KR20160108259A - Certification Request and Agent Method using Voice Feature - Google Patents

Abstract

Provided are an identity verification request and proxy method using voice feature information. The certification method according to the embodiment of the present invention performs voice certification and provides a result, when a voice certification service is requested to a server for performing the voice certification service. Thereby, even for companies which run small businesses and are hard to register and retain the voices of clients, identity verification by voice authentication can be carried out. In addition, the registration and retention of the voices of the clients can be integrated, so management is easy and the risk of information leakage and hacking can be reduced.

Description

(Certificate Request and Agent Method using Voice Feature)

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a personal authentication technology, and more particularly, to a method for performing personal authentication using a voice.

The most commonly used authentication methods are resident registration number, password, PIN, and public certificate. However, due to accidents such as leakage of personal information, resident registration numbers were limited except for some.

Other authentication methods, such as passwords, PINs, and public certificates, are not free from the risk of information leakage or hacking because they use fixed data. In addition, there are inconveniences such that the user must remember the data, and that the data must be stored in a storage medium.

Accordingly, it is possible to conduct authentication of the user who uses the biometric information of a user who does not need to memorize or store the data, but can perform the authentication without any additional facilities, and is also difficult to register / hold biometric information of customers by operating a relatively small- A method is sought to make it possible.

SUMMARY OF THE INVENTION The present invention is conceived to solve the problems as described above, and it is an object of the present invention to provide a method and apparatus for authentication of a voice authentication method by providing a voice authentication service to a server capable of performing a voice authentication service, System.

According to another aspect of the present invention, there is provided a method for authenticating a user, comprising: obtaining a voice of a customer; Extracting feature information from the voice of the customer; Requesting voice authentication while transmitting the feature information to a server; And receiving an authentication result from the server.

The obtaining step, the extracting step, the requesting step, and the receiving step are performed by a server operated by the second company or an application distributed by the second company, and the server is a server operated by the first company. .

The server may be a server that performs subscriber authentication in the customer center service of the first company.

According to another aspect of the present invention, there is provided a method for authenticating a user, the method including the steps of: inquiring of the server whether or not to join the voice authentication service of the customer; And when the customer is confirmed to be subscribed to the voice authentication service.

Further, the acquiring step may acquire a customer voice through a telephone or an application.

The data capacity of the feature information may be smaller than the data capacity of the customer voice.

The acquiring step acquires voices of a plurality of customers, and the extracting step extracts the characteristic information from the voices, and the requesting step requests voice authentication while transmitting the characteristic information, The step may receive the authentication results.

According to another aspect of the present invention, there is provided a method for authenticating a user, the method including: providing a service differentially based on an authentication result.

According to another aspect of the present invention, there is provided a server system including: an automatic response system for obtaining a customer voice; And an authentication request server for extracting the feature information from the customer voice, requesting voice authentication while transmitting the feature information to the external server, and receiving the authentication result from the external server.

According to another aspect of the present invention, there is provided a method of authenticating a person, comprising: receiving characteristic information of a customer voice; Comparing the feature information received in the receiving step with stored feature information to perform authentication of the user; And returning the authentication result.

According to another aspect of the present invention, there is provided a server system including: a DB storing characteristic information of a customer voice; And a server for receiving the characteristic information of the customer voice from outside, comparing the received characteristic information with the characteristic information stored in the DB to perform the identity authentication, and returning the authentication result.

INDUSTRIAL APPLICABILITY As described above, according to the embodiments of the present invention, it is possible to perform self-certification by voice authentication even for companies that are relatively small-scale businesses and are difficult to register / retain their voices.

Further, according to the embodiments of the present invention, it is possible to unify registration / retention of customers' voices, thereby simplifying management and reducing the risk of information leakage and hacking. In addition, since the information required in the authentication request / proxy process is transmitted in an encrypted state, the security is excellent.

In addition, according to the embodiments of the present invention, if an environment supporting a telephone call is established or a customer installs the application on a smart phone, the authentication service can be provided without additional facilities.

