KR102123112B1 - System and method for managing hospital asset - Google Patents

Abstract

Disclosed are a system for managing hospital assets and a method thereof. According to an embodiment, the system for managing hospital assets allows a hospital asset management system user to scan, with a hospital asset management terminal, surface QR codes of target hospital products and devices, allows the hospital asset management terminal to generate a first input signal based on a scan result, allows the hospital asset management terminal to input the first input signal to a pre-learned convolutional neural network in a blockchain network through a high-speed Internet connection network, allows a second network storage device among network storage devices on the blockchain network to acquire a first output signal based on an input to the convolutional neural network, allows the network storage devices to transmit the first output signal to the hospital asset management terminal, allows the hospital asset management terminal to output hospital asset information to the monitor of the hospital asset management terminal based on the transmitted first output signal, allows the second network storage device to generate a first order signal for an insufficient inventory of products and devices based on the first output signal of the convolutional neural network, and allows the second network storage device to share the first input signal, the first output signal, a use record for the convolutional neural network, and the first order signal with the first network storage device and a third network storage device through the blockchain network. Therefore, the system and the method can safely manage hospital assets by using deep-learning technology.

Description

Hospital asset management system and method{SYSTEM AND METHOD FOR MANAGING HOSPITAL ASSET}

The embodiments below relate to a hospital asset management system.

The management of hospital assets is generally done manually by humans, and even when it is done automatically, the problem of unauthorized removal of assets continues due to security gaps. Orders were placed manually even for insufficient inventory, which required a lot of manpower to manage the necessary assets. Therefore, it is necessary to study technology to make asset management transparent and safe using strong security programs such as blockchain networks, and to automatically place orders while holding asset management information as big data.

KR101946196 KR1020080015974 KR1020190014223 KR1020190069655

The embodiments are intended to safely manage hospital assets by applying deep learning technology to a hospital asset management system.

The embodiments are intended to enable comprehensive management of assets based on QR code information storage capabilities.

The embodiments are intended to facilitate user-based asset management through the use of a hospital asset management terminal.

The embodiments intend to make information big data through a blockchain network and use the security that has been revoked.

Hospital asset management system according to an embodiment of the hospital asset management system users target hospital products and devices-the products and devices include drugs, medical instruments, disposable treatment tools, office supplies and electronic devices-the surface QR code for hospitals Scanning with an asset management terminal; Generating a first input signal by the hospital asset management terminal based on the scan result; Inputting the first input signal into the pre-trained convolutional neural network in the blockchain network through the high-speed Internet connection network by the asset management terminal for hospital; Obtaining a first output signal by a second network storage device among network storage devices of the blockchain network based on an input of the convolutional neural network; The network storage devices transmitting the first output signal to the hospital asset management terminal; Based on the first output signal transmitted by the hospital asset management terminal, the hospital asset information-the hospital asset information includes the database search result of the QR code search information, the location of the asset, the current inventory amount, the order quantity, the order arrival Outputting a day, a scheduled arrival date, a risk level, and automatic order information to a monitor of a hospital asset management terminal; Generating, by the second network storage device, a first order signal for the product and device of insufficient inventory based on the first output signal of the convolutional neural network; The second network storage device sharing the first input signal, the first output signal, the usage record of the convolutional neural network, and the first order signal through the blockchain network with the first and third network storage devices It can contain.

According to one embodiment, the QR code is divided into second to ninth by moving the upper left to the first division, moving to the right and downward based on two virtual horizontal lines and two virtual vertical lines that divide the QR code into 9 equal parts. The first division is divided into, and contains the main category search information of the target product and device; A second segment containing mid-class search information of the target product and device; A third segment containing sub-class search information of the target product and device; A fourth division containing search information of a manufacturing company of the target product and device; A fifth division containing search information for manufacturing time of the target product and device; A sixth division containing search information for expiration dates of the target products and devices; A seventh division containing risk level search information of the target product and device; An eighth division containing price search information of the target product and device; And a ninth segment containing automatic connection information of the blockchain network of the target product and device.

According to one embodiment, the asset management terminal for the hospital is a camera that can read the QR code; A monitor that displays the camera screen of the QR code and asset information for the hospital of the product and device; And an embedded computer that encodes a first input signal from the QR code and outputs the hospital asset information from a first output signal, and the user first selects one of three modes of inventory management, use and disposal. Then, modify the content of the information included in the first input signal according to the selected mode, the first input signal includes the QR code and the user information of the hospital asset management terminal, and the inventory quantity according to the selected mode It may include information such as whether it is changed, used, and discarded, and may include information about problem products and devices due to theft and unspecified use.

