KR20230070708A - Method and system for detecting danger - Google Patents

Abstract

Disclosed are a method and a system for detecting a danger. According to an embodiment, the method comprises the steps of: monitoring a user and obtaining sound from the user; and detecting a dangerous situation of the user by selectively using a language-based danger detection model using, as an input parameter, the sound obtained from the user, wherein the language-based danger detection model is trained to infer the relationship between a verbal sound and a dangerous situation based on the learning data of the verbal sound, or a non-language-based danger detection model, wherein the non-language-based danger detection model is trained to infer the relationship between a non-verbal sound and a dangerous situation based on the learning data of the non-verbal sound. Therefore, the method can detect the dangerous situation of the user and provide care services for the dangerous situation.

Description

Danger detection method and system {METHOD AND SYSTEM FOR DETECTING DANGER}

The following embodiments relate to a risk detection system and its method, and more specifically to a technique for detecting a dangerous situation faced by a user.

Vulnerable groups such as the elderly, the disabled, infants, and minors are more likely to be exposed to risks than healthy adults, and when exposed to risks, they cannot solve the risks on their own, which can cause fatal results.

For example, the elderly, the disabled, and the vulnerable class of infants cannot arbitrarily request the dispatch of emergency personnel in the event of a sudden health problem such as heart attack, difficulty breathing, occurrence of underlying disease, or fall accident. In the event of an emergency, such as a gas leak or natural disaster, it may cause death due to delayed evacuation due to inconvenient movement.

For another example, since it is difficult for the vulnerable class of the elderly, the disabled, and minors to generate a police dispatch request when problems such as harassment and assault occur during life, coping with the situation is bound to be insufficient.

Therefore, it is necessary to propose a technology for detecting dangerous situations of vulnerable groups such as the elderly, the disabled, infants, and minors and providing care services to cope with the situation.

Embodiments are intended to propose a method and system for detecting a user's risky situation and providing a care service for coping with the risky situation.

At this time, one embodiment intends to propose a method and system using an artificial intelligence-based risk detection model to detect a user's dangerous situation.

In particular, one embodiment intends to propose a method and system for improving detection accuracy in using a risk detection model.

In addition, one embodiment intends to propose a method and system for providing an optimized care service by classifying a user's dangerous situation.

However, the technical problems to be solved by the present invention are not limited to the above problems, and can be variously expanded without departing from the technical spirit and scope of the present invention.

According to one embodiment, a danger sensing method includes monitoring a user and obtaining a sound from the user; and a language-based danger detection model using the sound acquired from the user as an input parameter, wherein the language-based danger detection model is trained to infer a relationship between the linguistic sound and a dangerous situation based on the learning data of the linguistic sound; or By selectively using a non-verbal-based risk detection model, wherein the non-verbal-based risk detection model is learned to infer a relationship between the non-verbal sound and a dangerous situation based on the learning data of the non-verbal sound, It may include detecting the situation.

According to one aspect, the detecting may be a step of using different risk sensing models for each of a verbal sound element and a non-verbal sound element included in the sound obtained from the user.

According to another aspect, the using may include: using the language-based risk detection model with the linguistic sound component as an input parameter; or using the non-verbal sound element as an input parameter for the non-verbal risk detection model.

According to another aspect, the detecting may include pre-learning the user's location information, biometric information, image information, and environment information using the user's location information, biometric information, image information, and environment information as input parameters. It may be characterized in that the step of detecting the dangerous situation of the user using the risk detection models.

According to another aspect, the detecting may further include providing a care service for coping with the user's dangerous situation when the user's dangerous situation is detected.

According to another aspect, the providing may include identifying a case corresponding to the risk situation of the user among a plurality of preset cases; and providing the care service corresponding to the identified case among the care services set for each of the plurality of cases.

According to another aspect, the care service includes at least one service of an ambulance dispatch request service, a police dispatch request service, a management personnel call service, or a guardian call service for the user to cope with a dangerous situation. can do.

According to another aspect, the providing may include the care service by including the information on the identified case in at least one signal of an emergency personnel dispatch signal, a police dispatch request signal, a management personnel call signal, or a guardian call signal. It may be characterized in that it is a step of providing a.

