KR102514735B1 - Health examination assist apparatus and method - Google Patents

Abstract

The present invention relates to an efficient health examination assisting device and method using artificial intelligence and big data analysis.
The health examination assisting method according to the present embodiment includes the steps of collecting examination-related information of a examinee, location information of examination stations for each examination item located in a hospital, and image-related information from CCTVs installed in the hospital; , The step of calculating the cluster of examiners at each checkup center using the location information of checkup centers and image-related information, the continuity information of checkup items that structured the independence and dependency between checkup items, and the time required for checkup for each checkup item The step of establishing a checkup flow plan for each examinee using the checkup time, travel time required to move to each checkup center, and cluster map, and the checkup flow plan for each examinee and the checkup order for each checkup item included in the checkup flow plan It may include providing a first electronic device equipped with an examiner, and providing a waiting examinee for each examination center and an examination order of the waiting examinee to a second electronic device provided in the examination center in correspondence with the examination order.

Description

Health examination assisting device and method {HEALTH EXAMINATION ASSIST APPARATUS AND METHOD}

The present invention relates to an efficient health examination assisting device and method using artificial intelligence and big data analysis.

Diagnosis and treatment of disease are necessary to maintain health. If a significant period has elapsed since the onset of the disease, it may already be too late for appropriate treatment. Therefore, the government recommends regular health checkups for early diagnosis of diseases, and provides health checkup services such as general health checkups, cancer checkups, infant checkups, life transition period checkups, oral checkups, and company (group) comprehensive health checkups. are doing

Currently, when visiting a hospital and receiving a health checkup, many examiners are passively undergoing checkups as they move according to the nurse's guidance, and some hospitals use RFID/QR codes to register the checkup order and manage the number of people on standby. there is.

In the past, when receiving a health checkup at most hospitals, people are receiving a checkup while moving according to the guidance of a resident nurse to receive a variety of checkups ranging from basic checkups to additional checkups such as ultrasound, CT, and MRI. However, as a simple nurse roughly judges the current checkup waiting list with the naked eye and guides the examiner's movement, sometimes the waiting time for a specific checkup increases, so it takes a lot of time for the checkup to receive a health checkup, It is difficult to grasp the information at a glance, so there may be inconvenience of having to wait until the time of the examination. In addition, from the point of view of hospitals, nurses who need to perform health examinations have added tasks such as guiding the examiner's movement, resulting in a decrease in efficiency and an increase in cost of the main task of health examinations.

The foregoing background art is technical information that the inventor possessed for derivation of the present invention or acquired during the derivation process of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention.

Domestic Patent Publication No. 10-2013-0129520 (November 29, 2013)

One object of the present invention is to assist in efficiently receiving health examinations by automating health examinations using artificial intelligence and big data analysis.

One task of the present invention is to register the personal information and examination items of the examinee, analyze the cluster for each examination item using the CCTV installed in the hospital, and establish and provide the optimal examination route plan through big data analysis, so that the examinee can It is to help make the examination more convenient.

The problem to be solved by the present invention is not limited to the above-mentioned problems, and other problems and advantages of the present invention that are not mentioned can be understood by the following description and more clearly understood by the embodiments of the present invention. It will be. In addition, it will be appreciated that the problems and advantages to be solved by the present invention can be realized by the means and combinations indicated in the claims.

The health examination assisting method according to the present embodiment includes the steps of collecting examination-related information of a examinee, location information of examination stations for each examination item located in a hospital, and image-related information from CCTVs installed in the hospital; , The step of calculating the cluster of examiners at each checkup center using the location information of checkup centers and image-related information, the continuity information of checkup items that structured the independence and dependency between checkup items, and the time required for checkup for each checkup item The step of establishing a checkup flow plan for each examinee using the checkup time, travel time required to move to each checkup center, and cluster map, and the checkup flow plan for each examinee and the checkup order for each checkup item included in the checkup flow plan It may include providing a first electronic device equipped with an examiner, and providing a waiting examinee for each examination center and an examination order of the waiting examinee to a second electronic device provided in the examination center in correspondence with the examination order.

The health checkup auxiliary device according to the present embodiment includes a collection unit that collects checkup-related information of an examinee, location information of checkup points for each checkup item located in a hospital, and image-related information from CCTVs installed in the hospital, and checkup-related information And, a calculation unit that calculates a cluster of examiners at each checkup center using location information of checkup centers and image-related information, continuity information of checkup items that structured the independence and dependency between checkup items, and checkup items for each checkup item Establishment department that establishes examination flow plan for each examinee using the examination time required for each city, travel time required for each examination center, and cluster map A first providing unit that provides a checkup order to a first electronic device equipped with an examinee, and a second provider that provides a checkup order of waiting examiners and waiting examiners at each checkup center to a second electronic device provided in the checkup center in response to the checkup order It may include a provisioning unit.

