KR20220057111A - Method and system to provide services to prevent and report verbal abuse and violence - Google Patents

Abstract

A system for providing service to prevent and report verbal abuse and assault according to a first embodiment of the present invention includes: a user terminal which transmits a verbal abuse and assault report call and a report message by using a service platform to prevent and report verbal abuse and assault; and a platform management server which provides location information and situation information of the user terminal to a designated institution server when the call and report message are received.

Description

{Method and system to provide services to prevent and report verbal abuse and violence}

The present invention relates to a method and system for preventing/reporting verbal abuse and assault.

Currently, it is difficult to deal with violent crimes while on the move. In particular, there are more than 2-3 cases per month in taxis, and violent crimes such as the abduction of female drivers are on the rise.

Furthermore, not only in taxis, but in these days of constant occurrence of large and small incidents in daily life, it is necessary to have a device that can determine whether the other person's words and actions are verbal or assaulted, and whether they are subject to punishment.

Laid-Open Patent Publication No. 10-2008-0045101 (Title of the invention: mobile security system)

An object of the present invention is to provide a system and method for preventing verbal abuse and assault/reporting that can solve the problems of the prior art.

Abusive language and assault prevention/report service system according to a first embodiment of the present invention for solving the above problems is a user terminal for transmitting abusive language and assault report call and report message using a verbal abuse and assault prevention platform; and a platform management server that provides location information and context information of the user terminal to a designated organization server when the call and report messages are received.

Abusive language and assault prevention/report service system according to a second embodiment of the present invention for solving the above problems is a user terminal for transmitting a voice or image input from the outside using a platform for preventing verbal abuse and assault; and a platform management that detects a voice or object for abusive language or assault in the voice or video transmitted from the user terminal, and requests a call to the user terminal to a competent authority when the detected voice or object satisfies the requirements for abusive language or assault Includes server.

Abusive language and assault prevention/reporting service method according to a second embodiment of the present invention for solving the above problems comprises the steps of transmitting video and audio information related to verbal abuse and assault acquired from a user terminal; Analyzing voice and video related to verbal abuse and assault in the platform management server; After determining whether or not there is a criminal punishment target based on the analyzed result, if it is a criminal punishment target, the step of searching for and extracting applicable criminal punishment law items It includes the step of automatically reporting to a related organization (police station, 119) while providing it to the terminal.

By using the abusive language and assault prevention/reporting service system and method according to an embodiment of the present invention, it is possible to block insulting remarks and actions of the other party, and to present clear legal punishment regulations for the other party's abusive language and assault to the other party. In addition, there is an advantage that it is possible to record and store the evidence of the opponent's verbal abuse and assault in real time.

Furthermore, by being provided with legal punishment provisions for sexual harassment, coercion, coercion, etc. as well as verbal abuse and assault, the user can be clearly provided whether the unsatisfactory words and actions of the other party are the subject of legal punishment. It provides the advantage of expediting subsequent punishment procedures.

In addition, there is an advantage in helping users without legal knowledge to conveniently appoint a criminal lawyer by introducing a criminal lawyer to an AI matching algorithm after abusive language or assault occurs.

1 is a network configuration diagram of a system for preventing/reporting verbal abuse and assault according to a first embodiment of the present invention.
2 to 4 are exemplary views showing execution screens of the verbal abuse and assault prevention/reporting service platform executed in the user terminal in FIG. 1 .
5 is a network configuration diagram of a system for preventing/reporting abusive language and assault according to a second embodiment of the present invention.
6 to 8 are exemplary views of execution screens of the verbal abuse and assault prevention/reporting service platform shown in FIG. 5 .
9 is a block diagram showing the detailed configuration of the platform management server shown in FIG.
10 is a flowchart illustrating a method for preventing/reporting abusive language and assault according to another embodiment of the present invention.
11 and 12 are flowcharts illustrating the process S810 shown in FIG. 10 in more detail.
13 and 14 are flowcharts illustrating S820 illustrated in FIG. 10 in more detail.