FIG. 1 is a block diagram illustrating a configuration of a system capable of performing identity authentication using voice feature information applicable to the present invention,
FIG. 2 is a flowchart showing a process of registering a voice of a customer,
FIG. 3 is a flowchart showing a procedure of a voice authentication service providing server performing a voice authentication for its service,
4 is a flowchart showing a procedure in which a voice authentication service providing server requests a voice authentication to a voice authentication service providing server for its service and a voice authentication service providing server performs voice authentication,
5 is a flowchart provided in a description of a process of providing a service differentially based on a voice authentication result.

Hereinafter, the present invention will be described in detail with reference to the drawings.

1. Voice Authentication System

FIG. 1 is a configuration diagram of a system capable of performing identity authentication using voice feature information to which the present invention is applicable. Hereinafter, 'authentication using voice feature information' is abbreviated as 'voice authentication'.

The voice authentication performed in the embodiments of the present invention is performed by telephone. Here, the telephone includes not only a mobile communication telephone but also a fixed telephone.

As shown in FIG. 1, the system to which the present invention is applicable includes a voice authentication service providing server 100, a voice authentication service using server 200, and a gateway server 300. The gateway server 300 is a server for interconnecting the voice authentication service providing server 100 and the voice authentication service using server 200.

The voice authentication service utilization server 200 requests voice authentication service to the voice authentication service providing server 100. The voice authentication service providing server 100 then performs a voice authentication for the voice authentication service use server 200, Results.

That is, the voice authentication service providing server 100 performs the voice authentication service using server 200 instead of the voice authentication required for providing the service to the customers.

The voice authentication service providing server 100 that performs the above functions includes an exchange 110, an IVR (Interactive Voice Response) system 120, a CTI (Computer Telephony Integration) system 130, (140), and a voice authentication DB (150).

The switch 110 connects the customer's telephone to the IVR system 120 and the IVR system 120 performs an automatic response to the customer's telephone. Then, when an agent connection is required, the IVR system 120 connects the customer's telephone to the CTI system 130. [

In this process, the voice authentication server 140 may register the voice of the customer in the voice authentication DB 150 or may perform the identity authentication using the voices of the customers registered in the voice authentication DB 150. [

On the other hand, the voice authentication server 140 acts on the voice authentication requested by the voice authentication service utilization server 200 and provides the authentication result.

It is preferable that the voice authentication service providing server 100 is constructed by a server operated by a company having a large number of customers. For example, it may be reasonable to operate a voice authentication service providing server 100 in a service provider or a manufacturer operating a large-scale business. This is because we can hold and manage voice information for many customers.

Of course, the voice authentication service providing server 100 may perform the voice authentication required for providing the service to the customers. For example, when a specific service provider / manufacturer operates the voice authentication service providing server 100, it is possible to use the voice authentication service providing server 100 for subscriber identity authentication in its own customer center service to be.

The voice authentication service utilization server 200 is preferably operated by a company that does not have many customers. For example, it is reasonable to operate the voice authentication service utilization server 200 in a home shopping, a small financial institution (a bank, an insurance company, etc.). Since it does not have voice information for many customers, it requests the voice authentication service providing server 100 having the voice authentication service to the authentication proxy.

The voice authentication service utilization server 200 that performs such functions includes an exchange 210, an IVR system 220, a CTI system 230, and a voice authentication request server 240.

The switch 210 connects the customer's telephone to the IVR system 220 and the IVR system 220 performs an automatic response to the customer's telephone. And, if an agent connection is required, the IVR system 220 connects the customer's telephone to the CTI system 230.

In this process, the voice authentication request server 240 requests the voice authentication server 140 of the voice authentication service providing server 100 to authenticate the voice of the customer, receives the authentication result, and transmits the authentication result to the IVR system 220 .

In the following, specific procedures for requesting and acting voice authentication services will be described in detail.

2. Voice Registration

2 is a flowchart provided in the explanation of the process of registering the voice of the customer for the voice authentication service by the voice authentication service providing server 100 shown in FIG.

2, when the customer subscribes / agrees to the voice authentication service (S410), the IVR system 120 requests the customer to utter a predetermined phrase (S420) and acquires the voice of the customer (S430) .

The voice of the customer obtained in step S430 is transmitted to the voice authentication server 140. [ The voice authentication server 140 extracts feature information from the voice of the customer (S440) and stores the extracted feature information in the voice authentication DB 150 (S450).

As a result, the voice registration of the customer is completed, and voice authentication to the registered customer becomes possible after that.

