KR20190125856A - method for analyzing voice phishing , system and terminal - Google Patents

Abstract

An implementation of the present invention relates to a method for analyzing voice phishing in real time by communicating with a voice phishing analysis server while a call incoming terminal is during a call. To this end, the method is characterized by comprising: a step in which an incoming terminal receives a call through a communication network; a step in which the phone number of a caller included in the received call is checked; a step in which caller information corresponding to the phone number of the caller is searched in a pre-stored address book; a step in which, if the correspondent caller information does not exist according to the search result, a voice phishing detection function is turned on to initiate a call record during the call; a step in which a call history that is being recorded during the call undergoes a STT conversion to become text; a step in which the text of the call history is streamed to the voice phishing analysis server during the call; and a step in which a notice is outputted when the result that the call history is suspected to be voice phishing is received from the voice phishing analysis server which analyzed the text of the call history during the call.

Description

Method for analyzing voice phishing, system and terminal

The present invention relates to a voice phishing analysis method, system and terminal.

Voice Phishing is a scam that uses telephones to impersonate related organizations to steal personal information or to send money. As voice phishing is becoming a social problem and known, people are aware of the dangers of voice phishing to some extent, but voice phishing techniques have evolved so well that recent cases of damage have been reported. He is hesitant to pick up a call from an incoming call, and even more people aren't answering calls from people who aren't registered in the address book.

As a conventional technique for preventing voice phishing, a service for storing a phone number used for voice phishing in a communication provider network and blocking a call at source or informing a called terminal is known, but when calling with a different calling number, There is no way to cope.

In addition, such information is limited before answering the call, and there is a limitation in that it cannot provide voice phishing in real time during a call.

The present invention has been made to solve the above problems, an embodiment of the present specification is to provide a voice phishing analysis method, voice phishing analysis system and the terminal.

According to an embodiment of the present disclosure, a call phishing terminal communicates with a voice phishing analysis server during a call, and the real-time voice phishing analysis method includes: receiving a call through a communication network by the called terminal; Checking a calling party's number included in the received call; Retrieving caller information corresponding to the calling party's telephone number from a pre-stored address book; If there is no corresponding caller information, turning on the voice phishing detection function and starting a call recording when the call is made; STT changing the text of the call recorded during the call, and texturing; Streaming the text of the call to a voice phishing analysis server during a call; And outputting an alert when receiving a result from the voice phishing analysis server analyzing the text of the call during the call, indicating that the call history is suspected to be voice phishing.

If there is no caller information corresponding to the search result, turning on the voice phishing detection function and starting a call recording during a call may include turning on or off the voice phishing detection function when there is no corresponding caller information. It further comprises the step of providing an interface to select.

The transmitting of the text of the call content to the voice phishing analysis server may include transmitting the text of the call content to the voice phishing analysis server according to whether or not the text of the call content matches a word included in a pre-stored dictionary. The pre-stored dictionary includes a key word dictionary and an organization name word dictionary that can be determined as voice phishing.

The outputting of the warning may include: notifying the called terminal by at least one of voice or text that a call history is suspected of voice phishing; Providing a reporting interface for reporting the call history to the voice phishing analysis server; And when the user selects a report through the report interface, the voice phishing analysis server storing text of a call history as a voice phishing case.

The voice phishing analysis server determines the similarity of the call history text received from the called terminal with a pre-stored voice phishing case model, and if the similarity is greater than or equal to a predetermined threshold, the call history is suspected to be voice phishing. It is characterized by judging.

Before turning on the voice phishing detection function and starting a call recording, during the call, based on the outgoing call number, checking whether a predetermined call recording is a phone number of an illegal country. It is done.

Before starting the call recording, it is determined whether the caller information matches a pre-stored voice phishing suspicion number, and if it matches the phishing suspicion number, the voice or text is suspected to be voice phishing without going through the next step. Notification in one or more ways.

Voice phishing analysis system that provides a real-time voice phishing analysis service while a call destination terminal according to another embodiment of the present disclosure, receives a call through a communication network, the calling party telephone number included in the received call Search caller information corresponding to the information stored in the address book, search results, if there is no corresponding caller information, turn on voice phishing detection, record the call history during the call and STT changes the recorded call history Receiving streaming text of the call content from the receiving terminal and the receiving terminal, and analyzing the text of the call content to provide an analysis result to the receiving terminal when the call history is suspected to be voice phishing; Voice Phishing Analysis Server.