In addition to this, another method for implementing the present invention, another system, and a computer readable recording medium storing a computer program for executing the method may be further provided.

Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

According to the present invention, by using artificial intelligence and big data analysis, by analyzing the number of people waiting for each examination, the required time, etc., and establishing and providing an efficient route plan, it is possible to solve the phenomenon in which examinations are concentrated on a specific examination, thereby reducing the examination wait time of the examinee. can reduce

In addition, by providing functions such as registering for examinations/checking the number of people on standby and time/checking notifications/monitoring of examination results, etc. Hospitals can automatically manage examiners and reduce costs through redeployment of manpower.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is an exemplary view of a health examination assistance system including a health examination assistance device, a first terminal, a second terminal, and a network connecting them to each other according to an exemplary embodiment.
2 is a block diagram schematically illustrating the configuration of a health examination assisting device according to an exemplary embodiment.
FIG. 3 is a block diagram schematically illustrating the configuration of an auxiliary management unit in the health checkup auxiliary device of FIG. 2 .
4 is an exemplary view of a neural network generating a cluster analysis result according to an exemplary embodiment.
5 is an exemplary view illustrating operations of a health checkup auxiliary device, a first electronic device, and a second electronic device according to an exemplary embodiment.
6 is a flowchart for explaining a health examination assisting method according to an exemplary embodiment.

Advantages and features of the present invention, and methods for achieving them will become clear with reference to the detailed description of embodiments in conjunction with the accompanying drawings. However, it should be understood that the present invention is not limited to the embodiments presented below, but may be implemented in a variety of different forms, and includes all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. . The embodiments presented below are provided to complete the disclosure of the present invention and to fully inform those skilled in the art of the scope of the invention to which the present invention belongs. In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded. Terms such as first and second may be used to describe various components, but components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, the same or corresponding components are assigned the same reference numerals, and overlapping descriptions thereof are omitted. I'm going to do it.

1 is an exemplary view of a health examination assistance system including a health examination assistance device, a first terminal, a second terminal, and a network connecting them to each other according to an exemplary embodiment. Referring to FIG. 1 , a health examination assistance system 1 may include a health examination assistance device 100 , a first electronic device 200 , a second electronic device 300 and a network 400 .

The health examination assisting device 100 may collect examination-related information of the examinee, location information of examination points for each examination item located in the hospital, and image-related information captured by a CCTV installed in the hospital, that is, a camera module (not shown). there is.

Here, the examination-related information of the examinee may include personal information of the examinee collected from the first electronic device 200 and one or more examination items to be examined by the examinee. In addition, location information of examination centers for each examination item may be set in advance or may be collected from the second electronic device 300 . In addition, the image-related information may include one or more image frames, a time at which the image frame was captured, location information of a CCTV, information on a view angle of a camera, and the like. Here, one or more image frames may include at least one human head.

The health examination assisting device 100 may calculate the population of examinees for each examination center by using examination-related information, location information of examination centers, and image-related information.

The health examination assisting apparatus 100 uses a neural network including a plurality of image frames including at least one human head included in the image frames, a plurality of convolutional layers, and a plurality of head detection networks, It is possible to generate a cluster analysis result for an image frame of . The health checkup assistant 100 considers the number of heads included in the cluster analysis result, the location information of the checkup center, the location information of CCTVs included in the image-related information, and the angle of view information of the CCTVs to determine the location of the examinee's body on the map of the hospital. As a result of mapping the locations, a cluster of examiners can be calculated for each examination center.

The health checkup auxiliary device 100 establishes a checkup movement plan for each examinee using continuity information of checkup items, checkup time required for checkup for each checkup item, travel time required for movement for each checkup location, and cluster diagram. can

Here, the continuity information of examination items may include structured data of independence and dependency between examination items. Data structured for independence among examination items may include structured data of examination items that do not need to be examined in advance in order to receive a certain examination item, for example, liver ultrasound, oral examination , blood pressure measurements, and the like. In addition, the structured data of dependencies between checkup items may include structured data of other checkup items that must be checked in advance in order to receive a checkup item. For example, the dependency data, In order to examine the gastric endoscopy, electrocardiography may be performed in advance.

In this embodiment, information related to continuity information, examination time, and travel time of examination items may be big data accumulated for a predetermined period, and the health examination assisting device 100 provides an optimal movement line through clustering and big data analysis. You can make a plan.

