JP6570689B2 - Name identification device, name identification method, and name identification program - Google Patents

Description

  The present invention relates to a name identification device, a name identification method, and a name identification program.

  In recent years, with the development of communication networks, various services are provided via the networks. And a user uses various services via a network using devices such as a PC (Personal Computer), a smartphone, and a tablet terminal.

  Here, the service provider may examine the suitability of the user when using the service. For example, the service provider examines that the user has made an illegal transaction in the past, and excludes the use and registration of a user who is recognized as having a risk of making an illegal transaction. For example, as a technique for examining the suitability of a user, a technique for examining a user by storing an unauthorized subscription pattern in advance and checking information transmitted from the user with the unauthorized subscription pattern is known.

JP 2011-76406 A

  However, with the above-described conventional technology, it is difficult to determine the identity of a user who uses a network with high accuracy. Specifically, the user can change information transmitted to and received from the service provider by creating different accounts or using different devices each time the service is used. For this reason, the service provider side may not appropriately acquire information for identifying the user. As a result, it becomes difficult for the service provider side to determine the identity of the user, and there is a risk of hindering user authentication and examination. In addition, since there are an enormous number of users who use services via the network, it is not realistic for humans to examine the suitability of each user in detail.

  Also, determining the identity of the user is useful for the service provider in applications other than screening. For example, a service provider can identify the same person as a trader who uses multiple different accounts and users who use multiple accounts in the provided service, and accurately grasp the user. It is desirable to be able to unify information and services provided.

  The present application has been made in view of the above, and an object thereof is to provide a name identification device, a name identification method, and a name identification program that can determine the identity of a user who uses a network with high accuracy.

  The name identification device according to the present application includes an acquisition unit that acquires access information, which is information acquired when accessed from a user terminal, and a user corresponding to the access information based on the access information acquired by the acquisition unit A determination unit that determines the degree of similarity between each other, and a name identification unit that, when the degree of similarity determined by the determination unit is equal to or greater than a predetermined threshold, names the users corresponding to the similarity as the same user. It is characterized by having.

  According to one aspect of the embodiment, there is an effect that the identity of a user who uses a network can be determined with high accuracy.

FIG. 1 is a diagram illustrating an example of a name identification process according to the first embodiment. FIG. 2 is a diagram illustrating a configuration example of the name identification device according to the first embodiment. FIG. 3 is a diagram illustrating an example of the browser information storage unit according to the first embodiment. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the first embodiment. FIG. 5 is a flowchart illustrating a name identification process procedure performed by the name identification apparatus according to the first embodiment. FIG. 6 is a diagram illustrating an example of a name identification process according to the second embodiment. FIG. 7 is a diagram illustrating a configuration example of the name identification device according to the second embodiment. FIG. 8 is a diagram illustrating an example of a usage history storage unit according to the second embodiment. FIG. 9 is a flowchart illustrating a name identification process procedure performed by the name identification apparatus according to the second embodiment. FIG. 10 is a diagram illustrating a configuration example of the name identification system according to the second embodiment. FIG. 11 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the name identification device.

  Hereinafter, a form for implementing a name identification apparatus, a name identification method, and a name identification program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the name identification device, the name identification method, and the name identification program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(First embodiment)
[1-1. Name identification process)
First, an example of name identification processing according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a name identification process according to the first embodiment. FIG. 1 shows an example in which a name identification process for identifying a user who uses a service provided by the name identification device 100 is performed by the name identification device 100 included in the name identification system 1.

In the example shown in FIG. 1, the user U1 has a user terminal 10 ₁ is PC. The user U2 is possessed with the user terminal 10 ₂ is smartphone, a user terminal 10 ₃ a tablet terminal. The user terminals 10 ₁ to 10 ₃ and the name identification device 100 are connected by a network N (not shown) (for example, the Internet). In the example of FIG. 1, the user terminal 10 ₂ and the user terminal 10 _3, and it shall be connected to the network N using the common router (: router) equipment.

The name identification device 100 is a server device managed by a service provider. Specifically, the name collation apparatus 100 provides various services by distributing web pages to the user terminals 10 ₁ to 10 ₃ . For example, the name collation apparatus 100 is a search site, an auction site, a shopping site, a news site, a weather forecast site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a web blog, and the like. Provide service. In the example shown in FIG. 1, the name collation apparatus 100 is providing the predetermined service SV1 to the user U1 and the user U2.

Here, the user terminal 10 ₁ in accordance with operation by the user U1, the service SV1, access the account (account) A11 (step S11). An account refers to a right to log in to a predetermined service. When using a service, a user receives an account setting from a service provider (for example, an administrator of the name collation apparatus 100) by a predetermined procedure. Here, the account A11 refers to an account assigned to the user U1 for using the service SV1. That is, the user terminal 10 _1, to the name identification device 100, by receiving authentication account A11, it is possible to use the service SV1.

The user terminal 10 ₁ in accordance with operation by the user U1, the service SV1, sometimes accessing the account A12 (step S12). In this case, the user U1 has received a plurality of account settings in the service SV1 provided by the name collation device 100.

Similarly, the user terminal 10 ₂ in accordance with operation by the user U2, the service SV1, accesses the account A21 (step S13). The user U2, since owns a plurality of user terminals 10 ₂ and 10 ₃ may use a user terminal 10 ₂ and the different user terminals 10 ₃ to use the service SV1. That is, the user terminal ₁₀₃ in accordance with operation by the user U2, the service SV1, which may be accessed by the account A22 (step S14).

Thus, for name identification device 100 to provide a service SV1, as in the example of the user U1, the same user sometimes accessed using multiple accounts from the same user terminal 10 _1. Further, there is a case where as in the example of the user U2, the same user accesses using multiple accounts from a plurality of user terminals 10 ₂ and 10 _3. In this case, it is difficult for the name collation apparatus 100 to specify the user using only the account information. That is, if the name collation apparatus 100 tries to determine the identity of the user based on the account information in each access, the name identification device 100 determines that each access in steps S11 to S14 is an access from a different user.

Therefore, in steps S11 to S14, the name identification device 100 acquires browser information that is information that can be acquired from the user terminals 10 ₁ to 10 ₃ when accessing by each account. And the name collation apparatus 100 memorize | stores the acquired browser information in the browser information storage part 121, and uses it for a user's determination process.