According to one embodiment, the blockchain network includes blocks including the database including the hospital products and devices and the pre-trained convolutional neural network dealing with the database; Chains connecting each block in chronological order; And the network storage devices storing the respective blockchains, the network storage devices comprising: a first network storage device including manufacturing companies of the target products and devices; The second network storage device including a hospital using the target products and devices; A third network storage device including a public institution associated with the target products and devices; And a high-speed Internet connection network connecting each network storage device.

According to an embodiment, the convolutional neural network uses the first input signal generated by encoding of the terminal to the surface QR code of the target product and device as an input, and includes the hospital asset information. With the output signal as an output, learning by receiving the learning signal from the network storage devices, learning the danger and abuse of the target product and device based on the learning result, and learning the time of order for the insufficient material An apparatus according to an embodiment of automatically generating the first output signal including order information and storing the information according to the learning result as big data in the database is combined with hardware, and any one of the methods described above It can be controlled by a computer program stored in the medium in order to execute the method of claim.

The apparatus according to an embodiment may be controlled by a computer program stored in a medium in order to execute the method of any one of the above-described methods in combination with hardware.

Embodiments can safely manage hospital assets by applying deep learning technology to a hospital asset management system.

Embodiments may enable comprehensive management of assets based on the ability to store information in QR codes.

Embodiments may facilitate user-based asset management through the use of a hospital asset management terminal.

Embodiments can make the information big data through the blockchain network and use the security that has been revoked.

1 is a flowchart illustrating a hospital asset management system according to an embodiment.
2 is a view for explaining the surface QR code of the hospital products and devices according to an embodiment.
3 is a view for explaining a hospital asset management terminal according to an embodiment.
4 is a diagram for explaining a blockchain network according to an embodiment.
5 is a diagram for describing a convolutional neural network according to an embodiment.
6 is an exemplary view of a configuration of an apparatus according to an embodiment according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, various changes may be made to the embodiments, and the scope of the patent application right is not limited or limited by these embodiments. It should be understood that all modifications, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosure form, and the scope of the present specification includes modifications, equivalents, or substitutes included in the technical spirit.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from other components. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When an element is said to be "connected" to another element, it should be understood that other elements may be present, either directly connected to or connected to the other element.

The terms used in the examples are used for illustrative purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, the terms "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts or combinations thereof described herein, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person skilled in the art to which the embodiment belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having meanings consistent with meanings in the context of related technologies, and should not be interpreted as ideal or excessively formal meanings unless explicitly defined in the present application. Does not.

In addition, in the description with reference to the accompanying drawings, the same reference numerals are assigned to the same components regardless of reference numerals, and redundant descriptions thereof will be omitted. In describing the embodiments, when it is determined that detailed descriptions of related known technologies may unnecessarily obscure the subject matter of the embodiments, detailed descriptions thereof will be omitted.

Embodiments may be implemented in various types of products, such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent cars, kiosks, and wearable devices.

1 is a flowchart illustrating a hospital asset management system according to an embodiment.

According to one embodiment, a user of a hospital asset management system may scan a surface QR code of a target hospital product and device with a hospital asset management terminal (101). The control device is a device for controlling a mechanical construction process, and may be implemented by, for example, a software module, a hardware module, or a combination thereof.

Products and devices according to one embodiment may include pharmaceuticals, medical instruments, disposable treatment tools, office supplies and electronic devices.

The medicament according to one embodiment includes, but is not limited to, drugs for oral administration, injection and application. Drugs include, but are not limited to, autonomic nervous system, cardiovascular system, respiratory system, digestive system, musculoskeletal system, central nervous system, endocrine system, urogenital system, skin system, infectious diseases and anti-cancer drugs, and other treatments used in hospitals It can be seen by those of ordinary skill in the health and medical field that it may be a drug.

Medical devices according to an embodiment include, but are not limited to, injection syringes, forceps, scalpels, forceps, Kelly, tweezers, retractors, scissors, mirrors and probes, and may be other medical devices used in hospitals. Anyone with ordinary knowledge in the field of medical health can know.

Disposable treatment tools according to an embodiment include, but are not limited to, bandages, gauze, bands, blades, injection needles, disposable endoscope tools, sutures and sutures, and may be other disposable treatment tools used in hospitals. Anyone with ordinary knowledge in the field of medical health can know.

Office supplies according to an embodiment include, but is not limited to, files, paper, pens, sharps, erasers, rulers, correction tapes, clipboards, scissors, glue, tapes, protractors, and compasses, and other office supplies used in hospitals Anyone with ordinary knowledge in the field of medical health can know.