The health checkup assisting device 100 may provide the first electronic device 200 equipped with the examiner with a checkup flow plan for each examinee and a checkup order for each checkup item included in the checkup flow plan. The first electronic device 200 generates a checkup movement plan for each examinee and a checkup order for each checkup item, the waiting number and time for each checkup item provided from the health checkup auxiliary device 100, and the checkup order of the examinee. alarm signal and examination result information may be output. An examiner may enter the examination center by an alarm signal output through the first electronic device 200, and may monitor examination result information output through the first electronic device 200 at the request of the examinee.

The health checkup auxiliary device 100 may provide the second electronic device 300 provided in the checkup center with a checkup order for a waiting examinee at each checkup center and a checkup order for each checkup item included in the movement plan. The second electronic device 300 may check and register the examiner information received from the health checkup auxiliary device 100, display the checkup waiting list, and delete examinees whose checkups have been completed from the checkup waiting list.

In this embodiment, part of the information provided to the second electronic device 300 by the health checkup assistant device 100 may be provided to the first electronic device 200 . That is, the health checkup auxiliary device 100 may provide the first electronic device 200 with information on the number of people on standby at each checkup center and the remaining time until the checkup of the examinee in correspondence with the checkup order for each checkup item included in the movement plan.

The first electronic device 200 may include a computing device operated by an examinee, and the second electronic device 300 may include a computing device provided in a medical examination center and operated by an examination manager. The first electronic device 200 and the second electronic device 300 access a health examination assistance application and/or a health examination assistance site provided by the health examination assistance device 100 to receive a health examination assistance service.

The first electronic device 200 and the second electronic device 300 may include a communication terminal capable of performing a function of a computing device (not shown), and may include a smartphone 201 operated by an examiner or an examination manager. , tablet PC (202), desktop computer (301), smart TV (302), notebook, PDA (personal digital assistant), laptop, media player, micro server, GPS (global positioning system) device, e-reader, digital It may be, but is not limited to, a broadcast terminal, navigation, kiosk, MP3 player, digital camera, consumer electronics and other mobile or non-mobile computing devices. In addition, the first electronic device 200 and the second electronic device 300 may be wearable terminals such as watches, glasses, hair bands, and rings having communication functions and data processing functions. The first electronic device 200 and the second electronic device 300 are not limited to the above, and a terminal capable of web browsing may be used without limitation.

The network 400 may play a role of connecting the health checkup auxiliary device 100 and the first electronic device 200 and the second electronic device 300 . Such a network 400 may be a wired network such as LANs (local area networks), WANs (wide area networks), MANs (metropolitan area networks), ISDNs (integrated service digital networks), wireless LANs, CDMA, Bluetooth, satellite communication However, the scope of the present invention is not limited thereto. In addition, the network 400 may transmit and receive information using short-range communication and/or long-distance communication. Here, the short-range communication may include Bluetooth, radio frequency identification (RFID), infrared data association (IrDA), ultra-wideband (UWB), ZigBee, wireless fidelity (Wi-Fi) technology, Telecommunications include code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), and single carrier frequency division multiple access (SC-FDMA) technologies. can do.

The network 400 may include connections of network elements such as hubs, bridges, routers, and switches. Network 400 may include one or more connected networks, such as a multiple network environment, including a public network such as the Internet and a private network such as a secure enterprise private network. Access to network 400 may be provided through one or more wired or wireless access networks. Furthermore, the network 400 may support an Internet of Things (IoT) network and/or 5G communication in which information is exchanged and processed between distributed components such as objects.

2 is a block diagram schematically illustrating the configuration of a health examination assisting device according to an exemplary embodiment. In the following description, descriptions of portions overlapping those of FIGS. 1 to 5 will be omitted. Referring to FIG. 2 , the health examination auxiliary device 100 includes a communication unit 110, a storage medium 120, a program storage unit 130, a database 140, a health examination auxiliary management unit 150, and a control unit 160. can include Also, in this embodiment, “unit” may be a hardware component such as a processor or a circuit, and/or a software component executed by the hardware component such as a processor.

The communication unit 110 is a communication interface necessary to provide transmission/reception signals between the health checkup auxiliary device 100, the first electronic device 200, and the second electronic device 300 in the form of packet data in conjunction with the network 400. can provide. Furthermore, the communication unit 110 may serve to receive a predetermined information request signal from the first electronic device 200 and/or the second electronic device 300, and the information processed by the health examination assistant management unit 150 may serve to transmit to the first electronic device 200 and/or the second electronic device 300. Here, the communication network is a medium that serves to connect the health checkup auxiliary device 100 and the first electronic device 200 and/or the second electronic device 300, and the first electronic device 200 and /or may include a path providing an access path so that information can be transmitted and received after the second electronic device 300 accesses the health checkup auxiliary device 100. In addition, the communication unit 110 may be a device including hardware and software necessary for transmitting and receiving signals such as control signals or data signals to and from other network devices through wired or wireless connections.

