CN117409935A - Intelligent medical management system and management method - Google Patents
Intelligent medical management system and management method Download PDFInfo
- Publication number
- CN117409935A CN117409935A CN202311391511.6A CN202311391511A CN117409935A CN 117409935 A CN117409935 A CN 117409935A CN 202311391511 A CN202311391511 A CN 202311391511A CN 117409935 A CN117409935 A CN 117409935A
- Authority
- CN
- China
- Prior art keywords
- patient
- data
- module
- information
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims description 47
- 238000012795 verification Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 238000013475 authorization Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000013527 convolutional neural network Methods 0.000 claims description 38
- 230000001815 facial effect Effects 0.000 claims description 35
- 230000007246 mechanism Effects 0.000 claims description 33
- 238000000034 method Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000003745 diagnosis Methods 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 11
- 230000000875 corresponding effect Effects 0.000 claims description 11
- 230000000903 blocking effect Effects 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 10
- 230000002596 correlated effect Effects 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 6
- 238000013145 classification model Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- GQWNECFJGBQMBO-UHFFFAOYSA-N Molindone hydrochloride Chemical compound Cl.O=C1C=2C(CC)=C(C)NC=2CCC1CN1CCOCC1 GQWNECFJGBQMBO-UHFFFAOYSA-N 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The application relates to wisdom medical management system technical field discloses wisdom medical management system, include: the system comprises a data sharing module, a patient data acquisition module, a data processing and feature extraction module, a model building training module, a face recognition and verification module and an authorization and control module, wherein a registration personnel information acquisition association module associates acquired face characteristic information with patient information; the patient data acquisition module collects shared data; the face recognition and verification module collects face images of a patient to be diagnosed; after verifying that the identity is correct, the authorization and control module automatically controls the door of the department to be opened, so that the patient with the called number enters the visit; according to the invention, the identity information is verified through the face recognition and verification module, and the authorization and control module can control the gate of the department to be opened after the verification is successful, so that the patient with the number can enter the doctor to visit, and the privacy leakage of the patient to visit caused by the entrance of the person during the doctor is avoided.
Description
Technical Field
The application relates to the technical field of intelligent medical management systems, in particular to an intelligent medical management system and an intelligent medical management method.
Background
The intelligent medical management system is a comprehensive medical management platform designed and developed by combining advanced information technology and data management technology with medical service requirements. It provides more efficient, safe, convenient medical services and management by integrating and managing various medical data, optimizing medical procedures and resource allocation, and intelligent medical management system generally includes the following features and functions:
1. electronic health record management: the health data of the patient is digitized and stored, including personal basic information, medical records, inspection reports, image data and the like, so that medical staff can conveniently review and manage the health data at any time.
2. Appointment registering system: the patient can make doctor reservation and registration through an online platform or a mobile application program, so that inconvenience of queuing and manual reservation and the like are avoided.
The intelligent medical management system aims to improve the quality and efficiency of medical service, improve the management level of hospitals and the experience of patients through application of information technology, and realize comprehensive medical informatization and intellectualization.
The prior art publication No. CN113223686B provides an intelligent medical management system and method based on a monitoring technology, and the intelligent medical management system and method are characterized in that after a security analysis signal is received by a security analysis unit, security area analysis is carried out on each floor in a hospital, security data acquisition of security equipment is carried out on each subarea after each subarea is received by a data acquisition unit, and security data is analyzed by a data analysis unit; the security data acquisition and analysis are carried out in each area of the hospital, so that the environmental security performance of the hospital is improved, and the working efficiency of medical management is enhanced.
The prior art schemes described above, although achieving the beneficial effects associated with the prior art arrangements, have the following drawbacks; when the technology is used, the function of improving the environmental safety performance of a hospital is realized, but the door of the department can be opened at will during the working of the existing department, and the technology is inconvenient to authorize and limit the doctor, so that outsiders enter the department during the doctor, the privacy of the doctor can be infringed, the team insertion of the staff can be caused, the disorder of a hospital management system is caused,
in view of this, we propose an intelligent medical management system and management method.
Disclosure of Invention
1. Technical problem to be solved
The technical problem in the background technology is solved, and the technical effect of authorizing and limiting the doctor is achieved.