The browser information refers to information that can be acquired based on an HTTP (HyperText Transfer Protocol) request transmitted from the browser of each user terminal when accessing the name collation apparatus 100. For example, browser information is information indicated by an HTTP header, and the information includes a plurality of items. Specifically, the name collation apparatus 100 includes access date and time, OS (Operating System) type and version of each user terminal, browser type and version, plug-in included in the browser, cookie (cookie). Information corresponding to each item is acquired, such as route information that is a communication route such as an HTTP referer, a communication device such as a router, and a proxy server. Further, the name identification device 100 acquires time difference information that is a time difference between the time at which the HTTP request is transmitted from each user terminal and the time at which the HTTP request is received by the name identification device 100. Moreover, the name collation apparatus 100 acquires the terminal identification information (for example, unique ID given beforehand to the user terminals 10 ₁ to 10 ₃ ), which is information for identifying each user terminal, when it can be acquired. That is, when accessing, the name identification device 100 acquires not only information such as an account that can be easily changed by the user but also browser information including items that are difficult for the user to change easily. Thereby, the name collation apparatus 100 can suppress the influence by a user's trend, such as changing an account and a terminal, and can perform a name collation process.

The name identification device 100 performs a process of determining the similarity of each browser information based on the browser information acquired in each access in steps S11 to 14 (step S15). For example, the name collation apparatus 100 performs scoring of the browser information by determining the similarity of a plurality of items included in the browser information, and determines the similarity of the browser information. Note that the name collation device 100 may not be able to acquire all the information listed as examples of the browser information. For example, depending on the settings of the user terminals 10 ₁ to 10 ₃ , the name collation device 100 may have items that cannot be acquired even with browser information. As an example, the name collation device 100 may not be able to acquire a cookie because the cookie is deleted by a user operation or is set not to send or receive a cookie by the user. Even in such a case, the name collation apparatus 100 can determine the similarity between the browser information by setting a plurality of items included in the browser information as determination targets.

  In the example illustrated in FIG. 1, the name collation apparatus 100 determines the similarity between the browser information acquired in the access from the account A11 and the browser information acquired in the access from the account A12. In this example, the name collation device 100 has similarities in time difference information, route information such as routing to reach the name collation device 100, and items such as OS and IP address in the browser information corresponding to both accounts. Judge as high. As a result, the name collation apparatus 100 determines that the browser information corresponding to the account A11 and the browser information corresponding to the account A12 have a similarity of “high”.

  Further, the name identification device 100 determines the similarity between the browser information acquired in the access from the account A21 and the browser information acquired in the access from the account A22. In this example, the name collation apparatus 100 determines that similarity is low in items such as OS and browser type in the browser information corresponding to both accounts. On the other hand, the name identification device 100 is time difference information, route information such as routing, and information indicated by an IP address (for example, information that estimates the location of the terminal based on the IP address assigned to the terminal using existing technology). ) And the like are determined to be highly similar. As a result, the name collation apparatus 100 determines that the browser information corresponding to the account A21 and the browser information corresponding to the account A22 have a similarity of “medium”. Note that the name identification device 100 determines that the account A11 and the accounts A21 and A22 and the account A12 and the accounts A21 and A22 have relatively few items, and the similarity is “low”. As described above, the name collation apparatus 100 determines the similarity between the browser information. And the name collation apparatus 100 determines the similarity of the users corresponding to the said browser information based on the determined similarity of browser information.

  And the name collation apparatus 100 performs the process of collating the user corresponding to browser information based on the judged similarity between users (namely, the similarity of browser information corresponding to a user) (step S16). For example, the name collation apparatus 100 provides a predetermined threshold for the similarity of browser information, and collates users corresponding to browser information that is equal to or greater than the predetermined threshold as the same user. In the example of FIG. 1, the name identification device 100 assumes that the user corresponding to the browser information having the similarity “medium” or higher as the predetermined threshold is the same user. Thereby, the name collation apparatus 100 collates the user U1 accessed with the account A11 and the user U1 accessed with the account A12 as the same user. Further, the name collation apparatus 100 collates the user U2 accessed with the account A21 and the user U2 accessed with the account A22 as the same user.

Thus, the name identification apparatus 100 according to the first embodiment acquires the browser information is information available from the browser of the user terminal 10 ₁ to 10 _3. And the name collation apparatus 100 determines the similarity of the users corresponding to the said browser information based on the acquired browser information. And the name collation apparatus 100 collates the users used as a comparison object as the same user, when the determined similarity is more than a predetermined threshold value.

  As described above, the user may have a plurality of accounts when using the service. In such a case, the name collation device 100 according to the first embodiment can be easily changed by the user by acquiring not only the account information and device information transmitted from the user but also the browser information of the user terminal. Information that cannot be obtained. And the name collation apparatus 100 can collate the user over multiple accounts accurately by collating a user based on the determination result of the similarity of the user based on browser information.

Thereby, the name collation apparatus 100 can have an advantageous effect in the application example shown below. For example, the name collation device 100 can eliminate improper use by the user in the provided service. In the example of FIG. 1, it is assumed that the user U1 is a user who has been found to be illegally used in the service SV1 logged in with the account A11 and whose use of the account A11 has been stopped. In this case, the user U1 may receive the issuance of the account A12 from the service SV1 again and try to continue using the service SV1. Name identification device 100 obtains browser information relating to the user terminal 10 _1, by identifying user U1 using multiple accounts, it is possible to supplement the user U1. In addition, although the user U2 accesses the name identification device 100 with a different account and a different device, the service SV1 to be used may be common. Even in this case, the name collation apparatus 100 can collate the user U2 who uses different accounts A21 and A22. Thereby, for example, the name collation device 100 presents the service content in line with the interest of the user U2 to the user U2 who uses the service SV1 in different environments, or distributes the advertising content tailored to the user U2. can do.

  As another application example, some users forget that they have been registered for an account, and try to use the same service SV1 after a certain period of time (for example, several months, several years, etc.). , You may be issued a new account. Even in such a case, the name collation apparatus 100 can take over user information and behavior history that existed in the past account, for example, by performing user name collation. Thereby, the name collation apparatus 100 can eliminate what is called a dormant account efficiently, and can utilize useful information, such as the service content which the user received in the past. Moreover, as another application example, even if it is a case where the same service SV1 is used depending on a user, the behavior characteristic in the case of using PC, and the behavior in the case of using a portable terminal such as a smartphone The characteristics may be different. Even in such a case, the name collation apparatus 100 can provide a service according to a common user by collating the user.

Hereinafter, the configuration and processing procedure of the above-described name identification device 100 will be described. Hereinafter, when it is not necessary to distinguish the user terminals 10 ₁ to 10 ₃ , these may be collectively referred to as “user terminal 10”.

