Information Processing Apparatus, Information Processing System, Information Processing Method, and Program

Abstract

Authenticate the user's identity accurately using fingerprinting technology. 【Solution means】 The present invention includes an acquisition unit 11a that acquires attribute information from the user's terminal device, an ID issuance unit 11b that issues a user ID related to the user, a storage unit 13 that stores the user ID and the attribute information in association with each other, a management unit 11c that manages the user ID, and a determination unit 11d that determines the user's identity by collating the user ID stored in the storage unit with a newly issued new user ID. The attribute information is classified into first to third layers according to the degree of change. The determination unit is an information processing device that performs identity determination by collating information related to the first and second layers with a high degree of change among the information included in the attribute information.

Description

Technical Field

[0001] The present invention relates to a technology for accurately authenticating the identity of a user using fingerprinting technology.

Background Art

[0002] Conventionally, Cookie and fingerprinting technologies have been used to identify users who access a website.

[0003] Fingerprinting technology is a technology for identifying the device (browser) used by a user, and collectively refers to attribute information such as information about the software used on the device, information about the device specifications, and information about the network as fingerprint information. According to fingerprinting technology, the identity of a user is authenticated based on this fingerprint information.

[0004] Here, for example, in Patent Document 1, when the user device is invariant, device fingerprinting is performed, and the result is compared with a snapshot of the device taken at the time of successful authentication. When the comparison is within a change or threshold, a technology that allows the persistence of authentication is disclosed.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, in Patent Document 1, there is no disclosure of classifying each piece of attribute information included in fingerprint information according to its importance in identity determination, and further using AI technology to perform identity determination based on these classifications.

[0007] The present invention has been made in view of such problems, and its object is to accurately authenticate the identity of a user by using fingerprinting technology and based on classification according to the importance of fingerprint information.

Means for Solving the Problems

[0008] To solve the above problems, an information processing apparatus according to an aspect of the present invention includes an acquisition unit that acquires attribute information from a user's terminal device, an ID issuance unit that issues a user ID related to the user, a storage unit that stores the user ID and the attribute information in association with each other, a management unit that manages the user ID, and a Record User determination unit that determines the identity of the user, and the attribute information is classified into first to third layers according to the degree of change, and the determination unit Check whether the newly issued new user ID already exists in the memory unit. If it does not exist, collate the information related to Layer 1 with a low degree of change. If the similarity is high, then collate the information related to Layer 2 with a low degree of change to perform the identity determination.

[0009] An information processing system according to another aspect of the present invention is an information processing system including a user's terminal device, an information processing apparatus, and an artificial intelligence server. The terminal device includes a transmission unit that transmits attribute information to the information processing apparatus. The information processing apparatus includes an acquisition unit that acquires attribute information from a user's terminal device, an ID issuance unit that issues a user ID related to the user, a storage unit that stores the user ID and the attribute information in association with each other, a management unit that manages the user ID, and a Record User determination unit that determines the identity of the user. The artificial intelligence server includes a generation unit that generates vector information using a learned model with the attribute information as an input. The attribute information is classified into first to third layers according to the degree of change, and the determination unit Check whether the newly issued new user ID already exists in the memory unit. If it does not exist, collate the information related to Layer 1 with a low degree of change. If the similarity is high, then collate the information related to Layer 2 with a low degree of change to perform the identity determination.

[0010] An information processing method according to another aspect of the present invention includes an acquisition unit that acquires attribute information from a user's terminal device, an ID issuance unit that issues a user ID related to the user, a storage unit that stores the user ID and the attribute information in association with each other, a management unit that manages the user ID, and a determination unit that , the previous determines the identity of the registered user, the attribute information is classified into first to third layers according to the degree of change, and the determination unit , Check whether the newly issued new user ID already exists in the memory unit. If it does not exist, collate the information related to Layer 1 with a low degree of change. If the similarity is high, then collate the information related to Layer 2 with a low degree of change to perform the identity determination.

