Apparatus for Searching and Guiding Evacuation of Occupants in a Building

Abstract

A rescuer search and evacuation guidance device within a building according to the present invention may include: a wing portion that generates lift for flight; a main body portion that approaches the exterior of the building where a fire has occurred through flight; a shooting portion installed in the main body portion and generates shooting data by photographing the interior of a window of the building; a first driving portion installed in the main body portion and outputs linear driving force by performing reciprocating linear motion between the main body portion and the window; a tapping member coupled to the end of the first driving portion; and a processor that performs a fire notification mode by analyzing the shooting data and, when a rescuer is detected, controlling the first driving portion and the wing portion so as to notify the rescuer of the fire by repeatedly colliding the tapping member with the window and applying vibration to the window.

Description

Technology Field

[0001] The present invention relates to a rescuer search and evacuation guidance device within a building, and more specifically, to a rescuer search and evacuation guidance device within a building that can notify a rescuer of a fire and guide the rescuer to evacuate by repeatedly striking a tapping member against a window near a rescuer located within the building to apply vibration to the window, and striking a breaking member against the window to break the window. Background Technology

[0003] Inside a burning building, visibility for rescuers becomes difficult due to smoke, high temperatures, and the risk of explosions, and direct entry by rescue personnel can expose them to serious danger. For this reason, technologies to quickly and accurately locate rescuers at fire scenes have been continuously researched. In particular, various response devices are being developed to observe the internal situation from the outside or to guide rescuers to approach windows.

[0004] For example, technology has been proposed to detect the location of rescuers within a building using surveillance cameras, thermal imaging cameras, or unmanned aerial vehicles (UAVs) for rescue search. Additionally, fire notification equipment utilizing flashing lights, sirens, or sound speakers is sometimes installed inside and outside the building to allow rescuers to recognize external rescue personnel.

[0005] However, conventional rescue search technology has the following problems.

[0006] First, fixed surveillance equipment installed inside buildings is susceptible to damage from high heat or flames, and its functionality is significantly limited once a fire has already occurred.

[0007] Second, conventional drone equipment used to monitor structural conditions from the outside of buildings faces difficulties in stable filming due to disturbances such as vibration or wind during flight, and has limited capabilities for providing repetitive warning signals to localized areas like windows.

[0008] Third, existing drone-based rescue systems have limitations in providing visual or auditory notifications to rescuers, and do not sufficiently provide physical notification means to induce rescuers to move immediately toward windows.

[0009] In particular, when a rescuer has lost consciousness or sound cannot be transmitted due to smoke, it is difficult to expect the rescuer to be aware of the situation using only simple audible alarms or lighting. Furthermore, even if the rescuer is located near a window, rescue efforts are often delayed because they fail to perceive the presence of external rescue personnel. Prior art literature

[0011] Korean Registered Patent No. 10-2271938 The problem to be solved

[0012] The objective of the present invention is to provide a rescuer search and evacuation guidance device within a building that can notify a rescuer of a fire and induce the rescuer to evacuate by repeatedly striking a tapping member against a window surrounding a rescuer located within the building to apply vibration to the window, and striking a breaking member against the window to break the window.

[0013] The objects of the present invention are not limited to those mentioned above, and other unmentioned objects and advantages of the present invention may be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0015] A rescuer search and evacuation guidance device within a building according to the present invention may include: a wing portion that generates lift for flight; a main body portion that approaches the exterior of the building where a fire has occurred through flight; a shooting portion installed in the main body portion and generates shooting data by photographing the interior of a window of the building; a first driving portion installed in the main body portion and outputs linear driving force by performing reciprocating linear motion between the main body portion and the window; a tapping member coupled to the end of the first driving portion; and a processor that performs a fire notification mode by analyzing the shooting data and, when a rescuer is detected, controlling the first driving portion and the wing portion so as to notify the rescuer of the fire by repeatedly colliding the tapping member with the window and applying vibration to the window.

[0016] The first driving unit comprises: a first stator that outputs the linear driving force; and a plurality of first shafts formed in a cylindrical shape and reciprocating linear motion by the first stator; wherein the plurality of first shafts are inserted into each other and slidably coupled so as to be able to expand or contract to perform the reciprocating linear motion.

[0017] The rescuer search and evacuation guidance device within the building may further include a breaking member formed in a cylindrical shape with a pointed end, which is coupled to the end of the leading first shaft located at the leading end among the plurality of first shafts, and such that the window is broken when it collides with the window.

[0018] The above-mentioned broken member may be formed such that the maximum outer diameter of the cross-section based on a virtual plane having a normal vector parallel to the direction of the reciprocating linear motion is less than or equal to the outer diameter of the first shaft at the foremost end.

[0019] The above tapping member is detachably coupled to the end of the topmost first shaft, and when coupled to the end of the topmost first shaft, a receiving space is formed inside to surround the broken member, and the maximum outer diameter of the cross-section based on the virtual plane may be formed to exceed the outer diameter of the topmost first shaft.

[0020] The processor can control the first stator such that when the rescuer is detected at a second time point after the maximum notification time has elapsed from a first time point when the execution of the fire notification mode has started, the first leading first shaft is inserted into the interior of a second first shaft adjacent to the first leading first shaft among the plurality of first shafts, and the tapping member is caught on the end of the second first shaft and separated from the first leading first shaft.

[0021] The processor can perform an evacuation guidance mode that controls the first drive unit and the wing unit so that when the tapping member is separated from the leading first shaft, the breaking member collides with the window, causing the window to break and inducing the rescuer to evacuate.