According to another aspect, the detecting may further include, when the user's dangerous situation is detected, providing the user with an alarm notifying that the user's dangerous situation has been detected. .

According to one embodiment, in a computer program recorded on a recording medium to execute a risk sensing method in combination with a computer system, the risk sensing method includes: monitoring a user and acquiring sound from the user; and a language-based danger detection model using the sound acquired from the user as an input parameter, wherein the language-based danger detection model is trained to infer a relationship between the linguistic sound and a dangerous situation based on the learning data of the linguistic sound; or By selectively using a non-verbal-based risk detection model, wherein the non-verbal-based risk detection model is learned to infer a relationship between the non-verbal sound and a dangerous situation based on the learning data of the non-verbal sound, It may include detecting the situation.

According to an embodiment, the risk detection system trains a language-based risk detection model to infer a relationship between the verbal sound and a dangerous situation based on the learning data of the verbal sound, and based on the learning data of the non-verbal sound a learning modeling unit that trains a non-verbal-based risk sensing model to infer a relationship between the non-verbal sound and the dangerous situation; a sound acquisition unit that monitors a user and acquires sound from the user; and a danger detection unit configured to detect a danger situation of the user by selectively using the language-based danger detection model or the non-verbal-based danger detection model as an input parameter using sound obtained from the user.

According to one aspect, the risk detection unit may use different risk detection models for each of the verbal sound element and the non-verbal sound element included in the sound obtained from the user.

According to the other side, the risk detection unit, the user's location information, biometric information, image information and environment information as an input parameter to the user's location information, biometric information, image information and environmental information, each pre-learned risk It may be characterized in that the dangerous situation of the user is detected using sensing models.

According to another aspect, the danger detection unit may provide a care service for coping with the user's dangerous situation when the user's dangerous situation is detected.

According to another aspect, the risk detection unit identifies a case corresponding to the dangerous situation of the user among a plurality of preset cases, and responds to the identified case among care services set for each of the plurality of cases. It may be characterized in that the care service is provided.

Embodiments may suggest a method and system for detecting a user's dangerous situation and providing a care service for coping with the dangerous situation.

At this time, one embodiment may propose a method and system using an artificial intelligence-based risk detection model to detect a user's dangerous situation.

In particular, one embodiment may propose a method and system for improving detection accuracy in using a risk detection model.

In addition, embodiments may propose a method and system for providing an optimized care service by classifying a user's dangerous situation.

However, the effects of the present invention are not limited to the above effects, and can be variously extended without departing from the technical spirit and scope of the present invention.

1 is a diagram illustrating an example of a network environment according to an embodiment.
2 is a diagram for explaining internal configurations of an electronic device and a server according to an exemplary embodiment.
3 is a block diagram illustrating an example of a risk detection system implemented in a processor of a server according to an embodiment.
4 is a flow chart illustrating a risk detection method according to an embodiment.
FIG. 5 is a diagram for explaining the use of a risk detection model in the risk detection method shown in FIG. 4 .
FIG. 6 is a diagram for explaining providing a care service in the risk detection method shown in FIG. 4 .
7A to 7B are diagrams for explaining the provision of a care service according to a case corresponding to a dangerous situation in the risk detection method shown in FIG. 4 .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention is not limited or limited by the examples. Also, like reference numerals in each figure denote like members.

In addition, terms used in this specification (terminology) are terms used to appropriately express preferred embodiments of the present invention, which may vary according to the intention of a viewer or operator or customs in the field to which the present invention belongs. Therefore, definitions of these terms will have to be made based on the content throughout this specification. For example, in this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. Also, as used herein, "comprises" and/or "comprising" means that a referenced component, step, operation, and/or element is one or more other components, steps, operations, and/or elements. The presence or addition of elements is not excluded. In addition, although terms such as first and second are used in this specification to describe various regions, directions, shapes, etc., these regions, directions, and shapes should not be limited by these terms. These terms are only used to distinguish one area, direction or shape from another area, direction or shape. Accordingly, a portion referred to as a first portion in one embodiment may be referred to as a second portion in another embodiment.

Also, it should be understood that the various embodiments of the present invention are different from each other but are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in one embodiment in another embodiment without departing from the spirit and scope of the present invention. In addition, it should be understood that the location, arrangement, or configuration of individual components in the scope of each embodiment presented may be changed without departing from the spirit and scope of the present invention.

