Medical care intelligent drying oven fused with AI picture recognition and application control method of medical care intelligent drying oven

Abstract

The invention relates to an AI picture recognition fused intelligent drying oven for medical care and an application control method thereof.By means of the AI picture recognition fused intelligent drying oven for medical care, basic information, including pictures, names, recommended drying oven temperature and recommended drying oven time, of to-be-placed medical care instruments can be input in advance and stored in a storage; when a to-be-placed medical instrument is placed, AI identification can be carried out on the collected image information Pic-a of the current to-be-placed medical instrument, a corresponding identification result is output, and the controller opens the corresponding drying unit according to the identification result and carries out drying according to the preset temperature and time. Therefore, conditions such as misplacement of nurses can be avoided, orderly management of medical facilities is facilitated, automatic drying of corresponding instruments can be realized, the occurrence rate of misplacement of the instruments in a drying oven is reduced, property loss of hospitals is reduced, and operation efficiency is greatly improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of medical and nursing equipment, and particularly to a smart oven for medical and nursing use integrating AI image recognition, an application control method thereof, and an electronic device. Background Art

[0002] As shown in the attached Figure 1 The medical and nursing oven is mainly used for drying medical and nursing instruments and medical facilities (medical and nursing instruments). Usage scenarios of the medical and nursing oven: After the medical and nursing items are cleaned in the cleaning room, the nurse needs to open the oven and put the medical and nursing items in; after drying, open the oven and take out the items.

[0003] Generally, there are about 5-10 ovens in the hospital supply room, and corresponding temperatures are set on the ovens. And it is crucial to put the items into the oven at the correct temperature. Low-temperature items are prohibited from being put into a high-temperature oven, as they will melt; precision instruments such as lenses are prohibited from being put into the oven, as the lenses will be damaged.

[0004] In actual applications, because there are a variety of medical and nursing instruments, it is difficult for nurses to remember the oven positions where these medical and nursing instruments should be placed and their working parameters, which often leads to problems such as misplacement and omission. In severe cases, precision instruments such as lenses will be lost, causing losses to the hospital. Summary of the Invention

[0005] To solve the above problems, the present application proposes a smart oven for medical and nursing use integrating AI image recognition, an application control method thereof, and an electronic device.

[0006] On the one hand, the present application proposes a smart oven for medical and nursing use integrating AI image recognition. The smart oven for medical and nursing use includes a plurality of drying units, and each drying unit is configured with a corresponding heating module and an electromagnetic door control module. It further includes:

[0007] An operation panel for pre-inputting the basic information of the medical and nursing instruments to be put in and saving them to a memory, including: pictures, names, recommended oven temperatures, and recommended oven times;

[0008] A camera deployed at the outer doorknob of the drying unit for collecting the image information Pic-a of the medical and nursing instruments to be put in currently and sending it to an AI processor;

[0009] An AI processor for providing image AI processing services, including: performing AI recognition on the collected image information Pic-a of the medical and nursing instruments to be put in currently, outputting the corresponding recognition results and sending them to a controller, and the recognition results include the names, recommended oven temperatures, and recommended oven times of the medical and nursing instruments to be put in currently;

[0010] A controller for logical control and calculation, including: judging whether to turn on the current drying unit according to the recognition result:

[0011] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, then turn on the electromagnetic lock control module of the corresponding drying unit;

[0012] Otherwise, turn it off;

[0013] A memory for storing information;

[0014] A power supply for power supply;

[0015] The camera and the memory are respectively communicatively connected to the AI processor;

[0016] The camera, the AI processor, the operation panel, the drying unit and the power supply are respectively electrically connected to the controller.

[0017] As an optional implementation of the present application, optionally, the controller is further configured to:

[0018] After judging whether to turn on the current drying unit, generate a corresponding judgment result:

[0019] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, then generate a corresponding correct matching judgment result;

[0020] Otherwise, generate a corresponding incorrect matching judgment result including the image information Pic-a of the current medical device to be placed;

[0021] Send the judgment result to the display.

[0022] As an optional implementation of the present application, optionally, the intelligent medical oven further includes:

[0023] A display for receiving and displaying the judgment result;

[0024] The display is electrically connected to the controller.

[0025] As an optional implementation of the present application, optionally, the controller is further configured to:

[0026] After receiving the recognition result, judge whether the current medical device to be placed is in the pre-stored list:

[0027] If not, generate a corresponding reminder notice for storing new devices and send it to the display;

[0028] Otherwise, give up.