2. Technical proposal
The embodiment of the application provides a smart medical management system, which comprises: the system comprises a data sharing module, a patient data acquisition module, a data processing and feature extraction module, a model building training module, a face recognition and verification module and an authorization and control module,
and a data sharing module: the data sharing module is used for sharing medical data and can share the identity information of the patient during registration;
registration personnel information acquisition association module: acquiring facial information of registration personnel through a camera fixedly arranged at the upper end of the registration machine; correlating the acquired face characteristic information with patient information, and storing the correlated information;
patient data acquisition module: the patient data acquisition module collects shared data, such as personal information and characteristic data of a patient, such as a name, a mobile phone number, an identity card number, a facial image and the like;
and the data processing and feature extraction module is used for: the data processing and feature extraction module cleans, processes and standardizes the acquired data, and extracts useful features from the patient's data through a machine learning algorithm so that the machine learning system can correctly utilize the data;
model building training module: the model building training module performs training optimization treatment on the model of the convolutional neural network by building a learning model of the convolutional neural network and utilizing the data after treatment and feature extraction;
face recognition and verification module: the face recognition and verification module collects face images of a patient to be diagnosed through imaging equipment at a diagnosis room gate, and then performs verification and determination by using a convolutional neural network model;
and the authorization and control module: after the identity is verified to be correct, the authorization and control module automatically controls the door of the department to be opened, so that the patient with the called number enters the doctor to avoid the entrance of a person in the team and the influence on the management of the hospital.
As an alternative to the technical solution of the present application, the data processing and feature extraction module includes a data preprocessing unit and a feature extraction unit;
the data preprocessing unit cleans, processes and normalizes the acquired data so that the machine learning system can correctly utilize the data;
the feature extraction unit extracts useful features from the patient's data through a machine learning algorithm, and can perform face recognition by using the face image data to extract facial features.
As an alternative to the technical solution of the present application, the data preprocessing unit adjusts the acquired image to a suitable size, typically using square images, with a size such as 128x128 or 256x256, which helps to maintain the aspect ratio of the image, and makes all the input images have the same size; through an image enhancement technology, the quality and the visualization effect of an image are improved by utilizing histogram equalization, so that details and features in a face image are enhanced, better input data is provided for a subsequent feature extraction and classification model, image data is subjected to standardization processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data has zero mean value and unit variance, and training of the model is facilitated.
As an alternative to the technical solution of the present application, the feature extraction unit generates a binary code according to a comparison result by comparing each pixel point with its neighboring pixels by using an LBP feature local texture feature representation method, and then converts the binary code into a decimal number as a feature value.
As an alternative to the technical solution of the present application, the model building training module builds a learning model of a Convolutional Neural Network (CNN), where the learning model CNN is composed of a plurality of convolutional layers, a pooling layer and a full-connection layer; the convolution layer can extract local features of the image, the pooling layer can reduce feature dimensions and maintain importance of the features, the full-connection layer can map the features to probabilities of different categories, the CNN can learn feature representation of the face through face images and corresponding labels in the training data set, further recognition, verification or classification tasks of the face are carried out, accuracy of the network can be improved through continuously adjusting network structures and training parameters, and more accurate and reliable face recognition results are achieved.
As an alternative scheme of the technical scheme of the application document, the face recognition and verification module can collect face images of the personnel to be treated by arranging the camera shooting equipment on the gate of the department, then preprocessing and extracting the collected images, inputting the extracted features into a trained learning model of a Convolutional Neural Network (CNN), and confirming the identity of the patient by the model through verification and comparison.
As an alternative scheme of the technical scheme, the authorization and control module authorizes the patient passing the verification, and at the moment, the intelligent lock on the department gate can be controlled to be automatically opened, so that the patient can enter the visit. If the entrance of the office is confirmed as the patient himself, the entrance is allowed; if the entrance of the office is confirmed to be not the patient himself, the person associated with the patient is sent out through a loudspeaker on the entrance of the office to remind the person and the patient himself to enter the office; if the entrance to the office is confirmed as not the patient himself, nor the person associated with the patient, then he is not allowed to enter the office.
As an alternative scheme of the technical scheme of the application document, the data sharing module is used for sharing medical data, and can share the identity information of the patient during registration;
as an alternative scheme of this application file technical scheme, registration personnel information acquisition association module gathers registration personnel's facial information through the camera of fixed setting in registration machine upper end to compare with the patient facial feature of registering that needs to visit that prestores in the database, confirm that registration personnel is patient himself. If the registering person is the patient himself, and meanwhile, the database stores the relevant information of the patient identity, the information association operation is not carried out; if the registering person is the patient himself (confirmed by comparing the patient identification card with the facial features); if the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient (such as address, telephone, facial features and the like) in a correlated manner; if the registered person is not the patient himself (for example, parents or other persons of child patients, relatives of old people or patients with inconvenient actions, etc.), the acquired face characteristic information is associated with the patient information, and the associated information is stored.
As an alternative to the technical solution of the present application, the authorization and control module includes: door plant, intelligent lock and adjustment mechanism;
the door plate is provided with an intelligent lock, and an adjusting mechanism is fixedly arranged in the door plate in a connecting way;
the door panel is provided with a display screen.
