KR102187215B1 - Intelligent troop status monitoring system - Google Patents

Abstract

The present invention provides a smart floating troops monitoring system including: a troops detection module including at least one weight sensor placed and built-in to detect weight on the bed top in a military, and a control unit which stores an assigned unique IP and a reference weight previously mapped to the bed and stored, compares the measured weight detected by at least one weight sensor and the reference weight, and outputs a result; and a floating troops monitoring server including a storage unit which assigns a unique IP to each troops detection module installed in at least one bed, stores the reference weight for each unique IP, and converts the reference weight into a database, and a judging unit which determines that the troops are out and outputs an alarm when the difference between the measured weight and the reference weight received from the control unit of the troops detection module exceeds a preset first threshold.

Description

Smart moving force monitoring system {INTELLIGENT TROOP STATUS MONITORING SYSTEM}

The present invention relates to a smart fluid force monitoring system, and provides a platform capable of monitoring sleeping, absent and sexual assault.

Leaving means leaving the workplace designated during working hours in violation of obligations. Departure is not only a departure from work or a designated place, but also a departure to the extent that it is impossible to perform the duties imposed on it. The word “unauthorized departure” emphasizes no permission, that is, unauthorized. In addition to hospitals and dormitories that manage patients and students, the word “departure” is used in the military as well.Duty of military law refers to any action or omission commanded by the sanctions of punishment. The provisions on the prohibition of job abandonment and departure from work place corresponding to Article 32 of the Service Regulations stipulate that soldiers shall not abandon their duties or leave the place of work without permission from their supervisor. Loss of service to the evacuees is the time and expense of training, compensation for arrest, time and expense of the Court-Martial, time and expense of guard post expense, maintenance cost of military prisons, and the person who replaces the evacuee. Include the time and expense of recruiting.

At this time, a method for monitoring defectors in various areas is being researched and developed. In this regard, Korean Patent Publication No. 2009-0000679 (published on January 8, 2009) and Korean Patent Publication No. 2018-0049499 ( May 11, 2018 (released on May 11, 2018) measures, displays and monitors medical information including vital signs including the patient's body temperature, heart rate and status, blood pressure, respiratory status and blood oxygen concentration, and monitors the patient. Through a network electrically connected to the device, medical information and personal information including the patient's gender, age, and name are output, and a plurality of pressure sensors are arranged at regular intervals above the bed matrix, and movements while sleeping A configuration is disclosed that allows detection and confirmation after waking up.

However, among the above-described configurations, in order to employ the former configuration, students or soldiers in the dormitory, not patients, must wear a monitoring device every day, so cases that cannot be measured properly may increase. The cost of construction increases, and there is a drawback that cannot be measured every day. In addition, even if the latter configuration is provided to monitor departure, only the movement itself can be monitored, but there is no method for confirming the absence of sexual assault, beating, or departure from the designated place where the movement becomes intense. not. Accordingly, research and development of a device capable of immediately reporting various crimes occurring in a group is required by monitoring not only the absence of a large number of personnel, but also movements due to beatings or sexual violence.

An embodiment of the present invention is to measure the weight on the bed by installing at least one weight sensor in the bed and summing at least one weight measured by the at least one weight sensor with an OR gate, and absent it from sleeping. And sexual assault, it is possible to remotely manage multiple areas even if monitoring and management personnel are not put in multiple areas, and an alarm is output so that the manager can immediately know when an emergency situation such as absence or sexual assault occurs. In the case of going out after payment, it is possible to provide a smart flow force monitoring method that can eliminate unnecessary alarms by preventing the alarm from sounding even if it is not detected. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention is stored in at least one weight sensor arranged and built to sense the weight on the bed upper plate in the army, and the assigned unique IP and pre-mapped to the bed. A unique IP is assigned to each military history detection module including a control unit that stores the reference weight and outputs the result by comparing the measured weight detected by at least one weight sensor with the reference weight, and at least one bed. , A storage unit that stores the reference weight for each unique IP and converts it into a database, and when the difference between the measured weight and the reference weight received from the control unit of the troop detection module exceeds a preset first threshold value, it is determined as troop departure and an alarm is output. It includes a moving force monitoring server including a determination unit.