The feature information extracted from the voice is also referred to as a voice print (Voice Print). The amount of data is much smaller than the voice in that the feature information is not voice data itself but information that characterizes the voice data.

Meanwhile, in order to enhance security, it is preferable to store the feature information in an encrypted state in step S450.

3. Voice Authentication

FIG. 3 is a flowchart provided in a description of a process in which the voice authentication service providing server 100 shown in FIG. 1 performs voice authentication for its service.

As shown in FIG. 3, when the customer's telephone is connected through the switchboard 110 (S510), the IVR system 120 requests the customer to utter a predetermined phrase (S520) and acquires the voice of the customer S530).

The voice of the customer obtained in step S530 is transmitted to the voice authentication server 140. [ The voice authentication server 140 extracts the feature information from the voice of the customer in step S540 and compares the feature information with the feature information stored in the voice authentication DB 150 to perform the identity authentication procedure in step S550.

Thereafter, the voice authentication server 140 transmits the voice authentication result in step S550 to the IVR system 120 (S560). The IVR system 120 transmits the voice authentication result to the CTI system 130, The telephone is connected to the CTI system 130 (S570).

4. Voice Certification Request / Acting

4 is a diagram illustrating a procedure in which the voice authentication service providing server 200 asks the voice authentication service providing server 100 for voice authentication for its service and the voice authentication service providing server 100 performs voice authentication Fig.

Communication between the voice authentication service providing server 100 and the voice authentication service using server 200 is performed through the gateway server 300. For convenience of illustration and explanation, the display of the gateway server 300 is omitted in FIG. Respectively.

4, when the customer's telephone is connected through the exchange 210 of the voice authentication service utilization server 200 (S605), the IVR system 220 determines whether the customer is subscribed to the voice authentication service, And inquires the authentication service providing server 100 (S610).

In step S610, the IVR system 220 transmits customer information (e.g., telephone number) to the voice authentication service providing server 100 to specify the customer.

The voice authentication server 140 of the voice authentication service providing server 100 confirms that the user is a subscriber to the voice authentication service and responds to the voice authentication service using server 200 (S615).

In the case of the voice authentication service subscribing customer, the IVR system 220 requests the customer to utter a predetermined phrase (S620), and obtains the voice of the customer (S625). The voice of the customer obtained in step S625 is transmitted to the voice authentication request server 240. [

The voice authentication requesting server 240 extracts the characteristic information from the voice of the customer (S630) and transmits it to the voice authentication server 140 of the voice authentication service providing server 100 (S635).

The voice feature information extraction in step S660 may be implemented using an API provided by the voice authentication server 140 of the voice authentication service providing server 100. [

In step S635, the characteristic information is encrypted and transmitted to the voice authentication server 140. In this case, the encryption method uses the same method as that used by the voice authentication server 140 for voice registration.

The voice authentication server 140 receiving the voice feature information compares the feature information stored in the voice authentication DB 150 and performs the authentication process (S640).

Thereafter, the voice authentication server 140 transmits the voice authentication result in step S640 to the voice authentication request server 240 (S645). The voice authentication requesting server 240 transmits the received voice authentication result to the IVR system 220 (S650).

Then, the IVR system 220 transmits the voice authentication result to the CTI system 230, and connects the customer's telephone to the CTI system 230 (S655).

5. Providing differentiated services according to the result of certification

In order to provide differential service, the concept of 'voice feature matching rate' used in 'self-certification result' is needed. The 'voice feature matching rate' is a value indicating the degree to which the voice authentication server 140 compares the voice feature information transmitted from the voice authentication service using server 200 with the feature information stored in the voice authentication DB 150, Quot; voice characteristic matching rate " is calculated by the voice authentication server 140. The voice characteristic matching rate may be expressed as a percentage or ratio.

The 'authentication result of the user' is information indicating whether the calling customer is the user, and the voice authentication server 140 determines the authentication result based on the 'voice feature matching rate'. For example, the voice authentication server 140 determines that the identity authentication is successful if the matching rate is 70% or more, and determines that the identity authentication is failed if the matching rate is less than 70%.

The voice authentication server 140 is supposed to transmit the voice feature matching rate to the voice authentication service providing server 100 and the CTI system 130 or 230 of the voice authentication service using server 200 together with the personal authentication result.