The storage medium 120 performs a function of temporarily or permanently storing data processed by the controller 160 . Here, the storage medium 120 may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto. The storage medium 120 may include built-in memory and/or external memory, and may include volatile memory such as DRAM, SRAM, or SDRAM, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, and flash ROM. , NAND flash memory, or non-volatile memory such as NOR flash memory, SSD. It may include a compact flash (CF) card, a flash drive such as an SD card, a Micro-SD card, a Mini-SD card, an Xd card, or a memory stick, or a storage device such as an HDD.

The program storage unit 130 collects examination-related information of the examinee, location information of examination centers for each examination category located in the hospital, image-related information from CCTVs installed in the hospital, examination-related information, and location information of examination centers And, the task of calculating the cluster degree of examiners by examination center using image-related information, the continuity information of examination items structured in the independence and dependency between examination items, the examination time required for each examination item, and the examination center A first electronic device equipped with the examiner to establish a checkup flow plan for each examinee using the travel time required for each movement and the cluster map, and the checkup flow plan for each examinee and the checkup order for each checkup item included in the checkup flow plan 200, a task of providing the second electronic device 300 provided in the checkup center with the checkup order of waiting screeners and waiting screeners for each checkup center in response to the checkup order for each checkup item included in the movement plan. It is equipped with control software that performs

The database 140 includes examination-related information of the examinee, location information of the examination center for each examination item located in the hospital, image-related information from CCTV installed in the hospital, continuity information of examination items, and examination required for each examination item Time information, travel time information required to move to each checkup center, cluster information calculated from the video frame, checkup movement plan information for each examinee, checkup order information for each checkup item, information on waiting screeners for each checkup center, and checkup waiting list A management database for storing checkup order information, hospital map information, checkup results according to checkup items, and the like may be further included.

In addition, the database 140 may include a user database that stores information on an examinee and/or a checkup manager to be provided with a health checkup assistance service. Here, the information of the examinee and/or the examination manager includes basic information such as the name, affiliation, personal information, gender, age, contact information, e-mail, address, image, etc. of the examinee and/or the examination manager, and ID (or e-mail) and information on authentication (login) of the examiner and/or examination manager, such as password, access country, access location, information on devices used for access, and information related to access, such as the connected network environment. .

In addition, the user database includes unique information of examiners and/or examination managers, information and/or category history provided by examiners and/or examination administrators who accessed a health examination assistance application or health examination assistance site, and the examinee and/or examination manager. Set environment setting information, resource usage information used by the examiner and/or examination manager, and billing and payment information corresponding to resource usage by the examiner and/or examination manager may be stored.

The health examination assistant management unit 150 may collect examination-related information of the examinee, location information of examination centers located in the hospital, and image-related information from CCTVs installed in the hospital.

The health examination assistant management unit 150 may calculate a population of examinees for each examination center by using examination-related information, location information of examination centers, and image-related information.

The health checkup assistant management unit 150 provides continuity information of checkup items that structured the independence and dependency between checkup items, checkup time required for checkup for each checkup item, travel time required for movement at each checkup center, and cluster degree Using , it is possible to establish a checkup movement plan for each examinee.

The health examination assistant management unit 150 may provide the first electronic device 200 equipped with the examinee with a examination flow plan for each examinee and an examination order for each examination item included in the examination flow plan.

The health checkup assistant management unit 150 may provide the second electronic device 300 provided in the checkup center with a checkup order for a waiting examinee at each checkup center and a checkup order for the waiting checkup person in response to the checkup order for each checkup item included in the movement plan.

The control unit 160, as a kind of central processing unit, may control the entire operation of the health examination assisting device 100 by driving control software loaded in the program storage unit 130. The controller 160 may include all types of devices capable of processing data, such as a processor. Here, a 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform functions expressed by codes or instructions included in a program, for example. As an example of such a data processing device built into hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated (ASIC) circuit), field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

FIG. 3 is a block diagram schematically illustrating the configuration of an auxiliary management unit in the health checkup auxiliary device of FIG. 2 . In the following description, descriptions of portions overlapping those of FIGS. 1 and 2 will be omitted. Referring to FIG. 3 , the health examination assistant management unit 150 may include a collection unit 151, a processing unit 152, a establishment unit 153, a first provision unit 154 and a second provision unit 155. there is.

The collection unit 151 may collect examination-related information of the examinee, location information of examination stations for each examination item located in the hospital, and image-related information from CCTVs installed in the hospital.

The processing unit 152 may calculate the population of examinees for each examination center by using examination-related information, location information of examination centers, and image-related information.

The processing unit 152 uses a neural network including a plurality of image frames including at least one head of at least one person included in at least one image frame, a plurality of convolutional layers, and a plurality of head detection networks, It is possible to generate a cluster analysis result for an image frame of .