[0022] The rescuer search and evacuation guidance device within the above-mentioned building may further include a memory in which an artificial intelligence model trained to detect the rescuer from the above-mentioned shooting data is stored.

[0023] The processor can input the above-mentioned shooting data as input data to the artificial intelligence model and receive detection result data representing the detection result of the rescuer as output data from the artificial intelligence model. Effects of the invention

[0025] According to the present invention, by repeatedly striking a tapping member against a window near a rescuer located within a building to apply vibration to the window, and striking a breaking member against the window to break the window, the rescuer can be notified of the fire and guided to evacuate the rescuer. Brief explanation of the drawing

[0027] FIG. 1 is a drawing illustrating a rescuer search and evacuation guidance device within a building and a building according to one embodiment of the present invention. FIG. 2 is a perspective view of a rescuer search and evacuation guidance device inside a building according to one embodiment of the present invention. FIG. 3 is a block diagram of a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention. FIG. 4 is a diagram illustrating the process of training an artificial intelligence model used in a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention. FIG. 5 is a diagram illustrating the process of a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention detecting a rescuer using an artificial intelligence model. FIG. 6 is a diagram illustrating the process of a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention performing a fire notification mode. FIG. 7 is a drawing illustrating the process of separating a tapping member of a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention. FIG. 8 is a diagram illustrating the process of a rescuer search and evacuation guidance device within a building according to one embodiment of the present invention performing an evacuation guidance mode. Specific details for implementing the invention

[0028] Hereinafter, various embodiments of the present invention are described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the present invention. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0029] In this document, expressions such as "have," "may have," "include," or "may include" refer to the existence of the relevant feature (e.g., numerical values, functions, operations, or components, etc.) and do not exclude the existence of additional features.

[0030] In this document, expressions such as “A or B”, “at least one of A or / and B”, or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B”, “at least one of A and B”, or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0031] Expressions such as "first," "second," "first," or "second" used in this document may modify various components regardless of order and / or importance, and are used merely to distinguish one component from another without limiting such components. For example, the first user device and the second user device may represent different user devices regardless of order or importance. As another example, without departing from the scope of rights set forth in this document, the first component may be named the second component, and similarly, the second component may be renamed the first component.

[0032] When it is stated that a certain component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that said certain component is directly connected to said other component or may be connected through said other component (e.g., a third component). On the other hand, when it is stated that a certain component (e.g., a first component) is "directly connected" or "directly connected" to said other component (e.g., a second component), it may be understood that no other component (e.g., a third component) exists between said certain component and said other component.

[0033] As used in this document, the expression "configured to" may be replaced, depending on the context, with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean "specifically designed to" in hardware. Instead, in some situations, the expression "device configured to" may mean that the device is "capable of" in conjunction with other devices or components. For example, the phrase “a control unit configured (or set) to perform A, B, and C” may mean a dedicated processor for performing said operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or an application processor) capable of performing said operations by executing one or more software programs stored in memory.

[0034] In particular, in this specification, “~module” and “~device” may include one or more of a Central Processing Unit (CPU), an Application Processor (AP), and a Communication Processor (CP).

[0035] In this specification, “~module” and “~device” refer to any type of hardware device comprising at least one processor, and may be understood to include software configurations operating on said hardware device according to the embodiments.

[0036] The terms used in this document are used merely to describe specific embodiments and are not intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art described in this document. Terms used in this document that are defined in general dictionaries may be interpreted as having the same or similar meaning as they have in the context of the relevant technology, and are not to be interpreted in an ideal or overly formal sense unless explicitly defined in this document. In some cases, even terms defined in this document may not be interpreted to exclude the embodiments of this document.

[0037] FIG. 1 is a drawing illustrating a rescuer search and evacuation guidance device within a building and a building according to an embodiment of the present invention; FIG. 2 is a perspective view of a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; FIG. 3 is a block diagram of a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; FIG. 4 is a drawing for explaining the process of training an artificial intelligence model used in a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; FIG. 5 is a drawing for explaining the process of generating a rescuer detection using an artificial intelligence model in a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; FIG. 6 is a drawing for explaining the process of performing a fire notification mode in a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; FIG. 7 is a drawing for explaining the process of separating a tapping member in a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention; and FIG. 8 is a drawing for explaining the process of performing an evacuation guidance mode in a rescuer search and evacuation guidance device within a building according to an embodiment of the present invention.

[0038] Referring to FIGS. 1 to 8, a rescuer search and evacuation guidance device (100) in a building according to one embodiment of the present invention is an unmanned aerial vehicle capable of flying outside a building (B) where a fire has occurred, and can be configured to photograph the inside of a window of the building (B) to search for the presence of a rescuer, and, if necessary, apply physical vibration or a breaking impact to the window (W) to induce the rescuer to recognize and evacuate.

[0039] A rescuer search and evacuation guidance device (100) in a building according to one embodiment of the present invention may include a main body (110), a wing (120), a camera (130), a second driving unit (140), a magnetic member (150), a first driving unit (160), a tapping member (170), a breakage member (180), a processor (P), a memory (190), and a communication unit (C).

[0040] The main body (110) can access the outside of the building (B) where the fire occurred through flight.

[0041] Additionally, the main body (110) may accommodate some components of the rescuer search and evacuation guidance device (100) within the building and be installed on the outside of the remaining components.