According to any one of the above-described problem solving means of the present invention, the weight on the bed is measured by installing at least one weight sensor in the bed and summing at least one weight measured by the at least one weight sensor with an OR gate. And, by dividing this into absence, sleeping, and sexual assault, multiple areas can be managed remotely, even if monitoring and management personnel are not put in multiple areas, and when an emergency situation such as absence or sexual assault occurs, the manager can immediately know. It outputs an alarm so that the payment is made and does not sound the alarm even if it is not detected, so that unnecessary alarms can be removed.This makes it easy to install and manage, but the cost is inexpensive, and it is convenient to manage as a module without restrictions. It is possible.

1 is a view for explaining a smart flow force monitoring system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating each component included in the system of FIG. 1.
3 is a view for explaining an embodiment in which the connection between the control unit of the force detection module and the network equipment in the smart fluid force monitoring system according to an embodiment of the present invention is implemented.
4 is a view for explaining an embodiment in which a connection between an OR gate of a control unit in a force detection module and at least one sensor according to an embodiment of the present invention is implemented.
5 is a view for explaining an embodiment in which the force detection module and the flow force monitoring server are connected according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially" and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used in the sense of the present invention. To assist, accurate or absolute figures are used to prevent unfair use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, or two or more units may be realized using one hardware. Meanwhile,'~ unit' is not meant to be limited to software or hardware, and'~ unit' may be configured to be in an addressable storage medium or configured to reproduce one or more processors. Thus, as an example,'~ unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , Subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays and variables. The components and functions provided in the'~ units' may be combined into a smaller number of elements and'~ units', or may be further divided into additional elements and'~ units'. In addition, components and'~ units' may be implemented to play one or more CPUs in a device or a security multimedia card.

In this specification, some of the operations or functions described as being performed by the terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification information of the terminal. Can be interpreted as.

In the present specification, the object of surveillance is described based on the soldier, but it will be said that it can be applied to various fields or areas such as patients in hospitals and students in dormitories.

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

1 is a view for explaining a smart flow force monitoring system according to an embodiment of the present invention. Referring to FIG. 1, the smart fluid force monitoring system 1 includes at least one force detection module 100, a fluid force monitoring server 300, at least one manager terminal 400, and at least one network equipment 500. ) Can be included. However, since the smart flow force monitoring system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as illustrated in FIG. 1, at least one force detection module 100 may be connected to the floating force monitoring server 300 through a network 200. In addition, the floating force monitoring server 300 may be connected to at least one troop detection module 100, at least one manager terminal 400, and at least one network equipment 500 through the network 200. In addition, at least one manager terminal 400 may be connected to the floating force monitoring server 300 through the network 200. In addition, the at least one network device 500 may be connected to the at least one force detection module 100 and the floating force monitoring server 300 through the network 200.

Here, the network refers to a connection structure in which information exchange is possible between respective nodes such as a plurality of terminals and servers, and examples of such networks include a local area network (LAN) and a wide area communication network (WAN: Wide Area Network), Internet (WWW: World Wide Web), wired/wireless data communication network, telephone network, wired/wireless television communication network, etc. Examples of wireless data networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), and Wi-Fi. , Internet, LAN(Local Area Network), Wireless LAN(Wireless Local Area Network), WAN(Wide Area Network), PAN(Personal Area Network), RF(Radio Frequency), Bluetooth(Bluetooth) network, NFC( Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

In the following, the term “at least one” is defined as a term including the singular number and the plural number, and even if the term “at least one” does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in a singular or plural.

The at least one medical history detection module 100 controls the weight on the bed collected through at least one sensor 110 with or without using a web page, app page, program, or application related to a smart fluid medical history monitoring service. ), and outputting the summed value. At this time, the at least one force detection module 100 receives a unique IP from the floating force detection server 300 and outputs a unique IP together when data is output, or so that the floating force detection server 300 can automatically recognize it. It may be an equipped device.

Here, the at least one medical history detection module 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one medical history detection module 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one military history detection module 100, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular) , PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband) Internet) terminal, smart phone (Smartphone), smart pad (Smartpad), tablet PC (Tablet PC), such as all kinds of handheld (Handheld) based wireless communication devices may be included.