[0029] As an optional implementation of the present application, optionally, in the AI processor, an image AI recognition model is deployed to recognize the image information Pic-a of the medical device to be placed and output the corresponding recognition result;

[0030] The method for generating the image AI recognition model includes:

[0031] Prepare in advance the images of a number of medical devices;

[0032] Use a convolutional neural network to extract the device image features in the image and add corresponding feature annotations, where the annotations include the recommended oven temperature and recommended oven time that match the corresponding device image features;

[0033] Statistically analyze the device image features of each medical device after annotation to form a feature set, and divide it into a training set and a validation set according to a preset ratio;

[0034] Input the training set into a preset CNN model for feature training and learning to generate the image AI recognition model;

[0035] Use the validation set to verify the recognition performance of the image AI recognition model:

[0036] If the verification passes, deploy and apply the image AI recognition model to the AI processor;

[0037] Conversely, repeat the above steps to reconstruct the image AI recognition model.

[0038] As an optional implementation of the present application, optionally, the controller is further configured to:

[0039] When closing the electromagnetic lock control module corresponding to the drying unit, start timing, and control the corresponding drying unit to work according to the recommended oven temperature and recommended oven time of the current medical device to be placed;

[0040] After reaching the recommended oven time, generate a corresponding drying end notification and send it to the display.

[0041] As an optional implementation of the present application, optionally, the display is further configured to: receive and display the drying end notification of the current medical device to be placed.

[0042] As an optional implementation of the present application, optionally, the intelligent medical oven further includes:

[0043] A communication unit for providing data communication between the intelligent medical oven and the nurse station background, including:

[0044] Report the working data of the intelligent medical oven to the background of the nurse station, and the background of the nurse station counts the oven log of the medical instruments to be placed.

[0045] The communication unit is electrically connected to the controller.

[0046] On the other hand, the present application proposes an application control method for an intelligent medical oven integrating AI image recognition, including the following steps:

[0047] Pre-input and save the basic information of the medical instruments to be placed.

[0048] When starting to place, place the current medical instrument to be placed at the outer doorknob of the drying unit, and the camera deployed here collects the image information Pic-a of the current medical instrument to be placed and sends it to the AI processor.

[0049] The AI processor performs AI recognition on the collected image information Pic-a of the current medical instrument to be placed, outputs the corresponding recognition result and sends it to the controller, and the recognition result includes the name, recommended oven temperature, and recommended oven time of the current medical instrument to be placed.

[0050] The controller judges whether the current medical instrument to be placed is in the pre-stored list according to the recognition result:

[0051] If not, generate a corresponding reminder notice for storing new instruments and send it to the display.

[0052] Otherwise, give up.

[0053] The controller judges whether to open the current drying unit according to the recognition result:

[0054] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, open the electromagnetic lock door control module of the corresponding drying unit; generate a corresponding correct matching judgment result and send it to the display.

[0055] Otherwise, close it; generate a corresponding matching error judgment result including the image information Pic-a of the current medical instrument to be placed and send it to the display.

[0056] Put the current medical instrument to be placed into the drying unit opened by the electromagnetic lock door control module and close it.

[0057] When the controller closes the electromagnetic lock door control module of the corresponding drying unit, start timing, and control the corresponding drying unit to work according to the recommended oven temperature and recommended oven time of the current medical instrument to be placed.

[0058] After reaching the recommended oven time, a corresponding drying end notice is generated and sent to the display.

[0059] The controller reports the working data of the intelligent medical oven to the nurse station background in real time through the communication unit, and the nurse station background counts the oven logs of the medical instruments to be placed.

[0060] On the other hand, the present application also proposes an electronic device, including:

[0061] A processor;

[0062] A memory for storing executable instructions of the processor;

[0063] Wherein, when the processor is configured to execute the executable instructions, the application control method described above is implemented.

[0064] Technical effects of the present invention:

[0065] Through the intelligent medical oven integrating AI image recognition, the present application can pre-enter the basic information of the medical instruments to be placed and save it in the memory, including: pictures, names, recommended oven temperatures, and recommended oven times; when placing the medical instruments to be placed, it can perform AI recognition on the image information Pic-a of the currently placed medical instruments, output the corresponding recognition results, and the controller opens the corresponding drying unit according to the recognition results and dries it at the preset temperature and time. Therefore, it can avoid situations such as misplacement by nurses, facilitate the orderly management of medical facilities, and can realize the automatic drying of corresponding instruments, reduce the incidence of misplacing instruments in the oven, reduce the property losses of the hospital, and greatly improve the operation efficiency.