Hereinafter, embodiments of the present specification will be described with reference to the accompanying drawings. However, it should be understood that the technology described herein is not limited to specific embodiments, and includes various modifications, equivalents, and/or alternatives of the embodiments of the present specification. . In connection with the description of the drawings, like reference numerals may be used for like components. In this specification, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of a corresponding characteristic (eg, a numerical value, function, operation, or component such as a part). and does not exclude the presence of additional features.

In this specification, expressions such as "A or B," "at least one of A and/and B," or "one or more of A or/and B" may include all possible combinations of the items listed together. . For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) includes at least one A, (2) includes at least one B; Or (3) it may refer to all cases including both at least one A and at least one B.

As used herein, expressions such as "first," "second," "first," or "second," can modify various elements, regardless of order and/or importance, and refer to one element. It is used only to distinguish it from other components, and does not limit the components. For example, the first user equipment and the second user equipment may represent different user equipment regardless of order or importance. For example, without departing from the scope of the rights described herein, a first component may be referred to as a second component, and similarly, the second component may also be renamed as a first component.

One component (eg, a first component) is "coupled with/to (operatively or communicatively)" to another component (eg, a second component); When referring to "connected to", it should be understood that the certain element may be directly connected to the other element or may be connected through another element (eg, a third element). On the other hand, when it is said that a component (eg, a first component) is "directly connected" or "directly connected" to another component (eg, a second component), the component and the It may be understood that other components (eg, a third component) do not exist between other components.

As used herein, the expression "configured to (or configured to)" depends on the context, for example, "suitable for," "having the capacity to ," "designed to," "adapted to," "made to," or "capable of." The term “configured (or configured to)” may not necessarily mean only “specifically designed to” in hardware. Instead, in some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts.

For example, the phrase "a processor configured (or configured to perform) A, B, and C" refers to a dedicated processor (eg, an embedded processor) for performing the corresponding operations, or by executing one or more software programs stored in a memory device. , may mean a generic-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

The terms used herein are used only to describe specific embodiments, and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meanings as commonly understood by one of ordinary skill in the art described herein. Among the terms used in this specification, terms defined in a general dictionary may be interpreted with the same or similar meaning as the meaning in the context of the related art, and unless explicitly defined in the present specification, have ideal or excessively formal meanings. is not interpreted as In some cases, even terms defined in this specification cannot be construed to exclude embodiments of the present specification.

Hereinafter, based on the accompanying drawings, a system and method for preventing/reporting abusive language and assault according to the first and second embodiments of the present invention will be described in more detail.

1 is a network configuration diagram of a system for preventing/reporting abusive language and assault according to a first embodiment of the present invention, and FIGS. 2 to 4 are execution of the abusive language and assault prevention/reporting service platform executed in the user terminal in FIG. It is an example diagram showing the screen.

1 , the verbal and assault prevention/report service system 100 according to the first embodiment of the present invention includes a user terminal 200 and a platform management server 300 .

Each component is generally connected through a network (network).

Here, the network refers to a connection structure capable of exchanging information between each node such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, LTE (Long Term Evolution) network, 5rd Generation Partnership Project (5GPP) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide) Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, and the like are included, but are not limited thereto.

The user terminal 200 may be configured to transmit a call and report message when event information about abusive language and assault provided by a third party is detected using the abusive language and assault prevention platform.

The user terminal 200 may be configured to record and store audio and video information about abusive language and assault provided by a third party by using the abusive language and assault prevention platform.

The user terminal 200 may be configured to output punishment regulations and warning messages for the situation when a third party's abusive language and assault is detected using the abusive language and assault prevention platform.

The user terminal 200 may be a terminal that provides the user with response guide information for responding to a third party's abusive language and assault through the abusive language and assault prevention platform.

