JP6856908B1 - Watching support method, information processing device, watching support system and computer program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a monitoring support method, an information processing device, a monitoring support system and a computer program which can be expected to balance the monitoring of a target person's financial transaction and the protection of the target person's privacy. A monitoring support method according to the present embodiment is a monitoring support method that supports a user to monitor a target person's monetary transaction, and an information processing device provides transaction information related to the target person's monetary transaction. , The normality of the monetary transaction of the target person is calculated based on the transaction information acquired from the server device that manages the account of the target person, and based on the acquired transaction information, the target person The presence or absence of an abnormality related to money transactions is determined, and when it is determined that there is no abnormality, the calculated normality is displayed on the user terminal device, and when it is determined that there is an abnormality, the calculated normality and the abnormality are determined. The transaction information related to the determined monetary transaction is displayed on the user terminal device. [Selection diagram] FIG. 7

Description

The present invention relates to a watching support method, an information processing device, a watching support system, and a computer program that support a user to watch over a subject's financial transactions.

Transfer fraud that tricks the other party by telephone, letter, e-mail, etc. and demands the transfer of money has become a social problem. In addition, with the aging of society, inappropriate monetary transactions due to dementia and the like are regarded as a problem. In order to protect the elderly and the like from such fraudulent damage or fraudulent transactions, a service that supports the family to watch over the account transactions of the elderly and the like has been proposed.

In Patent Document 1, when a withdrawal request is made by the account holder, the call is made to the licensor's telephone number to have the licensor talk directly with the account holder, and the conversation between the account holder and the licensor ends. Later, a withdrawal permission system was proposed in which the withdrawal was executed based on the permission of the licensor.

Japanese Unexamined Patent Publication No. 2012-185734

By disclosing information to family members in order to watch over account transactions, there is a problem that the privacy of the elderly and the like who are the targets of watching over is impaired. In the withdrawal permission system described in Patent Document 1, since the permission of the licensor is always required for the account holder to withdraw money, the privacy of the account holder cannot be protected.

The present invention has been made in view of such circumstances, and an object of the present invention is a monitoring support method and information processing that can be expected to achieve both monitoring of the subject's financial transactions and protection of the subject's privacy. The purpose is to provide equipment, watching support systems and computer programs.

The monitoring support method according to the embodiment is a monitoring support method that supports the user to monitor the monetary transaction of the target person, and the information processing device provides the transaction information related to the monetary transaction of the target person to the target person. The normality of the target person's monetary transaction is calculated based on the acquired transaction information acquired from the server device that manages the account, and the abnormality related to the target person's monetary transaction is calculated based on the acquired transaction information. When it is determined that there is no abnormality, the calculated normality is displayed on the user terminal device, and when it is determined that there is an abnormality, the calculated normality and the monetary transaction determined to be abnormal are displayed. The transaction information is displayed on the user terminal device, and the calculated time-series change in normality is displayed on the user terminal device .

In the case of one embodiment, it can be expected that both the monitoring of the target person's financial transactions and the protection of the target person's privacy are compatible.

It is a schematic diagram for demonstrating the outline of the monitoring support system which concerns on this Embodiment. It is a block diagram which shows the structure of the monitoring server device which concerns on this Embodiment. It is a schematic diagram for demonstrating one configuration example of a normality calculation model. It is a schematic diagram for demonstrating one configuration example of an abnormality determination model. It is a schematic diagram for demonstrating one configuration example of a watching DB. It is a block diagram which shows the structure of the user terminal apparatus which concerns on this embodiment. It is a flowchart which shows the procedure of the monitoring support processing performed by the monitoring server device which concerns on this embodiment. It is a flowchart which shows the procedure of the monitoring support processing performed by the monitoring server device which concerns on this embodiment. It is a flowchart which shows the procedure of the push notification processing performed by the user terminal apparatus which concerns on this embodiment. It is a schematic diagram which shows an example of the push notification by a user terminal device. It is a flowchart which shows the procedure of the watching support processing performed by the user terminal apparatus which concerns on this Embodiment. It is a schematic diagram which shows an example of a watching screen. It is a schematic diagram which shows an example of a watching screen. It is a schematic diagram which shows an example of a watching screen.

A specific example of the monitoring support system according to the embodiment of the present invention will be described below with reference to the drawings. It should be noted that the present invention is not limited to these examples, and is indicated by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

<System overview>
FIG. 1 is a schematic diagram for explaining the outline of the monitoring support system according to the present embodiment. The watching support system according to the present embodiment is a system that supports a user such as a family member or a guardian to watch over a monetary transaction by a person to be watched, such as an elderly person or a minor. Hereinafter, the person to be watched over may be simply referred to as the person to be watched. There are various types of monetary transactions for the person being watched over, such as withdrawal of deposits from a bank account, transfer to another person, purchase of goods, use of a credit card, debt contract, sale of goods, futures trading and margin trading. Transactions can be included. The relationship between the person to be watched and the user who watches over the guardian is not limited to, for example, the family relationship between the parent and his / her child, and the child and his / her relative, and may include various relationships such as a guardian and a guardian. In the present embodiment, the user is a person who watches over the monetary transaction of the target person, and the target person is a person who watches over the monetary transaction of the target person.

The monitoring support system according to the present embodiment includes a monitoring server device 1 and a user terminal device 3 used by the user. The monitoring server device 1 periodically acquires transaction information related to the monetary transaction of the monitoring target person from the financial server device 5 based on the account information of the monitoring target person registered in advance, and the normality and abnormality of the monetary transaction. Performs processing to determine the presence or absence of. When the monitoring server device 1 determines that there is an abnormality in the monetary transaction of the target person, the monitoring server device 1 notifies the user terminal device 3 used by the user who watches over the target person of the abnormality. The user who has been notified of the abnormality can take various measures such as contacting the person to be watched over, applying for suspension or cancellation of the abnormal transaction, and consulting with an expert.

Although only one financial server device 5 is shown in FIG. 1, various devices may be included in the financial server device 5. For example, the financial server device 5 may include a server device managed and operated by a bank, a securities company, a credit card company, a consumer finance company, or the like whose watch target person has an account or ID. Further, for example, the financial server device 5 may include a server device that manages buying and selling by virtual currency, electronic money, cashless payment, or the like. The financial server device 5 is not limited to the above-mentioned device, and may be any device as long as it stores or manages information related to the financial transaction of the person to be watched over.

The financial server device 5 stores information about the account of the person to be watched over. The information stored in the financial server device 5 includes biographical information such as the name, address, contact information, financial institution name, branch name, account type and account number of the target person, as well as the account balance, transaction amount, and transaction type (for example). (Deposit, withdrawal, transfer or transfer, etc.), transaction date and time, and transaction information such as trading partners are included. The financial server device 5 transmits transaction information of the designated target person in response to a request for information provision from the monitoring server device 1 that specifies the name and account number of the target person.

As the user terminal device 3, various information processing devices such as a smartphone, a tablet terminal device, or a personal computer can be used. For example, the user can use this smartphone as the user terminal device 3 of the monitoring support system according to the present embodiment by installing the application program for the monitoring support system according to the present embodiment on his / her own smartphone.

The monitoring server device 1 is a server device operated by a company, an organization, or the like that provides the monitoring support system according to the present embodiment. The watching server device 1 includes identification information for identifying the person to be watched, one or more account information possessed by the target person, and identification information for identifying the user who watches over the target person or the user terminal device 3 used by this user. It has a database that stores information in association with each other. The monitoring server device 1 acquires transaction information from the financial server device 5 for the monitoring target person registered in advance in this database, calculates the normality of the monetary transaction, determines the presence or absence of an abnormality, and the like.