The processing unit 152 may input a plurality of image frames to a neural network including a plurality of convolutional layers and a plurality of head detection networks in order to generate a result of cluster analysis. The processor 152 inputs the first feature map output from the first convolution layer to the first head detection network, and inputs the second feature map and the first feature map output from the second convolution layer to the second head detection network. And, the third feature map and the second feature map output from the third convolution layer may be input to the third head detection network. The processing unit 152 performs a convolution operation of the first feature map and the second feature map in the second head detection network, and the result data of the convolution operation of the second head detection network and the third feature in the third head detection network. A convolution operation between maps is performed, and heads included in a plurality of image frames are detected based on the output data of the first head detection network, the output data of the second head detection network, and the output data of the third head detection network. You can create cluster analysis results. Hereinafter, generation of a cluster analysis result using a neural network will be described with reference to FIG. 4 .

As an optional embodiment, the processing unit 152 defines a multi-task to improve the performance of a neural network that generates a cluster analysis result, and based on this, multi-task learning using a loss function technique can be applied. The multi-task learning technique can learn the most appropriate feature by simultaneously learning the following items.

In this embodiment, a head classification task (L _cls (p _i , p _i ^* )) of classifying whether the ith anchor is a head or not may be performed. That is, it is possible to learn a classifier that outputs 1 whenever possible for a positive anchor assigned to a head, and outputs 0 when possible for a negative anchor.

In this embodiment, the head bounding box regression task (L _box (t _i , t _i ^* )) can be performed.

In this embodiment, the final loss function (L = L _cls (p _i , p _i ^* ) +λ) is obtained by using the loss function according to the classification result of the head classification task and the loss function according to the prediction result of the head bounding box regression task. ₁ p _i ^* (L _box (t _i , t _i ^* )) can be calculated, and the cluster analysis result can be optimized so that the final loss function is minimized.

The processing unit 152 considers the number of human heads included in the cluster analysis result, location information of examination stations, location information of CCTVs included in the image-related information, and information on the angle of view of the CCTVs to determine the location of the examinee on the hospital map. As a result of mapping the locations, a degree of population of examiners for each examination center may be calculated.

The establishment unit 153 may establish a checkup flow plan for each examinee using continuity information of checkup items, checkup time required for checkup for each checkup item, travel time required for each checkup location, and cluster diagram. . Here, the examination time and the moving time may include an average time.

The establishment unit 153 may generate a random checkup sequence using continuity information of checkup items. The establishment unit 153 may calculate the total examination time by using the examination time, movement time, and cluster degree for each examination item included in the random examination sequence. In this embodiment, the total examination time can be calculated using Equation 1 below.

The establishment unit 153 may establish a checkup order in which the total checkup time calculated by Equation 1 is minimized as a checkup flow plan while repeatedly generating the checkup order.

The first providing unit 154 may provide the first electronic device 200 equipped with the examinee with the examination flow plan for each examinee and the examination order for each examination item included in the examination flow plan. The first providing unit 154 provides a checkup flow plan for each examinee, a checkup order for each checkup item, waiting time for each checkup item, an alarm signal generated when the checkup order of the examinee is reached, and checkup result information may be provided to the second electronic device 300.

The second providing unit 155 may provide the second electronic device 300 provided in the examination center with the waiting examinee and the examination order of the waiting examinee at each examination center corresponding to the examination order for each examination item included in the movement plan. The second providing unit 155 may provide the second electronic device 300 with information for confirming and registering examinee information, displaying an examination waiting list, and deleting an examinee whose examination has been completed from the examination waiting list. there is.

4 is an exemplary view of a neural network generating a cluster analysis result according to an exemplary embodiment. In the following description, descriptions of portions overlapping those of FIGS. 1 to 3 will be omitted.

Referring to FIG. 4 , the health examination assisting device 100 inputs (10) a plurality of image frames to a neural network including a convolutional network 510 including a plurality of convolutional layers and a plurality of head detection networks 520, 530, and 540. can

In an embodiment, the convolutional network 510 is a feature extraction network that extracts basic features for head detection, and can extract head features included in a plurality of image frames. In addition, the plurality of head detection networks 520 , 530 , and 540 may detect the head based on the head features extracted from the convolutional network 510 .

In an embodiment, the health examination assisting apparatus 100 may transfer feature maps output from a plurality of convolutional layers to each of the plurality of head detection networks 520 , 530 , and 540 . For example, the feature map output from the first convolutional layer 513 may be input to the first head detection network 520 and the second head detection network 530, and output from the second convolutional layer 512. The feature map may be input to the second head detection network 530 and the third head detection network 540, and the feature map output from the third convolution layer 511 may be input to the third head detection network 540. can

In one embodiment, the health checkup assisting device 100 may not perform a separate pre-processing process on the obtained plurality of frames. Computing resources can be saved by inputting the above-described plurality of frames to the neural network without preprocessing. In this way, according to the cluster degree calculation according to the present embodiment, the head can be detected in real time using only CPU resources.