[0042] The main body (110) may include a frame structure and an outer housing to maintain balance and rigidity during flight, and electronic circuits such as a power supply module, flight control circuit, drive control circuit, sensor module, and communication module may be placed in the internal space.

[0043] Additionally, on the outer side of the main body (110), a shooting unit (130), a second driving unit (140), and a first driving unit (160) are installed so as to face the window, and a wing unit (120) for flight control is installed so that the rescuer search and evacuation guidance device (100) within the building can be configured to approach the outer wall of the building (B) or maintain a stationary flight.

[0044] The wing portion (120) can generate lift for flight.

[0045] Additionally, the wing portion (120) may include a plurality of propellers rotatably installed on the outer side of the main body portion (110) and a drive motor that controls the rotational speed and direction of the propellers.

[0046] In addition, the wing portion (120) can be configured to perform ascent, descent, forward, backward, left and right movement, and stationary flight according to a control signal from the processor (P), and the magnitude and direction of the thrust can be independently controlled to enable fine position adjustment, particularly near the window (W) of the building (B).

[0047] The shooting unit (130) is installed in the main body (110) and can generate shooting data by shooting the interior of the window (W) of the building (B).

[0048] Additionally, the imaging unit (130) may be configured with an RGB camera, an infrared camera (IR camera), a thermal imaging camera, or a combination thereof to more accurately determine the presence of a rescuer, and the imaging data may include information such as the rescuer's body contour, movement, body temperature distribution, or temperature change of the internal space.

[0049] In addition, the shooting unit (130) is positioned on the front of the main body (110) and fixed so as to face the window (W), and may further include an image shake correction module or an optical zoom function to stably acquire images even during flight or stationary flight.

[0050] In addition, the shooting unit (130) can adjust the shooting angle or shooting frame according to the control signal of the processor (P), thereby expanding the rescuer search area in response to various heights and window structures of the building (B).

[0051] The first driving unit (160) is installed in the main body (110) and can output a linear driving force by performing reciprocating linear motion between the main body (110) and the window (W).

[0052] Such a first drive unit (160) may be equipped with a first stator (not shown) and a plurality of first shafts (161, 162).

[0053] The first stator can output a linear driving force of the first driving unit (160).

[0054] In addition, the first stator is a fixed part of a linear motor that generates linear motion using electromagnetic force, and may include a plurality of magnetic elements or coil windings inside.

[0055] And, the first stator may be configured to be positioned in a guide space formed along the axial direction of a plurality of first shafts (161, 162) to generate a driving force or a suction force for reciprocating linear motion for a plurality of first shafts (161, 162).

[0056] In addition, the first stator can adjust the magnitude and direction of movement of the driving force transmitted to the plurality of first shafts (161, 162) according to the magnitude and direction of the current supplied from the processor (P), so that the impact strength of the tapping member (170) described later or the impact of the breakage member (180) can be controlled according to the situation.

[0057] In addition, the first stator can be stably fixed to the main body (110) by combining it with a damping structure or a fixed support frame to absorb or minimize vibrations and reactions that occur during repetitive reciprocating motion.

[0058] A plurality of first shafts (161, 162) are formed in a cylindrical shape and can reciprocate linearly by the first stator.

[0059] These multiple first shafts (161, 162) are inserted into each other and slidably coupled so that they can reciprocate in a linear motion by expanding or contracting.

[0060] Additionally, a plurality of first shafts (161, 162) may be formed in a multi-stage structure to correspond to changes in distance between the main body (110) and the window (W), and each first shaft (161, 162) may be configured to have a guide surface so as to be movable along the axial direction within the interior of adjacent first shafts (161, 162).

[0061] In addition, the plurality of first shafts (161, 162) may be formed of a lightweight metal material or a high-strength composite material so that the electromagnetic force output from the first stator is effectively transmitted to the leading first shaft (161) located at the leading end, and a lubricating coating or a sliding member may be applied to minimize frictional resistance even during repeated operation.

[0062] In addition, the plurality of first shafts (161, 162) may include a guide structure or a support ring for maintaining alignment that suppresses axial shaking so that the flight attitude of the main body (110) is not disrupted even when the driving stroke of the first driving unit (160) increases.

[0063] Accordingly, the plurality of first shafts (161, 162) can extend or contract depending on the situation to transmit linear driving force so that the tapping member (170) or the breaking member (180) can stably reach the window (W).

[0064] Meanwhile, the second stage first shaft (162) is located on the outside of the leading first shaft (161) and is an intermediate stage shaft into which the leading first shaft (161) is inserted, and is slidably coupled in the axial direction according to the expansion or contraction operation of the first drive unit (160).

[0065] Additionally, the second stage first shaft (162) can provide a receiving space so that the leading first shaft (161) is fully inserted inside.

[0066] And, the second stage first shaft (162) may be formed such that the minimum inner diameter of the cross-section based on a virtual plane having a normal vector parallel to the direction of the reciprocating linear motion of the first drive unit (160) exceeds the maximum outer diameter of the cross-section of the first shaft (161) based on the virtual plane described above.

[0067] The tapping member (170) can be coupled to the end of the first driving member (160).

[0068] Specifically, the tapping member (170) is detachably coupled to the end of the leading first shaft (161), and when coupled to the end of the leading first shaft (161), a receiving space (170') is formed inside to surround the damaged member (180), and the maximum outer diameter of the cross-section based on a virtual plane having a normal vector parallel to the direction of the reciprocating linear motion of the first driving unit (160) can be formed to exceed the outer diameter of the leading first shaft (161).

