JP7528352B2 - Authorization Device - Google Patents

Description

The present invention relates to an authorization device that prevents fraudulent use of credit cards and other devices.

Patent document 1 describes how, in order to prevent fraudulent use such as credit card spoofing, the location of a mobile terminal is compared with the location of a store to determine whether or not it meets predetermined conditions, thereby judging whether or not the fraudulent use has occurred.

International Patent Publication No. 2011/040401

However, the technology described in Patent Document 1 is intended to prevent fraudulent use of credit cards in face-to-face interactions at stores, and is not intended to determine fraudulent use of credit cards in non-face-to-face interactions, such as online shopping.

Therefore, in order to solve the above-mentioned problems, the present invention aims to provide an authorization device that can prevent fraud in payment processing using credit cards, etc. for online shopping.

The authorization device of the present invention comprises a mobile terminal information acquisition unit that acquires mobile terminal location information of a user's mobile terminal, a payment terminal information acquisition unit that acquires payment terminal location information of a payment terminal at which the user is performing an operation for payment, and a judgment unit that judges the possibility of fraudulent use of the payment process by the payment terminal based on the mobile terminal location information and the payment terminal location information.

This invention makes it possible to prevent fraudulent use of payment processing such as online shopping.

A diagram showing the system configuration of a communication system including an authorization server 100 in the present disclosure. FIG. 13 is a diagram showing a correspondence table between IP addresses and regions. FIG. 13 is a diagram showing the match level and the probability of fraud. FIG. 13 is a diagram showing a history DB showing history information associated with the presence or absence of fraudulent use regarding a payment. FIG. 13 is a diagram showing a fraudulent use probability DB for providers and regions. FIG. 13 is a diagram showing a nearby area DB. A diagram showing the detailed configuration of the authorization comprehensive judgment unit 104. FIG. 2 is a block diagram showing the functional configuration of a learning device 104x. FIG. 13 is a diagram showing a specific example of a usage history DB 104z. 1 is a flowchart showing the operation of the authorization server 100 of the present disclosure. 13 is a flowchart showing the operation of the authorization comprehensive determination unit 104. A figure showing an example of a hardware configuration of an authorization server 100 relating to one embodiment of the present disclosure.

An embodiment of the present disclosure will be described with reference to the accompanying drawings. Where possible, identical parts are designated by the same reference numerals and duplicated descriptions will be omitted.

Figure 1 is a diagram showing the system configuration of a communication system including an authorization server 100 (hereinafter referred to as authorization server 100) in the present disclosure. As shown in Figure 1, this communication system includes the authorization server 100, a payment affiliated store server 200, a mobile terminal 300, a payment terminal 400, and a customer information database 500.

A user carrying a mobile terminal 300 operates the payment terminal 400. In accordance with the user's operation, the payment terminal 400 accesses the payment affiliated store server 200, which is an online shopping site. At that time, the user notifies the payment affiliated store server 200 of payment information such as a credit card number and performs the product purchase process. At this time, the mobile terminal 300 and the payment terminal 400 are generally in the same location. The authorization server 100 obtains the IP address of the payment terminal 400 from the payment affiliated store server 200.

Meanwhile, the authorization server 100 acquires location information (mobile terminal location information) from the mobile terminal 300. The authorization server 100 converts the IP address into location information (information indicating the area) and compares the location information (hereinafter referred to as payment terminal location information) with the location information acquired from the mobile terminal 300 to determine the validity of the user's location.

That is, the payment terminal location information obtained from the IP address is information indicating the range of the area, while the mobile terminal location information is coordinate information. Therefore, the authorization server 100 judges the validity of the user's location based on whether the payment terminal location information includes the mobile terminal location information. If the user's location is valid, the authorization server 100 judges that the user's use of the credit card is valid, and if the user's location is not valid, the authorization server 100 judges that the user's use of the credit card is invalid. Note that in this disclosure, the judgment of whether or not there has been fraudulent use of a credit card is targeted, but this is not limited to this. The same can be applied to payment processing by QR code, electronic money, bank, or telecommunications carrier. In this case, instead of the card number, the payment identifier of the QR code, the payment identifier of the electronic money, the bank code and its account number, the telecommunications carrier code, the customer number, etc. are treated as payment information.

The authorization server 100 will be described in more detail below with reference to Figure 1. The authorization server 100 includes an authorization control unit 101, a location information conversion unit 102, a judgment unit 103, and an authorization overall judgment unit 104.