[1-2. (Configuration of name identification device)
Next, the configuration of the name identification device 100 according to the first embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the name identification device 100 according to the first embodiment. As illustrated in FIG. 2, the name identification device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to a network N (not shown) by wire or wirelessly and transmits / receives information to / from the user terminal 10.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 2, the storage unit 120 includes a browser information storage unit 121 and a user information storage unit 122.

(About browser information storage unit 121)
The browser information storage unit 121 stores information related to browser information acquired when the user terminal 10 uses a service. Here, FIG. 3 shows an example of the browser information storage unit 121 according to the first embodiment. In the example illustrated in FIG. 3, the browser information storage unit 121 includes “access date / time”, “account”, “time difference information”, “route information”, “browser”, “OS”, “plug-in”, “IP ( Internet Protocol) address ".

  “Access date and time” indicates the date and time of access from the user terminal 10. In other words, the “access date / time” indicates the date / time when the service provided by the name collation apparatus 100 was used by the user terminal 10. “Account” indicates an account transmitted / received to / from the user terminal 10.

  “Time difference information” indicates information related to the time difference between the information transmitted from the user terminal 10 and the information received by the name identification device 100. “Route information” indicates information related to a route until information transmitted from the user terminal 10 reaches the name identification device 100. In the example of FIG. 3, an example in which schematic information such as “t01” and “R011” is stored in “time difference information” and “route information” is shown. Includes seconds indicating the passage of time. The “route information” includes information for identifying a router or proxy server used for communication.

  “Browser” indicates a browser used by the user terminal 10. For example, the browser is represented by a combination of “BR01” that is the name of the browser and “8.1” that is the version information, such as “BR01 (8.1)”. “OS” indicates an OS used by the user terminal 10. For example, the OS is represented by a combination of “OS01” that is the name of the OS and “10.3” that is version information, such as “OS01 (10.3)”. “Plug-in” indicates information of a plug-in incorporated in the browser. Although an example in which schematic information such as “P01” is stored in “plug-in” is shown, information on identification information (name, etc.) of an installed plug-in is actually stored in “P01”. included.

“IP address” indicates the IP address of the user terminal 10. In the example of FIG. 3, an example in which schematic information such as “IP-01” is stored in “IP address” is shown, but in reality, “N ₁ .N ₂ . Information such as “N ₃ .N ₄ ” (N _{1 to} N ₄ is a number from 0 to 255) is stored.

  That is, in FIG. 3, the browser information acquired from the user terminal 10 logged into the service with the account “A11” at “9:00 on December 15, 2014” has the time difference information “t01” The information is “R011”, the browser being used is “BR01 (8.1)”, the OS being used is “OS01 (10.3)”, and the information of the plug-in incorporated therein Indicates “P01” and the IP address includes information of each item such as “IP-01”.

  Although not shown in FIG. 3, the browser information storage unit 121 may store other information acquired as the user terminal 10 is accessed. For example, the browser information storage unit 121 stores identification information for identifying the user terminal 10. An example of identification information for identifying the user terminal 10 is a cookie. When a unique ID is assigned to the user terminal 10 in advance, the unique ID of the user terminal 10 is stored as information for identifying the user terminal 10.

(User information storage unit 122)
The user information storage unit 122 stores information related to the user subjected to the name identification process. Here, FIG. 4 shows an example of the user information storage unit 122 according to the first embodiment. In the example illustrated in FIG. 4, the user information storage unit 122 includes items such as “same user (account)”, “similarity”, and “determination item”.

  “Same user (account)” indicates an account name corresponding to the user terminal 10 used by the user for each user identified by the name identification unit 134 described later.

  “Similarity” indicates the degree of similarity between browser information used when name identification is performed. In the example of FIG. 4, the similarity is represented by the concept of “high” or “medium”, but the display method of the similarity is not limited to this. For example, the similarity may be represented by a numerical value scored from 1 to 100.

  The “determination item” indicates an item included in the browser information used when the determination unit 133 described later determines the similarity. FIG. 4 illustrates an example in which items determined to be similar by the determination unit 133 among the items used for determination are displayed. Note that all items used for determination may be stored in the determination items.

  That is, in FIG. 4, the user terminal 10 identified by the account “A11” and the user terminal 10 identified by the account “A12” are identified as being used by the same user and used for the determination process. The degree of similarity between the browser information is “high”, and the determination item is “route information, browser, OS, plug-in”.

(About the control unit 130)
Returning to the description of FIG. 2, the control unit 130, for example, various programs (an example of a determination program) stored in a storage device inside the name identification device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Is realized by using the RAM as a work area. The control unit 130 is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 2, the control unit 130 includes a providing unit 131, an acquiring unit 132, a determining unit 133, and a name collating unit 134, and implements or executes information processing functions and operations described below. . The internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 2, and may be another configuration as long as the information processing described later is performed. In addition, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 2, and may be another connection relationship.

(About the providing unit 131)
The providing unit 131 provides various services to the user terminal 10. Specifically, when the providing unit 131 receives an access request from the user terminal 10, the providing unit 131 distributes web pages corresponding to various services to the user terminal 10 as a response to the access request. For example, the providing unit 131 distributes a web page related to a search site corresponding to the search service, an auction site corresponding to the auction service, a shopping site corresponding to the shopping service, and the like.

  Here, the providing unit 131 receives account information transmitted from the user terminal 10. Then, the providing unit 131 provides a service corresponding to the user based on the received account information.

  The providing unit 131 updates the browser information storage unit 121 when web pages corresponding to various services are distributed to the user terminal 10. Specifically, the providing unit 131 stores the date and time when the access request is received from the user terminal 10 in the “access date and time” of the browser information storage unit 121. The providing unit 131 stores time difference information and route information in “time difference information” and “route information” of the browser information storage unit 121 based on browser information that can be acquired from the user terminal 10. Also, the providing unit 131 stores various information on the browser, OS, and plug-in of the user terminal 10 that has requested access in predetermined items of the browser information storage unit 121. Further, the providing unit 131 stores the IP address of the user terminal 10 obtained when the access request is received in “IP address” of the browser information storage unit 121. In addition, when possible, the providing unit 131 receives an HTTP (Hypertext Transfer Protocol) request as an access request, based on a user agent or the like set in the HTTP request header. Get identification information. For example, when the user terminal 10 holds a cookie, the providing unit 131 receives the cookie together with an access request from the user terminal 10. Thereby, the providing unit 131 can identify the user terminal 10 based on the cookie.