The fluid force monitoring server 300 may be a server that provides a smart fluid force monitoring service web page, an app page, a program, or an application. In addition, the floating force monitoring server 300 may be a server that is connected to at least one troop detection module 100 to receive and collect output values of the troop detection module 100, and output a state for each of at least one zone. . To this end, the floating force monitoring server 300 may be a server that assigns a unique IP to at least one troop detection module 100 and maps and stores at least one manager terminal 400. In addition, the floating medical history monitoring server 300 may be a server that sets the weight of each person as a reference weight in a unique IP, and in the case of a unique IP inputted with payment data from at least one manager terminal 400, the absence Even in the case, it may be a server that is set so that the alarm does not sound. And, when data such as absence or sexual violence is output, the floating force monitoring server 300 immediately transmits an alarm to the manager terminal 400, and if the manager terminal 400 does not immediately check it, a response exists. It may be a server that repeatedly attempts to unicast until there is an administrator terminal 400 to be configured.

Here, the moving force monitoring server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

The at least one manager terminal 400 may be a terminal of a manager using a web page, an app page, a program, or an application related to a smart fluid medical history monitoring service. In addition, the at least one manager terminal 400 uploads a case in which payment data exists when there is no departure such as vacation, outing, work, etc. within the area managed by the manager, and then from the medical history detection module 100 to the absence. Even if it is displayed, it may be a terminal that transmits data to the floating medical history monitoring server 300 so as not to sound an absence alarm in the case of being permitted to go out or receiving payment for going out. In addition, the at least one manager terminal 400 may upload the weight of the soldier using the corresponding bed for each unique IP to the floating force monitoring server 300. In addition, the at least one manager terminal 400 may be a terminal for receiving an alarm notifying the departure of the soldier, that is, an alarm message notifying absence or violence or sexual violence in the army, outputting it and receiving confirmation whether or not. .

Here, the at least one manager terminal 400 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one manager terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one manager terminal 400, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) It may include all kinds of handheld-based wireless communication devices such as terminals, smart phones, smart pads, and tablet PCs.

At least one network device 500, without using or using a web page, app page, program, or application related to the smart fluid force monitoring service, and the data collected from the at least one force detecting module 100 is a fluid force detection server It may be a device that performs transmission to 300.

FIG. 2 is a block diagram illustrating a flow force monitoring server included in the system of FIG. 1, and FIG. 3 is a diagram illustrating an embodiment in which a smart flow force monitoring service according to an embodiment of the present invention is implemented. to be.

Referring to FIG. 2, the fluid force monitoring server 300 may include a storage unit 310, a determination unit 320, a sexual violence monitoring unit 330, an absence confirmation unit 340, and a display unit 350. have.

In accordance with an embodiment of the present invention, the moving force monitoring server 300 or another server (not shown) operating in conjunction with at least one troop detection module 100, at least one manager terminal 400, and at least one In the case of transmitting a smart fluid force monitoring service application, program, app page, web page, etc. to the network device 500, at least one medical history detection module 100, at least one manager terminal 400, and at least one network The equipment 500 may install or open a smart fluid force monitoring service application, program, app page, web page, and the like. In addition, a service program may be driven in at least one medical history detection module 100, at least one manager terminal 400, and at least one network device 500 by using a script executed in a web browser. Here, the web browser is a program that allows you to use the Web (WWW: World Wide Web) service, which means a program that receives and displays hypertext described in HTML (Hyper Text Mark-up Language). For example, Netscape , Explorer, Chrome, etc. In addition, the application refers to an application program on the terminal, and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the storage unit 310 may assign a unique IP to each medical history detection module 100 installed in at least one bed, and store a reference weight for each unique IP to form a database. At this time, if there are beds or mattresses of 8 soldiers in the interior office, that is, one dormitory A in the army, the unique IP may be assigned as A-1, A-2, ...., A-8. And, the standard weight is the weight of a soldier wearing an A-1 bed or mattress. Based on this standard weight, if a weight less than the standard weight or no weight is detected at all, it is judged that the soldier is not in bed (absence notification), and if the detected weight is within the error range of the standard weight, it is judged as sleeping (sleeping indication) If a weight greater than the standard weight is detected, it is determined that there are multiple people in one bed (notification of sexual violence).

When the difference between the measured weight and the reference weight received from the control unit 120 of the military history detection module 100 exceeds a preset first threshold value, the determination unit 320 may determine that the military history is disengaged and output an alarm. . The troop detection module 100 stores at least one weight sensor 110 arranged and built-in to sense the weight on the bed top plate in the army, and the assigned unique IP and a reference weight previously mapped to the bed and stored, and at least one The measured weight sensed by the weight sensor 110 and the reference weight may be compared and the result may be output.