[0011] A program according to another aspect of the present invention causes a computer to function as an acquisition unit that acquires attribute information from a user's terminal device, an ID issuance unit that issues a user ID related to the user, a storage unit that stores the user ID and the attribute information in association with each other, a management unit that manages the user ID, and a Record User determination unit that determines the identity of the user, the attribute information is classified into first to third layers according to the degree of change, and the determination unit Check whether the newly issued new user ID already exists in the memory unit. If it does not exist, collate the information related to Layer 1 with a low degree of change. If the similarity is high, then collate the information related to Layer 2 with a low degree of change to perform the identity determination.

Advantages of the Invention

[0012] According to the present invention, it is possible to provide a technique for accurately authenticating the identity of a user based on classification according to the importance of fingerprint information using fingerprinting technology.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0015] <First Embodiment>

[0016] FIG. 1 shows and explains the configuration of an information processing system according to an embodiment of the present invention.

[0017] As shown in the figure, the information processing system according to the embodiment of the present invention includes a fingerprint server 1 as an information processing device, a user's terminal device 2, an AI server 3, a training device 4, and a database 13. These devices are wirelessly or wiredly communicably connected via a network such as the Internet. As the terminal device 2, various devices such as a smartphone, a tablet terminal, a notebook personal computer, and a desktop personal computer can be adopted.

[0018] In such a configuration, the user accesses a website 5 that they desire to view using the terminal device 2. The website 5 has a control tag 5A embedded therein, and due to the function related to the control tag 5A, fingerprint information as attribute information of a device or the like is transmitted from the terminal device 2 to the fingerprint server 1.

[0019] When the fingerprint server 1 acquires the fingerprint information, it issues a personal identification information (ID), and registers the acquired fingerprint information in the DB13 in association with the ID. The fingerprint server 1 further transmits the fingerprint information to the AI server 3, and at the AI server 3, the fingerprint information is converted into vector information using a learned model. This vector information is sent to the fingerprint server 1 and registered in the DB13 as data for determination processing.

[0020] The fingerprint server 1, although details will be described later, when authenticating the user's identity, obtains the similarity of the vector information associated with the ID, and determines whether the user is the same person or a different person based on the similarity. The determination result is sent to the website 5. Therefore, an advertisement server (not shown) that operates the website 5 can execute an optimal advertisement on the website 5 upon receiving the authentication result related to the user's identity.

[0021] In addition, the training device 4 acquires the registration data (ID, fingerprint information) in the DB13, trains the learning model of the AI server 3, and updates the learned model 3B, thereby devising to improve the accuracy of generating vector information.

[0022] Figure 2 is a functional block diagram of the fingerprint server.

[0023] As shown in the figure, the fingerprint server 1 has a control unit 11, a communication unit 12, and a storage unit 13. The communication unit 12 is realized by, for example, a NIC (Network Interface Card) or the like, and receives various information from the user's terminal device 2 via a communication network such as the Internet, and transmits the determination result of the user's identity and the like to the website 5.

[0024] The storage unit 13 is realized by, for example, a memory such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and a storage device such as an HDD (Hard Disc Drive), an SSD (Solid State Drive), and a flash memory, and stores, for example, user information, a learned model for determination processing, and various programs.

[0025] That is, the storage unit 13 stores fingerprint information, vector information, etc. in association with the user ID as user information.

[0026] Here, the fingerprint information is classified into the following three layers.

[0027] a) Layer 1 This is an extremely important item for identifying the user, and usually, in the case of the same user, it is an item that is not changed. For example, information with high security (information that can always be detected), information obtained from the hardware of the user's terminal device 2 and that cannot be changed or is rarely changed, information obtained from the user's browser and that cannot be changed or is rarely changed, etc. correspond to the items of Layer 1.

[0028] b) Layer 2 This is an item that is less likely to change if the user is the same. For example, information with high security (information that can always be detected), information obtained from the hardware of the user's terminal device 2 and that can be changed, information obtained from the user's browser and that can be changed, etc. correspond to the items of Layer 2.

[0029] c) Layer 3 This is an item that changes frequently. For example, information with low stability (information where detectable and non-detectable cases are mixed), information obtained from the hardware of the user's terminal device 2 but frequently changed, information obtained from the user's browser but frequently changed, etc. correspond to the items in layer 3.

[0030] More specifically, the items in layer 1 include the font list available in the browser, the validity of the browser's session storage, the validity of the browser's local storage, the availability of D in the browser, the availability of the API (Application Programming Interface) of the DB (Database), the vendor information and extension functions and features of the browser, the presence or absence of support for mathematical functions in the browser, the operating system, the memory capacity of the device and the number of CPU (Central Processing Unit) threads, the device platform of the device, the presence or absence of a video card, etc.

[0031] The items in layer 2 include the type of browser, the set language, the plugin list, the validity of the browser's cookies, the presence or absence of support for the browser's monochrome mode, the design contrast of the browser, the validity of the browser's PDF viewer, the user agent, the user's time zone information, the responsiveness to the touch screen, etc.

[0032] The items in layer 3 include the presence or absence of installation of a DOM blocker in the browser, the set font of the browser, the responsiveness to the browser's inverted color, the IP address, the screen frame (information regarding resolution and size), information regarding the operating system and CPU, the color depth in the browser (such as 24 bits), the screen resolution, the class of the CPU, the color gamut on the device (sRGB, P3, etc.), the validity of the forced color scheme, the responsiveness to the browser's high dynamic range, the time taken for data collection, the time of accessing the site, the currently accessed URL, the time stamp at the first registration, the time stamp at the last update, etc.

[0033] The control unit 11 is implemented by a processor such as a CPU or an MPU (Micro Processing Unit), and by reading and executing the program in the storage unit 13, it functions as, for example, an acquisition unit 11a, an ID (identification information) issuing unit 11b, a management unit 11c, a determination unit 11d, a communication control unit 11e, a training unit 11f, and a settlement unit 11g.

[0034] The acquisition unit 11a acquires the fingerprint information sent from the terminal device 2 by the action of the control tag 5A embedded in the website 5. The details of the fingerprint information are as described above, and its items are roughly classified into three layers 1 to 3 according to the importance. The ID issuing unit 11b issues a user ID (VisitorID) at the timing when the fingerprint information is acquired. The management unit 11c associates the issued VisitorID with the fingerprint information and stores and manages it in the storage unit 13.

[0035] The acquisition unit 11a transmits the acquired fingerprint information to the AI server 3, and in the AI server 3, as shown in FIG. 6, vector information is generated from the fingerprint information using the learned model 3B, the vector information is acquired, and the management unit 11c stores the vector information in the storage unit 13 in association with the VisitorID. The vector information is used for determining the identity of the user, which will be described later.

[0036] The determination unit 11d determines the identity of the user. That is, more specifically, the determination unit 11d checks whether the VisitorID already exists in the Visitor table of the storage unit 13 (see, for example, FIG. 9). If it exists, the VisitorID and the fingerprint information are registered in the management table, and the original user ID (OriginalVisitorID) that has already been registered is transmitted to the terminal device 2 as the determination result. On the other hand, when the VisitorID does not exist in the Visitor table of the storage unit 13, among the vector information related to the fingerprint information, the vector information related to layer 1 is collated. If the similarity is high, then the vector information related to layer 2 is collated. If a match can be confirmed in a predetermined number or more of items, the VisitorID and the fingerprint information are registered in the management table, and the original user ID (OriginalVisitorID) that has already been registered is transmitted to the terminal device 2 as the determination result. On the other hand, when a match of the vector information cannot be confirmed in a predetermined number or more of items for layer 2, a new VisitorID is issued and transmitted to the terminal device 2 as the determination result.

[0037] The state of this determination is as shown in FIG. 7. The vector information related to the fingerprint information acquired last time and the vector information related to the fingerprint information acquired this time are collated by a determination process, and the identity is determined based on the calculated similarity. In this example, the similarity is indicated by a value from 0 to 1. When the similarity is 1, it is determined to be the same person. When the similarity is from 0.90 to 0.99, it is regarded as the same person. When the similarity is from 0.01 to 0.89, it is regarded as a different person. When the similarity is 0, it is determined to be a different person. However, this is just an example, and it is of course not limited to this.

[0038] In the determination process by the determination unit 11d, it is also possible to use both the determination using the learned model and the rule-based determination. That is, the determination unit 11d uses the learned model stored in the storage unit 13, and uses the vector information related to the registered fingerprint information acquired last time and the vector information related to the fingerprint information acquired this time as input data to perform identity determination by the learned model, and obtains the first similarity as the output. Next, referring to the table related to the layer classification of the predetermined fingerprint information, collate each item of layer 1 and layer 2 based on the rule, and obtain the second similarity as the output. Then, integrate the first similarity and the second similarity, for example, by taking a weighted average, calculate the final third similarity, and determine the identity of the user based on the third similarity.

[0039] The communication control unit 11e functions as a transmission unit that controls to transmit the determination result by the determination unit 11d to the advertisement server of the website 5 or the like. The training unit 11f trains the learning model used in the determination process by the determination unit 11d. Specifically, using the user ID (visitorID) and the fingerprint information as a learning dataset, train the learning model, generate a learned model, and store and update it in the storage unit 13.

[0040] In addition to the above, the settlement unit 11g performs electronic settlement of the rebate amount or the like for the user when this system is applied to an affiliate service or the like.

[0041] Figure 3 is a hardware configuration diagram of the fingerprint server.

[0042] As shown in the figure, the information processing apparatus 1 includes a processor 101, a memory 102, a storage device 103, a communication interface 104, an input device 105, and an output device 106. The processor 101 is composed of a CPU, an MPU, a GPU (Graphics Processing Unit), etc.

[0043] The memory 102 is composed of a RAM, a ROM, etc. The storage device 103 is a so-called storage and is composed of an HDD, an SSD, a flash memory, etc.

[0044] The communication interface 104 is composed of an adapter, a modem, a router, various connectors, etc. for connecting to the communication network 4. The input device 105 is composed of a keyboard, a mouse, an operation switch, a microphone, etc. And the output device 106 is composed of a display, a speaker, etc.

[0045] In such a configuration, the processor 101 reads out the control program stored in advance in the storage device 103, expands it in the memory 102, and executes it, thereby functioning as the control unit 11 as detailed in FIG. 2.

[0046] FIG. 4 is a functional block diagram of the terminal device.

[0047] As shown in the figure, the terminal device 2 has a control unit 21, a communication unit 22, an input unit 23, an output unit 24, and a storage unit 25. The communication unit 22 is realized by, for example, a NIC, etc., and transmits fingerprint information, etc. to the fingerprint server 1 as an information processing device via a communication network such as the Internet, and receives a determination result (visitorID), etc. from the information processing device 1.

[0048] The input unit 23 has a camera, a microphone, a sensor, an operation device such as a keyboard or a mouse, etc. Input data is input from the operation device to the control unit 21. The output unit 24 has a speaker, a display, etc. Sound is emitted from the speaker, and an input screen, etc. is displayed on the display.

[0049] The storage unit 25 is realized by, for example, a memory such as a RAM or a ROM and a storage device such as an HDD, an SSD, or a flash memory, and stores, for example, acquired input information, image data related to received works, etc., and various programs.

[0050] The control unit 21 is implemented by a processor such as a CPU or an MPU. By reading and executing the program in the storage unit 23, it functions as, for example, a communication control unit 21a, a browser unit 21b, a main control unit 21c, etc. The communication control unit 21a functions as a transmission unit that transmits fingerprint information and the like to the fingerprint server 1 as an information processing device, and a reception unit that receives a determination result and the like from the fingerprint server 1. The browser unit 21b controls various screen displays on the display included in the output unit 24. The main control unit 21c is in charge of various other controls.

[0051] Hereinafter, with reference to the flowchart of FIG. 5, the processing procedure by the fingerprint server as the information processing device according to the embodiment of the present invention will be described in detail.

[0052] When the process starts, the acquisition unit 11a acquires the fingerprint information sent from the terminal device 2 by the action of the control tag 5A embedded in the website 5 (S1). The details of the fingerprint information are as described above, and its items are roughly classified into three layers 1 to 3 according to the importance. Subsequently, the ID issuance unit 11b issues a user ID (VisitorID) at the timing when the fingerprint information is acquired (S2). The management unit 11c associates the issued VisitorID with the fingerprint information and stores and manages it in the storage unit 13 (S3).

[0053] The acquisition unit 11a transmits the acquired fingerprint information to the AI server 3. In the AI server 3, as shown in FIG. 6, the generation unit 2B uses the learned model 3B to generate vector information from the fingerprint information, acquires the vector information, and the management unit 11c stores the vector information in the storage unit 13 in association with the VisitorID (S4). This vector information is used when determining the identity of the user, which will be described later.

[0054] Subsequently, the determination unit 11d determines the identity of the user (S5). That is, the determination unit 11d checks whether the VisitorID already exists in the Visitor table (see FIG. 9) of the storage unit 13. If it exists (branch to Yes in S6), the VisitorID and fingerprint information are registered in the management table, and the original user ID (OriginlVisitorID) that has already been registered is transmitted to the terminal device 2 as the determination result (S8).

[0055] On the other hand, if the VisitorID does not exist in the Visitor table of the storage unit 13 (branch to No in S6), among the vector information related to the fingerprint information, the vector information related to layer 1 is collated. If the similarity is high, then the vector information related to layer 2 is collated. If a match can be confirmed in a predetermined number or more of items (branch to Yes in S7), the VisitorID and fingerprint information are registered in the management table, and the original user ID (OriginalVisitorID) that has already been registered is transmitted to the terminal device 2 as the determination result (S8).

[0056] Regarding layer 2, if a match cannot be confirmed in a predetermined number or more of items (branch to No in S7), a new VisitorID is issued and transmitted to the terminal device 2 as the determination result (S10).

[0057] The state of such determination processing is as described above with reference to FIG. 7. The vector information related to the fingerprint information acquired last time and the vector information related to the fingerprint information acquired this time are collated by the determination processing, and the identity is determined based on the calculated similarity. In this example, the similarity is indicated by a value from 0 to 1. In the case of 1, it is the same person; in the case of 0.90 to 0.99, it is regarded as the same person; in the case of 0.01 to 0.89, it is regarded as a different person; and in the case of 0, it is determined to be a different person. However, this is just an example and is not limited thereto.

[0058] In the determination process (S4) by the determination unit 11d, a determination using a learned model and a rule-based determination are used in combination. That is, as shown in FIG. 8, the determination unit 11d first uses the learned model stored in the storage unit 13, and uses the vector information related to the registered fingerprint information acquired last time and the vector information related to the fingerprint information acquired this time as input data, and performs an identity determination by the learned model to obtain the first similarity as an output (S4-1). Next, referring to a table related to the layer classification of the predetermined fingerprint information, each item of layer 1 and layer 2 is collated based on a rule to obtain the second similarity as an output (S4-2). Then, the first similarity and the second similarity are integrated, for example, by taking a weighted average, to calculate the final third similarity, and the identity of the user is determined based on the third similarity (S4-3).

[0059] As described above, according to the first embodiment of the present invention, the fingerprint information is classified into three layers according to the degree such as the frequency of change, and appropriate identity determination can be performed according to the importance of each layer. Therefore, an advertising server or the like that has obtained a determination result can implement an optimal advertisement or the like for the user.

[0060] <Second Embodiment>

[0061] The information processing system according to the second embodiment is an application of the information processing system according to the first embodiment to an affiliate service. Since the configuration of each device is as described above with reference to FIGS. 1 to 4, the same reference numerals will be used to describe the same configuration below.

[0062] Hereinafter, with reference to the flowchart of FIG. 10, the processing procedure by the information processing system according to the second embodiment of the present invention will be described in detail.

[0063] When the process starts, upon receiving a user's access to the website (S21), the announcement server queries the fingerprint server 1 to obtain the OriginalVisitorID (S22), and registers it in the access history table (S23). An example of the access history table is as shown in FIG. 11, where the partner code, campaign code, and update date are stored in association with the OriginalVisitorID.

[0064] Subsequently, when the user performs account registration (S24), the OriginalVisitorID is obtained again (S25), the access history table is referred to, the campaign code associated with the OriginalVisitorID is obtained (S26), the transaction account data is updated (S27), and thus a series of processes are terminated.