[0066] According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present disclosure will become clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The drawings included in the specification and constituting a part of the specification, together with the specification, illustrate the exemplary embodiments, features, and aspects of the present disclosure and are used to explain the principles of the present disclosure.

[0068] Figure 1 Shows a schematic application diagram of a conventionally used medical oven;

[0069] Figure 2 Shows a schematic diagram of the composition of the application control system of the intelligent medical oven of the present invention;

[0070] Figure 3 Shows a schematic diagram of the AI model construction process in the AI processor of the present invention;

[0071] Figure 4Shown is a schematic diagram of the application control system for the intelligent medical oven of the present invention to communicate with the background. Detailed implementation manners

[0072] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. Identical reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0073] The term "exemplary" used herein means "serving as an example, embodiment, or illustration". Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

[0074] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following detailed implementation manners. Those skilled in the art should understand that the present disclosure can be implemented without some specific details. In some instances, means, elements, and circuits well known to those skilled in the art are not described in detail so as to highlight the gist of the present disclosure.

[0075] Embodiment 1

[0076] As Figure 2 shown, on the one hand, the present application provides an intelligent medical oven integrating AI image recognition. The intelligent medical oven includes a plurality of drying units, and each drying unit is configured with a corresponding heating module and an electromagnetic lock door control module. It further includes:

[0077] An operation panel for pre-inputting the basic information of the medical device to be placed and saving it to the memory, including: pictures, names, recommended oven temperatures, and recommended oven times;

[0078] A camera deployed at the outer doorknob of the drying unit for collecting the image information Pic-a of the current medical device to be placed and sending it to the AI processor;

[0079] An AI processor for providing image AI processing services, including: performing AI recognition on the collected image information Pic-a of the current medical device to be placed, outputting the corresponding recognition result and sending it to the controller. The recognition result includes the name, recommended oven temperature, and recommended oven time of the current medical device to be placed;

[0080] A controller for logical control and calculation, including: judging whether to open the current drying unit according to the recognition result:

[0081] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, then open the electromagnetic lock door control module of the corresponding drying unit;

[0082] Conversely, it is closed;

[0083] A memory for storing information;

[0084] A power supply for power supply;

[0085] The camera and the memory are respectively communicatively connected to the AI processor;

[0086] The camera, the AI processor, the operation panel, the drying unit and the power supply are respectively electrically connected to the controller.

[0087] The intelligent medical oven body is equipped with a number of drying units, and each drying unit is configured with a corresponding heating module and an electromagnetic lock door control module, which are respectively controlled by the controller to perform heating and door control. The electromagnetic lock door control module is mainly an electromagnetic lock for realizing the opening and closing of the drying unit, and can be understood in combination with the electromagnetic lock of the existing Fengchao cabinet. For the body structure of the intelligent medical oven, etc., the structure of the existing equipment can be referred to.

[0088] A camera is deployed on the outer door handle of each drying unit, and other electronic facilities such as the AI processor and the controller can be integrally installed at the corresponding positions of the intelligent medical oven. The device model, installation and fixing position, etc. are not limited in this embodiment. As shown in Table 1 below:

[0089]

[0090]

[0091] Table 1

[0092] Interaction process:

[0093] Operation panel data entry

[0094] Step 1: The operator selects the "Instrument entry" mode on the KTP700 panel, enters the instrument name, temperature (50 - 250 °C), time (5 - 180 minutes) and uploads a JPEG format picture.

[0095] Step 2: The panel verifies the legality of the input parameters (temperature tolerance of ±5 °C, time ≥ 5 minutes), and after passing the verification, writes to the MySQL database through the Modbus TCP protocol.

[0096] Image acquisition and recognition

[0097] Step 1: When the operator places the instrument, the DS-2CD2T47G2 camera triggers a capture (resolution 2560×1440), and automatically adjusts the fill light intensity to 500 - 800 Lux24.

[0098] Step 2: Jetson AGX Xavier calls the ResNet50 model for feature matching and outputs the recognition result (format: JSON {name, temp, time}). When the confidence level is ≥ 95%, it is sent to the PLC.