In this case, the first threshold value refers to a difference in weight when an adult male cannot have it. For example, if Private "Ga" weighs 60kg and the detected weight is 10kg, then Private "Ga" does not exist (true absent mode). In addition, if the detected weight is 100kg, it is determined that a soldier other than Private "A" has been replaced, and a notification of the absence of Private "A" is outputted (slow absence mode). At this time, since the reference weight, that is, the weight of each soldier is stored, the range of the soldier sleeping in the bed of Private “A” can be extracted. For example, if a soldier weighing 90 to 100 kg in the first quarter is the only soldier "I" and the weight is not being measured in the bed of the "I" soldier, then the "I" soldier prevents the absence of the "A" soldier from being known. In order to be able to assume that "go" was located in the soldier's bed.

In this case, in the true absence mode, the difference between the measured weight and the reference weight may be-(minus), and the absolute value of the first threshold may be ±10 kg of the reference weight. In the sub-sedation member mode, the difference between the measured weight and the reference weight may be + or -, and the absolute value of the first threshold may be ±10 kg or more. However, the error range is not limited to the above-described value because it may vary depending on the type of sleeping of each soldier or what clothes or items to wear.

In addition, at least one weight sensor 110 is, for example, two in the vicinity of the head of the bed, two in the arm portion, and two in the leg portion, and the controller 120 is an OR gate, and each weight sensor 110 Because the values of) are summed, the height can also be estimated. For example, suppose that soldier "A" and soldier "I" weigh the same 80kg but are different in height. In this case, if the "A" soldier is taller than the "I" soldier, the value detected by each weight sensor 110 is different. For example, there is a bed or mattress as shown in Table 1, (1,1) and (3,1) are on the head side, (1,3) and (3,3) are on the legs, and Suppose that the width is 60cm, the "Ga" soldier is 160cm tall, and the "I" soldier is 180cm tall. At this time, the output value of the "A" soldier's weight sensor 110 does not spread evenly between (1,1) to (1,3). On the contrary, the output value of the "I" soldier's weight sensor 110 spreads evenly across (1,1) to (1,3) (since the length of the bed mattress is 180cm in total). It is also possible to detect and prevent replacement of soldiers of the same weight through these distribution values.

Weight sensor (110)(1,1) Weight sensor (110)(1,2) Weight sensor (110)(1,3) Control unit 120 Weight sensor (110)(3,1) Weight sensor (110)(3,2) Weight sensor (110)(3,3)

Through this, it is possible to check whether the soldiers have changed beds with each other, or whether a soldier with a lower rank has replaced the position of a soldier with a higher rank in order to hide their absence. The sexual violence monitoring unit 330 includes a reference weight and a reference weight. When the difference between the measured weights received from the control unit 120 of the military history detection module 100 exceeds the second threshold, an alarm may be output as sexual violence occurs. In the case of sexual violence, in most cases, the weight of two or more people is detected on a bed.If the average adult male's weight added to the standard weight is detected, or the sum of the weights of soldiers in the dormitory is the result. If detected, a sexual violence alarm can be output. In addition, when a sexual assault occurs, a graph of a certain pattern can be obtained by the piston motion, so if the cycle in which the weight is applied is measured as a graph by grasping this, it is possible to determine whether or not there is sexual violence by grasping this. To this end, in addition to summing with an OR gate, the analog signal output from at least one weight sensor 110 is connected in parallel to receive input as it is, a low pass filter and an amplifier are further configured, and the amplifier is configured as an inverting amplifier to provide an analogue signal. A configuration for analyzing the signal as a graph may be further configured.

In this case, if the data set is not sufficient initially, it is possible to measure that the weight increase pattern corresponding to the piston motion periodically occurs after receiving each analog signal. However, after the data set is sufficiently accumulated, the collected weight increase/decrease pattern data may be converted into a spectrogram image using a Short-Time Fourier Trasnform (STFT). At this time, there is a problem that an error occurs in the frequency analysis technique for an abnormal signal of the Fourier transform, and a method capable of performing frequency analysis even at the moment when such an error occurs is required. Accordingly, STFT is a method of dividing the target signal by frame units in consideration of the stability of the signal and performing Fourier transform while moving a window of a certain size. It is a method of performing Fourier transform after applying a window function to the signal to be analyzed. The equation of STFT in the time domain is STFT(t,w)=∫x(τ-t)e- ^jwτ dτ, and the range of integral is from -infinity to +infinity. Here, x(τ) is the signal to be analyzed, and w(τ-t) is a window function. In addition, a spectrogram is a tool for visualizing and grasping sound and waves, and features a combination of a waveform and a spectrum. In the waveform, you can see the change in the time axis, that is, the change in the amplitude axis in the time domain, and in the spectrum, you can see the change in the amplitude axis according to the change in the frequency axis, whereas in the spectrogram, the difference in amplitude is printed according to the change in the time axis and the frequency axis. It is expressed as the difference in density or display color.