The face recognition and verification module comprises a face acquisition mechanism;
the adjusting mechanism is fixedly connected with a portrait collecting mechanism.
As an alternative to the technical solution of the present application, the adjusting mechanism includes a motor, a threaded rod, and an adjusting block;
the motor is fixedly connected with the inner wall of the door panel, a threaded rod is fixedly connected with the output end of the motor, an adjusting block is arranged on the outer wall of the threaded rod in a threaded connection mode, and the adjusting block is arranged in sliding fit with the inner wall of the door panel. The adjusting block is fixedly connected with the image acquisition mechanism.
The portrait acquisition mechanism comprises a shell and a camera;
the shell is fixedly connected with the regulating block, the camera is installed in the shell, the shell opening part sliding fit is provided with the clean fender lid, the clean fender lid one side is connected fixedly and is provided with the sponge strip, the sponge strip is arranged with camera outer wall sliding contact, the clean fender lid one end is connected fixedly and is provided with the spring, the spring other end is fixedly connected with the shell and is fixedly arranged, the clean fender lid and the door plant inner wall movable contact setting.
The invention provides an intelligent medical management method, which comprises the following steps:
s1, when a person registers a patient visit, a registration person information acquisition association module acquires facial information of the registration person through a camera fixedly arranged at the upper end of a registration machine, compares the facial information with facial features of the registration patient which needs to visit and is pre-stored in a database, and confirms whether the registration person is the patient himself or herself;
s11, if the registering person is the patient himself, and meanwhile, the relevant information of the patient identity is stored in the database, the information association operation is not carried out;
s12, if the registering person is the patient himself (through the comparison and confirmation of the patient identity card and the facial features); if the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient (such as address, telephone, facial features and the like) in a correlated manner;
s13, if the registered person is not the patient (such as parents of child patients or other persons, old people or relatives of patients with inconvenient actions, and the like), the acquired face characteristic information is associated with the patient information, and the associated information is stored;
s2, when a hospital number calling system calls the name of a corresponding patient, the patient stands at a department gate, then a face image is acquired through a camera device on the department gate, the acquired image is adjusted to be a proper size by the system, a square image is usually used, the size is 128x128 or 256x256, the aspect ratio of the image is kept, and all input images have the same size; through an image enhancement technology, the quality and the visual effect of an image are improved by utilizing histogram equalization, so that details and characteristics in a face image are enhanced, better input data are provided for a subsequent characteristic extraction and classification model, image data are subjected to standardized processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data have zero mean value and unit variance, and training of the model is facilitated;
s3, comparing each pixel point with the neighborhood pixels by using an LBP characteristic local texture characteristic representation method, generating a binary code according to a comparison result, converting the binary code into a decimal number as a characteristic value, and extracting image characteristics;
s4, a learning model of a Convolutional Neural Network (CNN) can learn the characteristic representation of the face through training the face image and the corresponding label in the data set, so that the face recognition, verification or classification task is carried out, the accuracy of the network can be improved through continuously adjusting the network structure and training parameters, and a more accurate and reliable face recognition result is realized;
s5, preprocessing and extracting features of the acquired images, inputting the extracted features into a trained learning model of a Convolutional Neural Network (CNN), and confirming the identity of a patient by the model through verification and comparison, wherein an authorization and control module authorizes the patient passing verification;
s51, if the entrance of the consulting room is confirmed to be the patient himself, allowing the patient to enter;
s52, if the entrance of the diagnosis room is confirmed to be not the patient himself, a voice prompt is sent out through a loudspeaker on the entrance of the diagnosis room to remind the patient himself to enter the diagnosis room;
s53, if the entrance of the consulting room is not the patient himself or the person associated with the patient, the consulting room is not allowed to enter the consulting room;
s6, controlling the intelligent lock on the department door to be automatically opened at the moment, so that the patient can enter the doctor.
3. Advantageous effects
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
1. the technical problems in the prior art are effectively solved due to the adoption of the technical means such as the patient data acquisition module, the identity information of the patient needs to be verified through the face recognition and verification module when the patient is in a doctor, and the door of a department can be controlled to be opened by the authorization and control module after the success of verification, so that the patient with the number can enter the doctor, the privacy leakage of the doctor patient caused by the entrance of the person in the doctor is effectively avoided, the team inserting behavior is avoided, and the proper management effect of the hospital is realized.
2. This application can realize adjusting the portrait collection mechanism through setting up adjustment mechanism, makes things convenient for portrait collection mechanism to carry out the collection of face image to the patient that different risees, sets up clean fender lid simultaneously, when not using the portrait collection mechanism, realizes automatically cleaning the cover to the camera, plays the effect to the clean protection of camera.