The user terminal 200 is a terminal that executes the verbal and assault platform 10, a smart phone, a portable terminal, a mobile terminal, a foldable terminal, personal information Terminal (Personal Digital Assistant: PDA), PMP (Portable Multimedia Player) Terminal, Telematics Terminal, Navigation Terminal, Personal Computer, Notebook Computer, Slate PC, Tablet PC (Tablet) PC), ultrabook (ultrabook), wearable device (including, for example, watch-type terminal (Smartwatch), glass-type terminal (Smart Glass), HMD (Head Mounted Display), etc.), Wibro (Wibro) terminal, Applicable to various terminals such as IPTV (Internet Protocol Television) terminals, smart TVs, digital broadcast terminals, AVN (Audio Video Navigation) terminals, A/V (Audio/Video) systems, flexible terminals, digital signage devices, etc. can

The user terminal 200 communicates with any internal component or at least one external terminal (video cam, console operation unit, etc.) through a wired/wireless communication network. Here, as wireless Internet technologies, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), Wimax (World Interoperability for Microwave Access: Wimax), HSDPA (High Speed Downlink Packet Access) ), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), etc. In this case, each of the terminals 200 and 400 transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above. In addition, short-range communication technologies include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and Near Field Communication (NFC). , Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi (Wi-Fi), Wi-Fi Direct (Wi-Fi Direct), etc. may be included. In addition, the wired communication technology may include Power Line Communication (PLC), USB communication, Ethernet, serial communication, optical/coaxial cable, and the like.

Also, the user terminal 200 may mutually transmit information with an arbitrary terminal through a Universal Serial Bus (USB).

In addition, the user terminal 200 includes technical standards or communication methods for mobile communication (eg, Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (EV-DO), Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), LTE- A (Long Term Evolution-Advanced), etc.) transmits and receives wireless signals to and from the base station, the server 200, the affiliated store terminal 300, and the like on a mobile communication network.

The user terminal 200 may be a terminal that accesses the platform management server 300 through the abusive language and assault prevention platform 10 .

The abusive language and assault prevention platform 10 may include applications, programs, web pages, etc. installed or driven in the user terminal 200 through a network.

Here, the web browser is a program that enables the use of a web (World Wide Web) service, and refers to a program that receives and displays hyper text described in HTML (hyper text mark-up languge), for example, Netscape (Netscape). ), Explorer, and Chrome.

In addition, the application means an application on a terminal, for example, includes an app (app) executed in a mobile terminal (smartphone). Apps can be downloaded and installed from the application market, a virtual marketplace where mobile content can be freely bought and sold.

Hereinafter, a more detailed function of the abusive language and assault prevention platform 10 executed in the user terminal 200 will be described.

2 to 4 are diagrams showing execution screens of the verbal abuse and assault prevention/reporting service platform according to the first embodiment of the present invention.

2 to 4 , the abusive language and assault prevention/report service platform 10 provided herein may include at least one or more interfaces 11 , 12 , and 13 .

First, the abusive language and assault prevention/report service platform 10 includes a warning message interface 11 , an assault report interface 12 , and an environment setting interface 13 .

The warning message interface 11 may be an interface for outputting a warning message related to verbal abuse and assault and punishment rules based on a user's touch signal.

The warning message interface 11 may be an interface for outputting any one of a plurality of warning comments related to abusive language and assault registered by a user in the setting interface by interworking with the environment setting interface 13 to be described later.

Next, the abusive language and assault report interface 12 may be an interface for requesting a report message and a report call for abusive language and assault based on the user's touch signal.

The abusive language and assault report interface 12 is linked with the environment setting interface 13, referring to FIGS. 3 and 4, and calling the abusive language and assault report with the contact number of the competent authority registered in the environment setting interface 13 It can be configuration.

Next, the environment setting interface 13 may be an interface for setting and registering the content of the warning message and the reporter's personal information.

In addition, the environment setting interface 13 may additionally include an interface for setting identification information (job, vehicle number, etc.) for confirming the user's identity.

Next, when the platform management server 300 receives event information of any one of a report call and a report message for abusive language and assault from the user terminal 200 , after analyzing the event information, it has jurisdiction over the designated abusive language and assault It may be a configuration that provides the location information of the user terminal 200 and the user's context information (abusive language and assault) to a competent authority server and/or terminal.

5 is a network configuration diagram of a system for preventing/reporting abusive language and assault according to a second embodiment of the present invention, and FIGS. 6 to 8 are an execution screen of the abusive language and assault prevention/reporting service platform shown in FIG. It is an exemplary view, and FIG. 9 is a block diagram showing the detailed configuration of the platform management server shown in FIG. 5 .

Referring to FIG. 5 , the verbal abuse and assault prevention/report service system 1000 according to another embodiment of the present invention includes a user terminal 1100 and a platform management server 1200 .