According to one embodiment, the electronic device may be a smart home appliance with a communication function. For smart household appliances, for example, electronic devices are televisions, digital video disk (DVD) players, audio, refrigerators, air conditioners, cleaners, ovens, microwave ovens, washing machines, air cleaners, set-top boxes, TVs. It may include at least one of a box (eg, Samsung HomeSyncTM, Apple TVTM, or Google TVTM), game consoles, electronic dictionary, electronic key, camcorder, or electronic picture frame.

According to an embodiment, the electronic device includes various medical devices (eg, magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), computed tomography (CT), photographing device, ultrasound device, etc.), navigation device, GPS receiver ( Global positioning system receiver (EDR), event data recorder (EDR), flight data recorder (FDR), automotive infotainment devices, marine electronic equipment (e.g. marine navigation devices and gyro compasses, etc.), avionics, security It may include at least one of a device, a head unit for a vehicle, an industrial or household robot, an automatic teller's machine (ATM) of a financial institution, or a point of sales (POS) of a store.

According to one embodiment, the electronic device is a furniture or part of a building/structure including a communication function, an electronic board, an electronic signature receiving device, a projector, or various measurement devices. It may include at least one of a device (for example, water, electricity, gas, or radio wave measurement devices). The electronic device according to an embodiment may be a combination of one or more of the various devices described above. Also, the electronic device according to an embodiment may be a flexible device. Also, it is apparent to those skilled in the art that the electronic device according to an embodiment is not limited to the above-described devices. The term user used in various embodiments may refer to a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).

An electronic device according to an embodiment includes a processor, a memory, a user interface, and a communication interface, and may be connected to another electronic device through a network. The communication interface may transmit and receive data to and from other electronic devices within a predetermined distance through a wired, wireless network, or wired serial communication. The network enables wired and wireless communication between electronic devices and various entities according to an embodiment. The electronic device can communicate with various entities over the network, and the network can use standard communication technologies and/or protocols. At this time, the network (network) includes, but is not limited to, the Internet (Internet), a local area network (LAN), a wireless local area network (LAN), a wide area network (WAN), a personal area network (PAN), and the like. Anyone who has ordinary knowledge in the field of communication technology can know that it can be another kind of network that can transmit and receive information.

QR code according to an embodiment is a medium for storing information in a two-dimensional form of length and width, to facilitate the representation and reading of data, a Quiet Zone, a position detection pattern, a timing pattern, an alignment pattern, format information, version information, It can be divided into areas such as data areas. A typical QR code can contain up to 7089 characters, up to 4296 alphanumeric characters, up to 2953 bytes in 8-bit bytes, and 1817 characters in Chinese characters. The QR code for the hospital asset management system will be described later with reference to FIG. 2.

The asset management terminal for a hospital according to an embodiment may be an electronic device including a communication function. For example, the electronic device includes a smart phone, a tablet personal computer (PC), a mobile phone, a video phone, an e-book reader, a desktop personal computer (PC), and a laptop. Laptop personal computer (PC), netbook computer, personal digital assistant (PDA), portable multimedia player (PMP), MP3 player, mobile medical device, camera, or wearable device (e.g. It may include at least one of a head-mounted-device (HMD) such as electronic glasses, an electronic garment, an electronic bracelet, an electronic necklace, an electronic appcessory, an electronic tattoo, a smart car, or a smart watch. Can be.

According to an embodiment, based on the scan result, the asset management terminal for hospital may generate a first input signal (102).

The first input signal according to an embodiment is a signal for input to a pre-learned convolutional neural network, and may be a result of encoding a QR code of a result scanned through a hospital asset management terminal into a binary signal. The process of encoding a binary signal by the hospital asset management terminal based on the QR code will be described later with reference to FIGS. 2 and 3.

According to one embodiment, the hospital asset management terminal may input the first input signal to the pre-trained convolutional neural network in the blockchain network through the high-speed Internet connection network (103).

The high-speed Internet connection network according to an embodiment generally refers to an Internet connection network having a speed of 10 Mb/s or more, and a method using a WIFI environment and a dedicated communication network may be used.

The convolutional neural network according to an embodiment includes a feature extraction neural network and a classification neural network, and the feature extraction neural network proceeds by sequentially stacking an input signal with a convolutional layer and a pooling layer. The convolution layer includes a convolution operation, a convolution filter, and an active function. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. The active function generally uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The pooling layer is a layer that serves to reduce the matrix size of the input, and uses a method of extracting a representative value by grouping pixels in a specific area. In the calculation of the pooling layer, an average value or a maximum value is generally used, but is not limited thereto. The operation is performed using a square matrix, and generally, a 9X9 matrix is used. The convolutional layer and the pooling layer are alternately repeated until the input is small enough while maintaining the difference.