In the present embodiment, the monitoring server device 1 includes a learned normality calculation model that has been machine-learned in advance, and calculates the normality of monetary transactions of the monitoring target person using this normality calculation model. The normality calculation model accepts, for example, time-series transaction information including the latest transaction information over a predetermined period or a predetermined number of times as input, and outputs a numerical value from 0 to 1 as normality for each received transaction information. To do. As the normality calculation model, a general-purpose trained model common to a plurality of subjects may be used, and a trained model dedicated to the subjects who have been trained or relearned for each subject is used. You may.

Further, the monitoring server device 1 according to the present embodiment includes a learned abnormality determination model that has been machine-learned in advance, and uses this abnormality determination model to determine whether or not there is an abnormality related to the monetary transaction of the person to be monitored. .. The abnormality judgment model accepts, for example, time-series transaction information including the latest transaction information over a predetermined period or a predetermined number of times as input, and determines whether or not there is an abnormality in each received transaction information from 0 to 1. It is output as a numerical value of, and the classification result of the type of abnormality is output. As the abnormality determination model, a general-purpose trained model common to a plurality of subjects may be used, and a trained model dedicated to the subjects who have been trained or relearned for each subject is used. May be good. Further, the abnormality determination model may be prepared for each type of abnormality.

As the type of abnormality output by the abnormality determination model, for example, a type such as high-frequency trading, high-value trading, after-hours trading, sudden trading, or suspicious person trading can be adopted. High-frequency trading is an abnormal type that indicates that the trading frequency is (abnormally) higher than the trading frequency so far. High-value transactions are an anomalous type that indicates that the transaction amount is (abnormally) high compared to the amount of transactions so far. After-hours trading is an abnormal type indicating that the target person has made a transaction during a time zone (for example, midnight or early morning) in which the transaction has not been performed so far. A sudden transaction is an abnormal type indicating that the target person has performed an aperiodic transaction different from a periodic transaction such as monthly or weekly. The suspicious person transaction is, for example, an abnormal type indicating that the trading partner is a partner registered on the blacklist or a partner not registered on the white list. The abnormal type is not limited to the above.

The monitoring server device 1 according to the present embodiment provides information on the monetary transaction of the target person to the user terminal device 3 of the user who watches over the target person. However, when the monitoring server device 1 determines that there is no abnormality in the monetary transaction of the person to be watched, the monitoring server device 1 transmits the normality calculated for the monetary transaction to the user terminal device 3, and the user terminal device 3 responds accordingly. Shows the normality of monetary transactions and their changes over time. At this time, the monitoring server device 1 does not transmit individual transaction information regarding the monetary transaction performed by the target person, that is, detailed information such as the amount of money and the trading partner regarding each transaction. As a result, the user can know the normality of a normal monetary transaction, but cannot know the individual transaction information, and can realize the privacy protection of the person to be watched over.

On the other hand, when it is determined that there is an abnormality in the monetary transaction of the person to be watched over, the watching server device 1 transmits the transaction information regarding the monetary transaction determined to be abnormal in addition to the normality of the monetary transaction to the user terminal device 3. To do. The user terminal device 3 displays the amount of money and transaction information of the trading partner and the like for the monetary transaction determined by the monitoring server device 1 to be abnormal, and notifies the user.

<Device configuration>
FIG. 2 is a block diagram showing a configuration of the monitoring server device 1 according to the present embodiment. The monitoring server device 1 according to the present embodiment includes a processing unit 11, a storage unit (storage) 12, a communication unit (transceiver) 13, and the like. In the present embodiment, it is assumed that the processing is performed by one server device, but a plurality of server devices may be distributed to perform the processing.

The processing unit 11 uses an arithmetic processing unit such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit) or a GPU (Graphics Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), or the like. It is composed of. The processing unit 11 reads and executes the server program 12a stored in the storage unit 12, thereby determining an abnormality related to the monetary transaction of the person to be watched, a process of notifying the user of the abnormality related to the monetary transaction, and the like. Perform various processes.

The storage unit 12 is configured by using a large-capacity storage device such as a hard disk. The storage unit 12 stores various programs executed by the processing unit 11 and various data required for processing by the processing unit 11. In the present embodiment, the storage unit 12 stores the server program 12a executed by the processing unit 11 and the learned normality calculation model 12b and the abnormality determination model 12c that have been machine-learned in advance. Further, the storage unit 12 is provided with a monitoring DB (database) 12d for storing information about the monitoring target person.

In the present embodiment, the server program 12a is provided in a mode of being recorded on a recording medium 99 such as a memory card or an optical disk, and the monitoring server device 1 reads the server program 12a from the recording medium 99 and stores it in the storage unit 12. However, the server program 12a may be written to the storage unit 12 at the manufacturing stage of the monitoring server device 1, for example. Further, for example, the server program 12a may be acquired by the server device 1 by communication while watching what is distributed by another remote server device or the like. For example, in the server program 12a, the writing device may read out what is recorded on the recording medium 99 and write it in the storage unit 12 of the monitoring server device 1. The server program 12a may be provided in the form of distribution via the network, or may be provided in the form of being recorded on the recording medium 99.

The monitoring server device 1 according to the present embodiment utilizes so-called artificial intelligence to perform processing such as calculation of normality and determination of abnormality regarding monetary transactions of the monitoring target person, and the normality used for these processing. It has a calculation model 12b and an abnormality determination model 12c. The normality calculation model 12b and the abnormality determination model 12c are learned learning models that have been machine-learned in advance, and for example, a learning model such as a neural network or SVM (Support Vector Machine) can be adopted. In the present embodiment, the normality calculation model 12b and the abnormality determination model 12c are subjected to learning and relearning processing by the monitoring server device 1. However, the learning and relearning processes of the normality calculation model 12b and the abnormality determination model 12c may be performed by another device. In this case, the normality calculation model 12b and the abnormality determination model 12c are combined with the server program 12a, for example. It may be provided via the recording medium 99, or may be distributed by, for example, another server device or the like separately from the server program 12a, and may be provided in any form.

FIG. 3 is a schematic diagram for explaining a configuration example of the normality calculation model 12b. The illustrated normality calculation model 12b has the structure of a neural network in which a plurality of neurons are interconnected. Since it is an existing technique, detailed description thereof will be omitted, but a neuron is an element that performs an operation on a plurality of inputs and outputs one value as an operation result. Neurons have information such as weighting coefficients and thresholds used in calculations. The normality calculation model 12b of the neural network aggregates the calculation results of the input layer that accepts the input of one or more data, the intermediate layer that performs arithmetic processing on the data received by the input layer, and the intermediate layer. It is provided with an output layer that outputs one or more values.

The normality calculation model 12b according to the present embodiment accepts time-series transaction information related to the monetary transaction of the person to be watched as input. In the illustrated example, the transaction information for N times from the transaction information 1 to the transaction information N is input to the normality calculation model 12b. Of these, transaction information 1 is the oldest transaction information, and transaction information N is the newest transaction information. Each transaction information includes information such as the amount of money, the balance, the transaction type, the date and time, and the trading partner related to the transaction. The normality calculation model 12b is configured to output N normalities related to monetary transactions related to each transaction information as numerical information of 0.00 to 1.00, respectively, in response to input of transaction information for N times. , The learning process is done in advance. In the present embodiment, the degree of normality indicates that the larger the value, the more normal the monetary transaction.