According to another exemplary embodiment of the present disclosure, a terminal for providing a real-time voice phishing analysis service by communicating with a voice phishing analysis server while a call is in a call includes a communication unit configured to receive a call through a communication network; A storage unit which stores an address book; Checking the calling party number included in the received call, searching for the calling party information corresponding to the calling party number in the address book, and if there is no corresponding calling party information, turning on the voice phishing detection function; And, during a call, starting a call recording and changing the call history recorded during the call by STT, and converting the text into a text, and outputting the information according to the control of the controller. Outputting an alert through the display unit when the text of the call is streamed to a voice phishing analysis server and receiving a result from the voice phishing analysis server analyzing the text of the call, indicating that the call history is suspected to be voice phishing. It features.

According to the present invention, it is possible to determine whether voice phishing in real time during a call.

In addition, since the call history is analyzed to determine whether the voice is phishing, the voice phishing may be determined even when the caller ID is manipulated, thereby reducing the possibility of being subjected to voice phishing.

1 is a view for explaining the components of the voice phishing analysis service system according to an embodiment of the present invention.
2 is a diagram illustrating a detailed block configuration of a called terminal according to the embodiment of FIG.
3 is a block diagram of a real-time voice phishing analysis server according to another embodiment of the present invention.
4 is a flowchart illustrating a real-time voice phishing analysis service method according to the embodiment of FIG. 3.
5 is a flowchart illustrating the construction of a voice phishing case model according to an embodiment of the present invention.
6 is a flowchart illustrating a real-time voice phishing analysis method according to an embodiment of the present invention.
7 is an example of a screen outputting a warning message of a called terminal according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. The construction of the present invention and the effects thereof will be clearly understood through the following detailed description. Prior to the detailed description of the present invention, the same components will be denoted by the same reference numerals even if they are displayed on different drawings, and the detailed description will be omitted when it is determined that the well-known configuration may obscure the gist of the present invention. do.

1 is a view for explaining the components of the voice phishing analysis service system according to an embodiment of the present invention.

The real-time voice phishing analysis service system includes a called terminal 100 and a voice phishing analysis server 200 for voice phishing analysis.

The called terminal 100 is a terminal of a called party that has received a call connection request from the calling terminal 10, which can perform a call service and is a communication terminal capable of transmitting and receiving data. The called terminal 100 may be any one of a smart phone, a personal digital assistant (PDA), a mobile communication terminal, and the like.

The receiving terminal 100 according to the present embodiment receives a call connection request and caller information from the caller, provides an incoming call notification screen for notifying the incoming call, and a terminal equipped with an application for voice phishing detection in an embedded form. to be. Of course, the terminating terminal 100 may mount an application in a form that is installed in the OS in the terminating terminal 100 by a user's manipulation or command.

The called terminal 100 according to the present embodiment performs an operation of receiving a voice call using the mounted application. When the call is received, the called terminal 100 executes the voice phishing detection application when the caller's telephone number of the call is an unregistered telephone number in the address book.

The voice phishing detection application textizes the call history during the call, forwards the textified call history to the voice phishing analysis server, and requests an analysis. This is an application that notifies you of this.

Voice phishing analysis server 200 is built on the service provider side to provide a real-time voice phishing analysis service. The voice phishing analysis server 200 may include a voice phishing case DB.

The voice phishing analysis server 200 analyzes the call history based on the voice phishing case DB when the call history is received from the called terminal 100, and if it is suspected that the result is voice phishing, the called terminal 100. Notify For analysis, stemming, correcting typos, vectorization, and similarity determination of the call history are performed. A detailed description of these steps will be provided later.

FIG. 2 illustrates a detailed block configuration of a called terminal according to the embodiment of FIG. 1 and particularly illustrates a mobile communication terminal such as a smartphone, which is one of user terminals, as an example.

Hereinafter, referring to FIG. 2, the operation of the called terminal 100 having the voice phishing detection application according to the embodiment will be described in detail.

The called terminal 100 includes a communication unit 110, a control unit 120, a display unit 130, a storage unit 140, and a key input unit 150.

First, the communication unit 110 receives an incoming call from the calling terminal by connecting to a communication network of a communication operator through a wired or wireless network, and when the called terminal 100 responds, between the calling terminal and the called terminal 100 of the user. Set the currency path.

In addition, the communication unit 110 performs data communication with an external server and the terminal.

The communication unit 110 may perform data communication while a call is in progress through a communication path set between the called terminal 100 and the calling terminal 10.