3. The registration personnel can be related to patient information, so that personnel entering a consulting room can be effectively controlled during the consultation, and the privacy of a patient is ensured.
Drawings
FIG. 1 is a schematic diagram of an overall workflow based on a smart medical management system and management method according to a preferred embodiment of the present application;
FIG. 2 is a schematic diagram showing the overall structure of a smart medical management system and a smart medical management method according to a preferred embodiment of the present invention;
FIG. 3 is a schematic view showing a door panel structure based on a smart medical management system and a management method according to a preferred embodiment of the present application;
FIG. 4 is a schematic cross-sectional development view of an adjusting mechanism and a portrait collecting mechanism based on an intelligent medical management system and a management method according to a preferred embodiment of the present invention;
the reference numerals in the figures illustrate: 1. a door panel; 2. an intelligent lock; 3. an adjusting mechanism; 4. a portrait acquisition mechanism; 101. a display screen; 301. a motor; 302. a threaded rod; 303. an adjusting block; 401. a housing; 402. a camera; 403. cleaning a blocking cover; 404. and (3) a spring.
Detailed Description
The present application is described in further detail below in conjunction with the drawings attached to the specification.
Referring to fig. 1, a smart medical management-based system includes: the system comprises a data sharing module, a patient data acquisition module, a data processing and feature extraction module, a face recognition and verification module, a model building training module and an authorization and control module,
and a data sharing module: the data sharing module is used for sharing medical data and can share the identity information of the patient during registration;
the registration personnel information acquisition and association module acquires facial information of registration personnel through a camera fixedly arranged at the upper end of the registration machine; correlating the acquired face characteristic information with patient information, and storing the correlated information;
patient data acquisition module: the patient data acquisition module collects shared data, such as personal information and characteristic data of a patient, such as a name, a mobile phone number, an identity card number, a facial image and the like;
and the data processing and feature extraction module is used for: the data processing and feature extraction module cleans, processes and normalizes the acquired data, and extracts useful features from the patient's data through a machine learning algorithm so that the machine learning system can correctly utilize the data;
model building training module: the model building training module performs training optimization processing on the model of the convolutional neural network by building a learning model of the convolutional neural network and utilizing the processed and feature extracted data;
face recognition and verification module: the face recognition and verification module collects face images of a patient to be diagnosed through camera equipment at a gate of a diagnosis room, and then performs verification and determination by using a convolutional neural network model;
and the authorization and control module: after the identity is verified to be correct, the authorization and control module automatically controls the door of the department to be opened, so that the patient with the called number enters the doctor, the entrance of a person in the team is avoided, the management of the hospital is influenced, and the privacy of the patient is protected.
Specifically, the data sharing module is used for sharing medical data and can share identity information of a patient during registration;
the registration personnel information acquisition association module is used for acquiring facial information of registration personnel through a camera fixedly arranged at the upper end of the registration machine and comparing the facial information with facial features of registered patients needing to visit prestored in a database to confirm whether the registration personnel are patients.
If the registering person is the patient himself, and the relevant information of the patient identity is stored in the database, no information association operation is performed.
If the registering person is the patient himself (confirmed by comparing the patient identification card with the facial features); if the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient (such as address, telephone, facial features and the like) in a correlated manner;
if the registered person is not the patient (such as parents or other persons of child patients, relatives of old people or patients with inconvenient actions, and the like), the acquired face characteristic information is associated with the patient information, and the associated information is stored;
the data processing and feature extraction module comprises a data preprocessing unit and a feature extraction unit;
the data preprocessing unit cleans, processes and normalizes the acquired data so that the machine learning system can correctly utilize the data;
the feature extraction unit extracts useful features from the patient's data by means of a machine learning algorithm, and can perform face recognition using the face image data to extract facial features.
The data preprocessing unit adjusts the acquired image to a proper size, typically using a square image, with a size such as 128x128 or 256x256, helping to maintain the aspect ratio of the image and making the input image the same size; through an image enhancement technology, the quality and the visualization effect of an image are improved by utilizing histogram equalization, so that details and features in a face image are enhanced, better input data is provided for a subsequent feature extraction and classification model, image data is subjected to standardization processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data has zero mean value and unit variance, and training of the model is facilitated.
The feature extraction unit generates binary codes according to the comparison result by comparing each pixel point with the neighborhood pixels by using the LBP feature local texture feature representation method, and then converts the binary codes into decimal numbers as feature values.
The model building training module builds a learning model of a convolutional neural network CNN, wherein the learning model CNN consists of a plurality of convolutional layers, a pooling layer and a full-connection layer; the convolution layer can extract local features of the image, the pooling layer can reduce feature dimensions and maintain importance of the features, the full-connection layer can map the features to probabilities of different categories, the CNN can learn feature representation of the face through face images and corresponding labels in the training data set, further recognition, verification or classification tasks of the face are carried out, accuracy of the network can be improved through continuously adjusting network structures and training parameters, and more accurate and reliable face recognition results are achieved.