Each of the components 1100 and 1200 is generally connected through a network.

Here, the network refers to a connection structure capable of exchanging information between each node such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, LTE (Long Term Evolution) network, 5rd Generation Partnership Project (5GPP) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide) Area Network), PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, and the like are included, but are not limited thereto.

The user terminal 1100 communicates with any internal component or at least one external terminal (video cam, console operation unit, etc.) through a wired/wireless communication network. Here, as wireless Internet technologies, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), Wimax (World Interoperability for Microwave Access: Wimax), HSDPA (High Speed Downlink Packet Access) ), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), etc. In this case, each of the terminals 200 and 400 transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above. In addition, short-range communication technologies include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and Near Field Communication (NFC). , Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi (Wi-Fi), Wi-Fi Direct (Wi-Fi Direct), etc. may be included. In addition, the wired communication technology may include Power Line Communication (PLC), USB communication, Ethernet, serial communication, optical/coaxial cable, and the like.

Also, the user terminal 1100 may mutually transmit information with an arbitrary terminal through a Universal Serial Bus (USB).

In addition, the user terminal 1100 is a technical standard or communication method for mobile communication (eg, Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Code Division Multi Access 2000 (CDMA2000), Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (EV-DO), Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), LTE- A (Long Term Evolution-Advanced), etc.) transmits and receives radio signals to and from a base station on a mobile communication network.

The user terminal 1100 may be a terminal that accesses the platform management server 1200 through the abusive language and assault prevention/report service platform 20 .

The user terminal 1100 records and stores the voice and video of abusive language and assault applied by the other party through the abusive language and assault prevention/report service platform 20, and provides the stored voice and image information as a platform management server to be described later. can do.

The user terminal 1100 may output the analysis result of the abusive language and assault-related voice and image analyzed by the platform management server 1200 through the abusive language and assault prevention/report service platform 10 as audio and video. .

Here, the analysis result may be a warning about whether or not there is a criminal punishment target for abusive language and assault, and punishment requirements.

The user terminal 1100 may be requested to connect with an attorney specializing in criminal law through the abusive language and assault prevention/report service platform 10 .

The user terminal 1100 may automatically report to a nearby police station or 119 when abusive language and assault occurs by the other party through the abusive language and assault prevention/report service platform.

Next, the platform management server 1200 analyzes the audio and video of the abusive language and assault provided from the user terminal 1100, and then generates and provides a warning message including a punishment rule corresponding to the abusive language and assault. .

In addition, the platform management server 1200 provides a matching service that matches the criminal lawyer registered in the database after determining whether the analyzed verbal and assault is a criminal punishment target.

More specifically, the platform management server 1200 includes a receiving unit 1210 , a voice processing/analysis unit 1220 , an image processing/analysis unit 1230 , a criminal punishment target determination unit 1240 , and a law item search unit 1250 . ), a report processing unit 1260 , an AI matching unit 1270 , and a platform providing unit 1280 .

The receiving unit 1210 may be configured to receive audio and video of verbal abuse and assault transmitted from the user terminal 1210 .

The voice processing/analysis unit 1220 analyzes words and sentences related to abusive language among voice information on abusive language.

The voice processing/analysis unit 1220 classifies the unique tones of the user and the other party into a spectrum in the voice transmitted from the user terminal (speech exchanged between the user and the other party), and then connects the classified spectra to allow the talker to Extracts spoken voice information.

In addition, the voice processing/analysis unit 1220 may include an SST engine that removes a silent section in the extracted voice for each extracted talker (user and counterpart) and then converts it into text.

Also, the voice processing/analysis unit 1220 may extract a type of word related to abusive language and sexual harassment from the converted text.

The voice processing/analysis unit 1220 may additionally extract the number of exposures of words related to the extracted abusive language and/or sexual harassment, the number of repetitions of the same word, and the like.

On the other hand, the voice processing/analysis unit 1220 may additionally extract a word that induces or means a sense of incongruity and coercion in the text obtained by converting the extracted voices of the interlocutors (user and counterpart).