The authorization control unit 101 is a part that receives information D1 sent from the payment affiliated store server 200. Information D1 includes the credit card card number, the IP address of the payment terminal, and the payment time. Here, the payment time indicates the time when the payment affiliated store server 200 processed the credit card payment. In addition, it may also be the time when the payment affiliated store server 200 made an authentication request to the authorization server 100 (i.e., the time when information D1 was sent). In addition, as described below, this information D1 may include at least one of information indicating the product or product type that is the subject of payment, the payment affiliated store (or its industry), and the payment amount.

The location information conversion unit 102 is a part that converts the IP address of the payment terminal 400 contained in the information D1 received by the authorization control unit 101 into location information of the payment terminal 400 (payment terminal location information). The method of converting from an IP address to location information is a known technology. For example, the location information conversion unit 102 can prepare a region conversion table 102a in which multiple IP addresses, etc. are classified by region (see FIG. 2), and use it to derive the region from the IP address. FIG. 2 is a diagram showing a specific example. In the figure, each IP address is divided into regions such as countries, prefectures, and cities, towns, and villages, but this is not limited to this. It may be divided into larger regions, or into regions shown in a mesh shape according to a predetermined rule. In addition to this, the Internet service provider (ISP) that issues the IP address may be associated with it. In the disclosure to be described later, it is used when calculating the fraudulent use probability for each ISP.

Then, the location information conversion unit 102 acquires information D2 including the converted payment terminal location information. Information D2 is configured by associating the converted location information with the card number and payment time acquired from information D1.

The judgment unit 103 is a part that acquires the mobile terminal location information of the mobile terminal 300 and the payment terminal location information converted and acquired by the location information conversion unit 102, and judges the level of match (degree of match).

The mobile terminal 300 periodically registers location information in the location information DB 300a. This location information DB 300a is a device operated by a communication carrier that manages a mobile communication network, and manages the mobile terminal location information of the mobile terminal 300. For example, the location information DB 300a stores the location information of the base station that the mobile terminal 300 uses for communication. This base station location information is treated as the mobile terminal location information. As shown in FIG. 1, the location information DB 300a stores information D3. The information D3 includes the terminal identification number of the mobile terminal 300, the mobile terminal location information, and the location acquisition time. The location acquisition time is the time of registration in the location information DB 300a. Note that the mobile terminal location information is not limited to this, and the mobile terminal 300 may register location information based on a positioning function such as GPS, or other location information based on base station positioning in a database such as the location information DB 300a. In addition, the location information is not limited to coordinate information, and may be area information based on the position of the base station.

The customer information DB 500 stores the card number of the credit card used by the user as a payment method and the terminal identification number of the mobile terminal 300. This customer information DB 500 is a database constructed in advance by the credit card company.

The judgment unit 103 uses the card number acquired by the authorization control unit 101 as a key to acquire a terminal identification number from the customer information DB 500, and then uses the terminal identification number as a key to acquire the mobile terminal location information of the mobile terminal 300.

The judgment unit 103 compares the mobile terminal location information thus acquired with the payment terminal location information converted by the location information conversion unit 102 to judge the validity of the use of the credit card that the user is about to use. That is, the judgment unit 103 can judge the validity of the use of the credit card based on the matching level (information indicating the degree of matching) between the mobile terminal location information and the payment terminal location information. For example, it judges whether the mobile terminal location information is included in the area indicated in the payment terminal location information. Then, it may judge the possibility of credit card fraud by judging to what area level (country level, prefecture level, etc.) the information matches. Note that it may also be possible to derive the area in which the mobile terminal 300 and the payment terminal 400 are located, derive the level at which the area is the same, and judge the possibility of credit card fraud accordingly.

The comprehensive authorization judgment unit 104 obtains the judgment result of the judgment unit 103 via the authorization control unit 101, and makes a comprehensive judgment on the possibility of fraudulent use of the credit card based on the judgment result as well as other judgment materials.

Next, the judgment processing of the judgment unit 103 and the overall authorization judgment unit 104 will be explained in more detail.

Processing by location match level
The determination unit 103 calculates the degree of risk according to the matching level between the mobile terminal location information and the payment terminal location information. Here, the matching level indicates, for example, the following matching states.

-Completely mismatched -Countries matched -Prefectures matched -Cities matched Fig. 3 is a diagram showing the match level DB 103a indicating the match level and the probability of fraudulent use. According to this diagram, it can be seen that the rate of fraudulent use is calculated for each match level. For example, the match level DB 103a stores that the rate of fraudulent use when countries match is 99%, and the rate of fraudulent use when prefectures match is 50%. In Fig. 3, the case where countries match means that the prefectures and cities are different. Similarly, the case where prefectures match means that the cities are different.