The face recognition and verification module can collect face images of the personnel to be treated by arranging the camera equipment on the gate of the department, then preprocessing and extracting the characteristics of the collected images, inputting the extracted characteristics into a trained learning model of the convolutional neural network CNN, and confirming the identity of the patient by the model in a verification and comparison mode; if the entrance of the office is confirmed as the patient himself, the entrance is allowed; if the entrance of the office is confirmed to be not the patient himself, the person associated with the patient is sent out through a loudspeaker on the entrance of the office to remind the person and the patient himself to enter the office; if the entrance to the office is confirmed as not the patient himself, nor the person associated with the patient, then he is not allowed to enter the office.
The authorization and control module authorizes the patient passing the verification, and at the moment, the intelligent lock on the department door can be controlled to be automatically opened, so that the patient can enter the doctor.
The invention provides an intelligent medical management method, which comprises the following steps:
s1, when a person registers a patient visit, a registration person information acquisition association module acquires facial information of the registration person through a camera fixedly arranged at the upper end of a registration machine, compares the facial information with facial features of the registration patient which needs to visit and is pre-stored in a database, and confirms whether the registration person is the patient himself or herself;
s11, if the registering person is the patient himself, and meanwhile, the relevant information of the patient identity is stored in the database, the information association operation is not carried out;
s12, if the registering person is the patient himself (through the comparison and confirmation of the patient identity card and the facial features); if the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient (such as address, telephone, facial features and the like) in a correlated manner;
s13, if the registered person is not the patient (such as parents of child patients or other persons, old people or relatives of patients with inconvenient actions, and the like), the acquired face characteristic information is associated with the patient information, and the associated information is stored;
s2, when a hospital number calling system calls the name of a corresponding patient, the patient stands at a department gate, then a face image is acquired through a camera device on the department gate, the acquired image is adjusted to be a proper size by the system, a square image is usually used, the size is 128x128 or 256x256, the aspect ratio of the image is kept, and the input image has the same size; through an image enhancement technology, the quality and the visual effect of an image are improved by utilizing histogram equalization, so that details and characteristics in a face image are enhanced, better input data are provided for a subsequent characteristic extraction and classification model, image data are subjected to standardized processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data have zero mean value and unit variance, and training of the model is facilitated;
s3, comparing each pixel point with the neighborhood pixels by using an LBP characteristic local texture characteristic representation method, generating a binary code according to a comparison result, converting the binary code into a decimal number as a characteristic value, and extracting image characteristics;
s4, a learning model of the convolutional neural network CNN can learn the characteristic representation of the face through the face image and the corresponding label in the training data set, further perform the task of face recognition, verification or classification, and can improve the accuracy of the network and realize more accurate and reliable face recognition results by continuously adjusting the network structure and training parameters;
s5, preprocessing and extracting features of the acquired images, inputting the extracted features into a trained learning model of the convolutional neural network CNN, and confirming the identity of a patient by the model in a verification and comparison mode, wherein an authorization and control module authorizes the patient passing verification;
s51, if the entrance of the consulting room is confirmed to be the patient himself, allowing the patient to enter;
s52, if the entrance of the diagnosis room is confirmed to be not the patient himself, a voice prompt is sent out through a loudspeaker on the entrance of the diagnosis room to remind the patient himself to enter the diagnosis room;
s53, if the entrance of the consulting room is not the patient himself or the person associated with the patient, the consulting room is not allowed to enter the consulting room;
s6, controlling the intelligent lock on the department door to be automatically opened at the moment, so that the patient can enter the doctor.
Referring to fig. 2-4, the authorization and control module includes: the intelligent lock comprises a door plate 1, an intelligent lock 2 and an adjusting mechanism 3;
an intelligent lock 2 is arranged on the door plate 1, and an adjusting mechanism 3 is fixedly arranged in the door plate 1;
the door panel 1 is mounted with a display screen 101.
The face recognition and verification module comprises a face acquisition mechanism 4;
the adjusting mechanism 3 is fixedly connected with a portrait collecting mechanism 4.
The adjusting mechanism 3 comprises a motor 301, a threaded rod 302 and an adjusting block 303;
the motor 301 is fixedly connected with the inner wall of the door plate 1, a threaded rod 302 is fixedly connected with the output end of the motor 301, an adjusting block 303 is arranged on the outer wall of the threaded rod 302 in a threaded connection mode, and the adjusting block 303 is arranged in a sliding fit with the inner wall of the door plate 1. The adjusting block 303 is fixedly connected with the image acquisition mechanism 4.