Next, the image processing/analysis unit 1230 may be configured to extract an object related to an assault from an image transmitted from the user terminal (an image in which the user and the other party are included or an image obtained by photographing the behavior of the other party).

The image processing/analysis unit 1230 may extract an object for a human body (face, hand, fist, foot, etc.) and an object for a weapon (a knife, a stick, etc.) from within the image.

More specifically, the image processing/analysis unit 1230 performs one or more pre-processing of the target region in the video image among binarization, sessionization, and noise removal, and then performs a Gaussian filter, a Laplacian filter, and a Gaussian filter. The target region may be deformed or improved by using Difference of Gaussian (DoG) and Canny edge detection.

For example, noise reduction using a Gaussian filter, etc., a gradient operation for detecting an edge component is performed (gradient operation), and a non-maximum value suppression for interpolating a broken edge line is performed (non -maximum suppression) and hysteresis thresholding that binarizes the edge map can be performed.

The image processing/analysis unit 1230 lattice-segments the image of the target area into blocks by using a Region Proposal Network (RPN), and extracts an object similar to a human body and a weapon within the grid-divided target area. .

The image processing/analysis unit 1230 normalizes and clusters blocks of the target region, and then specifically extracts and extracts objects in the target region using the R-CNN algorithm. It is analyzed whether the extracted objects are assault-related objects by comparing them with various assault-related objects that are learned by the R-CNN algorithm in the database and stored.

Next, the criminal punishment target determination unit 1240 determines the presence or absence of a criminal punishment target for verbal abuse and assault based on the result value of the voice processing/analysis unit 1220 and the result value of the image processing/analysis unit 1230 It can be configuration.

More specifically, the shape punishment target determination unit 1240 is the number of exposures of words related to abusive language and/or sexual harassment extracted from the voice processing/analysis unit 1220, the number of repetitions of the same word, After scoring the exposure frequency of the meaning word, if the calculated score exceeds a preset value or more, a criminal punishment target is determined.

In addition, the shape punishment target determination unit 1240 determines the types of objects related to the assault, the presence or absence of extraction between the objects, and the location of the objects in the image transmitted from the user terminal (images including the user and the other party or images of the other party's actions). Based on (adjacent degree), it is judged whether there is a shape punishment target.

In addition, in the case of an image, the criminal punishment target determination unit 1240 may determine the self-defense based on a change in position between objects.

Next, when the legal item search unit 1250 determines that the corresponding audio and video from the criminal punishment target determination unit 1240 are criminal punishment targets, verbal and/or sexual harassment extracted from the voice processing/analysis unit 1220 and Penalty law items (criminal law) are searched based on the number of exposures of related words, the number of repetitions of the same word, and the exposure frequency of words that induce or mean a sense of foreign exchange and coercion.

In addition, punishment laws based on the types of objects related to the assault, the presence or absence of extraction between objects, and their location (adjacentness) in the video transmitted from the user terminal (video including the user and the other party or a video recording the behavior of the other party) An item (criminal law) is searched in the database.

For reference, the criminal law aims to punish those who collectively or habitually commit robbery, or commit violent acts by carrying a weapon or other dangerous object.

The criminal law applies to crimes such as assault, injury, arrest, confinement, intimidation, trespassing, non-refusal to eviction, coercion, blackmail, and destruction.

Next, the report processing unit 1260 requests the user terminal to make an emergency call to the relevant agencies (police and fire stations) when the corresponding audio and image are determined by the criminal punishment target determination unit 1240 to be a criminal punishment target.

In addition, the report processing unit 1260 may transmit to the relevant agencies (police stations and fire stations) the punishment rule items for verbal abuse and assault extracted from the law item search unit and the location information of the user terminal to the competent authority.

Next, when the AI matching unit 1270 determines that the corresponding audio and image are the criminal punishment targets from the criminal punishment target determination unit 1240, the user terminal 1100 searches for a criminal lawyer in an adjacent location to the user terminal ( 1100) is provided.

The AI matching unit 1270 appoints a criminal lawyer related to any one of assault, injury, confinement, intimidation, house invasion, refusal to eviction, coercion, blackmail, and destruction of the criminal law for one day after appointing a criminal lawyer, and then to the user terminal You may request to appoint an attorney.