[0099] Logical Control and Access Management

[0100] Step 1: The S7-1200 PLC receives the recognition result and compares it with the current temperature set value of the oven (reads the data of the PT100 sensor through the analog input module).

[0101] Step 2: If the temperature deviation ≤ ±3°C and the time is within the preset range, trigger the opening of the YTL-280D electromagnetic lock; otherwise, record the error log and trigger an audible and visual alarm (buzzer frequency 2 kHz).

[0102] Data Synchronization and Auditing

[0103] Step 1: Redis cache updates the operation records of the instrument in real-time (including timestamp, operator ID), and synchronizes to the MySQL main database every 5 minutes (reports to the background through a communication module such as Bluetooth).

[0104] Step 2: The system automatically generates a daily report (PDF format), including abnormal event statistics and equipment operation status, and pushes it to the administrator terminal.

[0105] III. Safety and Maintenance Specifications

[0106] Data Security

[0107] The transmission layer uses AES-256 encryption (operation panel → PLC) and SM4 encryption (camera → AI processor).

[0108] The database implements RBAC permission control, and the operation log retention period ≥ 180 days.

[0109] Equipment Maintenance

[0110] Calibrate the PT100 temperature sensor monthly (accuracy ±0.5°C), and update the ResNet50 model weights quarterly (incremental training based on new instrument samples).

[0111] Lubricate and maintain the mechanical parts of the electromagnetic lock every 6 months to prevent jamming.

[0112] For example, in an application instance:

[0113] 1. First, the nurse inputs the common items in the oven into the system (including item pictures, names, recommended oven temperatures, and times). Two-person verification (will be uploaded to the background, and the background nurse will also verify).

[0114] 2. Since the set temperature of the oven is generally between 50 and 90, to avoid damaging the intelligent components, its AI recognition camera can be installed at the position of the oven door handle.

[0115] 3. Hold the oven handle in the cleaning room and start the AI picture system (or wake up the oven according to the number on the oven).

[0116] 4. After identifying the item, compare it with the set oven temperature of itself. If the match is correct (open the door). If the match is incorrect, give a reminder: "Honghong" (voice / vibration reminder). If the item is recognized, it should be placed in a low-temperature oven; "Honghong", high-temperature oven, please place it correctly. (Close the door without opening). Prevent errors from occurring.

[0117] 5. When an item that does not exist in the system is recognized, give a "Honghong" reminder. (For example, if the item is recognized and not in the directory, if it is a new item, please enter it into the system in time) (Close the door without opening). Prevent errors from occurring.

[0118] 6. After the items placed in the oven reach the set time, the oven door handle in the packing room lights up and gives a reminder (the display gives a reminder (image, indicator light or voice, etc.), detecting that the tourniquet and breathing bag have reached the time, please take them out in time).

[0119] As an optional implementation of the present application, optionally, the controller is further configured to:

[0120] After judging whether to open the current drying unit, generate a corresponding judgment result:

[0121] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, generate a corresponding correct matching judgment result;

[0122] Otherwise, generate a corresponding incorrect matching judgment result including the image information Pic-a of the current medical device to be placed;

[0123] Send the judgment result to the display.

[0124] The controller identifies the current medical device to be placed, judges whether the recognized information is consistent with the pre-stored recommended information. If they are consistent, then agree to put it into the corresponding oven. Otherwise, send a notification of an alarm reminder. Specifically, it is understood in combination with the previous "After identifying the item, compare it with the set oven temperature of itself. If the match is correct (open the door). If the match is incorrect, give a reminder: "Honghong" (voice / vibration reminder). If the item is recognized, it should be placed in a low-temperature oven; "Honghong", high-temperature oven, please place it correctly. (Close the door without opening). Prevent errors from occurring".

[0125] As an alternative implementation of the present application, optionally, the intelligent medical oven further includes:

[0126] A display for receiving and displaying the judgment result;

[0127] The display is electrically connected to the controller.

[0128] The display can be arranged on the outer side of each drying unit, and a high-temperature resistant display screen can be used.

[0129] As an alternative implementation of the present application, optionally, the controller is further configured to:

[0130] After receiving the recognition result, determine whether the current medical device to be placed is in a pre-stored list:

[0131] If not, generate a corresponding new device storage reminder notice and send it to the display;

[0132] Otherwise, give up.

[0133] Previously, when inputting pre-stored information, a list of each device will be generated in the system. Therefore, subsequently, the controller can determine whether the currently recognized device is a device on the list. If so, continue with the subsequent work; otherwise, remind the nurse to re-enter the information.