5 is a flowchart provided in a description of a process in which the voice authentication service providing server 100 and the voice authentication service using server 200 differentially provide services based on the authentication result.

As shown in FIG. 5, when the voice feature matching rate is less than 70% (S710-Y), the voice authentication service providing server 100 determines that the user authentication fails (S715). Accordingly, the CTI system 130 or 230 receives the authentication result information (failure of authentication of the user) from the voice authentication service providing server 100 and provides only the low security service to the customer (S720). In the case of a telebanking service as an example, it can be assumed that only the inquiry service is provided.

On the other hand, if the voice feature matching rate is 70% or more (S710-N), the voice authentication service providing server 100 determines that the authentication of the user is successful (S730). The voice authentication service providing server 100 transmits the authentication result information (authentication success of the user) and the voice feature matching rate information to the voice authentication service utilization server 200.

Then, the CTI system 130 or 230 of the voice authentication service utilizing server 200 determines which range the voice feature matching rate belongs to (S740).

If the feature matching rate is 70% or more but less than 90% (S740-Y), the CTI system 130 or 230 provides a service having a middle security level to the customer (S760). In the case of a telebanking service, for example, it may be assumed that a change of personal information is provided in addition to the inquiry service.

On the other hand, if the feature matching rate is 90% or more (S740-N, S750), the CTI system 130,230 provides a service having a high security level to the customer (S770). In the case of a telebanking service, for example, it is possible to provide a transfer service in addition to the inquiry service and personal information change.

6. Variation example

The flowchart shown in FIG. 5 corresponds to an example of a differential service, and various modifications are possible. For example, the voice feature matching rate can be further subdivided to provide differentiated services.

Furthermore, it is possible to simply determine whether or not to provide the service with only the authentication result of the person without the voice characteristic matching rate (for example, providing the service only to the customer who has successfully authenticated the voice).

In this case, the feature matching rate as a criterion for success in authentication may be set differently according to the type of service. For example, in the case of a telebanking service requiring high security, authentication is considered successful if the feature matching rate is "90%" or more. In the case of electronic service A / S reception & inquiry service which does not require high security, If the matching rate is 50% or more, it is treated as authentication success.

Up to now, preferred embodiments have been described in detail for a method of providing a differential service based on authentication of a person using voice feature information, an authentication request, an authentication proxy, and an authentication result.

In the above embodiments, it is assumed that there is only one customer, but this is merely an example. It is also possible to perform sequential authentication of a plurality of customers in a single telephone call. This is useful when, for example, an insured service authenticates an insured person and an insured person in a single call, or a credit card point transfer service authenticates a point transferor and a transferee in a single call.

In the above embodiment, the user authentication is assumed in the automatic answering telephone call with the customer, but this is merely an example for convenience of explanation. It goes without saying that the technical idea of the present invention can be applied to situations other than an automatic answering telephone.

For example, it is possible that the customer speaks the phrase determined by the instruction of the application installed in the smartphone of the user, rather than speaking the phrase determined by the instruction of the IVR system 120, 220.

At this time, the application can be provided by the voice authentication service utilization server 200 side. The application extracts the feature information from the voice of the customer using the API for extracting the voice feature information, transmits the extracted feature information to the voice authentication server 140 of the voice authentication service providing server 100, The results can be delivered. Then, the application can provide the service to the customer according to the authentication result.

It goes without saying that the technical idea of the present invention can also be applied to a computer-readable recording medium having a computer program for performing the functions of the apparatus and method according to the present embodiment. In addition, the technical idea according to various embodiments of the present invention may be embodied in computer-readable code form recorded on a computer-readable recording medium. The computer-readable recording medium is any data storage device that can be read by a computer and can store data. For example, the computer-readable recording medium may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical disk, a hard disk drive, or the like. In addition, the computer readable code or program stored in the computer readable recording medium may be transmitted through a network connected between the computers.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the present invention.

100: voice authentication service providing server
140: voice authentication server
150: Voice Authentication DB
200: Voice authentication service utilization server
220: IVR system
240: voice authentication request server

Claims (1)

Obtaining a voice of a customer;
Extracting feature information from the voice of the customer;
Requesting voice authentication while transmitting the feature information to a server; And
And receiving an authentication result from the server.

Images