The sexual violence monitoring unit 330 may extract feature data from the converted spectrogram image using a convolutional neural network (CNN). Since the spectrogram is output as an image, as a result, when comparing the analog graph of the weight sensor 110 when sexual violence occurs through image analysis, it is necessary to use an image to compare. At this time, when trying to calculate the similarity between different images, it is difficult to determine the degree of similarity between images through pixel-by-pixel comparison, so to solve this problem, the characteristics of the image are not compared by pixel-by-pixel. There is a method of extracting and comparing images, which is a deep learning technology, CNN.

CNN learns the features of an image by itself, can classify images and recognize patterns of images based on the learned features, and is suitable for image processing with a network structure using a convolution layer. Since images can be classified based on the features within, it is used in an embodiment of the present invention. However, it is not limited to CNN, and any method that can classify an image and extract its features will be possible.

The CNN can extract features of a spectrogram in a vector form and measure similarity between images using the extracted features. In an embodiment of the present invention to extract features of a spectrogram, a model using the basic structure of a convolutional neural network consisting of a convolution layer, an activation function layer, and a maximum pooling layer is used. It can be used, and a feature vector of a spectrogram can be extracted and used from a layer before a softmax layer used to classify an image before measuring the similarity. Basically, it can be used to measure similarity by extracting features from a CNN having a fully-connected layer and a model having a GAP layer (Global Average Layer) that obtains an average value on the feature map. .

As another model for measuring the similarity of the image, a CNN-based autoencoder model can also be used.The encoder is composed of a convolutional neural network structure, and a decoder for reconstructing compressed data as a result of the encoder ( Decoder). Spectrogram features are extracted from a specific layer of the learned autoencoder model, and feature vectors derived from the GAP layer can be used to measure image similarity. Euclidean distance and cosine similarity can be measured from the image feature vectors extracted through the above three models, and can be sorted according to the degree of similarity per spectrogram, that is, similarity. , Using the sorted order, not only the data judged to be the most similar for each spectrogram, but also the data judged to be the least similar can be checked.

At this time, vibration data may be extracted using the change in weight according to the piston motion, or vibration data may be extracted using a vibration meter. In this case, restructuring is performed on the XYZ axis in the time domain. After that, the feature data can be extracted using the CNN. The basic concept for this goes back to the principle of the movement of the weight about the time axis (time domain). The weight on the spring moves up and down over time, and leaves a graph by reciprocating the upper and lower limits based on the center point. Likewise, when a piston movement, including semi-rape and forced harassment, which is included in the category of sexual assault, starts, the vibration meter inside the mattress also starts to vibrate. In this case, when a geomagnetic sensor, a 9-axis sensor, an acceleration sensor, etc. are used, data generation and graph visualization on which direction of vibration is applied in the XYZ axis, how strong the vibration is, and how the pattern is. Since the generated graph is also an image, the sexual violence monitoring unit 330 may extract feature data for the vibration data using the above-described CNN.

After the feature data is extracted in this way, the sexual violence monitoring unit 330 may compare the extracted feature data with pre-stored sexual assault feature data. As described above, the feature data comparison can use the Eucladian distance as described above. Finally, the sexual violence monitoring unit 330 may select pre-stored feature data having the highest similarity as a result of the comparison. If the previously stored feature data having the highest similarity is selected as described above, it can be used as evidence to prove the sexual assault afterwards, which can be output from the manager terminal 400.

At this time, the manager terminal 400 may receive an alarm output from the fluid history monitoring server 300. In addition, the at least one manager terminal 400 may be mapped to and stored with a unique IP for each manager who manages the moving force. For example, if the manager "A" manages the dormitory 1 to the dormitory N, if the unique IP of the medical history detection module 100 included in the dormitory 1 to the dormitory N is from 1 to N, [1, ...N]-A can be mapped and saved.