The learning process of the learning model is a process of setting appropriate values for the coefficients and thresholds of each neuron constituting the neural network by using a large number of learning data (teacher data) given in advance. The normality calculation model 12b according to the present embodiment includes, for example, past time-series transaction information and normality (numerical value 1 for normal transactions, numerical value 0 for abnormal transactions) related to this transaction information. Learning is performed by a method such as a gradient descent method, a stochastic gradient descent method, or an error backpropagation method, using the teacher data associated with the above.

FIG. 4 is a schematic diagram for explaining a configuration example of the abnormality determination model 12c. The illustrated abnormality determination model 12c has a neural network structure and includes an input layer, an intermediate layer, and an output layer. The abnormality determination model 12c accepts time-series transaction information for M times from transaction information 1 to transaction information M as input. Further, the abnormality determination model 12c outputs the degree of abnormality related to the monetary transaction related to each transaction information as numerical information of 0.00 to 1.00 in response to the input of the transaction information for M times, and also outputs the abnormality degree to each transaction information. It is configured to output the result of classifying the abnormal type into L types from the abnormal type 1 to the abnormal type L, and the learning process is performed in advance. That is, the abnormality determination model 12c outputs M numerical values of the degree of abnormality and M × L numerical values of the abnormal type in response to the input of M transaction information. In the present embodiment, the degree of abnormality indicates that the larger the value, the more abnormal the monetary transaction. Further, the abnormality types 1 to L output by the abnormality determination model 12c are numerical information of 0.00 to 1.00, respectively, and the type for which the largest numerical value is output is the classification result of the abnormality type of the monetary transaction. ..

Further, the abnormality determination model 12c according to the present embodiment includes, for example, past time-series transaction information, an abnormality degree related to this transaction information (numerical value 1 for abnormal transactions, numerical value 0 for normal transactions), and the like. Learning is performed using the teacher data associated with the classification result of the abnormal type (numerical value 1 for the abnormal type corresponding to the classification result and numerical value 0 for the other abnormal types).

In the storage unit 12 of the monitoring server device 1, information such as the network configuration of the learning model and the values such as the coefficient and the threshold value of each neuron is stored as the normality calculation model 12b and the abnormality determination model 12c, respectively. .. The configuration of the normality calculation model 12b shown in FIG. 3 and the configuration of the abnormality determination model 12c shown in FIG. 4 are examples, and are not limited thereto. The normality calculation model 12b and the abnormality determination model 12c may be learning models such as RNN (Recurrent Neural Network) or CNN (Convolutional Neural Network). Further, the normality calculation model 12b and the abnormality determination model 12c do not have to be the learning model of the neural network, and may be, for example, the learning model of the SVM.

FIG. 5 is a schematic diagram for explaining a configuration example of the watching DB 12d. In the monitoring DB 12d according to the present embodiment, for example, "account information" and "user information" are stored in association with the "target person ID". The "target person ID" is identification information uniquely attached to the target person to be watched over. The "account information" is information about the account of the financial institution held by the person to be watched over, and includes, for example, information such as "financial institution information" and "account number". "Financial institution information" is information for identifying an institution that manages the account of a person to be watched over, and is configured to include, for example, information such as a financial institution name and a branch name. The "account number" is an identification number uniquely assigned to the account of the person to be watched over. The "user information" is information about a user who watches over the target person, and is information for specifying a destination such as an abnormality notification. The "user information" includes, for example, information such as a "user ID" and a "terminal ID". The "user ID" is identification information uniquely assigned to the user. The "terminal ID" is identification information uniquely attached to the user terminal device 3 owned by the user. It should be noted that such information is stored in the monitoring DB 12d by being registered by the user at the start of using the service of the monitoring support system according to the present embodiment.

In the illustrated example, the "target person A" of the watch target person has an account of the account number "0123" of the "financial institution X" and an account of the account number "4567" of the "financial institution Y", and this target It is stored in the watching DB 12d that the notification or the like regarding the person is transmitted to the "terminal i" of the "user a". In addition, the "target person B" of the watch target person has an account of the account number "8901" of the "financial institution Z", and sends a notification or the like regarding the target person to the "terminal j" of the "user b". Is stored in the watching DB12d. The monitoring server device 1 acquires the transaction information of the account shown in the account information from the financial server device 5 for the monitoring target person registered in the monitoring DB 12d, performs processing such as normality calculation and abnormality determination, and processes the processing result. Send to the destination shown in the user information.

In the illustrated example, 1 "user information" is associated with 1 "target person ID", but a plurality of "user information" is associated with 1 "target person ID". May be done. As a result, the monetary transaction of one target person can be watched by a plurality of users. Further, in the illustrated example, 1 "user information" is associated with 1 "account information", but a plurality of "user information" is associated with 1 "account information". May be good. As a result, the monetary transaction of one account can be watched by a plurality of users.

The communication unit 13 communicates with various devices via a network N including a mobile phone communication network and the Internet. In the present embodiment, the communication unit 13 communicates with the user terminal device 3 and the financial server device 5 via the network N. The communication unit 13 transmits the data given by the processing unit 11 to another device, and gives the data received from the other device to the processing unit 11.

The storage unit 12 may be an external storage device connected to the watching server device 1. Further, the monitoring server device 1 may be a multi-computer including a plurality of computers, or may be a virtual machine virtually constructed by software. Further, the monitoring server device 1 is not limited to the above configuration, and may include, for example, a reading unit that reads information stored in a portable storage medium, an input unit that accepts operation input, a display unit that displays an image, and the like. Good.

Further, in the processing unit 11 of the monitoring server device 1 according to the present embodiment, the processing unit 11 reads out and executes the server program 12a stored in the storage unit 12, thereby causing the transaction information acquisition unit 11a and the normality calculation unit. 11b, the abnormality determination unit 11c, the learning processing unit 11d, and the like are realized in the processing unit 11 as software-like functional units.

The transaction information acquisition unit 11a performs a process of acquiring transaction information of the person to be watched from the financial server device 5. The transaction information acquisition unit 11a repeatedly acquires transaction information from the financial server device 5 for each account of each target person registered in the monitoring DB 12d at a predetermined cycle such as one hour or one day, and acquires the acquired transaction information. It is temporarily stored in the storage unit 12.

The normality calculation unit 11b performs a process of calculating the normality of the monetary transaction of the person to be watched over. The normality calculation unit 11b reads out time-series transaction information acquired by the transaction information acquisition unit 11a and stored in the storage unit 12 for a predetermined number of times or for a predetermined period, and inputs the transaction information into the normality calculation model 12b. The normality calculation unit 11b can calculate the normality of the monetary transaction of the watched person by acquiring the normality output by the normality calculation model 12b in response to the input of the transaction information.

The abnormality determination unit 11c determines whether or not there is an abnormality related to the monetary transaction of the person to be watched over, and also performs a process of determining the type of abnormality. The abnormality determination unit 11c reads out the time-series transaction information acquired by the transaction information acquisition unit 11a and stored in the storage unit 12 for a predetermined number of times or for a predetermined period, and inputs the transaction information to the abnormality determination model 12c. The abnormality determination unit 11c determines that an abnormality has occurred in the monetary transaction when the degree of abnormality output by the abnormality determination model 12c exceeds a threshold value (for example, 0.5) in response to the input of transaction information. Further, the abnormality determination unit 11c determines the abnormality level by using a plurality of threshold values with respect to the abnormality degree output by the abnormality determination model 12c. For example, when the degree of abnormality exceeds the first threshold value of 0.5 and does not exceed the second threshold value of 0.7, the abnormality determination unit 11c sets the abnormality level as the warning level. Further, for example, when the degree of abnormality exceeds 0.7, which is the second threshold value, the abnormality determination unit 11c sets the abnormality level as the emergency level. Further, the abnormality determination unit 11c determines the type of abnormality by acquiring and comparing the numerical values for each abnormality type output by the abnormality determination model 12c. For example, the abnormality determination unit 11c can determine which one has the largest numerical value according to the abnormality type, and can use this as the abnormality type.