According to one embodiment, the classification neural network has a hidden layer and an output layer. In the convolutional neural network for the asset management system for hospitals, there are generally three or more hidden layers, and each hidden layer has 100 nodes, but it can be set to more than that in some cases. The active function of the hidden layer uses a ReLU function, a sigmoid function, and a tanh function, but is not limited thereto. The output layer node of the convolutional neural network can be 5 in total. The output layer activation function of the classification neural network uses a softmax function. The softmax function is a representative function of one-hot encoding. It is a function that makes the sum of all output nodes total 1, sets the output of the output node with the largest value to 1, and the output of the remaining output nodes to 0. . It is possible to select only one of the five outputs through the Softmax function.

The blockchain network according to an embodiment includes blocks storing a database and a chain connecting them in chronological order, and the database may store search results of search information indicated by the QR code in a table format. The stored database is managed as big data, and the blockchain network can help securely store the information in this database and make it available to limited users. The description of the blockchain network and the convolutional neural network will be described later with reference to FIGS. 4 and 5.

The second network storage device among the network storage devices of the blockchain network may acquire a first output signal based on the input of the convolutional neural network (104).

According to an embodiment, the convolutional neural network may have five outputs, each of which may be suitable for use, need for attention, forbidden to use, need to order, and need to order. The first output signal may include one of five outputs and at the same time may include a database search result based on the first input signal. The database search results may include major classification, medium classification, small classification, manufacturing company information, manufacturing time information, expiration date, risk level information, and price information of target hospital products and devices. It may include information such as inventory, order quantity, order arrival date, and order arrival date.

According to one embodiment, the network storage devices may transmit the first output signal to the hospital asset management terminal (105).

Network storage devices according to an embodiment may be an electronic device including a memory. This may include, but is not limited to, computers, laptops, smart phones, and portable terminals. The network storage devices may transmit the first output signal to the hospital asset management terminal simultaneously with the generation of the first output signal, wherein the network storage device is one or all of the first, second, and third network storage devices. Can be. Typically, communication with the asset management terminal for the hospital can be achieved through a second network storage device.

According to an embodiment, the hospital asset management terminal may output the hospital asset information to the monitor of the hospital asset management terminal based on the transmitted first output signal (106).

Asset information for hospitals according to an embodiment may include a database search result of QR code search information, the location of the asset, current inventory quantity, order quantity, order arrival date, expected order arrival date, risk level, and automatic order information.

The monitor of the asset management terminal for a hospital according to an embodiment may be any one of LCD, LED, OLED, and QLED displays, but is not limited thereto. The resolution of the monitor is generally 1334 X 750 pixels to 2436 X 1125 pixels, but is not limited thereto.

According to one embodiment, the second network storage device may generate a first order signal for products and devices of insufficient inventory based on the first output signal of the convolutional neural network (107).

According to one embodiment, the second network storage device is a network storage device of a hospital that actually uses a target product and device, and is connected to a hospital asset management terminal and a high-speed Internet connection network. When the second network storage device acquires the order-required signal from the first output signal, the second network storage device may generate the first order signal and automatically process the order of insufficient products and devices.

According to an embodiment, the second network storage device may share the first input signal, the first output signal, the usage record of the convolutional neural network, and the first order signal through the blockchain network with the first and third network storage devices. Yes (108).

According to one embodiment, the type of the signal transmitted from the second network includes a first input signal, a first output signal, a convolutional neural network usage record, a first order signal, etc., and each network storage device is based on these signals. The formed blocks can be created and verified. The first order signal may be delivered to a user of the first network storage device to form an order record. The use record of the convolutional neural network can enable the user to manage and record whether to use the hospital asset management terminal.

According to one embodiment, the asset management system for hospitals can safely manage the assets for hospitals by applying deep learning technology.

2 is a view for explaining the surface QR code of the hospital products and devices according to an embodiment.

According to one embodiment, the QR code is divided into the first upper part of the first left 201, based on two virtual horizontal lines and two virtual vertical lines that divide the QR code into 9 equal parts, and moves to the right and downward to the second 202. The first division 201 is divided into the ninth division 209, and contains the large category search information of the target product and device; A second division (202) containing mid-class search information of target products and devices; A third division (203) containing sub-class search information of the target product and device; A fourth division 204 containing search information of a manufacturer of a target product and device; A fifth division (205) containing search information of a manufacturing time of the target product and device; A sixth division 206 containing search information for expiration dates of target products and devices; A seventh division (207) containing risk level detection information of target products and devices; An eighth division 208 containing price search information of target products and devices; And a ninth division 209 containing automatic connection information of the blockchain network of the target product and device.