When the difference between the reference weight and the measured weight received from the control unit 120 of the military history detection module 100 exceeds a preset third threshold, the absence confirmation unit 340 may determine the absence and output an absence event. have. At this time, the absence event does not sound an alarm when the absence payment data is previously stored in the unique IP that outputs the absence event, unlike the determination of the absence of the military history by the first threshold value, and the absence payment data is stored in the unique IP that outputs the absence event. If it does not exist, an alarm can be output. In other words, if it is determined that it is not "departure" due to payment received for vacation or during night reconnaissance, the absence alarm should not be sounded. At this time, the criteria for distinguishing absence, sleeping and sexual assault are summarized in Table 2 below. However, it will be apparent that various numerical values or algorithms can be applied without being limited to the numerical values described.

Weight value (standard) Transfer data Remark small absence If necessary, set vacation and work route and perform weight detection (monitoring the availability of others) Set weight value 10Kg range sleep Absence (blinks red) 10 minutes after bedtime, automatic release when using bed ±20Kg or more 2 person use Red mark as possible sexual violence

The display unit 350 outputs a layout diagram of a bed on a floor plan for at least one interior office, a unique IP on the bed of the output layout, and a name previously mapped and stored, and state data output from the medical history detection module 100 May be overlaid, and the absence payment data input from at least one manager terminal may be mapped to a unique IP on the bed in the output layout and output together with the stored name. In this case, at least one weight sensor 110 The output terminal of may be connected to the input terminal of the OR gate included in the control unit 120, and the network equipment 500 may connect the floating force monitoring server and the force detection module 100 by wireless or wire, and the control unit ( The output terminal of 120) is connected to the input terminal of the network equipment 500, and the output terminal of the controller 120 may be connected to any one of a LAN port, an optical port, and a WIFI wireless port corresponding to the input terminal of the network equipment 500.

In addition, the floating force detection server 300 according to an embodiment of the present invention recognizes that the weight sensor 110 is installed and avoids it so that the possibility of assault or sexual assault is not excluded, an illegal type It is also possible to add a method of visually detecting an assault, which is a forceful event, using a scene histogram. At this time, the requirements for the crime of assault stipulated in the criminal law are as follows.

i) The perpetrator must be 1, and if the number of perpetrators is 2 or more, violence and special assault. In addition, ii) Weapons such as knives, clubs, bricks, and beer bottles should not be used, and in the case of assaulting with weapons or assaulting with weapons, special assaults and injuries are classified as injuries. iii) Injury will not occur, but if injuries do occur, an assault may be established depending on whether the injury is committed or intentional. In addition, if the assault falls under violence, aggravated punishment will be given, and the requirements for special assault are i) two or more criminals and ii) the use of weapons. Special assault is established even if a weapon is assaulted with a weapon, even if a weapon is not used.

On the other hand, the histogram is a graph showing the frequency distribution, which is expressed in a column shape so that the characteristics of the distribution of the observed data can be seen at a glance. It is also referred to as a column graph or columnar picture. On the horizontal axis, a point indicating the class interval of each class is marked, and a column with a height proportional to the frequency of this class is erected on the section for these class intervals. In image processing, the histogram is a very useful tool used to represent information about the contrast value of an image. Using this histogram, you can clearly see the composition of the image. In other words, it is possible to know in detail the contrast of light and dark and the distribution of light and dark values. This image histogram is just a bar graph of the intensity values of pixels. The intensity values that a pixel can have are plotted on the horizontal axis, and the frequency of each intensity value is plotted on the vertical axis.

The color histogram represents the distribution of intensity values for pixels in an image. The horizontal axis represents the intensity value of the 256-level image, and the vertical axis represents the frequency of each intensity value (level). The higher the graph, the higher the frequency. This histogram makes it possible to intuitively observe whether the contrast values are evenly spread or skewed to one side, so it helps to obtain a good quality image by widening the distribution of brightness values by adjusting the brightness when digitally working on images. The formula of the color histogram technique is shown in Equation 1 below.

Color histogram comparison (d _{r, g, b} (f _i ,f _j )) is calculated through a histogram comparison calculated separately for each RGB color space of two adjacent frames (f _i ,f _j ). Define and use as in Equation 1. H _i ^r (k), H _i ^g (k), H _i ^b (k) is the number of bins (k) (N) for each color space (r, g, b) in the frame (f _i ). Show. Although this method is very sensitive to the motion and contrast of the camera and object and causes a lot of data loss, it can be found that the histogram method is a good exchange factor between accuracy and speed.