The learning processing unit 11d performs machine learning processing on the normality calculation model 12b and the abnormality determination model 12c. The learning processing unit 11d performs machine learning of the learning model using, for example, teacher data in which time-series transaction information and information such as normality or abnormality are associated with each other, so that the normality calculation model 12b And the abnormality determination model 12c is generated. As the teacher data used for the learning process, at least in the first learning process, data created in advance by the designer or administrator of the monitoring support system based on the past transaction information stored in the financial server device 5, for example, is used. Be done. In the second and subsequent learning processes (re-learning processes), the learning process unit 11d creates teacher data using the data accumulated along with the operation of the monitoring support system, and the normality calculation model 12b and the abnormality determination model 12c. May be relearned.

As the normality calculation model 12b and the abnormality determination model 12c, a common learning model may be used for a plurality of watching targets, or an individual learning model may be used for each watching target. When an individual learning model is used for each watch target person, the learning processing unit 11d performs the learning process using the teacher data created based on the transaction information about the watch target person. The learning processing unit 11d performs the first learning process using the teacher data created based on the unspecified number of transaction information, and uses the teacher data created based on the transaction information related to the specific watch target person 2 The learning process after the first time may be performed.

FIG. 6 is a block diagram showing the configuration of the user terminal device 3 according to the present embodiment. The user terminal device 3 according to the present embodiment includes a processing unit 31, a storage unit (storage) 32, a communication unit (transceiver) 33, a display unit (display) 34, an operation unit 35, and the like. The user terminal device 3 is a device used by a user such as a family member or a guardian who watches over the target person, and may be configured by using an information processing device such as a smartphone, a tablet terminal device, or a personal computer.

The processing unit 31 is configured by using an arithmetic processing unit such as a CPU or MPU, a ROM, and the like. The processing unit 31 reads and executes the program 32a stored in the storage unit 32 to display the information transmitted from the monitoring server device 1 to the user, and the user's operation on the displayed information. Performs various processes such as accepting processes.

The storage unit 32 is configured by using a non-volatile memory element such as a flash memory. The storage unit 32 stores various programs executed by the processing unit 31 and various data required for processing by the processing unit 31. In the present embodiment, the storage unit 32 stores the program 32a executed by the processing unit 31. In the present embodiment, the program 32a is distributed by a remote server device or the like, which is acquired by the user terminal device 3 by communication and stored in the storage unit 32. However, the program 32a may be written in the storage unit 32, for example, at the manufacturing stage of the user terminal device 3. For example, in the program 32a, the user terminal device 3 may read the program 32a recorded on the recording medium 98 such as a memory card or an optical disk and store it in the storage unit 32. For example, in the program 32a, the writing device may read what was recorded on the recording medium 98 and write it in the storage unit 32 of the user terminal device 3. The program 32a may be provided in a mode of distribution via a network, or may be provided in a mode recorded on a recording medium 98.

The communication unit 33 communicates with various devices via a network N including a mobile phone communication network and the Internet. In the present embodiment, the communication unit 33 communicates with the monitoring server device 1 via the network N. The communication unit 33 transmits the data given by the processing unit 31 to another device, and gives the data received from the other device to the processing unit 31.

The display unit 34 is configured by using a liquid crystal display or the like, and displays various images, characters, and the like based on the processing of the processing unit 31.

The operation unit 35 accepts the user's operation and notifies the processing unit 31 of the accepted operation. For example, the operation unit 35 accepts a user's operation by an input device such as a mechanical button or a touch panel provided on the surface of the display unit 34. Further, for example, the operation unit 35 may be an input device such as a mouse and a keyboard, and these input devices may be configured to be removable with respect to the user terminal device 3.

Further, in the user terminal device 3 according to the present embodiment, the processing unit 31 reads and executes the program 32a stored in the storage unit 32, so that the push notification unit 31a, the display processing unit 31b, the communication operation receiving unit 31c, and the communication operation receiving unit 31c are executed. The correction operation receiving unit 31d and the like are realized in the processing unit 31 as a software-like functional unit. The program 32a may be a program dedicated to the monitoring support system according to the present embodiment, or may be a general-purpose program such as an Internet browser or a web browser.

When the push notification unit 31a receives a determination result from the monitoring server device 1 that there is an abnormality in the monetary transaction of the monitoring target person, the push notification unit 31a performs a process of displaying a message notifying the fact on the display unit 34. For example, when the user terminal device 3 is a smartphone, the push notification unit 31a displays a notification message on a basic screen such as a home screen or a lock screen of the smartphone. The push notification unit 31a is not a dedicated information display required screen displayed by a dedicated application program on the monitoring support system, but a home screen or desktop screen in which icons for starting the application program are displayed side by side, and user authentication. A lock screen or login screen that requests information input for the user, a standby screen that displays a specific image when the user does not perform an operation for a certain period of time, or an image by another application program is displayed. Then, a so-called push notification that displays a message for notification is performed.

The display processing unit 31b performs a process of displaying information related to the monetary transaction of the person to be watched over on the display unit 34. The display processing unit 31b performs a process of displaying a dedicated screen on the watching support system. The display processing unit 31b receives information such as a normality calculation result and an abnormality determination result regarding the monetary transaction of the watching target person transmitted from the watching server device 1, and displays based on the received information. For example, the display processing unit 31b displays a graph of the time-series changes in the normality calculated for the monetary transaction of the person to be watched over. Further, for example, the display processing unit 31b displays transaction information related to a monetary transaction determined to be abnormal.

The contact operation reception unit 31c performs a process of accepting an operation for contacting the person to be watched over. When, for example, the monitoring server device 1 determines that there is an abnormality in the monetary transaction of the monitoring target person, and the monitoring server device 1 notifies the user terminal device 3 to that effect, the contact operation reception unit 31c is the monitoring target person. Accepts contact operations. The contact operation reception unit 31c that has received the contact operation contacts the contact information registered in advance by the user by the contact method registered in advance. The contact operation reception unit 31c makes a call to a predetermined telephone number in order to contact the telephone installed at the home of the person to be watched, or the mobile phone or smartphone owned by the person, for example. .. Further, for example, the contact operation reception unit 31c transmits an e-mail to a smartphone or the like owned by the person to be watched, or transmits a message of SNS (Social Networking Service). The method of contacting the person to be watched is not limited to the above, and any method may be adopted.

The correction operation reception unit 31d performs a process of accepting an operation for correcting this determination after the monitoring server device 1 determines that there is an abnormality in the monetary transaction of the monitoring target person and notifies the user to that effect. .. As described above, the user who has been notified of the abnormality can contact the person to be watched over, and can confirm the correctness of the abnormality of the monetary transaction from the conversation with the person to be watched over. When the user can confirm that the monetary transaction determined to be abnormal is actually normal, the user can perform an operation to correct the abnormality determination by the watching server device 1. The correction operation reception unit 31d receives this correction operation and notifies the monitoring server device 1. In response to this notification, the monitoring server device 1 acquires the transaction information input to the abnormality determination model 12c when it determines that the corrected determination result is abnormal, and the monetary transaction is normal with respect to the acquired transaction information. It can be saved as teacher data for re-learning with information indicating that.