The portrait acquisition mechanism 4 comprises a housing 401 and a camera 402;
the shell 401 is fixedly connected with the regulating block 303, the camera 402 is installed in the shell 401, the cleaning blocking cover 403 is arranged at the opening of the shell 401 in a sliding fit mode, a sponge strip is fixedly connected to one side of the cleaning blocking cover 403 and is arranged in sliding contact with the outer wall of the camera 402, a spring 404 is fixedly connected to one end of the cleaning blocking cover 403, the other end of the spring 404 is fixedly connected with the shell 401, and the cleaning blocking cover 403 is movably contacted with the inner wall of the door plate 1.
The implementation principle based on the intelligent medical management system is as follows: when a person registers a patient visit, a registration person information acquisition association module acquires facial information of the registration person through a camera fixedly arranged at the upper end of a registration machine, compares the facial information with facial features of the registration patient which needs to visit and is pre-stored in a database, and confirms whether the registration person is the patient himself or not; if the registering person is the patient himself, and meanwhile, the database stores the relevant information of the patient identity, the information association operation is not carried out; if the registering person is the patient himself (confirmed by comparing the patient identification card with the facial features); if the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient (such as address, telephone, facial features and the like) in a correlated manner; if the registered person is not the patient (such as parents or other persons of child patients, relatives of old people or patients with inconvenient actions, and the like), the acquired face characteristic information is associated with the patient information, and the associated information is stored; when the hospital number calling system calls the name of a corresponding patient, the patient stands at a department gate, then a face image is acquired through camera equipment on the department gate, a motor 301 is utilized to drive a connected threaded rod 302 to rotate, so that the threaded rod 302 drives a connected adjusting block 303 to move, a portrait acquisition mechanism 4 moves to a required position, at the moment, when a cleaning blocking cover 403 is not limited, the cleaning blocking cover 403 is automatically opened under the action of a spring 404, and the camera 402 acquires the face image of the patient; the system then adjusts the acquired image to the appropriate size, typically using square images, of dimensions such as 128x128 or 256x256, helping to maintain the aspect ratio of the image and having the input image the same size; through an image enhancement technology, the quality and the visual effect of an image are improved by utilizing histogram equalization, so that details and characteristics in a face image are enhanced, better input data are provided for a subsequent characteristic extraction and classification model, image data are subjected to standardized processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data have zero mean value and unit variance, and training of the model is facilitated;
then comparing each pixel point with the neighborhood pixels by using an LBP characteristic local texture characteristic representation method, generating a binary code according to a comparison result, converting the binary code into a decimal number as a characteristic value, and extracting image characteristics;
the learning model of the convolutional neural network CNN can learn the characteristic representation of the human face through training the human face image and the corresponding label in the data set, further carries out the task of identifying, verifying or classifying the human face, and can improve the accuracy of the network and realize more accurate and reliable human face recognition results by continuously adjusting the network structure and training parameters;
then, preprocessing and feature extraction are carried out on the acquired images, the extracted features are input into a trained learning model of a convolutional neural network CNN, the model confirms the identity of a patient in a verification and comparison mode, an authorization and control module authorizes the patient passing verification, and if the patient is confirmed to be the patient himself at the gate of a diagnosis room, the patient is allowed to enter; if the entrance of the office is confirmed to be not the patient himself, the person associated with the patient is sent out through a loudspeaker on the entrance of the office to remind the person and the patient himself to enter the office; if the gate of the office is confirmed to be not the patient himself or not the person associated with the patient, then it is not allowed to enter the office; when the patient is allowed to enter, the intelligent lock on the department door is controlled to be automatically opened, so that the patient can enter the doctor.