(About the acquisition unit 132)
The acquisition unit 132 acquires browser information corresponding to the user terminal 10. Specifically, the acquisition unit 132 acquires various types of information from the browser information storage unit 121 when the later-described determination unit 133 starts processing to determine the similarity of browser information. For example, the acquisition unit 132 acquires various types of information from the browser information storage unit 121 periodically (for example, every day or every week). For example, the acquisition unit 132 acquires various types of information from the browser information storage unit 121 when an operation for performing a name identification process is performed by a service provider who is an administrator of the name identification device 100. At this time, the acquisition unit 132 may not acquire information that has been processed in the past from the browser information storage unit 121.

(About the determination unit 133)
The determination unit 133 determines the similarity between the browser information acquired by the acquisition unit 132. Further, the determination unit 133 determines the degree of similarity between users corresponding to the browser information based on the acquired browser information. For example, the determination unit 133 determines the degree of similarity between users corresponding to browser information based on the degree of similarity between browser information obtained by comparing the similarity of tendencies of browser information. This is because the combination of browser information having a high degree of similarity is highly likely that both user terminals 10 corresponding to the browser information are operated by the same user even when the transmitted accounts are different. means. In this case, for the information included in the browser information, the determination unit 133 has an access tendency (rough location, time, etc.) of the user terminal 10 that is the transmission source, a model tendency of the user terminal 10 (PC or tablet), and the like. The pattern indicated by is determined. For example, even if the account information is different, the determination unit 133 can find a predetermined pattern for the browser information when the browser information is acquired from the user terminal 10 operated by the same user. In this case, the determination unit 133 may determine the similarity of information displayed as a vector by digitizing a plurality of determination elements as the browser information pattern. For example, if the determination unit 133 can find a tendency such as concentration of access at a specific time, the determination unit 133 creates vector information having a high value of the determination element. Then, the determination unit 133 determines that the browser information indicated by vectors having similar distances and angles are high in similarity when displayed as vectors. As described above, the determination unit 133 can determine the similarity of browser information by determining the pattern of the browser information that is difficult for the user to change consciously.

  Specifically, the determination unit 133 according to the first embodiment compares the similarity of each item of browser information, determines the similarity of browser information based on the similarity of each item, and the browser The similarity of the user corresponding to the information is determined. That is, the determination unit 133 extracts browser information corresponding to a user terminal that uses a predetermined service, based on the account acquired from the browser information storage unit 121 by the acquisition unit 132. And the determination part 133 scores the similarity of browser information by comparing the some item contained in browser information, and determines the similarity of browser information based on the calculated score.

  For example, the determination unit 133 determines whether or not “time difference information” is similar among items included in the browser information to be compared. When the determination unit 133 is similar, the determination unit 133 calculates a high score for determining the similarity for the item. Similarly, the determination unit 133 determines whether items such as “route information”, “browser”, “OS”, and “plug-in” are similar. Specifically, in the route information, the determination unit 133 determines the similarity from the viewpoint of whether or not the user terminal 10 to be compared is accessing the name identification device 100 via the same route. To do. For example, if the determination unit 133 determines that the comparison target is via a router having the same identifier or a proxy server having the same identifier, the determination unit 133 determines the item related to the router information. The similarity is determined to be high as having similarity. The determination unit 133 determines whether the type and version of the browser and the OS are the same, and determines that the degree of similarity is high if they are the same. Further, the determination unit 133 determines whether or not the software included as a plug-in has commonality with respect to the plug-in, and determines that the degree of similarity is high when the commonality is high. If there is an item that has not been acquired by the acquisition unit 132, the determination unit 133 can skip the item and perform the determination process. Further, the determination unit 133 may determine the item content and the number of items to be determined by receiving an instruction from a person such as an administrator of the name collation device 100, for example.

  Moreover, the determination part 133 may determine the similarity of browser information by weighting evaluation of a predetermined item among several items contained in browser information. This is because if the terminal identification information such as a cookie included in the browser information matches, the user terminal 10 is likely to match even if the received account is different. That is, the determination unit 133 increases the weight of the item related to the terminal identification information, and in the browser information to be compared, when the item is matched, the browser is compared with the case where the other items are matched or similar. Adjust so that the degree of similarity between information is high.

  Moreover, the determination part 133 may determine the similarity between browser information using the item with the track record used by the determination process preferentially among several items contained in browser information. Specifically, the determination unit 133 preferentially uses information on items used to determine the level of similarity between users in the past, and determines the degree of similarity between users corresponding to browser information. . This is because the information included in the browser information includes many miscellaneous items, and the processing load increases when the similarity of all items is determined. That is, the determination unit 133 reduces the processing load by preferentially using items that have been used in the determination process in the past and were useful for determining the similarity of the browser information. Can do. For example, the determination unit 133 refers to information related to the similarity and the determination item stored in the user information storage unit 122 to extract items for which processing is prioritized.

  Moreover, the determination part 133 may determine the similarity of browser information by weighting the evaluation of the item with the track record used by the determination process among the some items contained in browser information. Specifically, the determination unit 133 weights the evaluation of information on items used to determine the level of similarity between users in the past, and determines the similarity between users corresponding to browser information. . As described above, the determination unit 133 can be used for the determination process with reference to items that have been used in the determination process in the past and were useful for determining the similarity of the browser information. For this reason, the determination unit 133 adjusts the weighting of a predetermined item that has been useful for the past determination processing by, for example, machine learning of the determination processing result, and performs the determination processing in which the weighting of the predetermined item is performed. Run. For example, the determination unit 133 adjusts an item that is a factor for determining a high degree of similarity of browser information in the past determination process so that the weight is heavier than other items. Thereby, the determination part 133 can perform the determination of the similarity with high accuracy.

  Moreover, the determination part 133 may determine the similarity of browser information based on the relationship of a some item among the items contained in browser information. A specific example will be described below. In such a case, the determination unit 133 determines the similarity between the two types of browser information that has received access at approximately the same time. Assume that the determination unit 133 determines that two types of browser information transmitted from different accounts are accessed by the same terminal based on the terminal identification information included in the browser information. On the other hand, it is assumed that the determination unit 133 determines that the information based on the IP addresses related to both browser information is dissimilar. As described above, it is possible to estimate a certain area of the user terminal 10 (for example, about a municipality) based on the IP address assigned to the user terminal 10 by using the existing technology. is there. At this time, the determination unit 133 may determine the similarity between the two types of browser information as “low” based on the relationship between a plurality of items “IP address” and “terminal identification information”.