[0134] The AI processor can provide image intelligent recognition services. It uses a convolutional neural network model for feature recognition and outputs corresponding feature annotation information to identify the current device information and output the recommended oven temperature and recommended oven time.

[0135] As an alternative implementation of the present application, optionally, in the AI processor, an image AI recognition model is deployed to recognize the image information Pic-a of the medical device to be placed and output the corresponding recognition result;

[0136] As Figure 3 shown, the generation method of the image AI recognition model includes:

[0137] Prepare several images of medical devices in advance;

[0138] Use a convolutional neural network to extract the device image features in the image and add corresponding feature annotations, where the annotations include the recommended oven temperature and recommended oven time that match the corresponding device image features;

[0139] Statistically analyze the device image features of each medical device after annotation to form a feature set, and divide it into a training set and a validation set according to a preset ratio;

[0140] Input the training set into a preset CNN model for feature training and learning to generate the image AI recognition model;

[0141] Use the validation set to verify the recognition performance of the image AI recognition model:

[0142] If the verification passes, deploy and apply the image AI recognition model to the AI processor;

[0143] Otherwise, repeat the above steps to reconstruct the image AI recognition model.

[0144] Images of different types of medical devices can be prepared by the administrator.

[0145] Image Acquisition and Preprocessing

[0146] Collect multi-angle images of medical devices (including surgical forceps, trays, etc.) through an industrial camera, with a resolution ≥ 1920×1080 and the format unified as JPEG / PNG.

[0147] Use OpenCV for data cleaning (removing glare and shadow interference) and enhancement processing (rotating ±15° and adjusting brightness by ±20%).

[0148] Feature Extraction and Annotation

[0149] Extract the texture and shape features of the device (output a 512-dimensional feature vector) based on the improved ResNet-50 convolutional neural network.

[0150] Annotation Rules:

[0151] # Example Annotation Data Structure

[0152] {

[0153] "Device Type": "Stainless Steel Surgical Forceps",

[0154] "Recommended Temperature": "121℃", / / Set according to the "Medical Disinfection Technology Specification"

[0155] "Recommended Time": "30min",

[0156] "Feature Hash Value": "a3f8b2c1d7" / / The unique identifier generated by the feature vector (used to provide security during data interaction and can be used for data security verification when sharing information with the nurse station background later)

[0157] }

[0158] The annotation tool uses LabelStudio, which supports multi-person collaborative annotation.

[0159] Model Training and Verification

[0160] Dataset Construction

[0161] Divide the dataset in a 7:3 ratio to ensure that the distribution deviation of each type of instrument in the training set / validation set is ≤ 5%;

[0162] Build a feature retrieval database (FAISS index) to accelerate feature comparison during training;

[0163] Model Training Optimization:

[0164] Use the PyTorch framework to build a CNN network, including:

[0165] Input layer: Standardize the 224×224 pixels;

[0166] Core module: 3 groups of convolutional layers (kernel_size = 3×3) + BN layer + ReLU activation;

[0167] Output layer: Softmax classification (instrument type) and regression layer (temperature / time prediction);

[0168] The loss function adopts a weighted combination of cross-entropy loss (classification) + MSE loss (regression) (weight ratio 1:0.8).

[0169] Performance Verification Criteria

[0170] Index Threshold requirement Testing method Accuracy rate of device classification ≥98％ Confusion matrix analysis Temperature prediction error ≤±2℃ Root mean square error (RMSE) Inference latency ≤200ms Actual measurement on edge device (Jetson Nano)

[0171] III. Model Deployment and Application

[0172] Lightweight Processing

[0173] Use TensorRT to quantize the model (FP32 → INT8), and compress the volume to 35% of the original model;

[0174] Deployment includes:

[0175] Inference engine: ONNX Runtime;

[0176] Dependency library: CUDA 11.6 + cuDNN 8.4

[0177] Configuration file: temperature_preset.json (preset disinfection parameter library).

[0178] AI Processor Integration (Load the model program into the processor chip by burning, etc.)

[0179] Hardware docking: Connect to an industrial camera through the MIPI-CSI interface, supporting 30fps real-time image input.