<Watching support processing>
FIG. 7 is a flowchart showing a procedure of watching support processing performed by the watching server device 1 according to the present embodiment. The processing unit 11 of the monitoring server device 1 according to the present embodiment performs the monitoring support processing shown in the figure for each target person. The transaction information acquisition unit 11a of the processing unit 11 acquires the transaction information of the monitoring target person from the financial server device 5 at a predetermined cycle, and at the timing when the predetermined cycle elapses from the previous information acquisition and the next information is acquired. It is determined whether or not the result has been reached (step S1). When the timing for acquiring the information has not been reached (S1: NO), the transaction information acquisition unit 11a waits until the timing for acquiring the information is reached.

When the information acquisition timing is reached (S1: YES), the transaction information acquisition unit 11a is a financial server that manages the target person's account based on the account information of the monitoring target person registered in the monitoring DB 12d of the storage unit 12. It communicates with the device 5 and acquires the transaction information of the watched person from the financial server device 5 (step S2).

The abnormality determination unit 11c of the processing unit 11 stores the time-series transaction information including the transaction information acquired in step S2 and the transaction information acquired before that and stored in the storage unit 12 as an abnormality of the storage unit 12. Input to the determination model 12c, and acquire the degree of abnormality output by the abnormality determination model 12c in response to this input. The abnormality determination unit 11c determines whether or not there is an abnormality related to the monetary transaction of the person to be watched based on the degree of abnormality acquired from the abnormality determination model 12c (step S3). If there is no abnormality (S3: NO), the processing unit 11 returns the processing to step S1.

When there is an abnormality (S3: YES), the processing unit 11 determines that the abnormality is an abnormality notification including information such as an abnormality level based on the abnormality degree output by the abnormality determination model 12c and an abnormality type classified by the abnormality determination model 12c. The transaction information related to the money transaction is transmitted to the user terminal device 3 (step S4), and the process is returned to step S1.

FIG. 8 is a flowchart showing a procedure of watching support processing performed by the watching server device 1 according to the present embodiment. The processing unit 11 of the monitoring server device 1 according to the present embodiment determines whether or not a request for acquisition of information regarding the monitoring target person has been received from the user terminal device 3 (step S11). If the acquisition request has not been received (S11: NO), the processing unit 11 waits until the acquisition request is received.

When the acquisition request is received (S11: YES), the transaction information acquisition unit 11a of the processing unit 11 communicates with the financial server device 5 that manages the account of the watched person related to the acquisition request, and the financial server device 5 performs communication with the financial server device 5. Acquire the transaction information of the person to be watched (step S12). The normality calculation unit 11b of the processing unit 11 stores the time-series transaction information including the transaction information acquired in step S12 and the transaction information acquired before that and stored in the storage unit 12 in the storage unit 12. By inputting to the normality calculation model 12b and acquiring the normality output by the normality calculation model 12b in response to this input, the normality related to the monetary transaction of the watched person is calculated (step S13). The processing unit 11 transmits the normality calculated in step S13 to the requesting user terminal device 3 (step S14).

Next, the abnormality determination unit 11c of the processing unit 11 stores the time-series transaction information including the transaction information acquired in step S12 and the transaction information acquired before that and stored in the storage unit 12 in the storage unit 12. Input to the abnormality determination model 12c, and acquire the abnormality degree and abnormality type output by the abnormality determination model 12c in response to this input (step S15). The abnormality determination unit 11c determines whether or not there is an abnormality in the monetary transaction of the person to be watched based on the degree of abnormality acquired in step S15 (step S16). If there is no abnormality (S16: NO), the processing unit 11 returns the processing to step S11. When there is an abnormality (S16: YES), information such as the abnormality type acquired in step S15 and the transaction information acquired in step S12 is transmitted to the requesting user terminal device 3 (step S17), and the step The process is returned to S11.

In the present embodiment, if there is no abnormality in the monetary transaction of the watching target person, the watching server device 1 does not send the transaction information of the watching target person to the user terminal device 3, thereby realizing the privacy protection of the watching target person. doing. However, if there is no abnormality in the monetary transaction of the watch target person, the watch server device 1 may transmit the transaction information of the watch target person to the user terminal device 3. In this case, the monitoring server device 1 attaches information such as a flag indicating that the monetary transaction is normal (no abnormality) to the transaction information and transmits the information to the user terminal device 3. If the received transaction information is a normal monetary transaction, the user terminal device 3 can realize the privacy protection of the person to be watched by not displaying the transaction information. Further, for example, the user terminal device 3 determines whether or not there is an abnormality in the monetary transaction based on the transaction information received from the monitoring server device 1, and when it is determined that there is no abnormality, the transaction information is not displayed and it is determined that there is an abnormality. If this is the case, transaction information may be displayed.

FIG. 9 is a flowchart showing a procedure of push notification processing performed by the user terminal device 3 according to the present embodiment. The push notification unit 31a of the processing unit 31 of the user terminal device 3 according to the present embodiment determines whether or not an abnormality notification from the monitoring server device 1 has been received (step S21). When the abnormality notification is not received (S21: NO), the push notification unit 31a waits until the abnormality notification is received. When the abnormality notification is received (S21: YES), the push notification unit 31a performs a so-called push notification in which a message notifying that there is an abnormality in the monetary transaction of the person to be watched is displayed on the display unit 34 (step S22). , Return the process to step S21.

FIG. 10 is a schematic diagram showing an example of push notification by the user terminal device 3. In this example, the user terminal device 3 performs push notification by superimposing and displaying a message on a basic screen such as a standby screen or a lock screen. The illustrated basic screen is a screen displayed when the user is not using the user terminal device 3 (for example, when a predetermined time has elapsed from the last operation), and is, for example, a date, time, etc. on a predetermined background image. It is a simple screen that displays the information of. When the user terminal device 3 according to the present embodiment receives an abnormality notification from the watching server device 1 while displaying this basic screen, the user terminal device 3 displays a window in the center of the basic screen and performs a push notification. ..

In this example, the user terminal device 3 displays "XXX Bank", "9 minutes ago", "Warning", "Mother may see payments that may be abnormal", etc. in the window displayed on the basic screen. Display a warning message. The illustrated message is an example and is not limited to this. The user terminal device 3 can display an appropriate message as a push notification based on the information included in the abnormality notification received from the monitoring server device 1.

FIG. 11 is a flowchart showing a procedure of watching support processing performed by the user terminal device 3 according to the present embodiment. In the user terminal device 3 according to the present embodiment, an application program (program 32a) for the watching support system is started in response to, for example, a tap operation on an icon provided on the home screen. At this time, the processing unit 31 performs activation processing such as securing a storage area and establishing communication (step S31). After the start-up process is completed, the processing unit 31 communicates with the monitoring server device 1 to request the acquisition of information, and acquires the information about the monitoring target person from the monitoring server device 1 (step S32). The information acquired by the user terminal device 3 at this time is normality information for monetary transactions that are not determined to be abnormal, and is determined to be abnormal level, abnormal type, and abnormal for monetary transactions that are determined to be abnormal. Information such as transaction information. The display processing unit 31b of the processing unit 31 displays on the display unit 34 a monitoring screen that displays information on the monetary transaction of the monitoring target person based on the information acquired in step S32 (step S33).