The application adopts the technical means such as the patient data acquisition module, and then realizes that when the patient is in a doctor, the identity information of the patient needs to be verified through the face recognition and verification module, and the door of the department can be controlled to be opened by the authorization and control module after the verification is successful, so that the patient who calls the number can enter the doctor to treat the doctor, the privacy leakage of the patient who is in the doctor due to the entrance of the person during the doctor is effectively avoided, and meanwhile, the queue insertion behavior is avoided, so that the management of the hospital is proper.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent medical management method is characterized by comprising the following steps:
s1, when a person registers a patient visit, a registration person information acquisition association module acquires facial information of the registration person through a camera fixedly arranged at the upper end of a registration machine, compares the facial information with facial features of registered patient to be treated, which are pre-stored in a database, confirms whether the registration person is the patient himself or herself, and associates the information;
s2, when a hospital call system calls the name of a corresponding patient, the patient stands at a department gate, then a face image is acquired through camera equipment on the department gate, then the system adjusts the acquired image to a proper size, the quality and the visual effect of the image are improved by histogram equalization through an image enhancement technology, image data are standardized, the average value of the image is subtracted from each pixel value, and then the standard deviation of the image is divided, so that the data have zero average value and unit variance, and training of a model is facilitated;
s3, comparing each pixel point with the neighborhood pixels by using an LBP characteristic local texture characteristic representation method, generating a binary code according to a comparison result, and converting the binary code into a decimal number as a characteristic value to extract image characteristics;
s4, a learning model of the convolutional neural network learns the characteristic representation of the face through the face image and the corresponding label in the training data set, so that the face recognition, verification or classification task is carried out, and the accuracy of the network is improved through continuously adjusting the network structure and the training parameters, so that a more accurate and reliable face recognition result is realized;
s5, preprocessing and extracting features of the acquired images, inputting the extracted features into a trained learning model of the convolutional neural network, and confirming the identity of a patient by the model in a verification and comparison mode, wherein an authorization and control module authorizes the patient passing verification;
s6, controlling an intelligent lock on a department gate to be automatically opened, so that a patient can enter a visit.
2. The smart medical management-based method of claim 1, wherein: the step S1 includes the steps of:
s11, if the registering person is the patient himself, and meanwhile, the relevant information of the patient identity is stored in the database, the information association operation is not carried out;
s12, if the registered person is the patient himself, but the patient related information is not stored in the database, automatically establishing a data file for the patient, and storing the information related to the patient in a correlated way;
and S13, if the registered person is not the patient, the acquired face characteristic information is associated with the patient information, and the associated information is stored.
3. The smart medical management-based method of claim 1, wherein: the step S5 includes the steps of:
s51, if the entrance of the consulting room is confirmed to be the patient himself, allowing the patient to enter;
s52, if the entrance of the diagnosis room is confirmed to be not the patient himself, a voice prompt is sent out through a loudspeaker on the entrance of the diagnosis room to remind the patient himself to enter the diagnosis room;
s53, if it is confirmed that the gate of the consulting room is not the patient himself or herself, nor the person associated with the patient, it is not allowed to enter the consulting room.
4. An intelligent medical management system comprising: the system comprises a data sharing module, a patient data acquisition module, a data processing and feature extraction module, a model building training module, a registration personnel information acquisition association module, a face recognition and verification module and an authorization and control module, and is characterized in that:
and a data sharing module: the data sharing module is used for sharing medical data and sharing the identity information of the patient during registration;
the registration personnel information acquisition and association module acquires facial information of registration personnel through a camera fixedly arranged at the upper end of the registration machine; correlating the acquired face characteristic information with patient information, and storing the correlated information;
patient data acquisition module: the patient data acquisition module is used for collecting shared data, including personal information and characteristic data of a patient;
and the data processing and feature extraction module is used for: the data processing and feature extraction module cleans, processes and standardizes the acquired data, and extracts useful features from the patient's data through a machine learning algorithm so that the machine learning system can correctly utilize the data;
model building training module: the model building training module performs training optimization treatment on the model of the convolutional neural network by building a learning model of the convolutional neural network and utilizing the data after treatment and feature extraction;
face recognition and verification module: the face recognition and verification module collects face images of a patient to be diagnosed through imaging equipment at a diagnosis room gate, and then performs verification and determination by using a convolutional neural network model;
and the authorization and control module: after the identity is verified to be correct, the authorization and control module automatically controls the door of the department to be opened, so that the patient with the called number enters the visit.
5. The intelligent medical management system according to claim 4, wherein: the data processing and feature extraction module comprises a data preprocessing unit and a feature extraction unit, wherein the data preprocessing unit cleans, processes and standardizes acquired data so that a machine learning system can correctly utilize the data, and the feature extraction unit extracts useful features from data of a patient through a machine learning algorithm, can conduct face recognition by utilizing face image data and extracts facial features.
6. The intelligent medical management system according to claim 5, wherein: the data preprocessing unit adjusts the acquired images to a proper size and enables all input images to have the same size; through an image enhancement technology, histogram equalization is utilized to improve the quality and the visual effect of an image, image data is subjected to standardization processing, the mean value of the image is subtracted from each pixel value, and then the pixel value is divided by the standard deviation of the image, so that the data has zero mean value and unit variance, and the model is convenient to train.
The feature extraction unit generates binary codes according to comparison results by comparing each pixel point with the neighborhood pixels by using an LBP feature local texture feature representation method, and then converts the binary codes into decimal numbers to serve as feature values.