1 is a diagram illustrating an example of a network environment according to an embodiment. The network environment of FIG. 1 shows an example including a plurality of electronic devices 110 , 120 , 130 , and 140 , a plurality of servers 150 and 160 , and a network 170 . 1 is an example for explanation of the invention, and the number of electronic devices or servers is not limited as shown in FIG. 1 .

The plurality of electronic devices 110, 120, 130, and 140 may be mobile or fixed terminals implemented as computer devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 include smart phones, mobile phones, tablet PCs, navigation devices, computers, laptop computers, digital broadcasting terminals, personal digital assistants (PDAs), and PMPs ( Portable Multimedia Player), user wearable devices (wearable devices), and the like. For example, the first electronic device 110 may communicate with the other electronic devices 120, 130, and 140 and/or the servers 150 and 160 through the network 170 using a wireless or wired communication method.

The communication method is not limited, and short-distance wireless communication between devices as well as a communication method utilizing a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, and a broadcasting network) that the network 170 may include may also be included. For example, the network 170 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , one or more arbitrary networks such as the Internet. In addition, the network 170 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or a hierarchical network, and the like. Not limited.

Each of the servers 150 and 160 communicates with the plurality of electronic devices 110, 120, 130, and 140 through the network 170 to provide commands, codes, files, contents, services, and the like, or a computer device or a plurality of computers. Can be implemented in devices.

For example, the server 160 may provide a file for installing an application to the first electronic device 110 accessed through the network 170 . In this case, the first electronic device 110 may install an application using a file provided from the server 160 . In addition, the server 150 is connected to the server 150 under the control of an operating system (OS) included in the first electronic device 110 or at least one program (for example, a browser or the installed application), and the server 150 provides services or content may be provided. For example, when the first electronic device 110 transmits a service request message to the server 150 through the network 170 under the control of an application, the server 150 transmits a code corresponding to the service request message to the first It can be transmitted to the electronic device 110, and the first electronic device 110 can provide content to the user by constructing and displaying a screen according to a code under the control of an application.

2 is a block diagram illustrating internal configurations of an electronic device and a server according to an exemplary embodiment. In FIG. 2, the internal configuration of the first electronic device 110 as an example of one electronic device that is a terminal for monitoring the user and the server 150 as an example of one server communicating with the user's terminal will be described. . Accordingly, hereinafter, the first electronic device 110 means a user's terminal for monitoring the user, and the server 150 means a server communicating with the user's terminal. Other electronic devices 120 , 130 , and 140 or the server 160 may also have the same or similar internal configuration.

The first electronic device 110 and the server 150 may include memories 211 and 221, processors 212 and 222, communication modules 213 and 223, and input/output interfaces 214 and 224. The memories 211 and 221 are computer-readable recording media and may include a random access memory (RAM), a read only memory (ROM), and a permanent mass storage device such as a disk drive. In addition, the memories 211 and 221 may store an operating system or at least one program code (for example, a code for an application installed and driven in the first electronic device 110). These software components may be loaded from a computer readable recording medium separate from the memories 211 and 221 . The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card. In another embodiment, software components may be loaded into the memories 211 and 221 through the communication modules 213 and 223 rather than computer-readable recording media. For example, at least one program is a program installed by files provided by developers or a file distribution system (eg, the above-described server 160) that distributes installation files of applications through the network 170 (eg, the above-described server 160). It may be loaded into the memories 211 and 221 based on the above-described application).

The processors 212 and 222 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to processors 212 and 222 by memories 211 and 221 or communication modules 213 and 223 . For example, the processors 212 and 222 may be configured to execute instructions received according to program codes stored in a recording device such as the memories 211 and 221 .

The communication modules 213 and 223 may provide a function for the first electronic device 110 and the server 150 to communicate with each other through the network 170, and other electronic devices (for example, the second electronic device 120). )) or a function for communicating with another server (for example, the server 160). For example, when the processor 212 of the first electronic device 110 wants to transmit data (eg, sound generated by a user during daily life) according to a program code stored in a recording device such as the memory 211, the data is communicated. According to the control of the module 213, it may be transmitted to the server 150 through the network 170.