In one embodiment, the number of multiple convolution layers and the number of multiple head detection networks included in the aforementioned neural network may be limited in order to limit the amount of computation. For example, the neural network may include 6 convolution layers, 5 max pooling layers, and a detection network, and the detection network includes 3 convolution layers and a detection layer. can do. However, note that this is only an example of a neural network configuration, and the number of layers included in the neural network according to the present embodiment is not limited thereto.

In addition, the health checkup assistance device 100 according to the present embodiment may not perform batch normalization in the neural network to improve network performance. In the case of a typical convolutional network, batch normalization is performed after convolutional operations are performed in the convolutional layer to increase convergence and stability of network learning. However, since the health examination assisting device 100 according to the present embodiment detects the head using limited computing resources, batch normalization may not be performed.

The convolutional network 510 according to the present embodiment includes a first convolutional layer (Conv. 128 x 1 x 1) 513, a second convolutional layer (Conv. 128 x 3x3) 512 and a third convolutional layer ( 128 x 3 x 3) 511 , and the first head detection network 520 may be included in the convolutional network 510 . In an embodiment, the first head detection network 520 may detect the head based on the first feature map of the head estimated by the first convolutional layer (Conv. 128 x 1 x 1) 513. .

In an embodiment, the second head detection network 530 detects the head based on the second feature map and the first feature map of the head estimated by the second convolution layer (Conv. 128 x 3 x 3) 512 ( detection) can be done. In an embodiment, the size of the first feature map may be different from the size of the second feature map by a previously performed convolution operation. Accordingly, the second head detection network 530 according to the present embodiment may perform upsampling on the first feature map in an upsample layer (upsample) to modify the first feature map to have the same size as the second feature map.

In an embodiment, the third head detection network 540 includes the third feature map of the head estimated by the third convolution layer (Conv. 128 x 3 x 3) 511 and output from the second head detection network 530. The head may be detected based on the second feature map. In an embodiment, the third head detection network 540 may increase the size of the second feature map output by the second head detection network 530 by performing upsampling. Then, the third head detection network 540 can detect the head based on the upsampled feature map and the third feature map of the head estimated by the third convolution layer (Conv. 128 x 3 x 3) 511. there is.

In this embodiment, the detection layer of the first detection network 520, the detection layer of the second detection network 530, and the detection layer of the third detection network 540 are three. Coordinates of a bounding box for an anchor and a head presence value may be output, and heads of various sizes may be detected through additional connection between the second convolutional layer 512 and the third convolutional layer 511.

The health checkup assistant device 100 includes output data (coordinates of the bounding box and head presence value) of the first head detection network 520 and output data of the second head detection network 530 (bounding box coordinates and head presence value). values) and the output data of the third head detection network 540 (coordinates of the bounding box and head existence value), the result of detecting the head included in the plurality of image frames is used as the output data 20, and the cluster diagram Analysis results can be generated.

5 is an exemplary view illustrating operations of a health checkup auxiliary device, a first electronic device, and a second electronic device according to an exemplary embodiment. In the following description, descriptions of overlapping parts with those of FIGS. 1 to 4 will be omitted.

Referring to FIG. 5 , the health examination assisting device 100 may calculate a population of examinees for each examination center by using examination-related information, location information of examination centers, and image-related information. In addition, the health checkup auxiliary device 100 uses the continuity information of checkup items, the checkup time required for checkup for each checkup item, the travel time required for movement at each checkup center, and the cluster diagram to determine a checkup movement plan for each examinee. can be established

The first electronic device 200 may transmit examination-related information to the health examination assistance device 100 . The first electronic device 200 may receive and output a checkup flow plan for each examinee and a checkup order for each checkup item included in the checkup flow plan from the health checkup auxiliary device 100 . The first electronic device 200 receives the number of people waiting for each checkup in response to the checkup order from the health checkup auxiliary device 100, the waiting time for the examinee, an alarm signal generated when the checkup order is reached, and the examiner's request As a result, monitoring information can be output. Upon receiving the alarm signal, the examinee can check the order of examination and enter the examination center without calling the nurse's voice. An examinee who has completed an examination for an arbitrary examination item may monitor examination result information through the first electronic device 200 .

The second electronic device 300 may output, from the health checkup auxiliary device 100, a checkup order for waiting screeners and waiting screeners for each checkup center corresponding to the checkup order for each checkup item included in the movement plan. The second electronic device 300 may check and register the examinee information received from the health checkup auxiliary device 100, display a waiting list for examination, and delete an examinee whose examination has been completed from the waiting list for examination. there is.