The controller 120 controls the overall operation of the called terminal 100 according to the operation program stored in the storage 140. The operation program as described above connects each component such as the display 130 and the key input unit 150, as well as the basic operating system required for the operation of the called terminal 100, and inputs / outputs data. Or software that is pre-programmed at the time of manufacture to operate an internal application or the like of the called terminal 100.

When the called terminal 100 is connected to the external calling party terminal, the controller 120 checks whether the calling party's phone number is a pre-stored phone number, and if it is not a registered phone number, voice phishing detection application. The call is recorded, the call is recorded with the calling terminal, and the recorded call is converted into text through a speech to text (STT) technique. STT technique refers to the process of a computer interpreting a speech language spoken by a person through speech recognition and converting the contents into text data.

The controller 120 transmits the textified call history to the security server 200 for voice phishing analysis through the communication unit 110.

The controller 120 records, converts, and transmits a call history during an arbitrary time interval or an arbitrary data length, thereby enabling real-time analysis.

In addition, the control unit 120 informs the subscriber that the voice phishing is in any one or more of voice or text when a call with the calling terminal is determined to be voice phishing as a result of the operation of the voice phishing detection application according to an embodiment of the present invention. Raise an alarm.

In this case, the control unit 120 may display such an alarm message in text by the display unit 130 or may generate a voice or an alarm sound through an audio unit (not shown).

The display unit 130 displays various types of information of the called terminal 100 under the control of the controller 120, and receives and displays key data generated by the key input unit 150 and various information signals of the controller 120. .

The storage 140 stores data and a program for the called terminal 100 to provide a voice phishing analysis service. In addition, the storage 140 includes an address book 145.

The storage 140 may inquire, store, and delete data at the request of the controller 120, and provide the result to the controller 120.

For example, the control unit 120 receives the caller information (caller's phone number) received through the communication unit 110 and the caller information according to the matching check request with the information stored in the address book 145, and the matching data is If there is, the caller information (for example, name) corresponding to the calling party's phone number may be transmitted to the controller 120.

The key input unit 150 may be composed of a plurality of numeric keys and function keys for requesting various operations of the called terminal 100, and generates corresponding key data when the user presses a predetermined key and outputs the generated key data to the controller 120. do. In addition, in the tablet computer such as a smart phone or an iPad, the key input unit 150 may use a touch screen on the display unit 130 as needed, instead of using a physical keypad. screen).

3 is a block diagram of a real-time voice phishing analysis server according to another embodiment of the present invention.

The voice phishing analysis server 200 includes an information transmission and reception unit 210, a controller 220, a model generator 230, a call content analyzer 240, and a database 250.

The information transmitting and receiving unit 210 transmits and receives various data through a communication network. In particular, the information transmitting and receiving unit 210 receives the text content of the call from the receiving terminal 100 and transmits to the control unit 220 or the database unit 250, and transmits the voice phishing analysis results to the receiving terminal 100 .

The controller 220 controls the overall operation of the called terminal 100 according to the operation program stored in the storage 140. The above operating program refers to software that connects each component, manages input / output of data, or preprogrammed software, as well as the basic operating system required for the operation of voice phishing analysis server and voice phishing analysis. .

The model generator 230 constructs a voice phishing model by performing a predetermined refining or processing on a document including the collected voice phishing cases. In other words, the model generator 230 may integrate various purified source data into one model and perform standardization.

In more detail, the model generator 230, in more detail, integrates the refined source data, extracts essential elements of voice phishing that are related to each other, and builds a model including the extracted essential elements. .

At this time, the pre-stored key word dictionary, typo word dictionary, organization name word dictionary may be used.

The key word dictionary is a set of words that overlap or are expected to appear in voice phishing cases, such as, for example, 'cannon passbook', 'theft of people' and 'investigation first class'.

A typo word dictionary is a set of examples of typos, for misleading results through STT or for the stemmer to recognize them as nouns.

An organization name word dictionary is a set of organization names that appear or are expected to appear in an overlapping voice phishing instance.

The call content analyzer 230 performs a real-time voice phishing suspicion analysis during the call of the called terminal 100 based on the generated voice phishing model.

The control unit 220 generates a message to notify the destination terminal 100 of the result, and transmits the generated message to the destination terminal 100 through the information transmitting and receiving unit 210.

The database unit 250 stores data and programs for performing real-time voice phishing analysis.

The database unit 250 may inquire, store and delete data according to a request of the controller 220, and provide the result to the controller 220.

The database unit 250 may store a morpheme analysis process, a similarity calculation algorithm, a key word dictionary, a typo word dictionary, and an organization name dictionary.