Key frames can be extracted by using a method of extracting as a color histogram, which is one of the scene change detection methods, from images extracted from each dormitory, corridor, toilet, etc. In the case of restrooms and public showers, especially in the case of hidden cameras, camera installation is prohibited, and abuse is frequently used in toilets or showers. In this way, if the video collected from the camera is expressed as a graph of a color histogram and recording starts from the part where the scene change occurs or the video extracted from the camera starts to be streamed and saved, it is designated as a crime location from the moment the assault begins and can be taken. It becomes. In other words, the camera generates a color histogram while operating, but before the crime, that is, before the scene change detection, the access of others is not possible, or it is operated only at the system stage to detect the scene without saving it, and the assault starts, that is, the scene change. When detection is performed, an alarm is sounded, and an image captured by the camera is stored, shared, and access permission is given to the client (the administrator terminal 400).

At this time, the threshold value can be different according to the characteristics of the video used for scene change detection, and the frame rate by the user, that is, the video is driven at several frames per second, and the frame for selecting a screen is It can also be arbitrarily adjusted according to the value of how many frames per second are selected and the type or capacity of the video. For example, if the threshold is high, fewer key frames are detected, and if the threshold is low, many key frames are detected. In other words, when detecting only the section where the scene change is severe, the threshold value can be increased, and when detecting the section where the scene change is not severe, for example, in order to detect the scene change even with a small movement, the threshold value is lowered. Just give it.

For example, suppose there are two soldiers in the bathroom and there is a fight. At this time, the camera is taking a picture and monitors it with a color histogram. A scene in which the graph exceeds a threshold is detected as a key frame of the video. If A was in front of B, but A suddenly swung around and caught B's edge, and it was detected as a key frame beyond the threshold, the image detected as a key frame is a video that the administrator can access to inform the fight and record, share, and Storage becomes possible. In addition, if A suppressed B with a fist while holding the leg of B and fell down, and this was detected as a key frame beyond the threshold, storage, sharing and access are allowed as in the first key frame, and the administrator terminal 400 It will be shared immediately and will be able to identify and discipline offenders.

Most of the scenes change drastically in order to assault. For example, in order to hit the opponent with a fist, a swing must be given, and in order to increase the force, the distance to which the swing is applied becomes longer, and the speed becomes faster, so the scene change occurs severely. Of course, in the case of exploiting the fact that it detects a scene change or using a special assault, that is, a weapon, the perpetrator may act slowly, but the victim struggles with extreme pain, which also causes a sharp transition. If multiple people are holding the victim, the degree of struggle is weaker than before, so if the threshold is set high, scene detection will not be possible, but if this is also lowered, detection is possible. Crimes that commit physical and mental assault in places where no cameras can be installed or surveillance is becoming more intelligent, and assault and violence are not justified by anything. Accordingly, an embodiment in which the possibility of assault is captured in detail by using a method using sound or vibration as well as a camera may be further possible.

Hereinafter, the operation process according to the configuration of the flow force monitoring server of FIG. 2 will be described in detail with reference to FIGS. 3 to 5 as an example. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

3, when a bed or mattress is installed in a dormitory, at least one weight sensor 110 and a control unit 120 are installed inside each bed or mattress, and the control unit 120 and the network equipment 500 are connected. The configuration diagram is shown. The medical history detection module 100 and the network equipment 500 installed in each bed may be connected wirelessly in addition to being connected by wire. In this case, based on IoT, each military history detection module 100 constitutes one node, and similarly, a unique IP may be set. Here, in the case of a node using a floating IP, the IP may not be specified. Therefore, when data is output using a unique identification code, for example, a serial number, the serial number is attached to the header and transmitted to distinguish the signal. You can do it.

Referring to FIG. 4, it can be seen that at least one weight sensor 110 is connected to the input terminal of the OR gate of the controller 120. According to the digital logic circuit of the OR gate, since an output value is output as the sum of all input values, the sum of weights measured by the six weight sensors 110 is output as the output of the OR gate. At this time, since other areas other than the weight sensor 110, that is, the human body receives gravity, each body part receives gravity toward the mattress and at the same time, there is a force supported by the mattress, even if the weight is measured using the weight sensor 110 The total may not match the person's weight. Assuming that the resulting error range is, for example, ± 10 kg, it can be determined that it is normal within this error range. For example, if there is a soldier with a weight of 70 kg, a weight measurement value of 50 kg to 80 kg is considered to be in the normal range, that is, sleeping.