6 is a flowchart for explaining a health examination assisting method according to an exemplary embodiment. In the following description, descriptions of portions overlapping those of FIGS. 1 to 5 will be omitted. The health examination assistance method according to the present embodiment may be performed by the controller 160 or the processor of the health examination assistance device 100 .

Referring to FIG. 6 , in step S610, the health checkup assistant device 100 collects checkup-related information of the examinee, location information of checkup centers for each checkup item located in the hospital, and image-related information from CCTVs installed in the hospital. .

In step S620, the health checkup assisting device 100 calculates a population of examinees at each checkup center by using checkup-related information, location information of checkup centers, and image-related information.

The health examination assisting device 100 uses a neural network including a plurality of image frames including at least one human head included in image-related information, a plurality of convolutional layers, and a plurality of head detection networks, A cluster analysis result for a plurality of image frames may be generated.

When generating the cluster analysis result, the health examination assisting device 100 may input a plurality of image frames to a neural network including a plurality of convolutional layers and a plurality of head detection networks. The health examination assisting device 100 inputs the first feature map output from the first convolutional layer to the first head detection network, and detects the second head with the second feature map and the first feature map output from the second convolutional layer. The third feature map, the second feature map, and the first feature map that are input to the network and output from the third convolution layer may be input to the third head detection network. The health examination assisting device 100 performs a convolution operation of the first feature map and the second feature map in the second head detection network, and the result data of the convolution operation of the second head detection network in the third head detection network and A convolution operation between the third feature maps is performed, and the head included in the plurality of image frames is based on the output data of the first head detection network, the output data of the second head detection network, and the output data of the third head detection network. It is possible to generate a cluster analysis result by detecting.

The health examination assisting device 100 considers the number of human heads included in the cluster analysis result, the location information of checkpoints, the location information of CCTVs included in the image-related information, and the angle of view information of the CCTVs on the hospital map. As a result of mapping the location of the examinee on , it is possible to calculate the cluster of examiners for each examination center.

In step S630, the health checkup auxiliary device 100 uses the continuity information of the checkup items, the checkup time required for checkup for each checkup item, the travel time required for movement for each checkup center, and the cluster diagram to determine the checkup flow for each examinee. Make a plan.

The health checkup auxiliary device 100 generates a random checkup order using the continuity information of checkup items, and calculates the total checkup time by using checkup time, movement time, and clustering for each checkup item included in the random checkup order. , and it is possible to establish a checkup order in which the total checkup time is minimized as a checkup flow plan while repeatedly generating the checkup order.

In step S640, the health checkup assisting device 100 provides the first electronic device 200 equipped with the examiner with a checkup flow plan for each examinee and a checkup order for each checkup item included in the checkup flow plan.

In step S650, the health checkup auxiliary device 100 transmits the checkup order of waiting screeners and waiting screeners for each checkup center to the second electronic device 300 provided in the checkup center in response to the checkup order for each checkup item included in the checkup flow plan. to provide.

Embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed on a computer through various components, and such a computer program may be recorded on a computer-readable medium. At this time, the medium is a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. An example of a computer program may include not only machine language code generated by a compiler but also high-level language code that can be executed by a computer using an interpreter or the like.

In the specification of the present invention (particularly in the claims), the use of the term "above" and similar indicating terms may correspond to both singular and plural. In addition, when a range is described in the present invention, it includes an invention in which individual values belonging to the range are applied (unless there is a description to the contrary), and each individual value constituting the range is described in the detailed description of the invention Same as

The steps constituting the method according to the present invention may be performed in any suitable order unless an order is explicitly stated or stated to the contrary. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is simply to explain the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms unless limited by the claims. it is not going to be In addition, those skilled in the art can appreciate that various modifications, combinations and changes can be made according to design conditions and factors within the scope of the appended claims or equivalents thereof.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments and should not be determined, and all scopes equivalent to or equivalently changed from the claims as well as the claims described below are within the scope of the spirit of the present invention. will be said to belong to

100: health examination aid
200: first electronic device
300: second electronic device
400: network

Claims (11)