The first division 201 according to an embodiment may include large-class search information of a target product and device. The large category search information may be information indicating whether the target product and device belong to any one of drugs, medical instruments, disposable treatment tools, office supplies, and electronic devices.

The second division 202 according to an embodiment may include middle classification search information of a target product and device. If the target product and device belong to the drug, any of the autonomous nervous system, cardiovascular system, respiratory system, digestive system, musculoskeletal system, central nervous system, endocrine system, urogenital system, skin system, infectious diseases and anticancer drugs It may include whether it belongs to one. The classification information may include whether the target product and device belong to any one among a syringe, forceps, scalpel, forceps, kelly, tweezers, retractor, scissor, mirror, and probe when the device belongs to a medical device. The middle class search information may include, if the target product and device belong to a disposable treatment tool, one of a bandage, a gauze, a band, a mesh blade, an injection needle, a disposable endoscope tool, a suture and a suture needle. The middle class search information may include, if the target product and device belong to office supplies, the product belongs to one of writing instruments, storage irons, drawing tools, and manufacturing tools. If the target product and device belong to an electronic device, the electronic device is classified into a home appliance, medical device, navigation device, GPS receiver, EDR, car infotainment device, ATM in financial institution, and industrial or household robot. It may include whether it belongs.

The third division 203 according to an embodiment may contain sub-class search information of a target product and device. The sub-class search information is search information belonging to the middle class, for example, the target product and device are drugs in the large category. In the case of the cardiovascular system in the middle class, the small class search information may include information such as antihypertensives, antiarrhythmic agents, anticoagulants, and vasodilators. have. For example, if the target product and device are medical devices in a large category, and if they correspond to forceps in a medium category, the small category search information may include information such as tissue forcep, Adison forcep, and sponge forcep. Even when other medium classification search information corresponds to disposable treatment tools, office supplies, and electronic devices, the small category search information may include specific level of product and device information.

The fourth division 204 according to an embodiment may contain search information of a manufacturing company of a target product and device. Manufacturing company search information is search information that can search for information of a company that manufactured a target product and device, and contains information for classifying different products for each manufacturing company even in products having the same function on a small category.

The fifth division 205 according to an embodiment may include search information of a target product and a manufacturing time of the device. Manufacturing time search information is information that can search for the date of manufacture of the target product and device, and may include specific time information.

The sixth division 206 according to an exemplary embodiment may include search information for expiration dates of target products and devices. Based on the search results of the database through the search period for the target products and devices, information such as the use of the first output signal may contain information such as suitable use, caution, and prohibition of use. However, this may not be the case in all cases including information such as prohibition of use.

The seventh division 207 according to an embodiment may include risk level detection information of a target product and device. Based on the search result of the database through the risk level search information of the target product and device, information such as suitable for use, need for attention, and prohibition of use may be included in the first output signal, but the first output signal is suitable for use and needs attention However, this may not be the case in all cases including information such as prohibition of use. In addition to the search results of risk level search information, criteria that divide risk levels from 0 to 5 can be adopted. In this case, risk level 0 is always safe, risk level 1 is safety when used by a person or person with a healthy body, risk level 2 is slightly attention when used by a person or person with a healthy body, risk level 3 Can mean unusable to a person or person with an unhealthy body, risk level 4 means high caution when using it to a person or person with a healthy body, and risk level 5 means absolute use.

The eighth division 208 according to an embodiment may include price search information of a target product and device. The price search information of the target products and devices allows information stored in the database to be searched in advance, but the database can be updated in real time through a network. Price information corresponding to the price search information may be displayed in won or dollars, but is not limited thereto.

The ninth division 209 according to an embodiment may contain automatic connection information of a blockchain network. Target products and devices with automatic connection information of the blockchain network can be connected to the blockchain network by forming a first input signal immediately upon scanning to the hospital asset management terminal. Conversely, even if the search information included in the first 201 to eighth divisions 208 is elaborated, if the ninth division 209 is incorrect, searching through a blockchain network may not be possible.

The QR code according to an embodiment may be encoded with information included in the first 201 to ninth divisions 209 into search information expressed in binary through a hospital asset management terminal. The asset management system for hospitals can enable comprehensive management of assets based on the ability to store information in QR codes.

3 is a view for explaining a hospital asset management terminal according to an embodiment.