Conversely, control signals, commands, contents, files, etc. provided under the control of the processor 222 of the server 150 pass through the communication module 223 and the network 170 to the communication module of the first electronic device 110. It can be received by the first electronic device 110 through 213. For example, control signals or commands of the server 150 received through the communication module 213 may be transferred to the processor 212 or memory 211, and content or files may be transferred to the first electronic device 110. Can be stored in a storage medium that can further include.

The input/output interface 214 may be a means for interface with the input/output device 215 . For example, the input device may include a device such as a microphone, camera, keyboard, or mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input/output interface 214 may be a means for interface with a device in which functions for input and output are integrated into one, such as a touch screen. As a more specific example, the processor 212 of the first electronic device 110 may receive, through the input/output interface 214, the user's living sound collected through a microphone, which is an input device of the first electronic device 110. .

Also, in other embodiments, the first electronic device 110 and the server 150 may include more components than those shown in FIG. 2 . However, there is no need to clearly show most of the prior art components. For example, the first electronic device 110 is implemented to include at least a part of the above-described input/output device 215 or other components such as a transceiver, a global positioning system (GPS) module, various sensors, and a database. may further include. As a more specific example, when the first electronic device 110 is a smartphone, a direction sensor, an acceleration sensor or a gyro sensor, various physical buttons, buttons using a touch panel, input/output ports, and vibrations, which are generally included in the smartphone, It can be seen that various components such as a vibrator for vibration can be implemented to be further included in the first electronic device 110 .

Hereinafter, specific embodiments of a risk detection method and system for detecting a user's dangerous situation will be described.

3 is a block diagram showing an example of a risk detection system implemented in a processor of a server according to an embodiment, FIG. 4 is a flow chart showing a risk detection method according to an embodiment, and FIG. 5 is in FIG. A diagram for explaining the use of a risk sensing model in the illustrated risk sensing method, FIG. 6 is a diagram for explaining providing a care service in the risk sensing method shown in FIG. 4, and FIGS. 7A to 7B are shown in FIG. It is a diagram for explaining that a care service is provided according to a case corresponding to a dangerous situation in the illustrated risk detection method.

A risk detection system implemented by a computer may be configured in the server 150 according to an embodiment. The server 150 uses a plurality of electronic devices 110 , 120 , 130 , 140 , and 150 that monitor a user, a client, to provide a risk detection service for detecting a dangerous situation of a user and when a dangerous situation is detected. As a subject providing a care service for coping with a dangerous situation, a risk detection method may be performed by performing steps S410 to S440 shown in FIG. 4 . Hereinafter, the danger detection method refers to a method of providing the described danger detection service and care service to a user.

To enable the server 150 to perform the risk detection method according to FIG. 4, the processor 222 of the server 150 includes a learning modeling unit 310, a sound acquisition unit (as shown in FIG. 3 as components) 320) and a risk detection unit 330. Depending on embodiments, components of the processor 222 may be selectively included in or excluded from the processor 222 . Also, components of the processor 222 may be separated or merged to express functions of the processor 222 according to embodiments. For example, at least some of the components of the processor 222 may be implemented in the processor 212 included in the first electronic device 110 that is a terminal for monitoring a user.

The processor 222 and components of the processor 222 may control the server 150 to perform steps S410 to S440 included in the risk detection method of FIG. 4 . For example, the processor 222 and components of the processor 222 may be implemented to execute instructions according to an operating system code and at least one program code included in the memory 221 .

Here, components of the processor 222 may be representations of different functions of the processor 222 performed by the processor 222 according to instructions provided by program codes stored in the server 150. . For example, the danger detection unit 330 may be used as a functional expression of the processor 222 that detects a user's dangerous situation.

The processor 222 may read necessary commands from the memory 221 loaded with commands related to the control of the server 150 before step S410 (not shown as a separate step in the drawing). In this case, the read command may include a command for controlling the processor 222 to execute steps S410 to S440 to be described later.

In step S410, the learning modeling unit 310 may learn and build a language-based risk detection model and a non-verbal-based risk detection model in advance.