A method of assisting a health examination, wherein at least a portion of each step is performed by a processor, comprising:
collecting, by a collecting unit, information related to examination of the examinee, location information of examination stations for each examination item located in the hospital, and image-related information from CCTVs installed in the hospital;
calculating, by a calculation unit, a cluster degree of examinees for each examination center using the examination-related information, location information of the examination centers, and the image-related information;
The establishment unit uses the continuity information of examination items that structured the independence and dependency between examination items, the examination time required for each examination item, the travel time required for each examination center, and the cluster diagram to determine the examinee's Establishing a plan for each examination route;
providing, by a first providing unit, the examination flow plan for each examinee and the examination order for each examination item included in the examination flow plan to a first electronic device equipped with the examinee; and
and providing, by a second providing unit, a waiting examinee for each examination center and an examination order of the waiting examinee corresponding to the examination order to a second electronic device provided in the examination center.
Health screening aid method. According to claim 1,
In the step of calculating the population,
Using a neural network including a plurality of image frames including at least one human head included in the image-related information, a plurality of convolutional layers, and a plurality of head detection networks, Including generating a cluster analysis result,
Health screening aid method. According to claim 2,
The step of generating the cluster analysis result,
inputting the plurality of image frames to a neural network including the plurality of convolutional layers and the plurality of head detection networks;
The first feature map output from the first convolution layer is input to the first head detection network, the second feature map and the first feature map output from the second convolution layer are input to the second head detection network, and the third feature map is input to the second head detection network. inputting the third feature map and the second feature map output from the convolution layer to a third head detection network; and
The second head detection network performs a convolution operation of the first feature map and the second feature map, and the third head detection network performs a convolution operation result data of the second head detection network and the second head detection network. A convolution operation between 3 feature maps is performed, and the plurality of image frames are generated based on the output data of the first head detection network, the output data of the second head detection network, and the output data of the third head detection network. Detecting the included head to generate a cluster analysis result,
Health screening aid method. According to claim 2,
After the calculation unit generates the cluster analysis result, the number of heads included in the cluster analysis result, location information of the medical examination center, CCTV location information included in the image related information, and CCTV Calculating a cluster of examiners for each examination center as a result of mapping the examiner's location on the hospital map in consideration of the angle of view information,
Health screening aid method. According to claim 1,
The step of establishing a checkup movement plan for each examinee,
generating a random checkup sequence using continuity information of the checkup items;
calculating a total examination time by using the examination time, the movement time, and the cluster degree for each examination item included in the random examination sequence; and
Establishing a checkup order in which the total checkup time is minimized as a checkup circulation plan while repeatedly generating the checkup order,
Health screening aid method. A computer-readable recording medium storing a computer program for executing any one of the methods of claims 1 to 5 using a computer. As a device to assist in health checkup,
a collection unit that collects examination-related information of the examinee, location information of examination stations for each examination item located in the hospital, and image-related information from CCTVs installed in the hospital;
a calculation unit that calculates a population of examinees at each examination center by using the examination-related information, the location information of the examination centers, and the image-related information;
The continuity information of examination items that structured the independence and dependency between examination items, the examination time required for each examination item, the travel time required for each examination center, and the examination movement line for each examinee using the above cluster diagram Establishment department that draws up plans;
a first providing unit that provides a first electronic device equipped with the examiner with a checkup flow plan for each examinee and a checkup order for each checkup item included in the checkup flow plan; and
A second providing unit configured to provide a waiting examinee for each examination center and an examination order of the waiting examinee to a second electronic device provided in the examination center in correspondence with the examination sequence;
Health check-up aids. According to claim 7,
The calculator,
Using a neural network including a plurality of image frames including at least one human head included in the image-related information, a plurality of convolutional layers, and a plurality of head detection networks, Configured to generate a cluster analysis result,
Health check-up aids. According to claim 8,
The calculator,
inputting the plurality of image frames to a neural network including the plurality of convolutional layers and the plurality of head detection networks;
The first feature map output from the first convolution layer is input to the first head detection network, the second feature map output from the second convolution layer and the first feature map are input to the second head detection network, and the third feature map is input to the second head detection network. Inputting the third feature map and the second feature map output from the convolution layer to a third head detection network;
The second head detection network performs a convolution operation of the first feature map and the second feature map, and the third head detection network performs a convolution operation result data of the second head detection network and the second head detection network. A convolution operation between three feature maps is performed, and the plurality of image frames are generated based on the output data of the first head detection network, the output data of the second head detection network, and the output data of the third head detection network. configured to detect included heads to generate a cluster analysis result;
Health check-up aids. According to claim 8,
The calculator,
After generating the cluster map analysis result, considering the number of heads included in the cluster map analysis result, location information of the medical examination center, CCTV location information included in the image related information, and CCTV view angle information As a result of mapping the location of the examiner on the hospital map, it is configured to calculate the cluster of examiners for each checkup,
Health check-up aids. According to claim 7,
The establishment department,
generating a random checkup sequence using the continuity information of the checkup items;
Calculate a total examination time by using the examination time, the movement time, and the cluster degree for each examination item included in the random examination sequence;
It is configured to establish a checkup order in which the total checkup time is minimized as a checkup flow plan while repeatedly generating the checkup order.
Health check-up aids.

Images