  As described above, the reason why the determination unit 133 determines that the similarity between the two types of browser information is “low” is that the users of the user terminals 10 that have accessed from an area that cannot move within a predetermined time are the same. This is because the possibility of being a user is low. For example, the determination unit 133 determines whether the two types of browser information to be compared based on information derived from the IP address are user terminals located in Setagaya-ku, Tokyo during a predetermined time “10 minutes”. 10 and browser information acquired from the user terminal 10 located in Nagoya, Aichi Prefecture. In this case, it is difficult to move from Setagaya Ward, Tokyo to Nagoya City, Aichi Prefecture in 10 minutes. As described above, depending on the relationship between a plurality of items included in the browser information, a contradiction may occur in the operation by the same user. In such a case, the determination unit 133 assumes that the terminal identification information included in the browser information is incorrect or forged for some reason, and reduces the similarity of the users corresponding to the two types of browser information. judge. In this way, the determination unit 133 can detect contradictory information, suspected fraud, and the like by determining the relationship between a plurality of items included in the browser information. A highly accurate determination process can be performed. The above processing may be performed using time difference information, route information, or the like, for example.

(About name collation part 134)
When the similarity determined by the determination unit 133 is greater than or equal to a predetermined threshold, the name identification unit 134 names the users that are comparison targets as the same user. Specifically, the name collation unit 134 according to the first embodiment determines the similarity between the users corresponding to the browser information based on the similarity between the browser information determined by the determination unit 133, and the similarity When the degree is higher than a predetermined threshold, the users to be compared are gathered together.

  The name identification unit 134 can arbitrarily set the predetermined threshold value for performing the name identification process. For example, a service provider may not require certain identity for users who use the service. For example, when it is desired to provide a service common to similar users, it may be sufficient if a certain degree of similarity is recognized by the users to be provided, even if they are not necessarily the same user. In such a case, the name collation unit 134 sets the threshold value for name collation for the similarity determined by the determination unit 133 to be lower than a value determined to have high user identity, thereby identifying the user The width of can be expanded. As a result, the name identification unit 134 not only identifies users whose identity is recognized, but also, for example, appropriately classifies a user group to which a service is provided, or identifies users who are likely to perform fraud as one user. Or categorizing as a layer.

[1-3. (Name identification processing procedure)
Next, the procedure of the name identification process performed by the name identification device 100 according to the first embodiment will be described with reference to FIG. FIG. 5 is a flowchart illustrating a name identification process procedure performed by the name identification device 100 according to the first embodiment.

  As illustrated in FIG. 5, the name collation apparatus 100 determines whether access has been received from the user terminal 10 (step S <b> 101). And the name collation apparatus 100 waits until it receives, when access is not received (step S101; No).

  On the other hand, the name collation apparatus 100 acquires the browser information corresponding to the user terminal 10, when access is received (step S101; Yes) (step S102). Then, the name collation apparatus 100 determines the similarity of browser information (step S103).

  And the name collation apparatus 100 determines whether the similarity of browser information is higher than a predetermined threshold value (step S104). And the name collation apparatus 100 does not collate the user corresponding to browser information as the same user, when the similarity of browser information is not higher than a predetermined threshold value (step S104; No) (step S106).

  On the other hand, when the similarity between browser information is higher than a predetermined threshold (step S104; Yes), the name collation apparatus 100 collates the user corresponding to the browser information as the same user (step S105).

[1-4. effect〕
As described above, the name identification device 100 according to the first embodiment includes the acquisition unit 132, the determination unit 133, and the name identification unit 134. The acquisition unit 132 acquires browser information that is information that can be acquired from the browser of the user terminal 10. Based on the browser information acquired by the acquisition unit 132, the determination unit 133 determines the degree of similarity between users corresponding to the browser information. When the similarity determined by the determination unit 133 is equal to or greater than a predetermined threshold, the name identification unit 134 identifies users corresponding to the similarity as the same user.

  As described above, the name collation apparatus 100 according to the first embodiment uses not information that can be easily changed by the user such as account information or device information but information that cannot be easily changed by the user such as browser information. Then, the degree of similarity of the user is determined. Thereby, the name collation apparatus 100 can determine the identity of a user who uses a plurality of accounts and devices with high accuracy and can perform name collation.

  In addition, the determination unit 133 determines whether the information corresponding to the browser information is based on the similarity between the browser information obtained by comparing the similarity of each item with respect to the information of the plurality of items included in the browser information. Determine similarity.

  Thus, since the name collation apparatus 100 which concerns on 1st Embodiment uses several items useful in order to measure a user's similarity among the acquired browser information, a user's identity is determined with high precision. can do.

  In addition, the determination unit 133 preferentially uses information on an item used to determine the level of similarity between users in the past among the information on a plurality of items included in the browser information. The degree of similarity between users corresponding to is determined.

  Thus, since the name collation apparatus 100 which concerns on 1st Embodiment can discriminate | determine the item to determine by learning the information used for the determination process, it determines a user's identity with high precision. In addition, the processing load can be reduced and the processing speed can be increased.

  In addition, the determination unit 133 performs weighting on the evaluation of information on items used in the past to determine the level of similarity between users among the information on the plurality of items included in the browser information, and the browser information The degree of similarity between users corresponding to is determined.

  Thus, since the name collation apparatus 100 which concerns on 1st Embodiment can weight the item to determine by learning the information used for the determination process, it determines a user's identity with higher precision. can do.

  In addition, the determination unit 133 determines whether the users corresponding to the browser information are based on the similarity between the browser information obtained based on the relationship between the items among the information of the items included in the browser information. The degree of similarity is determined.

  As described above, the name collation device 100 according to the first embodiment adds a determination regarding the relationship between items in which a plurality of items of browser information acquired from different accounts are contradictory to being established at the same time. The similarity of the user is determined. Thereby, the name collation apparatus 100 can improve the determination precision of a user's identity.

  In addition, the acquisition unit 132 preliminarily stores, as browser information, the network communication path of the user terminal 10, the OS of the user terminal 10, the browser software of the user terminal 10, the plug-in in the browser software, the IP address of the user terminal 10, and the user terminal 10. Information on at least one item of the set unique identifier is acquired.

  Thus, since the name collation apparatus 100 which concerns on 1st Embodiment acquires the various information which can be acquired from each account, and uses it for a user's identity determination process, it determines a user's identity with high precision. be able to.

(Second Embodiment)
In the first embodiment, an example is shown in which the services provided by the name collation device 100 are the same service. However, the services need not be the same service. In the second embodiment, an example in which the user terminals 10 using different services are identified will be described.

[2-1. Name identification process)
First, an example of the name identification process according to the second embodiment will be described with reference to FIG. FIG. 6 is a diagram illustrating an example of a name identification process according to the second embodiment. FIG. 6 shows an example in which name identification processing is performed by the name identification device 200.