Then, in response to a request from the authorization control unit 101, the judgment unit 103 calculates the probability of fraudulent use according to the matching level. For example, the judgment unit 103 refers to the matching level DB 103a, and calculates a fraudulent use rate of 99% when only the country matches but the prefecture does not match in the matching level between the mobile terminal location information and the payment terminal location information. When the prefecture does not match, it means that the lower-level location information, that is, the city, town, or village, does not match either. In that case, the judgment unit 103 can determine that a user other than the user who owns the mobile terminal 300 has used the credit card.

The authorization overall judgment unit 104 obtains the fraudulent use probability of 99% judged by the judgment unit 103 via the authorization control unit 101. The authorization overall judgment unit 104 judges fraudulent use based on the judgment result (fraudulent use probability) calculated by the judgment unit 103 and other information. Note that the other information will be explained in the section on processing of the authorization overall judgment described later.

Note that actual data is collected in advance for each matching level, and the above matching level DB 103a is defined based on the collected data. FIG. 4 is a diagram showing a history DB showing history information that associates mobile terminal location information, payment terminal location information, and the presence or absence of fraudulent use for the payment at that time. This history DB is stored in a payment management device (not shown), and the probability of fraudulent use (FIG. 3) can be derived based on the mobile terminal location information and the payment terminal location information for a specified period. The probability derivation process may be performed in the payment management device, or may be performed manually separately. The payment terminal location information is information indicating the area determined from the IP address. The mobile terminal location information is location information (or approximate location information) of the mobile terminal 300.

[Processing according to risk by Internet Service Provider (hereinafter referred to as ISP) or region]
In addition to or in combination with the above-mentioned processing according to the matching level, the determination unit 103 and the authorization comprehensive determination unit 104 can perform processing according to the risk of the ISP or region. The determination unit 103 performs such processing because the rate of fraudulent use may differ depending on the ISP or region.

Data on fraudulent use is compiled in advance for each ISP or region, and the percentage of fraudulent use is calculated. The authorization comprehensive judgment unit 104 has a database that associates the percentage of fraudulent use with each ISP or region.

Figure 5 is a diagram showing the fraudulent use probability DB for ISPs and regions. The judgment unit 103 is equipped with this fraudulent use probability DB. This fraudulent use probability DB compiles data from the history DB (see Figure 4) to determine the probability. When collating, payment terminal location information is derived based on the IP address of the payment terminal 400. The probability may be calculated mechanically or manually. Note that for each ISP, the IP addresses that the ISP can allocate are determined. Therefore, the authorization server 100 is equipped with a correspondence table (not shown) between ISPs and IP addresses allocated by the ISP, and the judgment unit can use the correspondence table to determine the ISP.

Then, the authorization control unit 101 acquires this information D1, and the judgment unit 103 uses the information D1 to derive at least either the ISP or the payment terminal location information. Then, the judgment unit 103 calculates the probability of fraudulent use by the payment terminal 400 based on at least either the derived ISP or the payment terminal location information. The judgment unit 103 calculates the fraudulent use probability taking into account both the fraudulent use probability calculated using the match level DB 103a and the fraudulent use probability calculated using the fraudulent use probability DB. Note that a simple multiplication may result in an extremely low fraudulent use probability, so it is advisable to prepare a fraudulent use probability DB that takes into account the match level. For example, when the match level DB 103a is referred to, there is a complete mismatch and the fraudulent use probability is 100%, but when the fraudulent use probability DB is referred to, the fraudulent use probability may be 1%. In this case, the probability of fraudulent use will be calculated to be extremely low, so it is necessary to carry out weighting processing so as to give a higher weight to the probability of fraudulent use based on the match level DB 103a.

The authorization comprehensive judgment unit 104 uses this probability to comprehensively judge whether the user's credit card has been fraudulently used.

[Processing taking into account distance between positions]
Even if the regions derived from the payment terminal location information and the mobile terminal location information, for example, the countries, match but the prefectures do not match, the distance between the locations may be very close, such as when the location information is around a prefectural border that crosses prefectures. In this way, when the prefectures derived from the payment terminal location information and the mobile terminal location information, respectively, determined by the determination unit 103, are close to each other (including adjacent), it is appropriate to process the process as if the prefectures or municipalities are at a level of matching. Then, in actual data, even if the prefectures or municipalities cross, if there is a lot of legitimate credit card use, the prefectures or municipalities are whitelisted.

To enable such processing, the judgment unit 103 stores a nearby area DB. Figure 6 is a diagram showing this nearby area DB. As shown in the figure, this nearby area DB is a database that defines that although prefectures are different, the cities, towns, and villages are adjacent to each other across prefectural borders and therefore are considered to be in the same area. This database is set in advance by an operator of the authorization server 100, etc., based on the history DB shown in Figure 4.