In more detail, the learning modeling unit 310 pre-learns a language-based risk detection model to infer a relationship between a verbal sound and a dangerous situation based on the learning data of the verbal sound, and based on the learning data of the non-verbal sound. As a result, a non-verbal-based risk detection model can be pre-trained to infer the relationship between non-verbal sounds and dangerous situations. Various well-known machine learning algorithms may be used in each learning process of the language-based risk detection model and the non-verbal-based risk detection model.

In this way, language-based risk detection models are trained based on the training data of verbal sounds, and non-verbal risk detection models are trained based on the training data of non-verbal sounds. Since each model is trained based on different learning data, the complexity of the learning process can be reduced, and dangerous situation detection accuracy can be improved in the step of detecting the user's dangerous situation (S430), which will be described later.

In step S420, the sound obtaining unit 320 may acquire sound from the user while monitoring the user. For example, the sound acquisition unit 320 may acquire the user's sound by receiving the user's sound worn by the user or collected from the terminal 110 located in the user's living space.

Here, the user's sound may include at least one of a verbal sound element and a non-verbal sound element. For example, the user's sound can be a non-verbal sound element such as "thump" caused by the user's fall accident, a non-verbal sound element such as the moan of "ah" produced by an injured user, and a user sound such as "help". may include linguistic sound elements that are uttered. This is only an example, and non-verbal sound elements or verbal sound elements that vulnerable groups such as the elderly, the disabled, infants, and minors can emit in a dangerous situation may be included in the user's sound.

In step S430, the danger detection unit 330 may detect the danger situation of the user by selectively using the sound obtained from the user as an input parameter, a language-based danger detection model or a non-verbal-based danger detection model.

At this time, the danger detection unit 330 may use different danger detection models for each of the verbal sound elements and non-verbal sound elements included in the sound obtained from the user.

For example, as shown in FIG. 5 , the danger detection unit 330 uses a language-based danger detection model as an input parameter for a linguistic sound element included in a sound acquired from a user, A dangerous situation can be detected, and the user's dangerous situation can be detected by using a non-verbal-based risk detection model as an input parameter for non-verbal sound elements included in sounds obtained from the user.

In detecting the user's dangerous situation, different risk detection models are used for each of the verbal sound elements and non-verbal sound elements included in the sound obtained from the user, so that the user's dangerous situation detection accuracy can be improved.

When the sound obtained from the user includes only verbal sound elements, only the language-based risk detection model is used, and when the sound obtained from the user includes only non-verbal sound elements, only the non-verbal risk detection model is used. should be used

However, when the sound obtained from the user includes both verbal sound elements and non-verbal sound elements, both the language-based danger detection model and the non-verbal-based danger detection model are used.

Even in this case, verbal sound elements may be analyzed based on the language-based risk sensing model, and non-verbal sound elements may be analyzed based on the non-verbal based risk sensing model. However, it is necessary to collect the analyzed results based on the language-based risk detection model and the non-verbal risk detection model.

To this end, the danger detection unit 330 uses a score representing the degree of risk situation of the user calculated as a result of analysis based on a language-based risk detection model and a risk situation of the user calculated as a result of analysis based on a non-verbal based risk detection model. The risk situation of the user can be detected with the average score representing the degree.

However, without being limited or limited thereto, the risk detection unit 330 may collect the analyzed results based on the language-based risk detection model and the non-verbal-based risk detection model in various ways in order to detect the user's dangerous situation.

Although it has been described that the abnormal danger detection unit 330 detects the user's dangerous situation using only the user's sound, the danger detection unit 330 is not limited or limited thereto, and the user's location information, biometric information (heartbeat, Blood pressure, etc.), image information (image captured in the user's living space), and environment information (temperature of the user's living space, etc.) can be further used to detect the user's dangerous situation.

For example, the risk detection unit 330 uses the user's location information, biometric information, image information, and environment information as input parameters, and a risk detection model pre-learned for each of the user's location information, biometric information, image information, and environment information. It is possible to detect the user's dangerous situation using them. Similarly, the risk detection unit 330 may use different risk detection models for the user's location information, biometric information, image information, and environment information. For a more specific example, the learning modeling unit 310 learns and builds a location information risk detection model, a biometric information-based hazard detection model, an image information-based hazard detection model, and an environmental information-based hazard detection model in advance. In 330, a location information risk detection model may be used when the user's location information is used, and a biometric information-based risk detection model may be used when biometric information is used.