Next, the contact operation reception unit 31c of the processing unit 31 determines whether or not the user has performed the contact operation to the person to be watched by accepting the operation for the contact button or icon provided on the watch screen. (Step S34). When a contact operation is performed (S34: YES), the contact operation reception unit 31c acquires information (for example, a telephone number or an e-mail address) regarding a method of contacting a person to be watched registered in advance (step S35). The contact operation reception unit 31c contacts the person to be watched by the contact method acquired in step S35 (step S36), and returns the process to step S33.

When the communication operation is not performed (S34: NO), the correction operation reception unit 31d of the processing unit 31 receives an operation for a button or icon for correcting the abnormality determination result provided on the monitoring screen, thereby. It is determined whether or not the correction operation has been performed by the user (step S37). If the correction operation has not been performed (S37: NO), the correction operation reception unit 31d returns the process to step S33. When the correction operation is performed (S37: YES), the correction operation reception unit 31d notifies the monitoring server device 1 of the correction (step S38), and returns the process to step S33.

In this flowchart, the user terminal device 3 generates an image to be displayed on the display unit 34 as a watching screen, but the present invention is not limited to this. For example, the watching server device 1 may generate an image to be displayed as a watching screen, and the generated image may be transmitted to the user terminal device 3. The user terminal device 3 displays the image received from the watching server device 1 on the display unit 34. Further, the user terminal device 3 monitors and transmits the information related to the operation such as the contact operation and the correction operation received from the user while the monitoring screen is displayed to the monitoring server device 1. The watching server device 1 receives information on the operation from the user terminal device 3, generates an image for updating the watching screen according to the content of the received operation, and transmits the image to the user terminal device 3. The user terminal device 3 updates the watching screen by receiving the image from the watching server device 1 and displaying it on the display unit 34.

12 to 14 are schematic views showing an example of a watching screen. The watching screen displayed by the user terminal device 3 immediately after the application program for the watching support system is started is, for example, the screen shown in FIG. The watching screen shown in FIG. 12 is provided with a watching target person information display area 101, a tab area 102, a score display area 103, and a transaction information display area 104. The user terminal device 3 displays information such as an image such as a face of the person to be watched, a name, and contact information in the information display area 101 of the person to be watched on the watching screen. The tab area 102 of the watching screen is provided with a tab labeled "report" and a tab labeled "notification", and the user terminal device 3 has one of the tabs. Accept selection from the user. The example shown in FIG. 12 is a watching screen in a state where the "report" tab is selected. The user terminal device 3 displays the title character string of "score transition", the current score "22", and a graph showing the time-series change of the score in a predetermined period in the score display area 103 of the watching screen. .. The "score" corresponds to the normality output by the normality calculation model 12b, and is a value obtained by multiplying the normality output in the range of 0 to 1 by 100. The user terminal device 3 displays in the transaction information display area 104 of the monitoring screen the history of transactions that the monitoring server device 1 has determined to be abnormal among the transactions performed by the monitoring target person during a predetermined period (for example, one month). The transaction information display area 104 does not display the history of transactions determined to be normal.

When the "notification" tab provided in the tab area 102 of the watching screen is selected, the user terminal device 3 switches the display to the watching screen shown in FIG. The watching screen shown in FIG. 13 is provided with a notification display area 105 in place of the score display area 103 and the transaction information display area 104 of the watching screen shown in FIG. The user terminal device 3 displays in the notification display area 105 information about transactions determined to be abnormal by the monitoring server device 1 in chronological order. In the example shown, the message "Warning There were multiple payments that may be abnormal in a short period of time" dated March 2 and the message "There was an urgent large withdrawal" dated October 20. The message "Warning: The frequency of transactions has been higher than usual for the past week" dated November 7 is displayed vertically in chronological order.

Labels such as "warning" and "urgent" at the beginning of each message indicate the abnormal level of the transaction made by the watched person. The monitoring server device 1 determines the abnormality level by comparing the abnormality degree output by the abnormality determination model 12c with a plurality of threshold values, and includes the determined abnormality level in the abnormality notification to the user terminal device 3 and transmits the determined abnormality level. ing. The user terminal device 3 can acquire the abnormality level included in the notification from the watching server device 1 and label each message with a label such as "warning" or "emergency".

Further, the content of each message is determined according to the type of abnormality determined by the monitoring server device 1. The monitoring server device 1 transmits the transaction determined to be abnormal by including the classification result of the abnormality type in the abnormality notification to the user terminal device 3. The user terminal device 3 stores in advance a table or the like associated with the error type and the message to be displayed, acquires the message corresponding to the abnormality type included in the notification from the monitoring server device 1 from the table, and displays the notification. It can be displayed in the area 105.

Further, in the notification display area 105, each message is displayed in a rectangular frame, and the character string "See details" is displayed at the lower right of each rectangular frame. When a touch operation is performed on this character string, the user terminal device 3 displays detailed information of the corresponding transaction. The watching screen shown in FIG. 14 is a case where detailed information regarding the message dated October 20 displayed in the notification display area 105 of the watching screen shown in FIG. 13 is displayed. The watching screen shown in FIG. 14 is provided with a detailed information display area 106 in place of the tab area 102 and the notification display area 105 of the watching screen shown in FIG.

The user terminal device 3 displays detailed information such as a date related to the transaction performed by the person to be watched, a message based on the abnormality level and the abnormality type, and a history of the transaction determined to be abnormal in the detailed information display area 106 of the monitoring screen. To do. Further, the user terminal device 3 may display various information related to this transaction below the detailed information. In this example, the user terminal device 3 has a message "ABCD has contacted us about this transaction" and a message "Please press" No problem "if there is no problem to improve accuracy". And the button 107 labeled "Send" OK? "" And the button 108 labeled "Consult an expert" are displayed.

The button 107 is for accepting an operation of contacting the person to be watched over regarding this transaction determined to be abnormal. The user terminal device 3 accepts a contact operation to the person to be watched by accepting a tap operation or the like for the button 107. When the contact operation is performed, the user terminal device 3 contacts the person to be watched over by the contact method registered in advance. Further, the button 108 is for accepting an operation of contacting an expert on money transactions, for example, a lawyer or a consumer center. When the tap operation or the like for the button 108 is received, the user terminal device 3 contacts a predetermined expert by a predetermined contact method.

The message "ABCD has contacted us about this transaction" displayed on the watching screen shown is that the user terminal device 3 that received the contact operation with the button 107 is to be watched by, for example, e-mail. It is displayed when a message such as a question about this transaction is sent to the person and the answer from the target person is obtained.

Further, the user terminal device 3 displays a button 109 labeled "no problem" together with a message "Please press" no problem "if there is no problem to improve accuracy". The button 109 is for accepting an operation of correcting the determination result of abnormality by the monitoring server device 1. The user terminal device 3 accepts the correction operation of the abnormality determination result by accepting the tap operation for the button 109. The user terminal device 3 that has received the correction operation notifies the monitoring server device 1 of the correction of the abnormality determination result. Upon receiving this notification, the monitoring server device 1 attaches the transaction information input to the abnormality determination model 12c when outputting the corrected determination result and the information indicating that the monetary transaction is normal with respect to this transaction information. Then, it is stored in the storage unit 12. The monitoring server device 1 uses these information stored in the storage unit 12 as teacher data for re-learning. The monitoring server device 1 relearns the normality calculation model 12b and the abnormality determination model 12c, for example, once a month, or when a predetermined number of teacher data are accumulated, for example.

<Modification example related to normality calculation processing>
In the above embodiment, the monitoring server device 1 calculates the normality of the person to be monitored regarding the monetary transaction by using the learned normality calculation model 12b that has been machine-learned in advance. However, the calculation of the normality may be performed by a method that does not use a learning model. The monitoring server device 1 can calculate the normality according to, for example, a predetermined normality calculation rule.