Referring to FIG. 3, the hospital asset management terminal includes a camera 301 capable of reading a QR code; A monitor 302 displaying a camera screen of a QR code and asset information for hospitals of products and devices; It may include an embedded computer that encodes the first input signal from the QR code and outputs hospital asset information from the first output signal to the monitor.

According to one embodiment, the camera 301 may be used for photographing a QR code. When the user places the QR code at a designated location through the monitor, the QR code can be automatically read to encode the first input signal. Encoding the first input signal may include converting information of the QR code into a binary signal. The binary signal can be generated as a matrix of 0 and 1, and the matrix can be generated separately for each division.

According to one embodiment, the user may first select one of three modes: inventory management 303, use 304, and disposal 305. When the user selects the inventory management 303 mode, only the function of searching and adding inventory information on the database in the blockchain network can be used. The method of reducing the amount of inventory on the database can only be done through the use 304 mode or the discard 305 mode. When the user selects the use 304 mode, the user may take a QR code with the camera of the hospital asset management terminal, and at the same time, the usage record for one inventory may be stored in the database. The used target products and devices cannot be added again through the inventory management 303 mode. When receiving a QR code search result and an unusable output result in the inventory management 303 mode, the corresponding product and device may be discarded. Disposal of the product and device can be performed by selecting the discard (305) mode, and the discard (305) mode allows the user to take a QR code with the camera of the hospital's asset management terminal, and for one inventory on the database. Discard records can be stored. The obsolete products and devices cannot be added again through the inventory management 303 mode. Each mode is designed for user convenience, and the system can be updated to reflect the user's convenience.

According to one embodiment, the first input signal may generate a limited form of the first input signal according to the selection of the inventory management 303, use 304, and discard 305 modes. The first input signal includes the user information 306 of the hospital asset management terminal, so that it is possible to store information capable of backtracking who has performed inventory management, use, and disposal in the database of the blockchain network. The user can register the information of the product and device in question due to theft and unspecified use through the QR code corresponding to the QR code of the corresponding product and device. The registration may be made through information included in the first input signal, and may be used for discovery of the product and device in question in the future. According to one embodiment, the use of a hospital asset management terminal may facilitate user-based asset management.

4 is a view for explaining a blockchain network according to an embodiment.

Referring to FIG. 4, the blockchain network includes blocks 401 including a database including hospital products and devices and a pre-trained convolutional neural network dealing with the database; Chains 402 connecting each block 401 in chronological order; And a first 410, a second 420, and a third network storage 430 for storing each blockchain.

According to an embodiment, the block 401 of the blockchain network may include a database storing search results of the search information indicated by the QR code in a table format and a pre-trained convolutional neural network handling the same. Each block 401 is generally connected in chronological order, so that new blocks 401 can be produced at 10 minute intervals. The contents of the already generated block 401 are stored in all network storage devices, and cannot be changed unless the majority of the contents are changed in time. For example, in a blockchain network having a total of 3 network storage devices, when it is assumed that there is one block 401 for each network storage device, if the contents of two or more blocks 401 cannot be changed within a limited time, Each block 401 may change the value of the block 401 having a different content from the majority to be equal to the majority by verification. Accordingly, it is possible to maintain high security. In fact, the number of network storage devices participating in the blockchain network may reach tens to hundreds of thousands, and thus, it may exhibit higher security.

Chains 402 according to an embodiment may be configured with a hash value. The chains 402 allow the blocks 401 to be consecutive in chronological order, and each block 401 can be connected using a hash value. In block 401, a database and a hash value of the database, a previous header, and a header of the current block may be stored. Here, the header of the current block functions as a previous header in the next block, so that each block 401 can be organically connected. In addition, the hash value is transformed into a completely different form when the contents of the block are changed even a little, which effectively prevents an attempt to change the contents of the database. Since the header of the current block becomes the total hash value including the database, the hash value of the database, and the previous header, it is difficult to successfully attempt to compromise security by effectively modifying the database and the hash value. Because, when the database and hash values are modified, the contents of the header are changed, and accordingly, the previous header that enters the next block is also changed, and accordingly, the header of the block is also changed, so that the previous header of the next block can be changed again. That is, all subsequent blocks 401 must be hacked. Therefore, it is possible to increase the security of the blockchain with the chain 402 through the hash value.

According to an embodiment, the network storage devices include a first network storage device 410 including manufacturing companies of target products and devices; A second network storage device 420 including a hospital using target products and devices; A third network storage device 430 including a public institution related to target products and devices; And a high-speed Internet connection network 403 connecting each network storage device. The first, second, and third network storage devices may be determined according to the number of practitioners included, the number of users, and the number of storage devices.