[0180] Output Protocol:

[0181] / / Recognition result data format

[0182] {

[0183] "device_id":"STM32F407",

[0184] "Recognition result":{

[0185] "Instrument type":"Titanium alloy bone drill",

[0186] "Confidence":0.963,

[0187] "Recommended parameters":{"Temperature":"134°C","Time":"25min"}

[0188] },

[0189] "Timestamp":"2025-03-03T14:22:35Z"

[0190] }。

[0191] Transmitted to the oven control system via RS485 / Ethernet.

[0192] For the feature training and learning of the CNN model, it can be understood and implemented by combining the application principles of the existing CNN model, while the verification methods such as F1 and accuracy are completed by the administrator.

[0193] As an alternative implementation of this application, optionally, the controller is further configured to:

[0194] When closing the electromagnetic lock and door control module corresponding to the drying unit, start timing, and control the corresponding drying unit to work according to the recommended oven temperature and recommended oven time of the medical device to be placed currently;

[0195] After reaching the recommended oven time, generate a corresponding drying end notification and send it to the display.

[0196] The controller will monitor the working parameters of each drying unit to make it reach the recommended oven temperature and recommended oven time, and when it reaches, the control unit will stop working.

[0197] As an alternative implementation of this application, optionally, the display is further configured to: receive and display the drying end notification of the medical device to be placed currently.

[0198] As Figure 4 shown, as an alternative implementation of this application, optionally, the intelligent medical oven further includes:

[0199] A communication unit for providing data communication between the intelligent medical oven and the nurse station background, including:

[0200] Report the working data of the intelligent medical oven to the nurse station background, and the nurse station background counts the oven logs of the medical devices to be put in;

[0201] The communication unit is electrically connected to the controller.

[0202] The present invention can also connect the intelligent medical oven with the background to realize background data sharing.

[0203] The controller is responsible for sensor data acquisition, device status control and Bluetooth communication protocol processing.

[0204] The oven integrates a DHT11 temperature and humidity sensor to monitor the internal environment parameters of the oven in real time. Add a door magnetic switch or an infrared sensor to detect the opening and closing state of the cabinet door to ensure the safety operation logic (such as starting the work process after closing the door).

[0205] Bluetooth communication module:

[0206] Select a low-power Bluetooth module (such as HC-05 / HM-10), communicate with the controller through the UART serial port, and realize the wireless transmission of the oven working data (temperature and humidity, running time, door status).

[0207] Support multi-device networking to ensure that the nurse station can receive the reported data of multiple ovens at the same time.

[0208] Data format definition

[0209] The reported data packet contains the following fields:

[0210] Device ID (uniquely identify the oven);

[0211] Temperature and humidity values (such as 25°C / 50%);

[0212] Working status (running / completed / faulty);

[0213] Instrument type code (such as surgical forceps, tray, etc.);

[0214] Timestamp (record the operation time).

[0215] Communication mechanism

[0216] Adopt the polling or event-triggered mode:

[0217] Regular reporting: Send real-time data every 5 minutes.

[0218] Status change trigger: Report immediately when the oven work is completed / faulty.

[0219] Data Encryption: Ensure transmission security through AES-128 encryption.

[0220] Nurse Station Backend System

[0221] Data Reception and Storage: Deploy the host computer software, receive data from multiple devices through a Bluetooth adapter, and store it in the MySQL database after parsing.

[0222] The logged content includes: instrument type, disinfection duration, temperature and humidity curve, operator ID, etc.

[0223] Visualization and Statistics Function

[0224] The dashboard displays the real-time device status (online / offline) and alarm information (such as temperature and humidity exceeding the standard).

[0225] Generate an instrument drying log report, and support filtering and exporting according to conditions such as time, instrument type, device ID, etc.

[0226] Security and Alarm Mechanism

[0227] Set Threshold Alarm: When the temperature and humidity exceed the preset range or the device is offline, trigger an audible and visual alarm and a text message reminder.

[0228] Permission Management: Distinguish between nurse and administrator roles and restrict sensitive operation permissions.

[0229] Obviously, those skilled in the art should understand that to implement all or part of the processes in the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above control embodiments. Those skilled in the art can understand that to implement all or part of the processes in the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above control embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (Hard Disk Drive, abbreviated as HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0230] Embodiment 2

[0231] Based on the implementation principle of Embodiment 1, on the other hand, this application proposes an application control method for a medical intelligent oven integrated with AI image recognition, including the following steps:

[0232] Pre-enter and save the basic information of the medical device to be placed.