[0069] Additionally, the tapping member (170) may be formed in various shapes to stably implement the intensity and form of vibration transmitted to the rescuer. For example, the tapping member (170) may be formed in a hemispherical shape, a cylindrical shape, a flat-head shape, or a shape having a protruding pad to be suitable for repeatedly colliding with the plane of the window (W), and may be configured to have a gentle curvature on its outer surface to transmit sufficient vibration while preventing local damage to the window (W) upon collision.

[0070] At this time, the tapping member (170) can be connected to the other end of a wire (171) connected to the main body (110) or the first driving unit (160) so that even if it is separated from the first shaft (161) at the foremost end of the first driving unit (160), it is not completely separated from the rescuer search and evacuation guidance device (100) within the building.

[0071] Additionally, the tapping member (170) may be formed of an elastic or semi-elastic material considering the transmission efficiency of collision sound and vibration. For example, rubber, silicone, urethane, synthetic rubber, rubber-based composite material, or a polymer material capable of shock absorption and elastic deformation may be applied.

[0072] In addition, the tapping member (170) may include a material having impact resistance and heat resistance so that wear is minimized even during repetitive reciprocating motion, and may be formed to be modularly replaceable as needed and can be replaced with various types of tapping tips to provide various vibration intensities or collision patterns.

[0073] Accordingly, the tapping member (170) can perform a stable and repetitive physical notification function to enable rescuers to recognize the fire by adjusting the intensity and vibration characteristics of the impact transmitted to the window (W).

[0074] The processor (P) can perform a fire notification mode by analyzing the shooting data and controlling the first driving unit (160) and the wing unit (120) so that when a rescuer is detected, the tapping member (170) repeatedly collides with the window and vibration is applied to the window to notify the rescuer of the fire.

[0075] Specifically, an artificial intelligence model (AI) can be trained to detect rescuers in the aforementioned shooting data using training data (TD).

[0076] Training data (TD) according to one embodiment may consist of images of the interior of a building taken in various environments, images of an actual rescuer or simulated target located near a window, thermal images including the posture, movement, and body temperature distribution of the rescuer, image data reflecting various environmental variables such as smoke, changes in light intensity, and night shooting, and correct answer (label) information indicating the outline or location of the rescuer.

[0077] In one embodiment, the artificial intelligence model (AI) may be implemented as a deep learning-based object detection or image classification model for recognizing the presence of a rescuer, body contours, movement, or heat distribution from captured data.

[0078] For example, artificial intelligence (AI) models may include object detection models based on Convolutional Neural Networks (CNN), such as the YOLO (You Only Look Once) family of models, SSD (Single Shot MultiBox Detector), and Faster R-CNN. These models are suitable for rescuer detection because they can output the location of human objects in an input image in the form of a bounding box.

[0079] In addition, the artificial intelligence (AI) model may include Transformer-based image processing models such as ViT (Vision Transformer), Swin Transformer, and DETR (Detection Transformer). These models can be configured to possess high robustness even in fire situations where various lighting conditions, smoke, and diffuse reflection are present.

[0080] According to one embodiment, the artificial intelligence model (AI) may be a thermal image-based recognition model. For example, a CNN-based classifier or a thermal image object detection model that analyzes the body heat pattern of a person captured by a thermal imaging camera may be used, thereby enabling the stable detection of a rescuer even in smoke or darkness.

[0081] Furthermore, the artificial intelligence (AI) model may be a model to which transfer learning techniques are applied. For example, it can be configured by fine-tuning a rescuer detection function specialized for building interior video based on pre-trained backbone models such as ResNet, EfficientNet, and MobileNet.

[0082] Accordingly, the artificial intelligence model (AI) can be implemented as various deep learning models to receive captured video or thermal image data and generate detection result data (DD) representing the detection result of a rescuer, and the present invention is not limited to the specific structure of such models.

[0083] Meanwhile, the processor (P) inputs the captured data (CD) as input data to the artificial intelligence model (AI) and receives the detection result data (DD), which represents the detection result of the rescuer, as output data from the artificial intelligence model (AI).

[0084] Afterward, the processor (P) can control the wing portion (120) so that the rescuer search and evacuation guidance device (100) inside the building moves to the vicinity of the window (W) where the rescuer is detected.

[0085] Next, the processor (P) can control the second drive unit (140) so that, before performing the fire alarm mode, the magnetic member (150) is magnetically attracted to the magnetic panel (M) installed at the bottom of the window (W) where a rescuer is detected, in order to prevent the rescuer search and evacuation guidance device (100) from shaking or becoming unstable in posture during the process in which the first drive unit (160) performs a reciprocating linear motion and the tapping member (170) repeatedly collides with the window (W).

[0086] At this time, the second driving unit (140) is installed in the main body (110) and can output a linear driving force by performing reciprocating linear motion between the main body (110) and the window (W).

[0087] Such a second drive unit (140) may be equipped with a second stator (not shown) and a plurality of second shafts (not shown).

[0088] The second stator can output the linear driving force of the second drive unit (140).

[0089] In addition, the second stator is a fixed part of a linear motor that generates linear motion using electromagnetic force, and may include a plurality of magnetic elements or coil windings inside.

[0090] In addition, the second stator may be configured to be positioned in a guide space formed along the axial direction of a plurality of second shafts to generate a driving force or a suction force for reciprocating linear motion for the plurality of second shafts.