For example, the monitoring server device 1 calculates the number of monetary transactions in a predetermined period (one month, one week, etc.) based on the transaction information of the monitoring target person. The monitoring server device 1 sets the normality to 1 until the calculated number of transactions exceeds the threshold value. When the number of transactions exceeds the threshold value, the monitoring server device 1 lowers the normality by, for example, inversely proportional to the increase in the number of transactions.

Further, for example, the monitoring server device 1 acquires the transaction amount of each monetary transaction based on the transaction information of the monitoring target person, or calculates the total value of the transaction amounts in a predetermined period. The monitoring server device 1 sets the normality to 1 until these transaction amounts exceed the threshold value. When the transaction amount exceeds the threshold value, the monitoring server device 1 lowers the normality by, for example, inversely proportional to the increase in the transaction amount.

Further, for example, the monitoring server device 1 acquires the time when the monitoring target person makes a monetary transaction based on the transaction information of the monitoring target person. For example, the monitoring server device 1 sets the time zone from 8:00 am to 7:00 pm as the time zone for normal transactions, and sets the normality to 1 for transactions performed in this time zone. The monitoring server device 1 sets the normality to 0 for transactions performed outside the normal transaction time zone, or lowers the normality to the extent that the transaction time deviates from this time zone.

Further, for example, the monitoring server device 1 acquires a partner with whom the monitoring target person has made a monetary transaction based on the transaction information of the monitoring target person. The monitoring server device 1 has, for example, a normality of 1 for a trading partner who has a track record of conducting transactions in the past. Further, the monitoring server device 1 has, for example, a white list of reliable trading partners, and when the trading partner of the monitoring target person is registered in the white list, the normality is set to 1. Further, the monitoring server device 1 has, for example, a blacklist of unreliable trading partners, and when the trading partner is registered in the blacklist, the normality is set to 0. When the trading partner is not registered in either the white list or the blacklist and there is no record of having made a transaction in the past, the monitoring server device 1 can set the normality to 0.5, for example.

The above-mentioned normality calculation rule is an example and is not limited to this, and the monitoring server device 1 may calculate the normality by using various normality calculation rules other than these. Further, the normality calculation rule may be a general-purpose rule common to a plurality of target persons, or may be a dedicated rule different for each target person. The monitoring server device 1 calculates a plurality of normalities using a plurality of normality calculation rules, integrates the calculated normalities (for example, calculates an average value), and obtains the final normality. Can be done.

<Modification example related to abnormality judgment processing>
In the above embodiment, the monitoring server device 1 uses a learned abnormality determination model 12c that has been machine-learned in advance to determine whether or not there is an abnormality related to the monetary transaction of the monitoring target person. However, the abnormality determination may be performed by a method that does not use a learning model. The monitoring server device 1 may determine the presence or absence of an abnormality according to, for example, a predetermined abnormality determination rule.

(Modification example 1)
For example, the monitoring server device 1 calculates the normality using the normality calculation model 12b (or according to a predetermined normality calculation rule), and determines the presence or absence of an abnormality by comparing the calculated normality with the threshold value. When the normality is less than the threshold value, the watching server device 1 determines that the monetary transaction of the watching target person is abnormal. Further, the monitoring server device 1 may determine the abnormality level by comparing the normality with a plurality of threshold values. These determination methods are substantially the same as the determination method based on the abnormality degree output by the abnormality determination model 12c described in the above embodiment, and the determination is made by regarding normality = (1-abnormality degree). Equivalent to.

Therefore, the monitoring server device 1 may integrate the normality calculation model 12b and the abnormality determination model 12c into one learning model. The integrated learning model may output either the normality or the anomaly, and the monitoring server device 1 can calculate the other from the output normality or the anomaly if necessary.

(Modification 2)
For example, the monitoring server device 1 can determine the presence or absence of an abnormality based on an abnormality determination rule similar to the normality calculation rule. The monitoring server device 1 acquires or calculates information such as the number of monetary transactions, the amount of money, the time, and the trading partner based on the transaction information of the monitoring target person, and determines the presence or absence of an abnormality based on the information. For example, the monitoring server device 1 can determine that there is an abnormality when the number of monetary transactions exceeds the threshold value. Further, for example, the monitoring server device 1 can determine that there is an abnormality when the amount of money transaction exceeds the threshold value. Further, for example, the monitoring server device 1 can determine that there is an abnormality when the transaction time is not in the normal time zone. Further, the monitoring server device 1 is abnormal when the trading partner is a partner who has no transaction record in the past, the trading partner is not registered in the white list, or the trading partner is registered in the blacklist. It can be determined that there is.

The monitoring server device 1 may determine the presence or absence of an abnormality using a plurality of abnormality determination rules. In this case, if it is determined that there is an abnormality by at least one abnormality determination rule, the final determination result is determined. It can be considered that there is an abnormality. Further, the monitoring server device 1 can determine which type of abnormality is based on which abnormality determination rule determines the abnormality.

<Summary>
The monitoring server device 1 according to the present embodiment having the above configuration acquires transaction information related to the monetary transaction of the monitoring target person from the financial server device 5 that manages the account of the target person, and is based on the acquired transaction information. The normality of financial transactions is calculated, and the presence or absence of abnormalities related to financial transactions is determined. The monitoring server device 1 outputs (transmits) the calculated normality to the user terminal device 3 when it is determined that there is no abnormality, and the user terminal device 3 outputs (displays) the normality related to the monetary transaction accordingly. When the monitoring server device 1 determines that there is an abnormality, it outputs the normality and transaction information to the user terminal device 3 together with the abnormality determination result. The user terminal device 3 that has received such information outputs the normality of the monetary transaction of the person to be watched over and the history of the transaction information determined to be abnormal. As a result, the monitoring support system according to the present embodiment can be expected to balance the monitoring of the monetary transaction of the monitoring target person by the user and the privacy protection of the monitoring target person.

Further, in the monitoring support system according to the present embodiment, when the monitoring server device 1 determines that there is no abnormality in the monetary transaction, the normality is output without outputting the history of the monetary transaction determined to be normal. As a result, the watching support system can prevent the user from viewing the history of the normal monetary transaction of the watching target person, and can realize the privacy protection of the watching target person.

Further, in the monitoring support system according to the present embodiment, the monitoring server device 1 determines the type of abnormality based on the transaction information, and when it is determined that there is an abnormality in the monetary transaction, the abnormality is recorded together with the normality and the transaction history. Outputs the type of. As a result, the user can easily know what kind of abnormality has occurred in the monetary transaction determined to be abnormal.

Further, in the monitoring support system according to the present embodiment, the monitoring server device 1 determines the degree of abnormality (abnormal level) based on the transaction information, and when it is determined that there is an abnormality in the monetary transaction, the normality and the transaction Outputs the degree of abnormality along with the history. This allows the user to determine how urgent the monetary transaction determined to be abnormal is.

Further, in the monitoring support system according to the present embodiment, the time-series normality calculated by the monitoring server device 1 is output to the user terminal device 3, and the user terminal device 3 displays, for example, a graph of changes in the normality over time. Output as. As a result, the user can grasp the change in the success or failure of the monetary transaction of the person to be watched over even when detailed information such as the transaction history cannot be obtained because it is not determined to be abnormal.