As illustrated in FIG. 6, the user terminals 10 ₁ to 10 ₃ use a service provided by the name collation device 200 in accordance with an operation by the user U3. In the example shown in FIG. 6, the user terminal 10 ₁ uses the account A31, accessed as merchants mall site provided by the name identification device 200 (step S21). The user terminal 10 _2, using an account A32, accessed as merchants mall site provided by the name identification device 200 (step S22). The user terminal ₁₀₃ uses the account A33, accessed as sellers auction site provided by the name identification device 200 (step S23).

And the name collation apparatus 200 which concerns on 2nd Embodiment is similar to the name collation apparatus 100 which concerns on 1st Embodiment about several user terminal 10 _{1-10 3} using various services, and the similarity degree of browser information. A determination process is performed (step S24). Here, in the example of FIG. 6, it is assumed that the name collation apparatus 200 determines the similarity corresponding to a predetermined range for the browser information corresponding to the user terminals 10 ₁ to 10 ₃ . Specifically, it is assumed that the name identification device 200 recognizes similarity in some items in the browser information but does not determine the similarity high enough to determine the identity of the user. On the other hand, it is assumed that the name collation apparatus 200 did not determine the similarity as low as to deny the user's identity because similarities were recognized in some items of the browser information. The above is, for example, that the browser information transmitted from the user terminals 10 ₁ to 10 ₃ is impersonated, so that useful information for determining the similarity of the browser information has not been sufficiently acquired. Can happen.

In such a case, the name collation device 200 according to the second embodiment acquires usage histories in various services of the user terminals 10 ₁ to 10 ₃ . The name identification device 200 stores the acquired usage history in the usage history storage unit 123.

And the name collation apparatus 200 performs a determination process also about the similarity of the utilization history in the various services of the user terminals 10 ₁ to 10 ₃ together with the determination of the similarity of the browser information. For example, name identification device 200, the user terminal 10 ₁ that is identified by the account A31 is, using the "exhibition shop name AAA" in the shopping mall site, and usage history that it has opened a shop dealing with the "predetermined commodity CCC-related", determining the user terminal 10 ₂ identified by the account A32 is, using the "exhibition shop name BBB" in the shopping mall site, the degree of similarity between the use history that it has opened a shop dealing with the "predetermined commodity CCC-related". Then, the name identification apparatus 200, when the use history obtained from both the user terminal 10 ₁ and 10 ₂ are determined to be similar, the similarity score by similarity score use history of the browser information to add. Thus, the name identification device 200, based on the usage history and browser information is acquired from the user terminal 10 ₁ and 10 _2, determines the similarity between "high".

In addition, the name identification device 200, the user terminal 10 _3, which is identified by the account A33, to get the usage history that has sent the "product CCC" in the auction site. Here, it is assumed that the exhibition information of the account A33 includes information related to “exhibition store name AAA” operated by the account A31 and “exhibition store name BBB” operated by the account A32 in the shipping mall site. For example, in the exhibition information of the account A33, product information of “exhibition store name AAA” and “exhibition store name BBB” is posted or linked.

That is, the name identification device 200, as described above, it acquires the use history of the user terminal ₁₀₃ identified by the account A33, used for the determination process. Name identification device 200 includes a user terminal 10 _3, to determine the similarity of the use history obtained from the user terminal 10 ₁ and 10 ₂ which adds the score of the similarity by the similarity score usage history of browser information . Thus, the name identification device 200 determines a user terminal _103, based on the usage history and browser information is acquired from the user terminal 10 ₁ and 10 ₂ which, the similarity between "medium". In this case, the name collation apparatus 200 may use the similarity between services as one of the determination elements. For example, the name collation apparatus 200 has a high relevance between a shopping mall site and an auction site, and determines a high degree of similarity for users who have a similar use history or a related use history on both sites. . On the other hand, the name collation apparatus 200 has a low relevance between the shopping mall site, the news site, the weather site, and the like, and the usage histories at both sites are evaluated low as an element for determining the identity of the user.

  And the name collation apparatus 200 performs the process of collating the user corresponding to browser information based on the determined similarity (step S25).

  As described above, the name collation device 200 according to the second embodiment acquires the usage history related to the service used by the user terminal 10, and the acquired usage history and the browser information of the user terminal 10 corresponding to the usage history. The similarity between users corresponding to the browser information is determined based on the similarity.

  As described above, the name collation device 200 according to the second embodiment collates users with different accounts as the same user by using the use history in the service in addition to the browser information. Thereby, the name collation apparatus 200 can pinpoint the user who uses a some account accurately, even if it is a case where it is difficult to determine a user's identity only from browser information. In addition, even when there are a plurality of services to be provided, the name collation apparatus 200 can identify users based on the usage history of each service. It becomes possible to capture in the service.

[2-2. (Configuration of name identification device)
Next, the structure of the name collation apparatus 200 which concerns on 2nd Embodiment is demonstrated using FIG. FIG. 7 is a diagram illustrating a configuration example of the name identification device 200 according to the second embodiment. As illustrated in FIG. 7, the name identification device 200 includes a usage history storage unit 123 in addition to the name identification device 100 according to the first embodiment.

(About the usage history storage unit 123)
The usage history storage unit 123 stores information related to usage history when the user uses the service. Here, FIG. 8 illustrates an example of the usage history storage unit 123 according to the second embodiment. In the example illustrated in FIG. 8, the usage history storage unit 123 includes items such as “update date and time”, “account”, “use service”, and “use history”.

  “Update date and time” indicates the date and time when information related to the usage history is updated. “Account” indicates an account transmitted / received to / from the user terminal 10. “Used service” indicates information for identifying a service used by the user. “Usage history” indicates information related to the usage history when the user uses the service. For example, the usage history is a log file in which information related to user behavior in the service is stored.

  That is, in FIG. 8, as information updated on “December 18, 2014, 6:00”, the user terminal 10 identified by the account “A31” is used in the service “SV01 (shopping mall site)”. This indicates that the user has a usage history as represented by the usage history “L01”.

(About the control unit 130)
Returning to the description of FIG. 7, each processing unit of the control unit 130 according to the second embodiment will be described. The acquisition unit 132 according to the second embodiment acquires a usage history related to a service used by the user terminal 10. For example, the acquisition unit 132 acquires the type of service used for each account. In addition, the acquisition unit 132 acquires a specific usage history for each account such as a history of opening a store, a history of buying and selling products, and a search for products on the shopping mall site provided by the providing unit 131. To do.