The determination unit 103 determines the level of match from each of the mobile terminal location information and the payment terminal location information, and if the countries match but the prefectures and municipalities do not match, it refers to the adjacent area DB. If the determination unit 103 determines, as a result of referring to the adjacent area DB, that the prefectures and municipalities indicated by the mobile terminal location information and the payment terminal location information are municipalities considered to be in the same area, it derives the corresponding probability of fraudulent use.

Even if the countries do not match, the same thing can be done if there is a nearby country. This is because there is a possibility of countries not matching due to cross-border extensions in mobile communication networks. Therefore, by preparing a DB of nearby countries, it is possible to achieve the same effect as above.

The detailed processing for nearby areas is as follows. The judgment unit 103 derives regional information (prefecture or city/town/village) from each of the payment terminal location information and the mobile terminal location information. The judgment unit 103 judges whether the regional information derived from the payment terminal location information has a grouped nearby area, and if so, refers to the nearby area DB. The judgment unit 103 then refers to the nearby area DB to determine the matching level of the regional information derived from each of the derived payment terminal location information and the mobile terminal location information. The judgment unit 103 derives the probability of fraudulent use according to the matching level, referring to the matching level DB shown in FIG. 3.

When the judgment unit 103 determines that the derived regional information does not have any grouped nearby regions, it performs a calculation process of the probability of fraudulent use based on the matching level by referring to the matching level DB without referring to the nearby region DB.

The comprehensive authorization judgment unit 104 makes a comprehensive judgment as to whether or not the user's credit card has been fraudulently used based on the probability of fraudulent use calculated by the judgment unit 103.

[Detailed configuration and processing of the authorization comprehensive determination unit 104]
Next, a description will be given of the comprehensive determination process performed by the authorization comprehensive determination unit 104. Fig. 7 is a diagram showing a detailed configuration of the authorization comprehensive determination unit 104. As shown in the figure, the authorization comprehensive determination unit 104 includes a comprehensive determination unit 104a, a whitelist DB 104b, and a prediction model 104c.

As shown in the figure, the authorization comprehensive judgment unit 104 has the function of making judgments based on a rule base and a risk base. A judgment based on a rule base is, for example, a judgment based on a whitelist DB 104b. In this disclosure, the authorization comprehensive judgment unit 104 judges that all events stored in the whitelist DB 104b are legitimate uses, regardless of the judgment by the judgment unit 103. An event here is, for example, an event in which the probability of fraudulent use derived by the judgment unit 103 is less than a predetermined value, or an event in which the payment terminal location information is in a predetermined region, for example Japan.

Note that instead of a whitelist, a blacklist may be used, or a blacklist DB may be added. For example, the blacklist DB may store country X, and the authorization comprehensive judgment unit 104 may refer to the blacklist DB and determine that the use is fraudulent if the country indicated in the payment terminal location information is country X. Also, it may be stored that the probability calculated by the judgment unit 103 is equal to or less than a predetermined value.

In addition, the overall judgment unit 104a may determine that use of a credit card involving physically impossible movement (making a payment in the United States and then immediately making a payment in Japan) is fraudulent use, regardless of the probability of fraudulent use determined by the judgment unit 103. In other words, the overall judgment unit 104a can determine that a user's movement across countries is physically impossible based on country information or information equivalent thereto included in the payment information.

In addition, the overall judgment unit 104a performs a judgment using the prediction model 104c as a risk-based judgment process. The overall judgment unit 104a inputs the fraudulent use probability calculated by the judgment unit 103, the payment amount, information on the affiliated store, and the like, into the prediction model 104c. The prediction model 104c outputs the overall credit card fraudulent use probability.

When applying the processing of the present disclosure, the product type, payment amount, and affiliated store name (or industry) are included in the above information D1, but this is not limiting and any one of these may be included for application. Furthermore, as shown in Figure 7, affiliated store information is extracted from a table (store information DB104d) that associates store names, affiliated store industry types, and the rate of fraudulent payments within that industry, and the industry and fraud probability are extracted using the store name as a key. This table is information set by the credit card operator. The credit card operator manages the rate of fraudulent use for each industry.

The prediction model 104c inputs the probability of fraudulent use, the affiliated store's industry, the rate of fraudulent payments, the product type, and the payment amount from the judgment unit 103, and outputs the probability of credit card fraud, which is an overall judgment result based on the above.

This prediction model 104c is trained based on the probability of fraudulent use, the type of business of the affiliated store, the rate of fraudulent payments, the product type, and the payment amount from the judgment unit 103. Details will be described later.

This prediction model 104c is constructed through learning by the learning device 104x. FIG. 8 is a block diagram showing the functional configuration of the learning device 104x. The learning device 104x includes a learning unit 104y, a usage history DB 104z, and a prediction model 104c1.