Although not shown as a separate step in FIG. 4 , when a dangerous situation for the user is detected, the danger detection unit 330 may provide the user with an alarm notifying that the dangerous situation for the user has been detected. For example, if the user's dangerous situation is detected, the danger detection unit 330 provides an alarm to the user through the user's terminal 110 to inform the user that a care service for coping with the dangerous situation will soon be provided because the dangerous situation is present. can do. Therefore, it is possible to allow the user to calmly wait for help in a dangerous situation, or to make the user recognize that the user has detected that the user is in a dangerous situation even though it is not a dangerous situation by erroneously analyzing the user's sound. Accordingly, by allowing the user to cancel the provision of the care service, provision of unnecessary care service due to misdetection may be prevented.

In step S440, when the danger detecting unit 330 detects the user's dangerous situation, it may provide a care service for the user to cope with the dangerous situation.

In more detail, the risk detection unit 330 identifies a case corresponding to the user's dangerous situation among a plurality of preset cases, thereby providing a care service corresponding to the identified case among care services set for each of the plurality of cases. can do.

Here, a plurality of cases describe dangerous situations that vulnerable groups such as the elderly, disabled, infants, and minors may find themselves in, and the care service is a service requesting emergency personnel to respond to dangerous situations, a service requesting police dispatch, and management personnel. It may include at least one service of a paging service or a guardian paging service. More detailed information is as shown in FIG. 6 below.

In risky situations in which the vulnerable are faced, the coping methods are slightly different depending on the type of risky situation. Accordingly, the risk detection unit 330 may provide a care service optimized for each of a plurality of cases by pre-establishing and maintaining a table as shown in FIG. 6 .

For example, as shown in FIG. 7A , as a result of identifying a case corresponding to a user's dangerous situation, when the user's dangerous situation is an emergency medical risk situation case such as a fall accident, the danger detector 330 detects the emergency medical risk. It is possible to provide a care service corresponding to a situation case (emergency personnel dispatch request service, guardian calling service).

For another example, as shown in FIG. 7B , as a result of identifying a case corresponding to a user's dangerous situation, when the user's dangerous situation is a female dangerous situation case in a single-person household, the danger detector 330 detects a female single-person household. Care services (police dispatch request service, help request alert generation service) corresponding to dangerous situations can be provided.

At this time, the danger detector 330 transmits a signal for providing a care service (eg, an ambulance dispatch request signal, a police dispatch request signal, a management personnel call signal, and a guardian call signal) to a target that is dispatched and called through the care service. (For example, emergency personnel, police, management personnel, guardians, etc.), it is possible to provide care services.

In addition, the risk detection unit 330 may include information on a case identified as corresponding to a user's dangerous situation, as described above, in a signal for providing a care service. For example, the danger detecting unit 330 includes information indicating that the user is in an emergency medical risk situation of a fall accident in the emergency personnel dispatch signal, so that the emergency personnel dispatched can rescue the user more quickly from the dangerous situation. .

In the process of identifying a case corresponding to the user's dangerous situation among a plurality of cases, the danger detection unit 330 may use the above-described risk detection models (a language-based risk detection model and a non-verbal-based risk detection model). can That is, the danger detection unit 330 detects the user's dangerous situation itself using danger detection models (language-based risk detection model, non-verbal risk detection model), and then uses the danger detection models (language-based danger detection model). , the non-verbal based risk detection model) can be used again to identify cases corresponding to the user's risk situation.

In addition, information other than sound required for each case may be different in order to improve accuracy in the case identification process and provide appropriate care services. For example, a user's biometric information, location information, and video information may be additionally required for emergency medical risk cases, infant assault risk cases, infant entrapment risk cases, and minor assault/abuse cases. The user's biometric information and user's location information may be additionally requested for the female risk case, and the user's biometric information and user's location information are required for the collapse accident risk case, fire and gas leak risk case, and natural disaster risk case. may additionally be required.