  Further, the determination unit 133 according to the second embodiment supports browser information based on the usage history acquired by the acquisition unit 132 and the similarity between the browser information of the user terminals 10 corresponding to the usage history. The degree of similarity between users is determined. For example, when the browser information alone is not sufficient to determine the degree of similarity between users, the determination unit 133 determines the similarity of the usage histories by comparing the user usage histories. And the determination part 133 considers the similarity of the determined usage history, and determines the similarity of users. For example, the determination unit 133 determines similarity for the relevance of the service itself used by the user. As an example, the determination unit 133 determines that use of a shopping mall site and use of an auction site are related. About the relevance of such a service, for example, the administrator of the name collation apparatus 200 may set in advance, or by storing information on services used by users with high similarity, such a result Information regarding a highly relevant service may be set by machine learning.

  Furthermore, the determination unit 133 may determine the similarity with respect to the usage mode of the service. For example, the determination unit 133 determines that the usage mode of opening a store on a shopping mall site is related to the usage mode of listing on an auction site. In addition, the determination unit 133 may use, for example, a case where different shopkeepers handle a predetermined number of similar products or perform similar campaigns at the same time as service usage modes. It is determined that there is a high possibility that such store openings are related to each other. In addition, for example, the determination unit 133 is related to a history of searching for a predetermined product name or purchasing such a product on a shopping site and a history of searching for the product name on a search site. judge. In this case, the determination unit 133 compares the consistency of the usage history files L01 to 03 and the like for each account stored in the usage history storage unit 123, the relevance of the service being used, and the like. The similarity of usage history is determined. Note that the determination unit 133 may determine the similarity between users who use the same service. For example, the determination unit 133 determines similarities in purchase tendency among users, such as a history of purchasing a plurality of products using the same shopping site, and purchasing a plurality of expensive products. Moreover, the determination part 133 may determine similarity including a user's action history. For example, the determination unit 133 determines the similarity between users corresponding to the usage history when there is a usage history until transition between various websites and finally purchase at the same shopping site. . As described above, by determining a more specific aspect as a comparison target, the determination unit 133 can determine the similarity regarding the service usage history between users with high accuracy. As described above, the determination unit 133 determines both the usage history that can occur when the user is on the store side and the usage history that can occur when the user is on the user side. Regardless of the position, similarity can be determined.

[2-3. (Name identification processing procedure)
Next, the procedure of the name identification process performed by the name identification device 200 according to the second embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating a name identification process procedure performed by the name identification device 200 according to the second embodiment.

  As illustrated in FIG. 9, the name collation device 200 determines whether access has been received from the user terminal 10 (step S <b> 201). And when the name collation apparatus 200 has not received access (step S201; No), it waits until it receives.

  On the other hand, the name collation apparatus 200 acquires the browser information corresponding to the user terminal 10, when access is received (step S201; Yes) (step S202). And the name collation apparatus 200 acquires also about the utilization log | history corresponding to the user terminal 10 in various services (step S203). Then, the name collation apparatus 200 determines the similarity of browser information (step S204).

  And the name collation apparatus 200 determines whether the determined similarity is higher than a predetermined threshold value (step S205). When the similarity is higher than a predetermined threshold (step S205; Yes), the name collation apparatus 200 collates the users corresponding to the browser information as the same user (step S206).

  On the other hand, if the similarity of the browser information is not higher than the predetermined threshold (Step S205; No), the name collation apparatus 200 determines whether the similarity of the browser information is within a predetermined range (Step S205). S207). If the degree of similarity is within the predetermined range (step S207; Yes), the name collation apparatus 200 further determines whether or not there is similarity in the usage history corresponding to the user (step S208).

  If it is determined that the user's usage history is similar (step S208; Yes), the users corresponding to the browser information and the usage history are identified as the same user (step S206). On the other hand, when it is determined that there is no similarity in the user's usage history (step S208; No), and when the similarity is not within a predetermined range (step S207; No), the name collation apparatus 200 is compared. The identified users are not identified as the same user (step S209).

[2-4. effect〕
As described above, the acquisition unit 132 according to the second embodiment acquires the use history related to the service used by the user terminal 10. Further, the determination unit 133 according to the second embodiment adds the browser information to the browser information based on the usage history acquired by the acquisition unit 132 and the similarity between the browser information of the user terminals 10 corresponding to the usage history. The degree of similarity between corresponding users is determined.

  As described above, the name collation device 200 according to the second embodiment collates users with different accounts as the same user by using the use history in the service in addition to the browser information. Thereby, the name collation apparatus 200 can pinpoint the user who uses a some account accurately, even if it is a case where it is difficult to determine a user's identity only from browser information.

[3. (Modification)
Each embodiment mentioned above may be implemented with various different forms other than the above-mentioned embodiment. Accordingly, other embodiments will be described below.

[3-1. account〕
In the above-described embodiment, an example in which a user uses a service using an account has been described. Here, depending on the user, an account may be registered in the name collation apparatus 100 at an arbitrary time using a service provided by the name collation apparatus 100 or the like (name collation apparatus 100 or name collation apparatus 200) without registering an account. In this case, the name collation apparatus 100 or the like can perform the above-described name collation process based on browser information corresponding to the same user.

[3-2. Web page〕
In each of the above-described embodiments, a predetermined website is shown as an example of a service provided by the name collation device 100 or the like. However, the name collation device 100 or the like may be an application installed on the user terminal 10 or a user terminal 10. You may provide services, such as an electronic book memorize | stored in video. The name collation device 100 or the like is based on browser information transmitted when an application provided to the user terminal 10, an electronic book, a video, or the like is downloaded or used, a user usage history, and the like. The name identification process may be performed.

[3-3. Example of usage history)
Moreover, in each embodiment mentioned above, the name collation apparatus 100 showed the example which acquires the store opening to a shopping site, the purchase history of goods, etc. as a user's utilization log | history. However, the name collation apparatus 100 may acquire further different information as the use history of the user. For example, the name identification device 100 includes a time stamp recorded when the user terminal 10 takes a predetermined action (for example, when accessing a specific service), and a position of the user terminal 10 at the time recorded in the time stamp. Get information. Thereby, the name collation apparatus 100 can acquire the information regarding a user's action pattern as a service utilization log | history. And the name collation apparatus 100 is based on the information extracted from the acquired user's action pattern, and the similarity of the users corresponding to browser information based on the similarity of browser information of the user terminal corresponding to this action pattern. Determine the degree. Thus, since the name collation apparatus 100 can determine the degree of similarity between users using an action history that the user is not aware of, such as a user's action pattern and a habit, the determination accuracy can be further improved.