The learning unit 104y performs a learning process using parameters stored in the usage history DB 104z according to a known machine learning method to construct a prediction model 104c1. This prediction model 104c1 corresponds to the prediction model 104c provided in the authorization comprehensive judgment unit 104 of the authorization server 100. In other words, the learned prediction model 104c1 is provided in the prediction model 104c of the authorization server 100.

The usage history DB 104z is a database that stores the history information of the information used by the authorization server 100 to determine whether a credit card has been fraudulently used. FIG. 9 is a diagram showing a specific example. As shown in the figure, the usage history DB 104z stores the date and time of payment using a credit card, the card number of the credit card, the judgment result by the judgment unit 103 (fraudulent use probability), the business type of the affiliated store, the percentage of past fraudulent payments at the affiliated store, the product type, the payment amount, and the result of fraudulent use. In order to learn the prediction model 104c1, the information D1 transmitted from the payment affiliated store server 200 shown in FIG. 1 includes the business type of the affiliated store, the product type, and the payment amount among various information stored in the usage history DB 104z. Information on the percentage of past fraudulent payments may also be included in the information D1, or since it is information determined for each affiliated store, it may be obtained separately from the affiliated store server and registered.

The percentage of past fraudulent transactions at an affiliated store indicates the fraudulent use of credit cards and is calculated by tallying up the fraudulent use of credit cards at that affiliated store over a specified period of time. This information is provided by the credit card company.

The authorization overall judgment unit 104 performs rule-based judgment processing and registers various information in the usage history DB 104z. The result of fraudulent use indicates whether the credit card in the record was used legitimately or fraudulently, and is registered after the fact by the credit card company operator.

The learning unit 104y learns from the information stored in the usage history DB 104z, using as explanatory variables the judgment result by the judgment unit 103 (probability of fraudulent use), the type of business of the affiliated store, the percentage of past fraudulent payments at the affiliated store, the product type, and the payment amount, and as objective variables the result of fraudulent use. This learning process is performed periodically using the latest usage history DB 104z.

In the present disclosure, before the prediction model is trained, the authorization comprehensive judgment unit 104 does not perform a risk-based comprehensive judgment, but performs a rule-based comprehensive judgment. At that time, in order to train the prediction model 104c, the judgment result (probability of fraudulent use) by the judgment unit 103, the payment amount, and information on the affiliated store are stored as a history DB in the usage history DB 104z. In addition, the credit card provider then checks for the presence or absence of fraudulent use, and the presence or absence of fraudulent use is registered in the history DB.

Next, the operation of the authorization server 100 of the present disclosure will be described. FIG. 10 is a flowchart showing the operation of the authorization server 100 of the present disclosure. The authorization control unit 101 receives an authentication request including information D1 including a card number, a payment terminal IP address, etc. from the payment affiliated store server 200 (S101).

The judgment unit 103 receives a query based on an authentication request from the authorization control unit 101 (S102). When the judgment unit 103 receives the query, the location information conversion unit 102 converts the payment terminal IP address included in the information D1 into payment terminal location information (S103).

The judgment unit 103 compares the customer information DB 500 and the location information DB 300a to obtain mobile terminal location information (S104). The judgment unit 103 compares the mobile terminal location with the payment terminal location, and calculates the probability of fraudulent use of the credit card based on the comparison result (S105).

The authorization control unit 101 sends the judgment result of the judgment unit 103 to the comprehensive authorization judgment unit 104 and performs inquiry processing. The comprehensive authorization judgment unit 104 makes a comprehensive judgment on the possibility of fraudulent use of the user's credit card based on the judgment result (S106). The authorization control unit 101 transmits the comprehensive judgment result judged by the comprehensive authorization judgment unit 104 to the payment affiliated store server 200. Note that the destination of the comprehensive judgment result is not limited to the payment affiliated store server 200, and it may be sent to a device that manages the payment.

Next, the judgment process by the authorization comprehensive judgment unit 104 will be described. FIG. 11 is a flowchart showing the operation of the authorization comprehensive judgment unit 104. The authorization comprehensive judgment unit 104 makes a comprehensive judgment based on a risk base (S201). For example, a prediction model is used to judge whether or not there is fraudulent use. The authorization comprehensive judgment unit 104 makes a comprehensive judgment based on a rule base (S202). For example, for a user listed on a whitelist, it is judged that there is no fraudulent use. When making a comprehensive judgment based on a rule base, a judgment is made based on the result (probability) of the comprehensive judgment based on a risk base. For example, when the probability of fraudulent use is low, a judgment based on a whitelist is further made as a rule base. Conversely, when the probability of fraudulent use is high, a process of switching the judgment method may be included, such as making a judgment based on a blacklist.