[0233] When starting to place, place the currently to-be-placed medical device at the outer door handle of the drying unit. The image information Pic-a of the currently to-be-placed medical device is collected by the camera deployed here and sent to the AI processor.

[0234] The AI processor performs AI recognition on the collected image information Pic-a of the currently to-be-placed medical device, outputs the corresponding recognition result and sends it to the controller. The recognition result includes the name of the currently to-be-placed medical device, the recommended oven temperature, and the recommended oven time.

[0235] The controller determines whether the currently to-be-placed medical device is in the pre-stored list according to the recognition result:

[0236] If not, generate a corresponding new device storage reminder notice and send it to the display.

[0237] Otherwise, give up.

[0238] The controller determines whether to open the current drying unit according to the recognition result:

[0239] If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, open the electromagnetic lock door control module of the corresponding drying unit; generate a corresponding correct matching judgment result and send it to the display.

[0240] Otherwise, close it; generate a corresponding matching error judgment result including the image information Pic-a of the currently to-be-placed medical device and send it to the display.

[0241] Place the currently to-be-placed medical device into the drying unit opened by the electromagnetic lock door control module and close it.

[0242] When the controller closes the electromagnetic lock door control module of the corresponding drying unit, start timing, and control the corresponding drying unit to work according to the recommended oven temperature and recommended oven time of the currently to-be-placed medical device.

[0243] When the recommended oven time is reached, generate a corresponding drying end notice and send it to the display.

[0244] The controller reports the working data of the intelligent medical oven to the nurse station background in real time through the communication unit, and the nurse station background statistics the oven log of the medical devices to be placed.

[0245] The above method should be understood in combination with the corresponding steps in Embodiment 1, and will not be elaborated in this embodiment.

[0246] Each module or step of the present invention described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network composed of multiple computing systems. Optionally, they can be implemented using program code executable by the computing system. Thus, they can be stored in a storage system for execution by the computing system, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0247] Embodiment 3

[0248] Furthermore, on the other hand, the present application also proposes an intelligent oven for medical care integrating AI image recognition and its application control method electronic device, including:

[0249] A processor;

[0250] A memory for storing instructions executable by the processor;

[0251] Wherein, when the processor is configured to execute the executable instructions, it implements an intelligent oven for medical care integrating AI image recognition and its application control method described in Embodiment 2.

[0252] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. Wherein, when the processor is configured to execute the executable instructions, it implements an intelligent oven for medical care integrating AI image recognition and its application control method described in Embodiment 2 above.

[0253] Here, it should be noted that the number of processors can be one or more. At the same time, in the electronic device of the embodiment of the present disclosure, an input system and an output system can also be included. Among them, the processor, the memory, the input system and the output system can be connected through a bus or in other ways, and specific limitations are not made here.

[0254] The memory, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and various modules, such as: the programs or modules corresponding to an intelligent oven for medical care integrating AI image recognition and its application control method of the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0255] The input system can be used to receive input numbers or signals. Among them, the signal can be a key signal related to the user settings and function control of the device / terminal / server. The output system can include a display device such as a display screen.

[0256] The embodiments of the present disclosure have been described above. The above description is exemplary and not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to technologies in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. An intelligent oven for medical care integrating AI image recognition, the intelligent oven for medical care includes a plurality of drying units, and each drying unit is configured with a corresponding heating module and an electromagnetic door control module, characterized in that, It further includes: An operation panel for pre-entering the basic information of the medical device to be placed and saving it to the memory, including: pictures, names, recommended oven temperatures, and recommended oven times; A camera deployed at the outer doorknob of the drying unit for collecting the image information Pic-a of the current medical device to be placed and sending it to the AI processor; An AI processor for providing image AI processing services, including: performing AI recognition on the collected image information Pic-a of the current medical device to be placed, outputting the corresponding recognition result and sending it to the controller, and the recognition result includes the name, recommended oven temperature, and recommended oven time of the current medical device to be placed; A controller for logical control and calculation, including: judging whether to open the current drying unit according to the recognition result: If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, then open the electromagnetic lock door control module of the corresponding drying unit; Otherwise, close it; A memory for storing information; A power supply for power supply; The camera and the memory are respectively communicatively connected to the AI processor; The camera, the AI processor, the operation panel, the drying unit, and the power supply are respectively electrically connected to the controller.