Next, the platform providing unit 1280 may be configured to provide the verbal and assault prevention/report service platform 20 .

The abusive language and assault prevention/report service platform 20 includes a warning message interface 21 , an abusive language and assault report interface 22 , a configuration interface 23 , and an AI abusive language/assault processing interface 24 .

The warning message interface 21 may be an interface for outputting a warning message related to verbal abuse and assault and punishment rules based on a user's touch signal.

The warning message interface 21 may be an interface for outputting any one of a plurality of warning comments related to abusive language and assault registered by a user in the setting interface by interworking with the environment setting interface 23 to be described later.

Next, the abusive language and assault report interface 22 may be an interface for requesting a report message and a report call regarding abusive language and assault based on the user's touch signal.

The abusive language and assault report interface 22 may be configured to interwork with the environment setting interface 23 to call a verbal abuse and assault report to a contact number of a competent authority registered in the environment setting interface 13 .

Next, the environment setting interface 13 may be an interface for setting and registering the content of the warning message and the reporter's personal information.

Next, the AI abusive language / assault processing interface 24 is operated based on the user's voice and touch signal, takes the voice and image based on the time when the user's input signal is input, and records and The captured audio and video are provided to the platform management server 1200 .

The AI abusive language and assault processing interface 24 performs a function of receiving and outputting information on the judgment result and punishment rules for determining whether verbal abuse and assault are present in the transmitted voice and video.

For reference, the platform management server 1200 disclosed in the present invention employs a deep learning learning algorithm, and the deep learning learning algorithm is a Deep Belief Network, Autoencoder, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Deep Q -Network and the like, and the deep learning learning algorithm listed in the present invention is only an example, and is not limited thereto.

In the present invention, an example of applying CNN (Convolutional Neural Network), which is any one of the deep learning learning algorithms listed above, and applying it to an AI and deep learning-based airport security search system has been described, but it is not limited thereto, and the user's choice Various types of deep learning learning algorithms may be used depending on the

10 is a flowchart illustrating a method for preventing/reporting abusive language and assault according to another embodiment of the present invention, FIGS. 11 and 12 are flowcharts illustrating the process S810 shown in FIG. 10 in more detail, and FIGS. 13 and FIG. 14 is a flowchart illustrating S820 illustrated in FIG. 10 in more detail.

10 to 14 , the method (S800) for preventing/reporting verbal abuse and assault according to the second embodiment of the present invention transmits video and audio information related to abusive language and assault acquired from the user terminal 1200, the platform After analyzing (S810) the audio and video related to verbal abuse and assault in the management server 1200, it is determined whether there is a criminal punishment target based on the analyzed result, and if it is a criminal punishment target, the applicable criminal punishment law items are searched. Extraction (S820).

Thereafter, the platform management server 1200 generates a warning message including punishment regulations and provides it to the user terminal, and at the same time automatically reports it to a related organization (police station, 119) (S830).

After that, when the process S840 is completed, a criminal lawyer for the corresponding verbal abuse and assault is matched to the user and recommended (S840).

Here, the S810 process is a process performed by the voice processing/analysis unit 1220 and the image processing/analysis unit 1230, for example, in the case of voice information, in the voice processing/analysis unit 1220 in the user terminal 1100. After classifying the unique tones of the user and the other party into a spectrum within the transmitted voice (speech exchanged between the user and the other party), the voice information uttered by the talker is extracted by connecting the classified spectrums, and the extracted talker (user and removing a silent section in the extracted voice for each counterpart), and then converting it into text.

In addition, the process of extracting a type of word related to abusive language and sexual harassment in the text converted by the voice processing/analysis unit 1220, the number of exposures of the extracted abusive language and/or words related to sexual harassment, the number of repetitions of the same word, etc. are added. It includes the process of extraction with In addition, it includes a process of additionally extracting words that induce or mean a sense of incongruity and coercion in the text obtained by converting the voices of the extracted interlocutors (user and counterpart).

In the case of image information, an object (face, hand) related to an assault in an image (image including the user and the other party or an image captured by the other party's actions) transmitted from the user terminal 1100 from the image processing/analysis unit 1230 , fists, feet, etc.) and objects for weapons (knife, stick, etc.) are extracted.