[0091] In addition, the second stator can adjust the magnitude and direction of movement of the driving force transmitted to the plurality of second shafts according to the magnitude and direction of the current supplied from the processor (P), so that the adsorption of the magnetic member (150) described later can be controlled according to the situation.

[0092] In addition, the second stator can be stably fixed to the main body (110) by combining it with a damping structure or a fixed support frame to absorb or minimize vibrations and reactions that occur during repetitive reciprocating motion.

[0093] A plurality of second shafts are formed in a cylindrical shape and can reciprocate linearly by means of a second stator.

[0094] These multiple second shafts are inserted into each other and slidably coupled so that they can reciprocate linearly by expanding or contracting.

[0095] Additionally, a plurality of second shafts may be formed in a multi-stage structure to correspond to changes in distance between the main body (110) and the window (W), and each second shaft may be configured to have a guide surface so as to be movable along the axial direction within the interior of an adjacent first shaft.

[0096] In addition, multiple second shafts may be formed of a lightweight metal material or a high-strength composite material so that the electromagnetic force output from the second stator is effectively transmitted to all second shafts, and a lubricating coating or a sliding member may be applied to minimize frictional resistance even during repetitive operation.

[0097] In addition, the plurality of second shafts may include a guide structure or a support ring for maintaining alignment that suppresses axial shaking so that the flight attitude of the main body (110) is not disrupted even when the driving stroke of the second driving unit (140) increases.

[0098] Accordingly, the plurality of second shafts can extend or contract depending on the situation, thereby performing the role of transmitting linear driving force so that the magnetic member (150) can stably reach the magnetic panel (M).

[0099] The magnetic member (150) can be coupled to the ends of a plurality of second shafts, and when the plurality of second shafts are extended, they can approach and magnetically attract a magnetic panel (M) installed in the lower area of ​​the window (W) by the second driving unit (140).

[0100] Additionally, the magnetic member (150) may be formed as a permanent magnet or an electric magnet to generate magnetism, and if the magnetic panel (M) is formed of a ferromagnetic metal material, it may be stably attracted by the magnetic force generated by the magnetic member (150).

[0101] At this time, the magnetic panel (M) may be a panel structure formed of a ferromagnetic metal material so that it is fixedly installed at the bottom part of the window (W) or in the surrounding area, and the magnetic member (150) of the rescuer search and evacuation guidance device (100) inside the building approaching from the outside can be magnetically attracted.

[0102] Additionally, the magnetic panel (M) may be permanently installed on the exterior wall or window frame of the building (B), or selectively placed only on a specific floor or at a specific location, and may be composed of a ferromagnetic metal such as iron (Fe), cobalt (Co), nickel (Ni), or an alloy thereof so as to secure sufficient adsorption force by the magnetic force generated by the magnetic member (150).

[0103] In addition, the magnetic panel (M) may be formed from a metal plate of a certain thickness or more to maintain structural stability even with changes in the external environment or thermal deformation, or may be manufactured as an integral part with the finishing material of the building's exterior wall.

[0104] In addition, the magnetic panel (M) may be formed of a material with high surface hardness so as not to be damaged by repeated attachment and detachment of the rescuer search and evacuation guidance device (100) within the building, or may include an uneven pattern or a fine surface treatment layer to increase adhesion during adsorption.

[0105] Accordingly, the magnetic panel (M) provides a fixed support surface to which the magnetic member (150), driven by the second driving unit (140), can be stably adsorbed, thereby enabling the rescuer search and evacuation guidance device (100) within the building to maintain a stable posture without shaking while performing a fire notification mode or an evacuation guidance mode.

[0106] Meanwhile, the magnetic member (150) may be configured to have sufficient adsorption force to withstand vibrations, reactions, external wind pressure, etc. that may occur while the rescuer search and evacuation guidance device (100) within the building performs a fire notification mode or an evacuation guidance mode, and may include a structure in which the magnitude of the magnetic force can be adjusted as needed.

[0107] Additionally, the magnetic member (150) can perform the function of improving flight stability so that the device (100) does not shake or rotate even when the tapping member (170) repeatedly collides with the window (W) by acting as an anchor point for the reaction force generated by the first driving unit (160) when the device (100) performs a stationary flight near the outer wall of the building (B).

[0108] In this way, the magnetic member (150) is driven by the second driving unit (140) and adheres to the magnetic panel (M) to perform the posture stabilization function of the device (100), and can perform the role of fixing the main body (110) so that the tapping member (170) or the damaged member (180) can stably approach the window (W) during the execution of the fire notification mode or evacuation guidance mode.

[0109] Meanwhile, the processor (P) controls the second driving unit (140) so that when a rescuer is detected, the magnetic member (150) is magnetically attracted to the magnetic panel (M), and when the magnetic member (150) is magnetically attracted to the magnetic panel (M), the fire alarm mode can be performed.

[0110] At this time, the processor (P) can drive the first drive unit (160) to perform a fire alarm mode and control the tapping member (170) to repeatedly collide with the outer surface of the window (W) at a predetermined frequency and intensity.

[0111] In addition, the processor (P) can maintain the flight stability of the device (100) by adjusting the thrust and rotational speed of the wing portion (120) in real time to minimize changes in the attitude of the main body portion (110) caused by the reaction generated during the repeated collision process of the tapping member (170).

[0112] And, the processor (P) can transmit physical stimuli to allow a rescuer to approach the window (W) or recognize an external rescuer by adjusting the intensity of the vibration, the frequency of collision, or the pattern of collision applied to the window (W).