4 is a flowchart illustrating an operation in a voice phishing analysis system according to an embodiment of the present invention. Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 3.

First, the receiving terminal 100 receives an incoming call request from the calling terminal (S110). After checking the caller's telephone number of the received call, check whether the caller's telephone number (outgoing information) is stored in a pre-stored address book (S120).

As a result of checking in step S120, when the called terminal 100 does not have a number that matches the phone number stored in the address book previously stored (S130), the voice phishing detection application is driven.

Before launching the voice phishing detection application, provide the user with an on / off selection interface for driving the voice phishing detection application, thus only driving the voice phishing detection application if the user selects on for driving the voice phishing detection application. It can also be implemented.

Upon providing the voice phishing detection application driving on / off selection interface, the voice notification detection application is turned on, the user is notified that the call history is stored.

After S130, before driving the voice phishing detection application, it is possible to confirm whether the call recording is a telephone number of an illegal country based on the outgoing telephone number.

Examples of countries where call recording is illegal are France and the United States, and such country codes are stored in advance, so that if the first digit of an outgoing telephone number matches the country code, the call of the country where call recording is illegal Judging by the number.

As such, the voice phishing detection application is not run for calls originating from countries where call recording is illegal.

In operation S130, it may be determined whether the calling party's telephone number matches a pre-stored voice phishing suspicious number. If the calling party's telephone number matches the pre-stored voice phishing suspicion number, it may be notified through voice or text that the voice phishing is suspected without going through the following steps.

When the voice phishing detection application is driven, the called terminal 100 records the call between the calling terminal and the called terminal through recording and the like (S140), and converts the recorded contents into an STT conversion text (S150).

The called terminal 100 transmits the textualized call contents to the voice phishing analysis server (S160).

The text of the call is transmitted to the voice phishing analysis server according to whether the text of the call is matched with a word included in a dictionary stored in advance.

The prestored dictionary includes a key word dictionary and an organization name word dictionary that can be determined to be voice phishing.

The key word dictionary may include, for example, any one or more of a cannon book, identity theft, an investigation team, and a police agency.

The institution name word dictionary may include a set of institution names such as the Financial Supervisory Service, IBK, Shinhan Bank, etc.

The security server analyzes the textualized call content received from the called terminal 100 (S170), and analyzes the call history to determine whether voice phishing is suspected (S180).

When the call analysis analyzed in step S180 is suspected to be voice phishing, the voice terminal suspects voice phishing is notified to the called terminal 100 (S190).

When the receiving terminal 100 is notified of the voice phishing suspicion from the security server, it generates an alert indicating that the current call is suspected of voice phishing (S200). The called terminal 100 may be performed by displaying an alarm text on a display screen or outputting a voice or warning sound during a call.

The voice phishing detection application of the called terminal 100 provides a call selection screen during a call (S210), and provides a report selection screen including an interface for reporting the call history to the voice phishing analysis server to enable reporting. do.

When the user selects a report on the report selection screen, the called terminal 100 notifies the voice phishing analysis server of the report fact, so that the voice phishing analysis server stores the contents of the call and stores the text as a voice phishing case, To learn (S220).

In step S180, the voice phishing analysis server discards the received textified call content when the call content is not suspected to be voice phishing (S230).

5 is a flowchart illustrating the construction of a voice phishing case model according to an embodiment of the present invention.

Voice-phishing case-specific documents are collected (S510).

The extracted body or document content is saved as a text file with special characters and spaces removed, such as *, &, and ^.

The morpheme is analyzed in the text of the document (S520). Analyze stemming from text in the document.

More specifically, the morphemes are analyzed in the text of the document to distinguish word units and parts of speech. The morphological analyzer, which is commercially available, is applied to the document contents stored in text form, and the main text is divided into morphemes. Next, remove the stop words from the distinct morphemes. In other words, among the morphemes pressed by the morphological analyzer, the stopwords having no meaning in the index word are removed. Terminology elimination removes all other parts of speech such as probes, verbs, conjunctions, adjectives, etc., except for nouns and compound nouns stored in the morpheme analyzer.

Next, since a typo may occur during STT conversion according to the pronunciation of a person, the typo is replaced with a normal word by referring to a pre-stored typo dictionary (S530). For example, 'bank' can be replaced with 'bank'.

The voice phishing script is vectorized (S540). Word2Vec's Doc2Vec technique can be used.

Through this step, it is possible to build a voice phishing case model (S550).