5, in each manager terminal 400, command and control room, or the floating force monitoring server 300 itself, sleeping (normal), absence (abnormality/alarm), absence (normal/non-alarm) and sexual assault (abnormal/alarm) ), the layout of each bed for each dormitory is a plan view to intuitively identify the case of), and a screen displaying the name, rank, and status is shown. If it is absent but it is normal, that is, if it is a vacation, it is not marked as absent, but a red alarm is not given while indicating vacation. However, if it is absent but abnormal, for example, if it is not on the bed but not on vacation, work, or outside work, a red flashing and lighting indication is displayed to notify the manager. At this time, it is possible to transmit a text message or an emergency message (a forced alarm ignoring an alarm on/off indication) or a call to the manager terminal 400 without excluding outputting the sound together.

Matters that are not described with respect to the smart flow force monitoring method of FIGS. 2 to 5 are the same as the contents described above for the smart flow force monitoring method through FIG. 1 or can be easily inferred from the description below. It should be omitted.

The smart fluid force monitoring system according to the exemplary embodiment described with reference to FIG. 5 may also be implemented in the form of a recording medium including computer-executable instructions such as an application or program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The smart flow force monitoring method according to an embodiment of the present invention described above may be executed by an application basically installed in a terminal (this may include a program included in a platform or an operating system basically installed in the terminal), It may be executed by an application (that is, a program) directly installed on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the smart flow force monitoring method according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed basically in the terminal or directly installed by the user, and can be recorded by a computer such as in the terminal. Can be recorded on media.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (10)

At least one weight sensor arranged and built-in to sense the weight on the bed top in the army, and a given unique IP and a reference weight previously mapped to the bed and stored, are stored, and the measured weight and reference detected by the at least one weight sensor A military history detection module including a control unit for comparing weights and outputting the result; And
A storage unit for assigning a unique IP to each military history detection module installed on the at least one bed, and storing a reference weight for each unique IP to form a database, and the difference between the measured weight and the reference weight received from the control unit of the medical history detection module A determination unit that determines as a military history departure and outputs an alarm when it exceeds a preset first threshold, and sexual violence when the difference between the reference weight and the measured weight received from the control unit of the military history detection module exceeds a second threshold When the difference between the reference weight and the measured weight received from the control unit of the military history detection module exceeds a preset third threshold value, the sexual assault monitoring unit outputs an alarm as occurrence, and an absence confirmation unit that outputs an absence event A floating force monitoring server including;
Including,
The output terminal of the at least one weight sensor is connected to the input terminal of the OR gate included in the control unit,
The sexual violence monitoring unit, the difference between the measured weight received from the control unit exceeds a second threshold value, analyzes the analog signal output from the at least one weight sensor, and then STFT ( Short-Time Fourier Trasnform) is used to convert a spectrogram image, and when feature data is extracted using a convolutional neural network (CNN), a notification is output as sexual violence occurs,
The absence confirmation unit does not sound an alarm when the absence payment data is previously stored in the unique IP that outputs the absence event, and outputs an alarm when the absence payment data does not exist in the unique IP that outputs the absence event. Smart fluid force monitoring system.
delete The method of claim 1,
The smart flow force monitoring system,
At least one manager terminal for receiving an alarm output from the fluid history monitoring server;
Including more,
Wherein the at least one manager terminal is mapped and stored with the unique IP for each manager who manages the moving force.
delete delete delete The method of claim 1,
The smart flow force monitoring system,
Network equipment for wirelessly or wired connection between the moving force monitoring server and the force detecting module;
Smart flow force monitoring system, characterized in that it further comprises.
The method of claim 7,
The output terminal of the control unit is connected to the input terminal of the network equipment,
An output terminal of the control unit is connected to one of a LAN port, an optical port, and a WIFI wireless port corresponding to the input terminal of the network equipment.
The method of claim 1,
The floating force monitoring server,
A display unit that outputs a layout diagram of the bed on a floor plan for each of the at least one interior office, and overlays a name previously mapped and stored with the unique IP on the bed of the output layout map, and state data output from the medical history detection module;
Smart flow force monitoring system, characterized in that it further comprises.
The method of claim 9,
The floating force monitoring server,
A smart fluid medical history monitoring system, characterized in that the absent payment data input from at least one manager terminal is output along with a name previously mapped to the unique IP on the bed in the output layout and stored.

Images