[0113] Meanwhile, the damaged member (180) is connected to the end of the leading first shaft (161) located at the leading end among the plurality of first shafts (161, 162), and may be formed in a cylindrical shape with a leading end so that the window (W) is damaged when it collides with the window.

[0114] Such, the maximum outer diameter of the cross-section of the damaged member (180) based on a virtual plane having a normal vector parallel to the direction of the reciprocating linear motion of the first driving member (160) can be formed to be less than or equal to the outer diameter of the leading first shaft (161).

[0115] Additionally, the breaking member (180) may be formed to have various advanced structures to maximize the breaking efficiency of the window (W). For example, the breaking member (180) may include a conical tip, a pyramidal tip, or a spike-shaped tip to concentrate high pressure locally on the brittle material of the window (W), and the angle or curvature of the tip may be designed to vary according to the impact transmission characteristics.

[0116] In addition, the broken member (180) may be formed from a high-strength metal material having impact resistance and wear resistance, such as tool steel, high-carbon steel, stainless steel, alloy steel, or tungsten-based cemented carbide, so that it is not deformed or broken by impact during the breaking operation. If necessary, it may include a heat-treated metal or a surface hardness enhancement treatment such as a carbide coating or DLC (Diamond-Like Carbon) coating to increase hardness.

[0117] In addition, the damaged member (180) may be formed with a substantially solid internal structure to maintain damage efficiency even during repeated collisions, and may have an axially symmetric structure to maintain alignment with respect to the collision direction. Furthermore, the damaged member (180) may include a fixing pin or screw connection structure at the connection part with the leading first shaft (161) so that the impact force transmitted by the reciprocating linear motion of the first driving unit (160) is concentrated and transmitted along the axial direction of the leading first shaft (161) without loss.

[0118] Accordingly, the breaking member (180) is composed of a material having a high hardness and an advanced shape that locally concentrates the impact applied to the window (W), thereby enabling it to perform a key function of quickly breaking the window (W) in evacuation guidance mode to secure an escape route for rescuers.

[0119] Such a broken member (180) can be accommodated inside the tapping member (170) as described above.

[0120] Accordingly, while the fire alarm mode is being performed, the damaged member (180) is prevented from being exposed to the outside, thereby blocking unnecessary damage to the window (W), and the impact transmitted to the window (W) is cushioned even when the tapping member (170) repeatedly collides with the window (W), so that only vibration can be stably provided to the rescuer.

[0121] In addition, since the damaged member (180) is exposed to the outside only when the tapping member (170) is separated, the damage operation and the notification operation are clearly distinguished during the mode switching process, thereby ensuring both the operational stability of the device (100) and user safety.

[0122] To this end, the processor (P) can control the first stator so that when a rescuer is detected at a second time point after a preset maximum notification time has elapsed from a first time point when the fire notification mode is started, the first shaft (161) is adjacent to the first shaft (161) and the first shaft (161) is inserted into the second first shaft (162), and the tapping member (170) is caught on the end (162a) of the second first shaft (162) and separated from the first shaft (161).

[0123] Specifically, as a preliminary step for performing an evacuation guidance mode, the processor (P) can drive the first drive unit (160) in a contraction direction to control the first shaft (161) at the foremost stage to gradually move into the interior of the first shaft (162). At this time, the tapping member (170) moves together while being coupled to the end of the first shaft (161) at the foremost stage, but since the outer diameter of the tapping member (170) is formed to be larger than the inner diameter of the end (162a) of the first shaft (162) at the foremost stage, the tapping member (170) may be caught by the end (162a) of the first shaft (162) at the foremost stage as the first shaft (161) continues to be inserted into the interior of the first shaft (162).

[0124] At this time, the leading first shaft (161) is continuously drawn in the contraction direction by the first stator, while the tapping member (170) is restricted from axial movement by the end (162a) of the second first shaft (162), so a relative displacement occurs between the end of the leading first shaft (161) and the tapping member (170). Accordingly, the tapping member (170) can be separated from the leading first shaft (161) as the fastening structure (e.g., a locking projection and a locking groove, a snap coupling, a friction coupling, etc.) set at the connection part with the end of the leading first shaft (161) is released.

[0125] Additionally, since a receiving space (170') is formed inside the tapping member (170) to surround the damaged member (180), after the leading first shaft (161) is fully inserted into the second first shaft (162), the tapping member (170) is fixed to the outside by the end (162a) of the second first shaft (162), and only the damaged member (180) is exposed to the outside together with the end of the leading first shaft (161).

[0126] Accordingly, through the above process, the tapping member (170) is mechanically and safely separated, and the damaged member (180) is exposed to the outside, so that when the processor (P) subsequently drives the first driving unit (160) again in the expansion direction, the damaged member (180) can directly collide with the window (W) and break the window (W), thereby stably performing an evacuation guidance mode.

[0127] Afterward, the processor (P) can perform an evacuation guidance mode by controlling the first drive unit (160) and the wing unit (120) so that when the tapping member (170) is separated from the leading first shaft (161), the breaking member (180) collides with the window (W), causing the window (W) to break and inducing the evacuation of rescuers.

[0128] More specifically, the processor (P) can control the driving speed, stroke length, and number of repetitions of the first driving unit (160) so that the damaged member (180) can secure sufficient collision energy, thereby controlling the damaged member (180) to advance at high speed toward the outer surface of the window (W).

[0129] At this time, the first driving unit (160) can secure a collision force corresponding to the material and thickness of the window (W) by adjusting the output pattern of the electromagnetic force so that the damaged member (180) is accelerated just before it touches the window (W).