6 is a flowchart illustrating a real-time voice phishing analysis method according to an embodiment of the present invention.

The voice phishing analysis server (hereinafter referred to as an analysis server) receives the call history converted into text from the called terminal (S610).

Stemming the textual call history (S620).

The typo is corrected using the pre-stored typo dictionary (S630).

The corrected text in which the typo is corrected is vectorized (S640).

The similarity between the pre-stored voice phishing case model and the current call history is determined (S650). The similarity between the script and the call history of the prestored voice phishing case model is determined. More specifically, the dot product of the vector of the script and the vector of the voice phishing currency is obtained to calculate the cosine similarity.

In addition, the similarity may be calculated by using a JaroWinkler algorithm that determines the degree of matching by shifting the positions of words in a sentence.

Alternatively, the similarity may be determined by appropriately combining the cosine similarity and the JaroWinkler algorithm. For example, the final similarity may be calculated by cosine similarity * 0.3 + JaroWinkler similarity * 0.7 and the like.

If the similarity is greater than a predetermined threshold (for example, 80%) (S660), the voice terminal suspects voice phishing warning (S670).

If the similarity is less than the predetermined threshold, the call history is continuously monitored or voice phishing analysis ends.

7 is an example of a screen outputting a warning message of a called terminal according to an embodiment of the present invention.

When the called terminal is notified of the voice phishing suspicion about the call by the voice phishing analysis server, the call terminal outputs a message 620, which warns the voice phishing suspicion, as shown in FIG.

The screen 610 may include an input button 632, a cancel button 631, and a call termination button 633.

The user can select the report of the call history through the input button 632, can continue the call without reporting the call history through the cancel button 631, the call and voice phishing suspicion application through the call end button 633 Can be terminated.

At this point, it will be understood that each block of the flowchart illustrations and combinations of flowchart illustrations may be performed by computer program instructions. Since these computer program instructions may be mounted on a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, those instructions executed through the processor of the computer or other programmable data processing equipment may be described in flow chart block (s). It creates a means to perform the functions. These computer program instructions may be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular manner, and thus the computer usable or computer readable memory. It is also possible for the instructions stored in to produce an article of manufacture containing instruction means for performing the functions described in the flowchart block (s). Computer program instructions may also be mounted on a computer or other programmable data processing equipment, such that a series of operating steps may be performed on the computer or other programmable data processing equipment to create a computer-implemented process to create a computer or other programmable data. Instructions for performing the processing equipment may also provide steps for performing the functions described in the flowchart block (s).

In addition, each block may represent a portion of a module, segment, or code that includes one or more executable instructions for executing a specified logical function (s). It should also be noted that in some alternative implementations, the functions noted in the blocks may occur out of order. For example, the two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending on the corresponding function.

In this case, the term '~ part' used in the present embodiment refers to software or a hardware component such as an FPGA or an ASIC, and '~ part' performs certain roles. However, '~' is not meant to be limited to software or hardware. '~ Portion' may be configured to be in an addressable storage medium or may be configured to play one or more processors. Thus, as an example, '~' means components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, and the like. Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and the 'parts' may be combined into a smaller number of components and the 'parts' or further separated into additional components and the 'parts'. In addition, the components and '~' may be implemented to play one or more CPUs in the device or secure multimedia card.

Those skilled in the art will appreciate that the present disclosure may be embodied in other specific forms without changing the technical spirit or essential features of the present disclosure. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive. The scope of the present specification is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and the equivalent concept are included in the scope of the present specification. Should be interpreted.

On the other hand, the present specification and drawings have been described with respect to the preferred embodiments of the present specification, although specific terms are used, it is only used in a general sense to easily explain the technical content of the present specification and to help the understanding of the invention, It is not intended to limit the scope of the specification. It will be apparent to those skilled in the art that other modifications based on the technical spirit of the present disclosure may be implemented in addition to the embodiments disclosed herein.