As described above, the authorization comprehensive judgment unit 104 makes a comprehensive judgment based on a risk base, and then makes a comprehensive judgment based on a rule base, but this is not limited to this. The judgment may be based only on a rule base, or only on a risk base. Without making a comprehensive judgment by the authorization comprehensive judgment unit 104, the authorization control unit 101 may simply divide the judgment result by a threshold value using the judgment unit 103 and send it to a device that performs final approval of the credit card payment, such as the payment affiliated store server 200.

Next, the effect of the authorization server 100 of the present disclosure will be described. In the authorization server 100, the authorization control unit 101 functions as a mobile terminal information acquisition unit that acquires mobile terminal location information of the user's mobile terminal 300, and a payment terminal information acquisition unit that acquires payment terminal location information of the payment terminal 400 where the user is performing an operation for payment. Then, the judgment unit 103 judges the possibility of fraudulent use of the credit card by the payment terminal 400 based on the mobile terminal location information and payment terminal location information acquired by the authorization control unit 101.

This configuration makes it possible to accurately determine fraudulent use of the payment process by the payment terminal 400. In other words, if it cannot be determined that the payment terminal 400 and the mobile terminal 300 held by the user are in the same area based on the payment terminal location information of the payment terminal 400 and the mobile terminal location information of the mobile terminal 300 held by the user, it can be determined that the user has not performed a payment process such as a credit card using the payment terminal 400. In such a case, it can be determined that the credit card has been used fraudulently.

In the present disclosure, the authorization server 100 further includes a customer information DB 500 (customer information storage unit) that stores the credit card number (corresponding to payment information) input to the payment terminal 400 in association with the identification number of the mobile terminal 300.

The determination unit 103 acquires an identification number of the mobile terminal 300 based on the credit card number (payment information) included in the information D1 transmitted from the payment terminal 400, based on the customer information stored in the customer information DB 500. Then, the determination unit 103 acquires mobile terminal location information from the location information DB 300a that stores location information of the mobile terminal 300, based on the identification number. This determination unit 103 functions as a mobile terminal location information acquisition unit. In this disclosure, an example has been given of sending the credit card number itself, but tokenized information may also be sent.

In this disclosure, the authorization server 100 can obtain the location of a user attempting to process a payment such as a credit card by utilizing the location information of the mobile terminal 300. Therefore, by determining the consistency of the user's location using the location of the payment terminal 400 and the location of the mobile terminal 300, it is possible to determine fraudulent use of the credit card.

In addition, in the authorization server 100 of the present disclosure, the authorization control unit 101 functions as an IP address acquisition unit that acquires the IP address of the payment terminal 400. The authorization control unit 101, which also functions as a payment terminal information acquisition unit, acquires payment terminal location information based on the IP address.

According to the present disclosure, it is possible to obtain the IP address when the payment terminal 400 accesses the payment affiliated store server 200, and based on that, obtain payment terminal location information indicating the actual location. Therefore, it is possible to grasp the location of the payment terminal 400 being operated by the user, and use that to determine the validity of the user's location.

In addition, the authorization server 100 of the present disclosure further includes an authorization overall judgment unit 104 that functions as a business judgment unit that judges the ISP that is the connection business for connecting the payment terminal 400 to the payment processing line. The authorization overall judgment unit 104 judges the possibility of fraudulent use by the payment terminal 400 based on the ISP used in addition to the judgment result (fraudulent use probability) by the judgment unit 103.

According to the present disclosure, the probability of credit card fraud can be determined based on the ISP used by the payment terminal 400. This is because different ISPs are more likely to have fraudulent credit card use.

In addition, in the authorization server 100 of the present disclosure, the authorization comprehensive judgment unit 104 functions as a region judgment unit that judges the payment terminal location information of the payment terminal 400. The authorization comprehensive judgment unit 104 judges the possibility of fraudulent use by the payment terminal 400 based on the payment terminal location information in addition to the judgment result (fraudulent use probability) by the judgment unit 103.

According to the present disclosure, the possibility of fraudulent use of a credit card by the payment terminal 400 is determined based on the region in which the payment terminal 400 is located. This is because there are trends in fraudulent use of credit cards depending on the region.

In addition, in the authorization server 100 disclosed herein, the judgment unit 103 judges the possibility of fraudulent use of the credit card by the payment terminal 400 based on the level of match between the mobile terminal location information and the payment terminal location information.