Therefore, in the process of identifying a case corresponding to the user's dangerous situation among a plurality of cases, the risk detection unit 330 is a risk detection model pre-learned for each of the user's location information, biometric information, image information, and environment information. (location information risk detection model, biometric information-based hazard detection model, image information-based hazard detection model, and environmental information-based hazard detection model) can be additionally used.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. can be embodied in Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (15)

monitoring a user and obtaining a sound from the user; and
A language-based danger detection model using the sound acquired from the user as an input parameter - the language-based danger detection model is trained to infer a relationship between the verbal sound and a dangerous situation based on the learning data of the verbal sound - or The danger situation of the user is selectively used by using a language-based risk detection model, wherein the non-verbal risk detection model is learned to infer a relationship between the non-verbal sound and the danger situation based on the learning data of the non-verbal sound. step of detecting
Hazard detection method comprising a. According to claim 1,
The detecting step is
and using different risk detection models for each of a verbal sound element and a non-verbal sound element included in the sound obtained from the user. According to claim 2,
The steps of using
using the language-based risk detection model with the linguistic sound component as an input parameter; or
Using the non-verbal sound element as an input parameter for the non-verbal risk detection model.
Risk detection method comprising at least one step of. According to claim 1,
The detecting step is
Using the user's location information, biometric information, image information, and environment information as input parameters, risk detection models pre-learned for the user's location information, biometric information, image information, and environment information are used to determine the user's dangerous situation. A risk detection method characterized in that the step of detecting. According to claim 1,
The detecting step is
Providing a care service for coping with the user's dangerous situation when the user's dangerous situation is detected
Risk detection method further comprising a. According to claim 5,
The step of providing,
identifying a case corresponding to the risk situation of the user among a plurality of preset cases; and
Providing the care service corresponding to the identified case among the care services set for each of the plurality of cases.
Risk detection method comprising a. According to claim 5,
The care service,
The danger detection method comprising at least one service of an ambulance dispatch request service, a police dispatch request service, a management personnel call service, or a guardian call service for coping with the user's dangerous situation. According to claim 5,
The step of providing,
The step of providing the care service by including information on the identified case in at least one signal of an ambulance personnel dispatch signal, a police dispatch request signal, a management personnel call signal, or a guardian call signal. According to claim 1,
The detecting step is
If the dangerous situation of the user is detected, providing the user with an alarm notifying that the dangerous situation of the user has been detected.
Risk detection method further comprising a. In a computer program recorded on a recording medium to execute a risk detection method in combination with a computer system,
The risk detection method,
monitoring a user and obtaining a sound from the user; and
A language-based danger detection model using the sound obtained from the user as an input parameter - the language-based danger detection model is trained to infer a relationship between the verbal sound and a dangerous situation based on the learning data of the verbal sound - or The danger situation of the user is selectively used by using a language-based risk detection model, wherein the non-verbal risk detection model is trained to infer a relationship between the non-verbal sound and the danger situation based on the learning data of the non-verbal sound. step of detecting
A computer program recorded on a recording medium containing a. A language-based risk detection model is trained to infer a relationship between the verbal sound and the dangerous situation based on the learning data of the verbal sound, and the relationship between the non-verbal sound and the dangerous situation based on the learning data of the non-verbal sound a learning modeling unit that trains a non-verbal risk detection model to infer;
a sound acquisition unit that monitors a user and acquires sound from the user; and
A danger detection unit for detecting a dangerous situation of the user by selectively using the language-based danger detection model or the non-verbal-based danger detection model as an input parameter using the sound obtained from the user.
Hazard detection system that includes. According to claim 11,
The danger detection unit,
and using different risk detection models for each of the verbal sound element and the non-verbal sound element included in the sound obtained from the user. According to claim 11,
The danger detection unit,
Using the user's location information, biometric information, image information, and environment information as input parameters, risk detection models pre-learned for the user's location information, biometric information, image information, and environment information are used to determine the user's dangerous situation. Hazard detection system, characterized in that for detecting. According to claim 11,
The danger detection unit,
and providing a care service for coping with the user's dangerous situation when the user's dangerous situation is detected. According to claim 14,
The danger detection unit,
Identifying a case corresponding to the risk situation of the user among a plurality of preset cases, and providing the care service corresponding to the identified case among care services set for each of the plurality of cases. detection system.

Images