[0130] Additionally, the processor (P) can control the thrust and direction of the wing portion (120) to offset the reaction force in order to prevent the main body portion (110) from being pushed backward or rotating in the event of a collision. For example, the processor (P) can increase the rotational speed of the wing portion (120) at the moment of collision or slightly tilt the aircraft in a specific direction to minimize changes in attitude caused by the impact of the collision.

[0131] And, the processor (P) monitors the degree of opening of the window (W) and the change in the rescuer's position through the shooting unit (130) after the window (W) is broken, and can finely adjust the position of the device (100) so that the rescuer can approach the window (W) and escape to the outside.

[0132] At this time, the processor (P) can secure a safe space for the rescuer's movement by adjusting the flight path and stopping position so that the main body (110) does not collide with the edge of the damaged window (W) or the internal structure.

[0133] In addition, the processor (P) can be controlled to provide visual, auditory, or physical guidance signals to allow a rescuer to evacuate to a location where an external rescue team is waiting, while maintaining a stable posture of the rescuer search and evacuation guidance device (100) inside the building, taking into account the falling of glass fragments or the eruption of smoke inside the building that may occur after the window (W) is broken.

[0134] For example, the processor (P) can recognize the direction of movement of the rescuer using the camera unit (130), and then output a lighting signal indicating the direction the rescuer should move, or guide the flight position of the device (100) to move slowly forward of the rescuer's path.

[0135] Accordingly, the processor (P) can safely break the window (W) through the evacuation guidance mode and secure an escape route for the rescuer to move outside, and then continuously track the change in the rescuer's location to maintain the flight stability and guidance function of the rescuer search and evacuation guidance device (100) within the building until the rescuer reaches a safe area.

[0136] Meanwhile, the processor (P) controls the overall operation of the rescuer search and evacuation guidance device (100) within the building. Specifically, the processor (P) can control the overall operation of the rescuer search and evacuation guidance device (100) within the building by executing at least one instruction stored in the memory (190). In particular, the processor (P) can be implemented as a single processor (P) as well as as a plurality of processors (P).

[0137] The processor (P) may be implemented in various ways. For example, one or more processors (P) may include one or more of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), MIC (Many Integrated Core), DSP (Digital Signal Processor), NPU (Neural Processing Unit), hardware accelerator, or machine learning accelerator. One or more processors (P) may control one or any combination of other components of the rescuer search and evacuation guidance device (100) within a building and may perform operations or data processing related to communication. One or more processors (P) may execute one or more programs or instructions stored in memory (190). For example, one or more processors (P) may perform a method according to one embodiment of the present disclosure by executing one or more instructions stored in memory (190).

[0138] In the embodiments of the present disclosure, the processor (P) may refer to a system-on-chip (SoC) in which one or more processors (P) and other electronic components are integrated, a single-core processor (P), a multi-core processor (P), or a core included in a single-core processor (P) or a multi-core processor (P), wherein the core may be implemented as a CPU, GPU, APU, MIC, DSP, NPU, hardware accelerator, or machine learning accelerator, but the embodiments of the present disclosure are not limited thereto.

[0139] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one processor (P) or by a plurality of processors (P). For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor (P), or the first operation and the second operation may be performed by a first processor (P) (e.g., a general-purpose processor (P)) and the third operation may be performed by a second processor (P) (e.g., an artificial intelligence dedicated processor (P)).

[0140] One or more processors (P) may be implemented as a single-core processor (P) including one core, or as one or more multi-core processors (P) including multiple cores (e.g., homogeneous multi-core or heterogeneous multi-core). When one or more processors (P) are implemented as multi-core processors (P), each of the multiple cores included in the multi-core processor (P) may include an internal memory (190) of the processor (P), such as an on-chip memory (190), and a common cache shared by the multiple cores may be included in the multi-core processor (P). Additionally, each of the multiple cores (or some of the multiple cores) included in the multi-core processor (P) may independently read and execute program instructions for implementing a method according to one embodiment of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one embodiment of the present disclosure.

[0141] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor (P), or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor (P), or the first operation and the second operation may be performed by a first core included in a multi-core processor (P) and the third operation may be performed by a second core included in a multi-core processor (P).

[0142] The processor (P) can perform operations using the output value obtained from the artificial intelligence model.

[0143] Artificial intelligence models can be constructed by considering the application field of the recognition model, the purpose of learning, or the computing performance of the device. Additionally, artificial intelligence models may be, for example, models based on neural networks.

[0144] An artificial intelligence model can be designed to simulate the structure of the human brain on a computer. The artificial intelligence model may include multiple network nodes with weights that simulate neurons of a human neural network. The multiple network nodes may each form a connection relationship to simulate synaptic activity, in which neurons transmit and receive signals through synapses.

[0145] Artificial intelligence models may include, for example, neural network models or deep learning models developed from neural network models. In deep learning models, multiple network nodes may be located at different depths (or layers) and exchange data according to convolutional connection relationships. For example, models such as Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), and Bidirectional Recurrent Deep Neural Networks (BRDNN) may be used as artificial intelligence models, but are not limited thereto.

[0146] A deep learning model may include multiple artificial neural network layers. The artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of these, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0147] A deep learning model may include a learning algorithm. For example, it may include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples mentioned above. An artificial intelligence model may include a plurality of artificial neural network layers.

[0148] The memory (190) stores various programs or data temporarily or non-temporarily and transmits the stored information to the processor (P) upon the call of the processor (P). Additionally, the memory (190) can store various information required for the operation, processing, or control operation of the processor (P) in an electronic format.