7. The intelligent medical management system according to claim 4, wherein: the model building training module builds a learning model of the convolutional neural network, wherein the learning model consists of a plurality of convolutional layers, a pooling layer and a full-connection layer; the convolution layer can extract local features of the image, the pooling layer can reduce feature dimensions and maintain importance of the features, the full-connection layer can map the features to probabilities of different categories, the CNN can learn feature representation of the face through face images and corresponding labels in the training data set, further recognition, verification or classification tasks of the face are carried out, accuracy of the network can be improved through continuously adjusting network structures and training parameters, and more accurate and reliable face recognition results are achieved.
8. The intelligent medical management system according to claim 4, wherein: the face recognition and verification module can collect face images of the personnel to be treated by arranging the camera equipment on the gate of the department, then preprocessing and extracting the characteristics of the collected images, inputting the extracted characteristics into a trained learning model of the convolutional neural network, and confirming the identity of the patient by the model through verification and comparison.
9. The intelligent medical management system according to claim 4, wherein: the authorization and control module includes: door plant, intelligent lock and adjustment mechanism; the door plate is provided with an intelligent lock, and an adjusting mechanism is fixedly arranged in the door plate in a connecting way; the door plate is provided with a display screen;
the face recognition and verification module comprises a face acquisition mechanism;
the adjusting mechanism is fixedly connected with a portrait collecting mechanism.
10. The smart medical management system of claim 9, wherein: the adjusting mechanism comprises a motor, a threaded rod and an adjusting block;
the motor is fixedly connected with the inner wall of the door panel, a threaded rod is fixedly connected with the output end of the motor, an adjusting block is arranged on the outer wall of the threaded rod in a threaded connection manner, and the adjusting block is arranged in sliding fit with the inner wall of the door panel; the adjusting block is fixedly connected with the portrait collecting mechanism;
the portrait acquisition mechanism comprises a shell and a camera;
the shell is fixedly connected with the regulating block, the camera is installed in the shell, the sliding fit of the opening of the shell is provided with a cleaning blocking cover, one side of the cleaning blocking cover is fixedly connected with a sponge strip, and the sponge strip is in sliding contact with the outer wall of the camera to form a cleaning blocking cover and movably contact with the inner wall of the door plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311391511.6A CN117409935A (en) | 2023-10-25 | 2023-10-25 | Intelligent medical management system and management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311391511.6A CN117409935A (en) | 2023-10-25 | 2023-10-25 | Intelligent medical management system and management method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117409935A true CN117409935A (en) | 2024-01-16 |
Family
ID=89493977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311391511.6A Pending CN117409935A (en) | 2023-10-25 | 2023-10-25 | Intelligent medical management system and management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117409935A (en) |
-
2023
- 2023-10-25 CN CN202311391511.6A patent/CN117409935A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110491004B (en) | Resident community personnel safety management system and method | |
| CN110443923B (en) | Hotel safety management method based on artificial intelligence | |
| US7158657B2 (en) | Face image recording system | |
| US6504470B2 (en) | Access control method and apparatus for members and guests | |
| US6816603B2 (en) | Method and apparatus for remote medical monitoring incorporating video processing and system of motor tasks | |
| CN112233300A (en) | Community passing epidemic prevention monitoring joint defense system and method based on artificial intelligence | |
| CN102880781B (en) | On-line examination intelligent monitoring system | |
| CN113191725A (en) | Method and system for managing and controlling access of hospital personnel, storage medium, equipment and terminal | |
| CN111126219A (en) | Transformer substation personnel identity recognition system and method based on artificial intelligence | |
| CN114267111A (en) | All-in-one traffic control method, system and equipment | |
| CN109326009A (en) | A kind of system and method that speeds passage through customs based on recognition of face | |
| CN112151161A (en) | Health physical examination control system and control method based on biological recognition technology | |
| CN208580582U (en) | A kind of recognition of face assisting in diagnosis and treatment system | |
| CN118039193B (en) | 5G technology-based extra-hospital rehabilitation guidance and monitoring evaluation system | |
| CN117238452A (en) | Regional medical image cloud and inspection result mutual recognition sharing platform | |
| CN111798951A (en) | Self-help medical guide system for infectious diseases | |
| CN115410304A (en) | Self-learning-based chicken house breeding safety prevention and control method and system | |
| JP2002304651A (en) | Device and method for managing entering/leaving room, program for executing the same method and recording medium with the same execution program recorded thereon | |
| CN214476427U (en) | Intelligent admission information registration robot system | |
| CN110993122A (en) | Medical health information management system based on cloud computing | |
| CN117409935A (en) | Intelligent medical management system and management method | |
| CN116313021B (en) | Medical treatment management system and method for hospital | |
| CN113221725A (en) | Risk processing method and system | |
| KR20090065716A (en) | Ubiquitous security and healthcare system using the iris | |
| JP2013077067A (en) | Face authentication database management method, face authentication database management device, and face authentication database management program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |