KR102139257B1 - System for providing non face to face authentication service - Google Patents

Abstract

The present invention relates to a system for providing a contact-free authentication service which is to confirm a user and prevent money laundering by processing contact-free authentication of the user with a photo or image according to regulations of financial action task force on money laundering (FATF). According to the present invention, the system comprises: a user information registering unit for requesting a user for a first evidence file including an identification photo photographed with a face of a corresponding user and a second evidence file including a photo or image of the corresponding user to register the same; a user confirming unit for confirming the truth of an identification of the user included in the first and second evidence files by using an artificial intelligence algorithm and user data predetermined as faked and performing user authentication to detect counterfeiting; and a user authentication result providing unit for providing a user with a result through the user confirming unit and a user risk level calculating unit.

Description

System for providing face-to-face authentication service{SYSTEM FOR PROVIDING NON FACE TO FACE AUTHENTICATION SERVICE}

An embodiment of the present invention relates to a system for providing an in-person authentication service.

In general, the non-face-to-face authentication service refers to a service that does not verify the direct identification of the person who intends to join to use the company's service, but submits documents necessary for identification and verifies the authentication.

Most companies that provide services related to financial transactions or cryptocurrency transactions require identification of users using the services. At this time, the provisions of the International Financial Laundering Anti-Money Laundering (FATF: Financial　Action　Task　Force　on　Money　Laundering) In order to follow, each country's financial institution or cryptocurrency handling company must perform the user's face-to-face authentication.

Published Patent Publication No. 10-2014-0038590 (Publication date: March 31, 2014) Published Patent Publication No. 10-2018-0007541 (Publication date: January 23, 2018)

In an embodiment of the present invention, in accordance with the provisions of the International Money Laundering Prevention Financial Measures Organization (FATF: Financial　Action　Task　Force　on　Money 따라Laundering), the user's face-to-face authentication is processed by a picture or video to prevent user identification and money laundering. For non-face-to-face authentication service providing system.

The system for providing a non-face-to-face authentication service according to an embodiment of the present invention requests a first proof file including a photo ID of a user and a second proof file including a photo or video of the user from the user. User information register to receive registration; A user identification unit for detecting falsification by performing authenticity verification and identification of a user's identification card included in the first proof file and the second proof file using artificial intelligence algorithm and user data previously determined by counterfeiting; A user risk level that extracts at least one or more user data included in the ID of a normal authenticated user through the user identification unit, compares the extracted user data with blacklist data, and calculates a user's risk level according to the comparison result Calculation unit; And a user authentication result providing unit that provides a result through the user identification unit and the user risk level calculation unit to the user.

In addition, the user identity verification unit, using the OCR (optical character reader) character recognition unit for recognizing and digitizing the text present in the ID photo; An MRZ identification unit that recognizes a machine readable zone (MRZ) present in the ID photograph and confirms the identity on a distributed protocol; A human face discrimination unit for determining whether each of the first and second evidence files includes a human face using an artificial intelligence algorithm; Using an artificial intelligence algorithm, the user's face included in the first proof file is compared with the user's face included in the second proof file to calculate similarity and determine whether the user's face matches each other according to the calculated similarity part; And when a new submission of the first evidence file and the second evidence file is performed, the user's faces included in the first evidence file and the second evidence file are compared and matched against the forged discrimination user faces of the previously constructed accounting image database. It may include a forged history user detection unit to detect whether there is data.

In addition, the user identification unit, the MRZ verification unit, the user's face match determination unit and the forged history user detection unit stores data for a normal authenticated user in a normal authentication record database, for a user who is not normal authentication Further comprising a database management unit for storing and managing the forgery confirmation record data in the accounting image database, and the user face matching determination unit may perform machine learning of an artificial intelligence algorithm with data newly stored in the accounting image database.

In addition, the user risk level calculator may set the user's name, gender, date of birth, and nationality information as variables, and calculate the user's risk level through comparison with the blacklist data based on the set variables.

In addition, the user risk level calculation unit, when comparing the variable for the user's name is set to allow changes to uppercase, lowercase, pronunciation distinction, accents and order, and if the variable for the user's gender is not available It is assumed that it matches the blacklist data, and if the variable for the user's date of birth is not available, it can be assumed that the blacklist data is close.

In addition, the user authentication result providing unit, whether the authentication or non-authentication as a result through the user identity verification unit and the user risk level calculation unit, the comparison result and risk level through the user risk level calculation unit, and the non-authentication the user identity verification unit Through this, it is possible to provide each reason for non-authentication including the part detected by the forgery.

According to the present invention, according to the provisions of the international anti-money laundering financial countermeasures organization (FATF: Financial　Action　Task　Force　on　Money　Laundering), a non-face-to-face authentication of a user is processed with a photo or video to prevent user identification and money laundering A face-to-face authentication service providing system can be provided.

1 is a schematic diagram of the overall configuration of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention.
2 is a flowchart illustrating an overall operation process of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention.
3 is a block diagram showing the overall configuration of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention.
4 is a block diagram showing a detailed configuration of a user identification unit according to an embodiment of the present invention.
5 and 6 are views for explaining a forgery detection operation of the user's identity verification unit according to an embodiment of the present invention.
7 is a view for explaining the abusing detection operation of the counterfeit history user detection unit according to an embodiment of the present invention.
8 and 9 are diagrams illustrating a method of calculating a risk level of a user risk level calculator according to an embodiment of the present invention.

Terms used in the specification will be briefly described, and the present invention will be described in detail.

The terminology used in the present invention has been selected, while considering the functions in the present invention, general terms that are currently widely used are selected, but this may vary according to the intention or precedent of a person skilled in the art or the appearance of new technologies. In addition, in certain cases, some terms are arbitrarily selected by the applicant, and in this case, their meanings will be described in detail in the description of the applicable invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the contents of the present invention, rather than a simple term name.

When a certain part of the specification "includes" a certain component, this means that other components may be further included instead of excluding other components unless otherwise specified. In addition, terms such as “... unit” and “module” described in the specification mean a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software. .

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

1 is a schematic diagram of an overall configuration of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention, and FIG. 2 is a flow chart showing for explaining the overall operation process of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention 3 is a block diagram showing the overall configuration of a system for providing a non-face-to-face authentication service according to an embodiment of the present invention, and FIG. 4 is a block diagram showing the detailed configuration of a user identification unit according to an embodiment of the present invention, 5 and 6 are diagrams for explaining the forgery detection operation of the user identification unit according to an embodiment of the present invention, and FIG. 7 is for explaining the abusing detection operation of the forgery history user detection unit according to the embodiment of the present invention 8 and 9 are views illustrating a method of calculating a risk level of a user risk level calculator according to an embodiment of the present invention.

1 to 3, the non-face-to-face authentication service providing system 1000 according to an embodiment of the present invention includes a user information registration unit 100 and a user identification unit 200 and an AML (KYC (Customer Identification)) part. Anti-money laundering) includes a user risk level calculator 300 and a user authentication result provider 400 which are parts.

The non-face-to-face authentication service providing system 1000 is divided into a platform part and a server part, and the platform is installed in a system of a provider that provides services related to financial transactions or virtual currency transactions to receive non-face-to-face authentication services from the server. have. Accordingly, the platform may be implemented in the form of a program or application installed on the user terminal, and the server may be implemented in the form of a computer program device connected through the platform and the Internet.

The user terminal, as well as a mobile communication device such as a smartphone (smartphone), smart pad (smart pad), tablet PC (Tablet PC), as well as a general PC, and PCS (Personal Communication System), GSM (Global System for Mobile communications) ), PDC(Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access) and Wibro (Wireless Broadband Internet) terminals.

The server is a database-based web server, and has the same configuration as a conventional web server in hardware, and is implemented in various languages such as C, C++, Java, Visual Basic, and Visual C in software. It may include a program module that performs various functions. In addition, it can be implemented using web server programs provided in various ways according to operating systems such as DOS, Windows, Linux, Unix, and Macintosh on general server hardware. have.

In addition, the server is connected to the user terminal through a network, and examples of such a network include RF, 3GPP (3rd Generation Partnership Project) network, LTE (Long Term Evolution) network, 5GPP (5rd Generation Partnership Project) network, and WIMAX (World Interoperability for Microwave Access (Internet), Internet, Local Area Network (LAN), Wireless Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), Bluetooth network, NFC network , Satellite broadcasting networks, analog broadcasting networks, DMB (Digital Multimedia Broadcasting) networks, and the like.

The user information registration unit 100 includes a first proof file including a photo ID of the user and a photo or video of the user from the user (a customer who needs non-face-to-face authentication in the platform operator's position). The second proof file can be requested or registered as non-face-to-face authentication data.

Here, the first proof file means a picture of the user himself with the identification card such as a passport and the corresponding ID card, and the second proof file means a picture or video of the first proof file and another user himself photographed himself. . The platform can provide guide information for the first and second evidence files to process the face-to-face authentication, and can register the files with the attached files.

The user identification unit 200 uses the artificial intelligence algorithm (machine learning, deep learning) and user data previously determined by counterfeiting to verify the authenticity of the user's identification card included in the first proof file and the second proof file. It is possible to detect the forgery by performing the user authentication.

To this end, the user identity verification unit 200 includes a character recognition unit 210, an MRZ verification unit 220, a face recognition unit 230, a user face match determination unit 240, and a forged history user, as shown in FIG. 4. It may include a detection unit 250 and the database management unit 260.

The character recognition unit 210 may recognize, digitize, and store text existing in the ID photograph using an optical character reader (OCR). At this time, the recognized text data may include information such as the user's name, gender, date of birth, and nationality.

The MRZ verification unit 220 may recognize a machine readable zone (MRZ) present in an ID photo (for example, a passport) to check the correspondence on a distributed protocol.

For example, the information on the MRZ at the bottom of the personal information portion of the passport may be recognized, and it may be verified whether the text data (passport personal information) recognized and stored through the text recognition unit 210 and the information of the MRZ match each other.

The human face identification unit 230 may determine whether human objects are included in objects in the first proof file and the second proof file using artificial intelligence algorithms (machine learning and deep learning). That is, it is possible to recognize whether the object in the photo of the first evidential file and the object in the photo in the second evidential file represent a human face, and then proceed with a subsequent user face matching determination process. At this time, if it is not recognized as a human face, the user may be guided to register another picture, or a message to explain the reason for the failed authentication may be provided along with a message for authentication failure.

The user face match determination unit 240 calculates similarity by comparing the user face included in the first evidence file and the user face included in the second evidence file by using an artificial intelligence algorithm (machine learning, deep learning) And, it can be determined whether they match each other according to the calculated similarity.

For example, as illustrated in FIG. 5, when a feature point is extracted from the user's face holding the passport in the first proof file and the user's own face in the second proof file, and the result is compared, the match rate is calculated, and the match rate is greater than or equal to It can be judged to be the same person, and at this time, by extracting the feature points for the user's face in the photo in the passport, we can calculate the mutual agreement rate for the three user's face photos and determine whether they are the same person through similarity determination based on the feature points. have. At this time, if the result of the determination on the user's face of each picture is found to be normal authentication or matching, the corresponding data may consist of normal authentication record data and be stored in the normal authentication record database 20. In the case of forgery or mismatch, a separate false It can be composed of submitted records and stored in the abusing image database 10.

In addition, as shown in FIG. 2, in the case of forgery or inconsistency, the corresponding data may be transmitted to an artificial intelligence algorithm (machine learning, deep learning) part and used as machine learning data as manipulation or false data. When a new submission to the user is received, it can be loaded from the abusing image database 10 and used for comparison of fake photos. As described above, the user face match determination unit 240 may perform machine learning of the artificial intelligence algorithm with data newly stored in the viewing image database 10.

The counterfeit history user detection unit 250, upon new submission of the first and second evidence files, determines the user's faces included in the corresponding first and second evidence files, respectively, as forgeries stored in the previously constructed image database 10 Compared to the user faces, it is possible to detect whether there is matching data.

A person who submits false data for identity authentication, such as identification, by falsification or falsification, has a high probability of repeatedly conducting the same action, so the data on previously submitted cases determined to be falsified is stored and saved as an accounting image database. (10) is built, when the user submits new evidence, based on a deep learning algorithm, as shown in FIG. 7, compares the previously submitted counterfeit photos and the newly submitted photos to confirm abusing, and compares the threshold And metadata of each picture can be effectively adjusted according to data accumulation.

The database management unit 260 stores the data for the normal authenticated user through the MRZ verification unit 220, the user face match determination unit 240, and the forged history user detection unit 250 in the normal authentication record database 20 And, it is possible to store and manage counterfeit confirmation record data for a user who is not normally authenticated in the accounting image database 10.

The user risk level calculating unit 300 extracts at least one or more user data included in the ID of the normal authenticated user through the user identification unit 200, compares the extracted user data with blacklist data, The user's risk level can be calculated according to the comparison result.

The user risk level calculating unit 300 sets the name, gender, date of birth (or date of birth) and nationality information of the normal authenticated user as variables, and compares and matches the blacklist data based on the set variables. Through this, the user's risk level can be calculated and the risk level for each user can be classified based on each preset comparison factor.

The user risk level calculating unit 300 is a component for preventing money laundering, and such money laundering prevention can exert the same effect as blacklist management from a person's perspective. Politicians, criminals, etc. can be checked to see if there is matching information based on name, gender, date of birth (or date of birth), and nationality. At this time, a wide variety of variables are generated during the actual comparison. For example, as shown in FIG. 9, when searching with the name'Lee Kun-hee', a wide variety of results may be output.

To this end, the user risk level calculator 300 may classify the risk level for each user based on the variable type of Table 1 and the risk type and level setting table of Table 2 below.

<Table 1>

<Table 2>

Referring to Table 1, the user risk level calculating unit 300 may be set to allow changes to uppercase, lowercase, pronunciation distinction relief, accent, and order when comparing variables for the user's name. In addition, when comparing the user's gender, it is assumed that if the variable for the user's gender is not available, it is assumed to match the blacklist data, and if the variable for the user's date of birth is not available, it can be assumed to be close to the blacklist data. Here, when it is close to the blacklist data, a report may be issued according to a request of a company using the service. In addition, in the case of the date of birth, the comparison process may be performed by dividing the comparison group into years, years and months, and years, months, and days. In the case of nationality, it can be judged that the match is made only when the match is complete.

Referring to Table 2, the user risk level calculating unit 300 is divided into a red flag and a yellow flag, and the high risk level is high, medium, and low. It can be classified as, and is applied to a person who matches the official list regardless of the risk level, and the corresponding user information can be registered as a list of the AML database 40. In addition, the yellow flag may be determined as a risk level for a user whose name and nationality are matched without having a date of birth.

The user authentication result providing unit 400 may provide the user with a result through the user identification unit 200 and the user risk level calculating unit 300. More specifically, the user authentication result providing unit 400 is the result through the user identification unit 200 and the user risk level calculating unit 300, whether authentication or non-authentication, through the user risk level calculating unit 300 A comparison result, a risk level, and a non-authentication reason including a portion detected as a forgery through the user identity verification unit 200 during non-authentication may be provided to the user through the platform.

What has been described above is only one embodiment for implementing the non-face-to-face authentication service providing system according to the present invention, and the present invention is not limited to the above embodiment, and as claimed in the following claims Anyone who has ordinary knowledge in the field to which the present invention pertains without departing from the gist will have the technical spirit of the present invention to the extent that various changes can be made.

1000: Non-face-to-face authentication service provision system
100: user information register
200: user identification
210: character recognition unit
220: MRZ confirmation unit
230: human face discrimination unit
240: user face match determination unit
250: counterfeit history user detection unit
260: database management
300: user risk level calculator
400: user authentication result provider
10: Abusing image database
20: Normal authentication record database
30: Blacklist database
40: AML database

Claims (4)

A user information registration unit for requesting and registering a first proof file including a photo of the ID photographed with the user's face and a second proof file including a photo or video of the user;
A user identification unit for detecting falsification by performing authenticity verification and user authentication of a user's identification card included in the first proof file and the second proof file using artificial intelligence algorithm and user data previously determined by forgery;
At least one or more user data included in the ID of the normally authenticated user is extracted through the user identification unit, the extracted user data is compared with the blacklist data, and the user's risk level is calculated according to the comparison result. A user risk level calculating unit that sets name, gender, date of birth, and nationality information as variables, and calculates a user's risk level through comparison with the blacklist data based on the set variable; And
Non-face-to-face authentication service providing system, characterized in that it comprises a user authentication result providing unit for providing a result through the user identification unit to the user.
According to claim 1,
The user identity verification unit,
A character recognition unit for recognizing and digitizing and storing the text present in the ID card using an optical character reader (OCR);
An MRZ confirmation unit that recognizes a machine readable zone (MRZ) present in the ID photograph and confirms the identity on a distributed protocol;
A face recognition unit for determining whether each of the first and second evidence files includes a human face using an artificial intelligence algorithm;
Using an artificial intelligence algorithm, the user's face included in the first proof file is compared with the user's face included in the second proof file to calculate similarity and determine whether the user's face matches each other according to the calculated similarity part; And
When newly submitting the first proof file and the second proof file, the data matched by comparing the user faces included in the first proof file and the second proof file to the counterfeit discrimination user faces of the previously constructed accounting image database. Non-face-to-face authentication service providing system comprising a forgery history user detection unit for detecting whether there is.
According to claim 2,
The user identity verification unit,
The MRZ verification unit, the user face matching discrimination unit, and the counterfeit history user detection unit store data for a normal authenticated user in a normal authentication record database, and forgery confirmation record data for a user who is not normally authenticated is the viewing image Further comprising a database management unit to store and manage in the database,
The user face match determination unit,
A system for providing an in-person authentication service, characterized in that machine learning of an artificial intelligence algorithm is performed with data newly stored in the abusing image database.
According to claim 1,
The user authentication result providing unit,
A non-face-to-face authentication service providing system, each of which provides authentication or non-authentication as a result through the user's identity verification unit, and a non-authentication reason that includes a part detected by forgery through the user identity verification unit when non-authentication.

Images