According to an embodiment, the first network storage device 410 may include manufacturing companies of the target products and devices, and the manufacturing companies of the target products and devices may be one or more, and storage used by each company The number can be determined by the number of devices. The first network storage device 410 may process an order received through the first order signal.

According to one embodiment, the second network storage 420 may include a hospital using target products and devices. The second network storage device 420 is a network storage device that is closest to users who use a hospital asset management terminal, and provides an environment that can maximize the function of a database in a blockchain network and a convolutional neural network handling the same. can do. The second network storage device 420 may generate a first order signal based on the first output signal, and may be a central subject that exchanges signals with the first (410) and third (430) network storage devices. have.

According to an embodiment, the third network storage device 430 may include a public institution related to target products and devices. The third network storage device 430 may include public institutions related to medical and health in general, and through the participation of public institutions, it can be ensured whether the hospital is transparently managed and safely managed. The user of the third network storage device 430 is an organization that tracks a product that has been discarded, a problem product due to theft and unspecified use, and can track it based on a record on the database of the blockchain network. The asset management system for hospitals can make information big data through the blockchain network and use the security that has been withdrawn.

The high-speed Internet connection network 403 according to an embodiment is a connection network including wired, wireless, and optical cable technologies, such as a local area network (LAN), a wireless local area network (LAN), a wide area network (WAN), and a personal area network (PAN). Area Network) and the like.

5 is a diagram for describing a convolutional neural network according to an embodiment.

Blocks according to an embodiment may include a pre-trained convolutional neural network, the convolutional neural network as a first input signal 501 generated by the encoding of the terminal to the surface QR code of the target product and device, , A first output signal 502 including hospital asset information may be used as an output.

According to an embodiment, the convolutional neural network may learn to output search information in the database from search information of the QR code in the database. The pre-trained artificial neural network has 3 or more hidden layers, and each hidden layer may have 50 or more hidden nodes. ReLU function, sigmoid function and tanh function can be used as the active function of each hidden node, but is not limited thereto. As a function of the output node, a softmax function using one-hot encoding can be used. The output selects only one classification according to the one-hot encoding technique, and can execute commands from the selected classification.

According to one embodiment, the first output signal 502 of the convolutional neural network is a search information result in a database for search information of a QR code, a learning result of the convolutional neural network for a learning signal, and an order for generating a first order signal It may include a result containing information on the quantity and time of order.

According to an embodiment, the first order signal may be a signal generated by the second network storage device based on the order quantity and the time of order of the insufficient material in the first output signal 502. Accordingly, the first output signal 502 may include an order quantity and an order point of insufficient material based on a database inquiry result. The method of determining the order quantity and the time of order of the material lacking the first output signal 502 is achieved through learning of the convolutional neural network. The network storage devices generate a learning signal 503 reflecting the frequency of orders and the average inventory quantity based on the database, so that learning of the convolutional neural network can be achieved.

According to an embodiment, the convolutional neural network may learn by receiving a learning signal 503 from network storage devices. Users of the network storage devices may store information on the result of the use of the target product and device in the hospital asset management terminal, and the network storage devices may generate a learning signal 503 based on the storage result. For example, when the risk of the drug is set to a low level on the information in the provided database, it can be generated a learning signal 503 including such content if it is found that various side effects or strong toxicity are found as a result of use in an actual hospital. have. In this example, according to the learning result of the convolutional neural network according to the learning signal 503, it can be modified to set a high risk on the database. Accordingly, the convolutional neural network can learn the risk and abuse of the target product and device based on the learning result.

The learning signal 503 according to an embodiment is made based on an error between a correct answer and an output value. In some cases, an SGD using a delta, a batch method, or a method using a back propagation algorithm may be used. The convolutional neural network performs learning by modifying an existing weight by the learning signal 503, and may use momentum in some cases. The cost function can be used to calculate the error, and the cross entropy function can be used as the cost function.

According to one embodiment, the database may store information as big data, and may be continuously updated through a high-speed Internet connection network connected to a blockchain network. Therefore, whenever the use of the target product and device is changed due to a change in policy, a violation of medical law, or a change in a hospital account, the change can be reflected in real time.

6 is an exemplary view of a configuration of an apparatus according to an embodiment.

The device 1201 according to an embodiment includes a processor 1202 and a memory 1203. The device 1201 according to an embodiment may be the above-described server or terminal. The processor may include at least one device described above with reference to FIGS. 1 to 5, or may perform at least one method described above with reference to FIGS. 1 to 5. The memory 1203 may store information related to the above-described method or a program implemented with the above-described method. The memory 1203 may be volatile memory or nonvolatile memory.