2. The intelligent oven for medical use integrating AI image recognition according to claim 1, characterized in that, The controller is further used for: After judging whether to open the current drying unit, generating a corresponding judgment result: If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, then generate a corresponding correct matching judgment result; Otherwise, generate a corresponding incorrect matching judgment result including the image information Pic-a of the current medical device to be placed; Send the judgment result to the display.

3. The intelligent oven for medical use integrating AI image recognition according to claim 2, characterized in that, The intelligent medical oven further includes: A display for receiving and displaying the judgment result; The display is electrically connected to the controller.

4. An intelligent oven for medical use integrating AI image recognition according to claim 1, characterized in that, The controller is further used for: After receiving the recognition result, judging whether the current medical device to be placed is in the pre-stored list: If not, then generate a corresponding reminder notice for storing new devices and send it to the display; Otherwise, give up.

5. An intelligent oven for medical use integrating AI image recognition according to claim 1, characterized in that, In the AI processor, an image AI recognition model is deployed for recognizing the image information Pic-a of the medical device to be placed and outputting the corresponding recognition result; The generation method of the image AI recognition model includes: Prepare several images of medical devices in advance; Use a convolutional neural network to extract the device image features in the images and add corresponding feature annotations, and the annotations include the recommended oven temperature and recommended oven time that match the corresponding device image features; Statistically analyze the device image features of each medical device after annotation to form a feature set, and divide it into a training set and a validation set according to a preset ratio; Input the training set into a preset CNN model for feature training and learning to generate the image AI recognition model; Use the validation set to verify the recognition performance of the image AI recognition model: If the verification passes, then deploy and apply the image AI recognition model to the AI processor; Conversely, repeat the above steps to reconstruct the image AI recognition model.

6. The intelligent oven for medical use integrating AI image recognition according to claim 1, characterized in that, The controller is further configured to: When closing the electromagnetic lock door control module corresponding to the drying unit, start timing, and control the corresponding drying unit to operate according to the recommended oven temperature and recommended oven time of the medical device to be placed currently; After reaching the recommended oven time, generate a corresponding drying end notification and send it to the display.

7. An intelligent oven for medical use integrating AI image recognition according to claim 6, characterized in that, The display is further configured to: receive and display the drying end notification of the medical device to be placed currently.

8. The intelligent oven for medical use integrating AI image recognition according to claim 1, characterized in that, The intelligent medical oven further includes: A communication unit for providing data communication between the intelligent medical oven and the nurse station background, including: Reporting the working data of the intelligent medical oven to the nurse station background, and the nurse station background statistically analyzes the oven log of the medical device to be placed. The communication unit is electrically connected to the controller.

9. An application control method for the intelligent oven for medical care integrating AI image recognition according to any one of claims 1-8, characterized in that, It includes the following steps: Pre-input and save the basic information of the medical device to be placed. When starting to place, place the currently to-be-placed medical device at the outer doorknob of the drying unit, and the camera deployed here collects the image information Pic-a of the currently to-be-placed medical device and sends it to the AI processor. The AI processor performs AI recognition on the collected image information Pic-a of the currently to-be-placed medical device, outputs the corresponding recognition result and sends it to the controller, and the recognition result includes the name, recommended oven temperature, and recommended oven time of the currently to-be-placed medical device. The controller judges whether the currently to-be-placed medical device is in the pre-stored list according to the recognition result: If not, generate a corresponding new device storage reminder notification and send it to the display. Conversely, give up. The controller judges whether to open the current drying unit according to the recognition result: If the recommended oven temperature in the recognition result matches the oven temperature of the corresponding drying unit, open the electromagnetic lock door control module of the corresponding drying unit; generate a corresponding correct matching judgment result and send it to the display; Conversely, close it; generate a corresponding matching error judgment result including the image information Pic-a of the currently to-be-placed medical device and send it to the display. Put the currently to-be-placed medical device into the drying unit opened by the electromagnetic lock door control module, and close it. When the controller closes the electromagnetic lock door control module corresponding to the drying unit, start timing, and control the corresponding drying unit to operate according to the recommended oven temperature and recommended oven time of the currently to-be-placed medical device. After reaching the recommended oven time, generate a corresponding drying end notification and send it to the display. The controller reports the working data of the intelligent medical oven to the nurse station background in real time through the communication unit, and the nurse station background statistically analyzes the oven log of the medical device to be placed.

10. An electronic device, characterized in that, It includes: A processor; A memory for storing processor-executable instructions; Wherein, when the processor is configured to execute the executable instructions, it implements the application control method described in claim 9.

Images