100: called terminal
110: communication unit
120: control unit
130: display unit
140: storage unit
150: key input unit
200: Voice Phishing Analysis Server
210: information transmission and reception
220: control unit
230: model generation unit
240: call content analysis unit
2450: database unit

Claims (15)

As a method for real-time voice phishing analysis by communicating with a voice phishing analysis server while a call destination terminal is in a call,
Receiving, by the called terminal, a call through a communication network;
Checking the calling party's number included in the received call;
Retrieving caller information corresponding to the calling party's telephone number from a pre-stored address book;
If there is no corresponding caller information, turning on the voice phishing detection function and starting a call recording when the call is made;
STT changing the text of the call recorded during the call, and texturing;
Streaming the text of the call to a voice phishing analysis server during a call;
Outputting an alert when receiving a result from the voice phishing analysis server analyzing the text of the call during a call that the call history is suspected to be voice phishing;
Voice phishing analysis method comprising a. The method of claim 1,
When there is no corresponding caller information as a result of the search, turning on the voice phishing detection function and starting a call recording during a call,
Providing an interface for selecting on / off of a voice phishing detection function when there is no corresponding caller information as a result of the search;
Voice phishing analysis method further comprising. The method of claim 1, wherein the text of the call is transmitted to a voice phishing analysis server.
The text of the call is transmitted to the voice phishing analysis server according to whether the text of the call is matched with a word included in a dictionary stored in advance.
The pre-stored dictionary, voice phishing analysis method comprising a key word dictionary and an organization name word dictionary that can be determined to be voice phishing. The method of claim 1, wherein the outputting of the warning comprises:
Notifying the called terminal by at least one of voice or text that a call history is suspected of voice phishing;
Providing a reporting interface for reporting the call history to the voice phishing analysis server; And
If the user selects a report through the report interface, the voice phishing analysis server storing text of a call history as a voice phishing case;
Voice phishing analysis method comprising a. The method of claim 1, wherein the voice phishing analysis server determines the similarity with the voice phishing case model stored in advance in the call history text received from the called terminal,
And if the similarity is greater than or equal to a predetermined threshold as a result of the determination, determining that the call history is suspected to be voice phishing. The method of claim 1,
Before turning on the voice phishing detection function and starting a call recording,
Checking whether a predetermined call recording is a telephone number of an illegal country based on the outgoing telephone number;
Voice phishing analysis method further comprising. The method of claim 1, wherein before the call recording is started, it is determined whether the caller information matches a pre-stored voice phishing suspicion number. Voice phishing analysis method, characterized in that the notification of any one or more of the voice or text. A voice phishing analysis system that provides a real-time voice phishing analysis service during a call termination terminal,
Receives a call through the communication network, retrieves the caller information corresponding to the information stored in the address book with respect to the calling party's telephone number included in the received call, and detects the voice phishing when there is no corresponding caller information as a result of the search. To turn on, recording the call history during the call and STT to change the recorded call history, the destination terminal to text;
Voice phishing analysis server receiving the streaming text of the call content from the called terminal, analyzing the text of the call content, and if the call history is suspected to be voice phishing, providing a result of analysis to the called terminal
Voice phishing analysis system comprising a. The method of claim 8, wherein the called terminal,
And, if there is no corresponding caller information, providing an interface for selecting on or off of the voice phishing detection function. The method of claim 8,
The called terminal provides a report interface for reporting the call history to the voice phishing analysis server, and when a report is selected through the report interface, notifying the voice phishing analysis server that a report is selected.
And if the voice phishing analysis server is notified of the report selection, storing the text of the call history as a voice phishing case. The method of claim 8,
The voice phishing analysis server determines the similarity of the call history text received from the called terminal with a pre-stored voice phishing case model, and determines that the call history is suspected to be voice phishing when the similarity is more than a predetermined threshold. Voice phishing analysis system, characterized in that. The method of claim 8,
The called terminal checks whether the call recording is a telephone number of an illegal country based on the calling telephone number, and turns on a voice phishing detection function when the calling telephone number is not a telephone number of a country where call recording is illegal. Real time voice phishing analysis system, characterized in that. A terminal for providing a real-time voice phishing analysis service by communicating with a voice phishing analysis server during a call terminal,
A communication unit for receiving a call through a communication network;
A storage unit which stores an address book;
Checking the calling party number included in the received call, searching for the calling party information corresponding to the calling party number in the address book, and if there is no corresponding calling party information in the search result, turning on the voice phishing detection function, A control unit which starts a call recording during a call and changes the text of the call recorded during the call by STT and textizes the call;
A display unit for outputting information under the control of the controller;
Including,
The control unit may transmit the text of the call content to a voice phishing analysis server during a call, and when the call history is received from the voice phishing analysis server analyzing the text of the call content, suspected to be voice phishing, the display unit. Terminal for outputting a warning through. The method of claim 13,
And the control unit provides an interface for selecting on or off of the voice phishing detection function when there is no corresponding caller information. The method of claim 13,
The control unit provides a report interface for reporting the call history to the voice phishing analysis server, and when a report is selected through the report interface, notifying the voice phishing analysis server that a report is selected. .

Images