According to an embodiment, the processor 1202 may execute a program and control the device 1201. The code of the program executed by the processor 1202 may be stored in the memory 1203. The device 1201 is connected to an external device (for example, a personal computer or a network) through an input/output device (not shown) and can exchange data.

The embodiments described above may be implemented by hardware components, software components, and/or combinations of hardware components and software components. For example, the devices, methods, and components described in the embodiments include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors (micro signal processors), microcomputers, and field programmable gates (FPGAs). It can be implemented using one or more general purpose computers or special purpose computers, such as arrays, programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

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

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described by the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (5)

In the method of managing assets for hospitals based on artificial intelligence,
Scanning the QR code on the surface of the hospital's asset management system by the user of the hospital's asset management system, the target hospital product and device-the product and device comprising a medicament, medical device, disposable treatment tool, office supplies and electronic device;
Generating a first input signal by the hospital asset management terminal based on the scan result;
Inputting the first input signal into the pre-trained convolutional neural network in the blockchain network through the high-speed Internet connection network by the asset management terminal for hospital;
Obtaining a first output signal by a second network storage device among network storage devices of the blockchain network based on an input of the convolutional neural network;
The network storage devices transmitting the first output signal to the hospital asset management terminal;
Based on the first output signal transmitted by the hospital asset management terminal, the hospital asset information-the hospital asset information includes the database search result of the QR code search information, the location of the asset, current inventory, order quantity, order arrival date Outputting the order arrival date, the risk level and the automatic order information to a monitor of the hospital asset management terminal;
Generating, by the second network storage device, a first order signal for the product and device of insufficient stock based on the first output signal of the convolutional neural network;
The second network storage device sharing the first input signal, the first output signal, the usage record of the convolutional neural network, and the first order signal through a blockchain network with the first and third network storage devices
Including,
Generating the first input signal based on the scan result is
Dividing the QR code into 9 segments, dividing the upper left into a first segment based on two virtual horizontal lines and two virtual vertical lines, and moving the right and downward segments into second to ninth segments;
Encoding the classification information of the products and devices contained in the first segment into a matrix corresponding to the binary signal, and encoding the classification information of the products and devices contained in the second segment into the matrix corresponding to the binary signal. And encodes subclass search information of the products and devices contained in the third segment into a matrix corresponding to a binary signal, and searches manufacturer information of the products and devices contained in the fourth segment corresponding to a binary signal. Encoding into a matrix, encoding the product and device manufacturing time search information contained in the fifth segment into a matrix corresponding to a binary signal, and binary expiration search information of the product and device contained in the sixth segment Encoding into a matrix corresponding to a signal, encoding the risk level search information of the products and devices contained in the seventh segment into a matrix corresponding to a binary signal, and price searching information of the products and devices contained in the eighth segment Is encoded in a matrix corresponding to a binary signal, and the automatic connection information of the blockchain network of the product and device contained in the ninth division-information included in the first to eighth divisions is stored in the automatic connection information. Encoding the retrieved from the blockchain network by a matrix corresponding to a binary signal;
Generating the first input signal corresponding to the pre-trained convolutional neural network based on a binary signal according to an encoding result of the first to ninth divisions
Receiving one of the modes of inventory management, use, and disposal from the user;
If the mode of inventory management is selected, generating a first input signal limited to searching and adding inventory information to the database in the blockchain network;
If the mode of use is selected, generating a first input signal limited to storing usage records of inventory of the target hospital product and device on the database; And
When the mode of revocation is selected, a revocation record of the inventory of the target hospital product and devices on the database-information corresponding to the revocation record cannot be added back to the database by the inventory management mode- Generating a first input signal limited to storing
Including,
Acquiring the first output signal is
Applying the first input signal generated based on the QR code to the convolutional neural network, thereby obtaining a first output including information on use suitability, attention required, use prohibited, order required and order unnecessary;
By applying the first input signal generated based on the QR code to the convolutional neural network, large classification, medium classification, small classification, manufacturing company information, manufacturing time information, expiration date information, risk level information of a target hospital product and device, Obtaining a second output including price information, location of target products and devices, current inventory quantity, order quantity, order arrival date and order arrival date information; And
Obtaining the first output signal corresponding to the hospital asset information based on the first output and the second output.
Including,
The convolutional neural network is learned by learning signals according to information including risks of the products and devices on the database and side effects information corresponding to the use result,
The first order signal is generated based on the first output signal generated by the convolutional neural network previously learned to determine the product and device of the shortage inventory,
The convolutional neural network is trained by a learning signal generated based on the order frequency and average inventory quantity on the database,
How to manage hospital assets.
delete delete delete delete

Images