[0149] The memory (190) may include, for example, at least one of a main memory and an auxiliary memory. The main memory may be implemented using a semiconductor storage medium such as ROM and / or RAM. The ROM may include, for example, a conventional ROM, EPROM, EEPROM and / or MASK-ROM. The RAM may include, for example, a DRAM and / or SRAM. The auxiliary memory may be implemented using at least one storage medium capable of storing data permanently or semi-permanently, such as a flash memory (190) device, an SD (Secure Digital) card, a solid state drive (SSD), a hard disk drive (HDD), an optical recording medium such as a magnetic drum, a compact disc (CD), a DVD, or a laser disc, a magnetic tape, a magneto-optical disc and / or a floppy disk.

[0150] The memory (190) can store an artificial intelligence model, output data obtained based on input data input to the artificial intelligence model, usage information obtained based on the output data, and reconstruction information for reconstructing the artificial intelligence model obtained based on the usage information.

[0151] The communication unit (C) is a module for performing data communication with the outside of the rescuer search and evacuation guidance device (100) within the building, and can transmit and receive various control signals, shooting data, status information or analysis results in conjunction with the processor (P).

[0152] The communication unit (C) can be configured to enable a rapid response to a rescue situation by transmitting the operating status of the device (100) in real time to an external rescue team, a central control system, or a remote control device.

[0153] Additionally, the communication unit (C) may be configured to support various wireless communication methods. For example, the communication unit (C) may include one or more short-range or long-range wireless communication technologies such as Wi-Fi, Bluetooth, LTE (Long Term Evolution), 5G NR (New Radio), WLAN, RF communication, or dedicated structural wireless protocols. These communication methods may be automatically selected and switched to minimize signal interference that may occur in the structure or fire environment of the building (B).

[0154] The present invention has been described above with reference to preferred embodiments. Those skilled in the art will understand that the present invention can be implemented in modified forms without departing from the essential characteristics of the invention. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the invention is defined by the claims, not by the foregoing description, and all variations within the scope of the claims should be interpreted as being included in the invention.

[0155] As described above, although the present invention has been explained by limited embodiments and drawings, the present invention is not limited thereto, and it is obvious that various modifications and variations are possible within the scope of the technical spirit of the present invention and the equivalent scope of the claims described below by those skilled in the art to which the present invention belongs. Explanation of the symbols

[0157] 100: Search and rescue device for rescuers inside buildings 110 : Main body 120 : Wing part 130 : Filming Department 140 : Second drive unit 150 : Magnetic component 160: First drive unit 170 : Tapping defect 180 : Damaged part 190 : Memory P : Processor C : Communications Department B: Buildings W : Window M: Magnetic panel

Claims

Claim 1 A rescuer search and evacuation guidance device within a building comprises: a wing portion that generates lift for flight; a main body portion that approaches the exterior of the building where a fire has occurred through flight; a photographing portion installed in the main body portion and generates photographic data by photographing the interior of a window of the building; a first driving portion installed in the main body portion and outputs linear driving force by performing reciprocating linear motion between the main body portion and the window; a tapping member coupled to the end of the first driving portion; and a processor that performs a fire notification mode by analyzing the photographic data and controlling the first driving portion and the wing portion so that when a rescuer is detected, the tapping member repeatedly collides with the window to apply vibration to the window, thereby notifying the rescuer of the fire; wherein the first driving portion comprises a first stator that outputs the linear driving force; A plurality of first shafts formed in a cylindrical shape and reciprocating linear motion by means of the first stator; wherein the plurality of first shafts are inserted into each other and slidably coupled so as to expand or contract to reciprocate linear motion, and a breaking member formed in a cylindrical shape with an end having a tip shape such that the window is broken when it collides with the window, the breaking member is coupled to the end of the leading first shaft located at the leading end among the plurality of first shafts.The apparatus further comprises, wherein the maximum outer diameter of the cross-section of the breaking member based on a virtual plane having a normal vector parallel to the direction of the reciprocating linear motion is formed to be less than or equal to the outer diameter of the leading first shaft, and the tapping member is detachably coupled to the end of the leading first shaft, wherein when coupled to the end of the leading first shaft, an internal receiving space is formed to surround the breaking member, and the maximum outer diameter of the cross-section based on the virtual plane is formed to exceed the outer diameter of the leading first shaft, and the processor controls the first stator such that if the rescuer is detected at a second time point after a preset maximum notification time has elapsed from a first time point when the execution of the fire notification mode has started, the leading first shaft is inserted into the interior of a second first shaft adjacent to the leading first shaft among the plurality of first shafts and into which the leading first shaft is inserted, and the tapping member is caught on the end of the second first shaft and separated from the leading first shaft, and the A rescuer search and evacuation guidance device within a building, characterized in that the processor performs an evacuation guidance mode in which, when the tapping member is separated from the leading first shaft, the breaking member collides with the window, causing the window to break and inducing the rescuer's evacuation. Claim 2 A rescuer search and evacuation guidance device within a building according to claim 1, further comprising a memory in which an artificial intelligence model learned to detect the rescuer from the captured data is stored. Claim 3 A rescuer search and evacuation guidance device within a building, characterized in that, in paragraph 2, the processor inputs the above-mentioned shooting data as input data to the above-mentioned artificial intelligence model and receives detection result data representing the rescuer detection result as output data from the above-mentioned artificial intelligence model.

Images