For example, after the image processing/analysis unit 1230 performs at least one of binarization, sessionization, and noise removal on a target region in the video image, a Gaussian filter, a Laplacian filter, and a Gaussian difference ( After transforming or improving the target region by using Difference of Gaussian: DoG and Canny edge detection, the image of the target region is converted into a block unit (Patch) using a Region Proposal Network (RPN). It includes a series of processes of performing grid division and extracting objects similar to human bodies and weapons within the grid division target area.

In addition, after normalizing and clustering the patch of the target region, the R-CNN algorithm is used to specifically extract the objects in the target region, and the extracted objects are R- It includes a process of analyzing whether the extracted objects are assault-related objects by comparing them with various assault-related objects that are learned and stored with a CNN algorithm.

Next, in the process S820, the number of exposures of words related to abusive language and/or sexual harassment extracted in the process S810 by the shape punishment target determination unit 1240, the number of repetitions of the same word, a feeling of foreign exchange and coercion of words that induce or mean After scoring the exposure frequency, if the calculated score exceeds a preset value or more, it may be a process of determining a target of criminal punishment.

In addition, the shape punishment based on the type of object related to the assault, the presence or absence of extraction between objects, and the location (adjacentness) in the image transmitted from the user terminal (image including the user and the other party or the image of the other party's behavior) It may be a process of determining whether a target exists.

In addition, in the case of an image, step S820 includes a process of determining a just bearing based on a change in position between objects.

Next, in the process S830, when the legal item search unit 1250 determines that the corresponding audio and video are the subject of criminal punishment in the process S820, the words related to abusive language and/or sexual harassment extracted from the voice processing/analysis unit 1220 It includes the process of searching for items of punishment laws (criminal law) based on the number of exposures, the number of repetitions of the same word, and the exposure frequency of words that induce or mean a sense of foreign exchange and coercion.

In addition, punishment laws based on the types of objects related to the assault, the presence or absence of extraction between objects, and their location (adjacentness) in the video transmitted from the user terminal (video including the user and the other party or a video recording the behavior of the other party) It involves searching for items (criminal law) in a database.

Therefore, by using the abusive language and assault prevention/report service system and method according to the first and second embodiments of the present invention, it is possible to block abusive language and behavior of the other party, and clear legal punishment for the other party's abusive language and assault It is possible to present regulations to the other party, and also has the advantage of being able to record and store the evidence of the other party's verbal abuse and assault in real time.

Furthermore, by being provided with legal punishment provisions for sexual harassment, coercion, coercion, etc. as well as verbal abuse and assault, the user can be clearly provided whether the unsatisfactory words and actions of the other party are the subject of legal punishment. It provides the advantage of expediting subsequent punishment procedures.

In addition, there is an advantage in helping users without legal knowledge to conveniently appoint a criminal lawyer by introducing a criminal lawyer to an AI matching algorithm after abusive language or assault occurs.

In the above, the present invention has been described in detail with reference to the embodiments, but those of ordinary skill in the art to which the present invention pertains may make various substitutions, additions and modifications within the scope not departing from the technical spirit described above. Of course, it should be understood that such modified embodiments also fall within the protection scope of the present invention as defined by the appended claims below.

first embodiment
100: Abuse and assault prevention/report service system
200: user terminal
300: platform server
10: Abuse and assault prevention/report service platform
second embodiment
1000: Abuse and assault prevention/report service system
1100: user terminal
1200: platform management server
1210: receiver
1220: voice processing / analysis unit
1230: image processing / analysis unit
1240: Criminal punishment target judgment unit
1250: law item search unit
1260: Report processing department
1270: AI matching unit
1280: platform provider
20: Abusive language and assault prevention/reporting service platform

Claims (14)