In the present disclosure, the payment terminal location information is information derived from the IP address of the payment terminal 400, and is generally not very accurate. Therefore, it is considered that it is not necessary to determine fraudulent use if there is a match at the national or prefectural level, without requiring a match at a fine level such as a city, town, or village level. For this reason, in the present disclosure, an effective judgment can be made by making a judgment according to the level of match between the mobile terminal location information and the payment terminal location information.

In addition, in the authorization server 100 disclosed herein, the judgment unit 103 judges the possibility of fraudulent use of a credit card by the payment terminal 400 based on whether the area indicated by the mobile terminal location information is close to the area indicated by the payment terminal location information, even if the area indicated by the payment terminal location information does not include the mobile terminal location information.

As mentioned above, the area indicated by the payment terminal location information is generally not derived with a high degree of accuracy. Therefore, if it can be determined that the area indicated by the mobile terminal location information is close to the area indicated by the payment terminal location information, it may be possible to determine that the person is in the same area.

In addition, the authorization server 100 of the present disclosure further includes a predictive model 104c that outputs a comprehensive judgment result based on input information including the judgment result by the judgment unit 103.

According to the present disclosure, it is possible to perform predictive processing based on machine learning using input information including judgment results (probability of fraudulent use), enabling accurate judgments.

The input information includes, in addition to the judgment result (probability of fraudulent use), at least one of the following: the industry of the payment affiliate which is the store that requested the payment from the payment terminal 400, the type of purchased goods which are the subject of the payment from the payment terminal 400, the percentage of past fraudulent payments in the industry of the payment affiliate which is the store that requested the payment, and the payment amount.

This information represents trends in credit card fraudulent use. By utilizing the predictive model 104c trained using this information, it is possible to accurately determine whether a credit card is being fraudulently used.

Therefore, the prediction model 104c is constructed by machine learning using, in addition to the judgment result (probability of fraudulent use), at least the industry of the payment affiliate that is the payment requesting store of the payment terminal (information about the payment affiliate), the type of product that is the payment target of the payment terminal, the percentage of past fraudulent payments in the industry of the payment affiliate that is the payment requesting store, and one of the payment amounts as explanatory variables, and the result of fraudulent use for the payment request as the objective variable.

The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and connected directly or indirectly (e.g., using wires, wirelessly, etc.) and these multiple devices. The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judgement, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the transmission function is called a transmitting unit or transmitter. In either case, as mentioned above, there are no particular limitations on the method of implementation.

For example, the authorization server 100 in one embodiment of the present disclosure may function as a computer that performs processing of the authorization method of the present disclosure. FIG. 12 is a diagram showing an example of a hardware configuration of the authorization server 100 in one embodiment of the present disclosure. The above-mentioned authorization server 100 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

In the following description, the term "apparatus" may be interpreted as a circuit, device, unit, etc. The hardware configuration of the authorization server 100 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

Each function in the authorization server 100 is realized by loading a specific software (program) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned judgment unit 103, the authorization overall judgment unit 104, the location information conversion unit 102, etc. may be realized by the processor 1001.

The processor 1001 also reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes the computer to execute at least a part of the operations described in the above-mentioned embodiment is used. For example, the judgment unit 103 may be realized by a control program stored in the memory 1002 and running on the processor 1001, and may be similarly realized for other functional blocks. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store a program (program code), software module, etc. that is executable to implement the authorization method according to one embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmission/reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of, for example, Frequency Division Duplex (FDD) and Time Division Duplex (TDD). For example, the above-mentioned authorization control unit 101 may be realized by the communication device 1004. The authorization control unit 101 may be implemented in a physically or logically separated transmitting unit and receiving unit.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one configuration (e.g., a touch panel).

In addition, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

In addition, the authorization server 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

The notification of information is not limited to the aspects/embodiments described in the present disclosure, and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), higher layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or combinations thereof. In addition, the RRC signaling may be called an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, etc.

Each aspect/embodiment described in this disclosure may be applied to at least one of systems utilizing LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (new Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), or other suitable systems, and next generation systems enhanced based on these. In addition, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G, etc.).

The processing steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be reordered unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

Information, etc. may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer). It may also be input/output via multiple network nodes.

The input and output information, etc. may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information, etc. may be overwritten, updated, or appended. The output information, etc. may be deleted. The input information, etc. may be transmitted to another device.

The determination may be based on a value represented by a single bit (0 or 1), a Boolean (true or false) value, or a numerical comparison (e.g., with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Additionally, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), then these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

In addition, terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

As used in this disclosure, the terms "system" and "network" are used interchangeably.

In addition, the information, parameters, etc. described in this disclosure may be represented using absolute values, may be represented using relative values from a predetermined value, or may be represented using other corresponding information. For example, radio resources may be indicated by an index.

