; The data processing apparatus of claim 1 , comprising:

3. 3. The data processing device of claim 2, wherein the prediction unit inputs into the learning model the monthly cash balances of the target business for the past year up to a base month and amounts corresponding to one or more account items for the month prior to the base month, and obtains the future monthly cash balances output from the learning model as predicted cash balances for the target business for multiple future months.

4. The data set includes statistical information on the cash balance for each of the plurality of months, The data processing device according to claim 2 , wherein the learning model generation unit generates the learning model using statistical information on the cash balance for a plurality of past months as an explanatory variable.

5. The data set includes, for each of the multiple months, amounts corresponding to one or more account items, such as capital, advance payments, accounts receivable, long-term borrowings, interest received, sales, end-of-period inventory, profits on sales of securities, accounts receivable, and miscellaneous income, 5. The data processing device of claim 4, wherein the learning model generation unit generates the learning model using at least one of capital, advance payments, accounts receivable, long-term borrowings, interest received, sales, end-of-period inventory, profits on sales of securities, accounts receivable, and miscellaneous income as explanatory variables.

6. 6. The data processing device according to claim 2, wherein the output control unit controls to output a warning when the predicted cash balance for each of future months of the target business acquired by the prediction unit is less than a predetermined threshold value.

7. 6. The data processing device according to claim 2, wherein the output control unit controls to output a warning when the balance after applying the corresponding monthly accounts receivable and accounts payable to each of the future multiple monthly projected cash balances of the target business acquired by the prediction unit is less than a predetermined threshold.

8. A data processing device as described in any one of claims 2 to 5, wherein the output control unit controls to output a reference trend, which is the trend of the predicted cash balance for each of multiple future months of the target business acquired by the prediction unit, a large balance trend in which the cash balance for the multiple months is larger than the reference trend, and a small balance trend in which the cash balance for the multiple months is smaller than the reference trend.

9. 1. A computer-implemented data processing method, comprising: A determination step of determining the cash balance of each month of the business operator since the beginning of the fiscal year by adding the business operator's monthly income and expenditure to the business operator's past beginning balance; a data storage step of storing a data set in a data storage unit, the data set including the cash balances for each of the multiple months identified in the identification step and amounts corresponding to one or more account items for each of the multiple months; a learning model generation step of performing supervised learning using as training data a plurality of monthly cash balances in the future for a reference month among the plurality of monthly cash balances included in the data set, a plurality of monthly cash balances in the past from the reference month among the plurality of monthly cash balances included in the data set, and amounts corresponding to one or more account items in the month preceding the reference month among the plurality of monthly cash balances included in the data set, to generate a learning model having at least the plurality of monthly cash balances in the past from the reference month and amounts corresponding to one or more account items in the month preceding the reference month as explanatory variables and the plurality of monthly cash balances in the future as objective variables; A data processing method comprising:

10. On the computer, A determination step of determining the cash balance of each month of the business operator since the beginning of the fiscal year by adding the business operator's monthly income and expenditure to the business operator's past beginning balance; a data storage step of storing a data set in a data storage unit, the data set including the cash balances for each of the multiple months identified in the identification step and amounts corresponding to one or more account items for each of the multiple months; a learning model generation step of performing supervised learning using as training data a plurality of monthly cash balances in the future for a reference month among the plurality of monthly cash balances included in the data set, a plurality of monthly cash balances in the past from the reference month among the plurality of monthly cash balances included in the data set, and amounts corresponding to one or more account items in the month preceding the reference month among the plurality of monthly cash balances included in the data set, to generate a learning model having at least the plurality of monthly cash balances in the past from the reference month and amounts corresponding to one or more account items in the month preceding the reference month as explanatory variables and the plurality of monthly cash balances in the future as objective variables; A program for executing the above.

Images