[3-4. Device configuration〕
Moreover, in each embodiment mentioned above, the name collation apparatus 100 grade | etc., Showed the example which provides various services. However, a device that performs a process for identifying users and a device that provides various services may be different devices. This point will be described with reference to FIG. FIG. 10 is a diagram illustrating a configuration example of the name identification system 1 according to the second embodiment.

The control unit 130 of the name collation apparatus 200 illustrated in FIG. 10 does not include the providing unit 131 but includes the acquisition unit 132 and the determination unit 133. Also, the name identification apparatus 200 shown in FIG. 10, through the network N, the service providing apparatus 20 ₁ and 20 ₂ are connected. The service providing apparatuses 20 ₁ and 20 ₂ are server apparatuses for providing various services via the network N. For example, the service providing apparatus 20 ₁ and 20 ₂ is managed by the name identification device 200 receives access from the user terminal 10, when the name identification device 200 receives an access from the user terminal 10, a variety of services to the user terminal 10 provide. For example, the service providing apparatus 20 ₁ includes a providing unit for providing a shopping mall service, the service providing apparatus 20 ₂ includes a providing unit for providing an auction service. Then, the service providing apparatus 20 ₁ and 20 ₂ transmits information such as usage history when the user uses the service to name identification device 200. As described above, the name identification device 200 illustrated in FIG. 10 serves as a front-end server that communicates with the user terminal 10. That is, the name identification processing has been described above is executed by the name identification device 200 is a front-end server that manages the service providing apparatus 20 ₁ and 20 _2.

  Further, the name identification device 200 illustrated in FIG. 10 may not include the storage unit 120. Specifically, the name identification device 200 illustrated in FIG. 10 may be connected to an external database server that holds the storage unit 120. Moreover, the name collation apparatus 200 shown in FIG. 10 is applicable also to the name collation apparatus 100. FIG.

[4. Others]
In addition, among the processes described in the above-described embodiments, all or part of the processes described as being automatically performed can be manually performed, or have been described as being manually performed. All or a part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the determination unit 133 and the name identification unit 134 illustrated in FIG. 2 may be integrated.

  Moreover, each embodiment mentioned above can be combined suitably in the range which does not contradict a process content.

[5. Hardware configuration)
Moreover, the name collation apparatus 100 which concerns on embodiment mentioned above is implement | achieved by the computer 1000 of a structure as shown, for example in FIG. FIG. 11 is a hardware configuration diagram illustrating an example of a computer 1000 that realizes the functions of the name identification device 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and the data generated by the CPU 1100 via the communication network 500 is sent to the other devices. Send to device.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the name identification device 100, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. In addition, each data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from other devices via the communication network 500.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art It is possible to implement the present invention in other forms with improvements.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 name identification system 10 user terminal 100 name identification device 110 communication unit 120 storage unit 121 browser information storage unit 122 user information storage unit 123 usage history storage unit 130 control unit 131 providing unit 132 acquisition unit 133 determination unit 134 name identification unit

Claims (12)

An acquisition unit for acquiring browser information , which is information that can be acquired from the browser of the user terminal;
A determination unit that determines the similarity between a plurality of browser information acquired by the acquisition unit;
When the similarity determined by the determination unit is equal to or greater than a predetermined threshold, a name identification unit that identifies users who use the user terminal that is the transmission source of browser information corresponding to the similarity as the same user,
The name collation apparatus characterized by having provided. The determination unit
On the basis of the similarity of the browser information each other is determined by comparing the trend of similarity browser information has, determines the similarity between users corresponding to the browser information,
The name collation apparatus of Claim 1 characterized by the above-mentioned. The determination unit
Based on the similarity between the browser information obtained by comparing the similarity of each item in the information of a plurality of items included in the browser information , the similarity between users corresponding to the browser information is determined. ,
The name collation apparatus of Claim 1 or 2 characterized by the above-mentioned. The determination unit
Among the information of a plurality of items included in the browser information , the information of the items used for determining the level of similarity between users in the past is used preferentially, and the users corresponding to the browser information Determine the similarity,
The name collation apparatus of Claim 3 characterized by the above-mentioned. The determination unit
Among the information of a plurality of items included in the browser information , weighting is performed on the evaluation of the information of items used in the past to determine the level of similarity between users, and between users corresponding to the browser information Determine the similarity,
The name collation apparatus of Claim 3 or 4 characterized by the above-mentioned. The determination unit
Based on the similarity between the browser information obtained based on the relationship between the items among the information of the plurality of items included in the browser information , the similarity between the users corresponding to the browser information is determined. To
The name collation apparatus as described in any one of Claims 3-5 characterized by the above-mentioned. The acquisition unit
To get the usage history for the service to be used before to Kiyu over The terminal,
The determination unit
Based on the usage history acquired by the acquisition unit, the degree of similarity between users corresponding to the browser information is determined.
The name collation apparatus as described in any one of Claims 1-6 characterized by the above-mentioned. The acquisition unit
As the usage history, obtain a purchase history or search history in the service,
The determination unit
Based on the purchase history or search history acquired by the acquisition unit, determine the similarity between users corresponding to the browser information ,
The name collation apparatus of Claim 7 characterized by the above-mentioned. The acquisition unit
As the usage history, acquire location information of a user who uses the service, and time information when the location information is acquired,
The determination unit
Based on the position information and time information acquired by the acquisition unit, the degree of similarity between users corresponding to the browser information is determined.
The name collation apparatus of Claim 7 or 8 characterized by the above-mentioned. The acquisition unit
As the browser information , the network communication path of the user terminal, the OS of the user terminal, the browser software of the user terminal, the plug-in in the browser software, the IP address of the user terminal, and a unique preset in the user terminal Obtaining information about at least one item of the identifier,
The name collation apparatus as described in any one of Claims 1-9 characterized by the above-mentioned. A name identification method performed by a computer,
An acquisition step of acquiring browser information , which is information that can be acquired from the browser of the user terminal;
A determination step of determining a degree of similarity between a plurality of browser information acquired by the acquisition step;
When the similarity determined by the determination step is equal to or greater than a predetermined threshold, a name identification step of identifying users who use the user terminal that is the transmission source of browser information corresponding to the similarity as the same user,
Name identification method characterized by including. An acquisition procedure for acquiring browser information , which is information that can be acquired from the browser of the user terminal;
A determination procedure for determining a similarity between a plurality of browser information acquired by the acquisition procedure;
When the similarity determined by the determination procedure is equal to or greater than a predetermined threshold, a name identification procedure for identifying users who use the user terminal that is the transmission source of browser information corresponding to the similarity as the same user,
A name identification program characterized by causing a computer to execute.

Images