In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. In addition, "judgment" and "decision" can include considering resolving, selecting, choosing, establishing, comparing, etc., to be a "judgment" or "decision." In other words, "judgment" and "decision" can include considering some action to be a "judgment" or "decision." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

The terms "connected" and "coupled", or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access". As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and light (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added by translation, such as a, an, and the in English, this disclosure may include that the nouns following these articles are in the plural form.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." In addition, the term may mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

100...authorization device, 101...authorization control unit, 102...location information conversion unit, 102a...regional conversion table, 103...judgment unit, 104...authorization overall judgment unit, 104a...overall judgment unit, 104b...whitelist DB, 104c...prediction model, 104c1...prediction model, 104x...learning device, 104y...learning unit, 200...payment affiliated store server, 300...mobile terminal, 400...payment terminal, 500...customer information database.

Claims (7)

A mobile terminal information acquisition unit that acquires mobile terminal location information of a user's mobile terminal;
a payment terminal information acquisition unit that acquires payment terminal location information of a payment terminal where a payment operation is being performed by the user;
a calculation unit that calculates a fraud probability for a payment process by the payment terminal according to a degree of match between the mobile terminal location information and the payment terminal location information;
a business operator determination unit that determines a connection business operator for connecting the payment terminal to a payment processing line;
A database that stores the probability of fraudulent use of the connection carrier;
a determination unit that determines the possibility of fraudulent use based on the fraudulent use probability calculated by the calculation unit and the fraudulent use probability for payment processing by the payment terminal based on the connection carrier obtained by referring to the database; and
An authorization device comprising: A mobile terminal information acquisition unit that acquires mobile terminal location information of a user's mobile terminal;
a payment terminal information acquisition unit that acquires payment terminal location information of a payment terminal where a payment operation is being performed by the user;
a calculation unit that calculates a fraud probability for a payment process by the payment terminal based on a degree of agreement between the mobile terminal location information and the payment terminal location information;
a region determination unit that determines a region in which the payment terminal is located based on the payment terminal location information ;
a storage unit that stores the probability of fraudulent use in the region in association with the probability of fraudulent use in the region;
a determination unit that determines the possibility of fraudulent use with respect to a payment process by the payment terminal based on the fraudulent use probability calculated by the calculation unit and the fraudulent use probability with respect to a payment process by the payment terminal calculated based on the area indicated by the payment terminal location information;
An authorization device comprising : A mobile terminal information acquisition unit that acquires mobile terminal location information of a user's mobile terminal;
a payment terminal information acquisition unit that acquires payment terminal location information of a payment terminal where a payment operation is being performed by the user;
a calculation unit that calculates a fraudulent use probability for a payment process by the payment terminal according to a degree of match between the mobile terminal location information and the payment terminal location information;
a determination unit that determines a possibility of fraudulent use of the payment processing by the payment terminal based on the fraudulent use probability;
Equipped with
Define regions in advance for each hierarchical level according to size,
A region for each of the predefined hierarchical levels is derived from the payment terminal location information and the mobile terminal location information, respectively;
the calculation unit determines whether there is a match on a regional basis for each hierarchical level based on the region for each hierarchical level derived from the mobile terminal location information and the region for each hierarchical level derived from the payment terminal location information, and calculates the fraudulent use probability to be smaller when there is a match with a lower hierarchical region of smaller size, calculates the fraudulent use probability to be larger when there is a match with a higher hierarchical region of larger size, and calculates the fraudulent use probability to be larger when there is no match with a higher hierarchical region.
Authorization device. the calculation unit calculates a fraudulent use probability according to a degree of coincidence between the areas of the hierarchical levels when the area of the lower hierarchical level indicated by the mobile terminal location information is close to the area of the lower hierarchical level indicated by the payment terminal location information even if the area of the lower hierarchical level indicated by the payment terminal location information does not include the mobile terminal location information;
4. An authorization device according to claim 3 . The determination unit is
a prediction model that inputs the fraudulent use probability calculated by the calculation unit as input information and outputs a determination result indicating the possibility of fraudulent use based on the input information ;
An authorization device according to claim 3 or 4 . The input information includes, in addition to the probability of fraudulent use , at least one of information on the payment requesting store of the payment terminal, a payment target of the payment terminal, a rate of past fraudulent payments in the information on the payment requesting store, and a payment amount.
An authorization device according to claim 5 . The predictive model is
The probability of fraudulent use is constructed by machine learning using at least one of information about the payment request store of the payment terminal, the payment target of the payment terminal, the rate of past fraudulent payments in the information about the payment request store, and the payment amount as explanatory variables, and the result of fraudulent use for the payment request as an objective variable.
7. An authorization device according to claim 6 .

Images