A user terminal that sends a call and report message to report abusive language and assault using the abusive language and assault prevention/report service platform; and
Abusive language and assault report/prevention service system including a platform management server that provides location information and situation information of the user terminal to a designated institution server when the call and report message are received.
According to claim 1,
The abusive language and assault prevention/report service platform is
Abusive language and assault report/prevention system, characterized in that it outputs a warning message for verbal abuse and assault based on the user's input signal.
3. The method of claim 2,
The abusive language and assault prevention/report service platform is
Abusive language and assault report/prevention system, characterized in that it includes a setting interface for setting and registering the warning message by the user.
4. The method of claim 3,
The abusive language and assault prevention/report service platform is
Abusive language and assault prevention/reporting service system that transmits the user's personal information and report signal when receiving the user's input signal.
A user terminal that transmits an externally input voice or video using a verbal abuse and assault prevention/report service platform;
A platform management server that detects a voice or object for abusive language or assault in the voice or video transmitted from the user terminal, and requests a call to the user terminal from the competent authority when the detected voice or object satisfies the requirements for abusive language or assault Abusive language and assault prevention/reporting service system that includes.
6. The method of claim 5,
The platform management server
Abusive language and assault prevention/reporting service system that analyzes the audio and video of abusive language and assault provided from the user terminal, and then generates and provides a warning message including a punishment rule corresponding to the abusive language and assault.
6. The method of claim 5,
The platform management server
After classifying the unique tones of the user and the other party into a spectrum in the voice transmitted from the user terminal (speech exchanged between the user and the other party), the classified spectrum is connected to extract voice information uttered by the speaker Abusive language and assault prevention/reporting service system including a voice processing/analysis unit that converts into text after removing the silent section in the voice.
6. The method of claim 5,
The platform management server
After pre-processing the image transmitted from the user terminal, a target region is designated, the image of the target region is lattice-divided into blocks using RPN (Region Proposal Network), and within the lattice-divided target region Image processing/analysis to analyze whether the extracted objects are assault-related objects by comparing them with various assault-related objects stored by learning the extracted objects with an R-CNN algorithm in the database after extracting objects similar to the human body and weapons Abusive Language and Assault Prevention/Reporting Service System, including Wealth.
8. The method of claim 7,
The platform management server
After scoring the number of exposures of words related to verbal abuse and/or sexual harassment extracted from the voice processing/analysis unit, the number of repetitions of the same word, and exposure frequency of words that induce or mean foreign language and coercion, the calculated Abusive language and assault prevention/reporting service system including a criminal punishment target determination unit that determines a criminal punishment target when the score exceeds a preset value.

9. The method of claim 8,
The platform management server
A shape punishment target determination unit for determining whether a shape punishment target exists based on the types of objects related to the assault extracted from the image processing/analysis unit, the presence or absence of extraction between objects, and a location (proximity),
The criminal punishment target determination unit abusive language and assault prevention/reporting service system for determining self-defense based on a change in position between the objects.
10. The method of claim 9,
The platform management server
When it is determined by the criminal punishment target determination unit that the corresponding voice is a criminal punishment target, the number of exposures of words related to abusive language and/or sexual harassment extracted from the voice processing/analysis unit 1220, the number of repetitions of the same word, the feeling of foreign exchange And abusive language and assault prevention/reporting service system including a law item search unit that searches for and provides punishment law items (criminal law) based on the exposure frequency of words that induce or mean coercion.
11. The method of claim 10,
The platform management server
When the image is judged to be a criminal punishment target by the criminal punishment target determination unit, the punishment law item (criminal law) is stored in the database based on the types of objects extracted by the image processing/analysis unit, whether or not the objects are extracted, and the degree of proximity Abusive language and assault prevention/reporting service system that includes a legal item search unit that is searched and provided by .
13. The method of claim 11 or 12,
The platform management server
When it is determined by the criminal punishment target determination unit that the corresponding audio and video are criminal punishment targets, abusive language and assault prevention/reporting further comprising an AI matching unit that searches for a criminal lawyer in an adjacent location from the user terminal and provides it to the user terminal service system.
Transmitting video and audio information related to verbal abuse and assault acquired from a user terminal;
Analyzing voice and video related to verbal abuse and assault in the platform management server;
After judging whether or not there is a target of criminal punishment based on the analyzed result, if it is a target of criminal punishment, the step of searching and extracting applicable criminal punishment law items; and
Abusive language and assault prevention/reporting service method comprising the step of generating a warning message including punishment laws in the platform management server and providing it to a user terminal, and automatically reporting it to a related organization (police station, 119).

Images