[0065] As described above, according to the second embodiment of the present invention, by managing the OriginalVisitorID issued by the fingerprint server in association with the campaign code, it becomes possible to appropriately distribute rewards to users, such as affiliates.

[0066] Although the embodiments of the present invention have been described above, it goes without saying that the present invention is not limited thereto and various improvements and modifications can be made without departing from the gist thereof.

[0067] For example, the application example of this embodiment is not limited to the affiliate service described above, and it goes without saying that it can be applied to a wide variety of uses.

Explanation of Reference Numerals

[0068] 1... Fingerprint server, 2... Terminal device, 3... AI server, 3A... Generation unit, 3B... Trained model, 4... Training device, 5... Website, 5A... Tag, 11... Control unit, 11a... Acquisition unit, 11b... ID issuance unit, 11c... Management unit, 11d... Judgment unit, 11e... Communication control unit, 11f... Training unit, 11g... Settlement unit, 12... Communication unit, 13... Memory unit, 21... Control unit, 21a... Communication control unit, 21b... Browser unit, 21c... Main control unit, 22... Communication unit, 23... Operation unit, 24... Display unit, 25... Memory unit 25, 101... Processor, 102... Memory, 103... Storage device, 104... Communication interface, 105... Input device, 106... Output device.

Claims

1. An acquisition unit that acquires attribute information from a user's terminal device; an ID issuing unit that issues a user ID related to the user; a storage unit that stores the user ID and the attribute information in association with each other; A management unit for managing the user ID; A determination unit that determines the identity of the user, The attribute information is classified into first to third layers according to the degree of change, The determination unit checks whether the newly issued new user ID already exists in the storage unit, and if not, compares information related to layer 1, which has a low degree of change, and if the degree of similarity is high, compares information related to layer 2, which has a low degree of change, to perform the identity determination. Information processing device.

2. Among the attribute information, the first layer is classified as items that are extremely important in identifying a user and do not change for the same user, the second layer is classified as items that are unlikely to change for the same user, and the third layer is classified as items that change frequently. The information processing device according to claim 1.

3. The determination unit performs the determination of the identity by collating vector information obtained by converting the attribute information. The information processing device according to claim 1 .

4. An information processing system comprising a user terminal device, an information processing device, and an artificial intelligence server, The terminal device a transmission unit that transmits attribute information to the information processing device, The information processing device includes: An acquisition unit that acquires attribute information from a user's terminal device; an ID issuing unit that issues a user ID related to the user; a storage unit that stores the user ID and the attribute information in association with each other; A management unit for managing the user ID; A determination unit that determines the identity of the user, The artificial intelligence server includes: A generation unit that generates vector information using a trained model with the attribute information as an input, The attribute information is classified into first to third layers according to the degree of change, The determination unit checks whether the newly issued new user ID already exists in the storage unit, and if not, compares information related to layer 1, which has a low degree of change, and if the degree of similarity is high, compares information related to layer 2, which has a low degree of change, to perform the identity determination. Information processing system.

5. The acquisition unit acquires attribute information from a terminal device of a user, an ID issuing unit issues a user ID related to the user; A storage unit stores the user ID and the attribute information in association with each other, A management unit manages the user ID, A determination unit determines the identity of the user, The attribute information is classified into first to third layers according to the degree of change, The determination unit checks whether a newly issued new user ID already exists in the storage unit, and if not, compares information related to layer 1, which has a low degree of change, and if the degree of similarity is high, compares information related to layer 2, which has a low degree of change, to perform the identity determination. Information processing methods.

6. Computer, An acquisition unit that acquires attribute information from a user's terminal device; an ID issuing unit that issues a user ID related to the user; a storage unit that stores the user ID and the attribute information in association with each other; A management unit for managing the user ID; a determination unit for determining the identity of the user; The attribute information is classified into first to third layers according to the degree of change, The determination unit checks whether the newly issued new user ID already exists in the storage unit, and if not, compares information related to layer 1, which has a low degree of change, and if the degree of similarity is high, compares information related to layer 2, which has a low degree of change, to perform the identity determination. program.

Images