Further, in the monitoring support system according to the present embodiment, when the monitoring server device 1 determines that there is an abnormality, the user terminal device 3 is notified by push of the abnormality, and the user terminal device 3 pushes the notification to the user in response to this notification. I do. As a result, when it is determined that there is an abnormality in the monetary transaction, it is possible to promptly notify the user to that effect.

Further, in the monitoring support system according to the present embodiment, after the monitoring server device 1 determines that there is an abnormality and outputs the normality, history, etc., the user communicates with the person to be monitored. Accept. When the communication operation is accepted, the user terminal device 3 (or the watching server device 1) carries out communication between the user and the watching target person. The communication from the user terminal device 3 to the person to be watched may be performed via the watching server device 1 or may be performed without going through the watching server device 1.

Further, in the monitoring support system according to the present embodiment, when the user determines that there is no abnormality in the monetary transaction determined by the monitoring server device 1 as having an abnormality, the user performs a correction operation for correcting the determination result of the abnormality. The terminal device 3 accepts it. In response to the correction operation, the monitoring server device 1 stores the transaction information of the monetary transaction related to the corrected determination result. As a result, the monitoring server device 1 can memorize and store information when the judgment is erroneous, and can relearn the learning model or modify the judgment rule based on this information, and the judgment system. Can be expected to improve.

In the present embodiment, the financial server device 5 and the watching server device 1 are separate devices, and the watching server device 1 acquires transaction information from the financial server device 5, but the present invention is not limited to this. .. For example, the financial server device 5 and the watching server device 1 may be used as one device. In this case, the financial server device 5 may calculate the normality and determine the presence or absence of an abnormality only for the transaction information of the account managed by itself. When a plurality of accounts owned by a person to be watched are dispersed among a plurality of financial institutions, the financial server device 5 of each financial institution may individually calculate the normality and determine the presence or absence of an abnormality. Further, for example, an information processing device such as a smartphone used by the person to be watched may perform processing such as calculation of normality and determination of presence / absence of abnormality, and the processing result may be transmitted to the user terminal device 3.

Further, the user terminal device 3 may perform processing such as calculation of normality based on transaction information and determination of presence / absence of abnormality. In this case, the monitoring server device 1 may acquire transaction information from one or more financial server devices 5 and transmit it to the user terminal device 3, and the user terminal device 3 may directly from one or more financial server devices 5. You may obtain transaction information on the server.

The embodiments disclosed this time should be considered as exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of claims, not the above-mentioned meaning, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1 Watching server device 3 User terminal device 5 Financial server device 11 Processing unit 11a Transaction information acquisition unit 11b Normality calculation unit 11c Abnormality judgment unit 11d Learning processing unit 12 Storage unit 12a Server program 12b Normality calculation model 12c Abnormality judgment model 12d Watching DB
13 Communication unit 31 Processing unit 31a Push notification unit 31b Display processing unit 31c Communication operation reception unit 31d Correction operation reception unit 32 Storage unit 32a Program 33 Communication unit 34 Display unit 35 Operation unit 98,99 Recording medium

Claims (10)

It is a monitoring support method that supports the user to monitor the target person's financial transactions.
Information processing device
The transaction information related to the monetary transaction of the target person is acquired from the server device that manages the account of the target person.
Based on the acquired transaction information, the normality of the monetary transaction of the target person is calculated.
Based on the acquired transaction information, it is determined whether or not there is an abnormality related to the monetary transaction of the target person.
When it is determined that there is no abnormality, the calculated normality is displayed on the user terminal device.
When it is determined that there is an abnormality, the calculated normality and the transaction information related to the monetary transaction determined to be abnormal are displayed on the user terminal device .
Display the calculated time-series change in normality on the user terminal device.
Watching support method. When the information processing device determines that there is no abnormality, the transaction information relating to the monetary transaction determined to be normal is not transmitted to the user terminal device.
The monitoring support method according to claim 1. The information processing device
Based on the acquired transaction information, the type of abnormality related to the monetary transaction of the target person is determined.
When it is determined that there is an abnormality, the user terminal device is displayed with the calculated normality and transaction information related to the monetary transaction determined to be abnormal, as well as the type of the determined abnormality.
The monitoring support method according to claim 1 or 2. The information processing device
Based on the acquired transaction information, the degree of abnormality related to the monetary transaction of the target person is determined.
When it is determined that there is an abnormality, the user terminal device is displayed with the calculated normality and transaction information related to the monetary transaction determined to be abnormal, as well as the degree of the determined abnormality.
The monitoring support method according to any one of claims 1 to 3. When the information processing device determines that there is an abnormality, a push notification is given to the user terminal device.
The monitoring support method according to any one of claims 1 to 4. The information processing device
After determining that there is an abnormality and outputting the normality and the transaction information, the user accepts an operation for communicating with the target person.
When the operation is accepted, communication is performed between the user and the target person.
The monitoring support method according to any one of claims 1 to 5. The information processing device
When the user determines that there is no abnormality in the monetary transaction of the target person based on the result of the communication, the operation for correcting the determination result of the abnormality is accepted.
When the operation is accepted, the information related to the monetary transaction determined by the user to be normal is stored.
The monitoring support method according to claim 6. An information processing device that assists the user in watching over the target person's financial transactions.
An acquisition unit that acquires transaction information related to the target person's monetary transaction from a server device that manages the target person's account.
Based on the acquired transaction information, a calculation unit that calculates the normality of the monetary transaction of the target person, and
Based on the acquired transaction information, a determination unit that determines whether or not there is an abnormality related to the monetary transaction of the target person, and
A processing unit that performs a process of displaying information on a user terminal device used by the user based on the calculation result of the calculation unit and the determination result of the determination unit is provided.
The processing unit
When it is determined that there is no abnormality, the calculated normality is displayed on the user terminal device.
When it is determined that there is an abnormality, the calculated normality and the transaction information related to the monetary transaction determined to be abnormal are displayed on the user terminal device .
Display the calculated time-series change in normality on the user terminal device.
Information processing device. It is a monitoring support system that supports the user to monitor the target person's financial transactions.
Calculation to calculate the normality of the monetary transaction of the target person based on the acquisition unit that acquires the transaction information related to the monetary transaction of the target person from the server device that manages the account of the target person, and the acquired transaction information. Based on the acquired transaction information, the user determines whether or not there is an abnormality related to the monetary transaction of the target person, and the user determines the calculation result of the calculation unit and the determination result of the determination unit. It has a processing unit that performs processing to display information on the user terminal device to be used, and when the processing unit determines that there is no abnormality, the calculated normality is displayed on the user terminal device and it is determined that there is an abnormality. In this case, the calculated normality and the transaction information related to the monetary transaction determined to be abnormal are displayed on the user terminal device, and the time-series change in the calculated normality is displayed on the user terminal device. Watching server device and
A monitoring support system including a terminal device having a display processing unit that performs processing for displaying information on the display unit based on the calculation result by the monitoring server device and the determination result. A computer program that causes a computer to perform processing to assist the user in watching over the target person's financial transactions.
On the computer
The transaction information related to the monetary transaction of the target person is acquired from the server device that manages the account of the target person.
Based on the acquired transaction information, the normality of the monetary transaction of the target person is calculated.
Based on the acquired transaction information, it is determined whether or not there is an abnormality related to the monetary transaction of the target person.
When it is determined that there is no abnormality, the calculated normality is displayed on the user terminal device.
When it is determined that there is an abnormality, the calculated normality and the transaction information related to the monetary transaction determined to be abnormal are displayed on the user terminal device .
A computer program that causes the user terminal device to display a time-series change in the calculated normality.

Images