CN116999026A - Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging - Google Patents

Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging Download PDF

Info

Publication number
CN116999026A
CN116999026A CN202310967608.0A CN202310967608A CN116999026A CN 116999026 A CN116999026 A CN 116999026A CN 202310967608 A CN202310967608 A CN 202310967608A CN 116999026 A CN116999026 A CN 116999026A
Authority
CN
China
Prior art keywords
infrared
patient
edge
chinese medicine
traditional chinese
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
Application number
CN202310967608.0A
Other languages
Chinese (zh)
Inventor
张永财
莫钰君
唐广发
黄林石
陈健林
陈晓书
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongguan City College
Original Assignee
Dongguan City College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Dongguan City College filed Critical Dongguan City College
Priority to CN202310967608.0A priority Critical patent/CN116999026A/en
Publication of CN116999026A publication Critical patent/CN116999026A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0075—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/117—Identification of persons
    • A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
    • A61B5/1176—Recognition of faces
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • A61B5/7445—Display arrangements, e.g. multiple display units
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • 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
    • 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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Fuzzy Systems (AREA)
  • Physiology (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Alternative & Traditional Medicine (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Human Computer Interaction (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a traditional Chinese medicine constitution identification method and equipment combining edge calculation and infrared imaging, wherein the method comprises the following steps: the method comprises the steps of collecting infrared images of all parts of a patient body through a terminal, and sending the infrared images to an edge end; analyzing the infrared image through the edge end to acquire temperature information of each part of the patient body; determining the areas with abnormal temperature in each part of the patient body, and marking the areas with abnormal temperature on the infrared image to obtain a composite infrared image; analyzing the temperature information of each part of the body of the patient according to the trained traditional Chinese medicine constitution identification model, and determining the traditional Chinese medicine constitution type of the patient; and transmitting the composite infrared image of the patient and the type of the physique of the traditional Chinese medicine to the cloud server. The infrared image of the user can be obtained through the infrared thermal imager, the speed and accuracy of data processing are improved by combining edge calculation, the operation is simple and convenient, the cost is low, and the infrared thermal imaging system is widely applied to various places such as hospitals, clinics and physical examination centers.

Description

Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging
Technical Field
The invention relates to the technical field of data analysis and processing, in particular to a traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging.
Background
The medical infrared thermal imaging technology can visualize and image concepts such as yin and yang, cold and heat abstracted from traditional Chinese medicine, is used for evaluating the change of yin and yang balance of a human body, identifies yin and yang and cold and heat of syndrome, has the characteristics of no contact, no radiation, no wound, rapidness and convenience and the like, is widely applied to the aspects of health evaluation of illness, early warning of diseases, evaluation of intervention effects and the like, and has good application prospects. Constitution is a comprehensive, relatively stable state of the human body that exists for a long time. Different traditional Chinese medicine syndrome types have obvious differences on infrared thermal imagers. The infrared thermal imaging technology provides visual evidence for the clinical differentiation and typing of the physique of the traditional Chinese medicine. According to the constitution type, the corresponding adjustment is made pertinently, the constitution is intervened in advance, and the occurrence probability of diseases can be effectively reduced, so that the development of the traditional Chinese medicine treatment without diseases is promoted.
However, the infrared thermal imaging technology currently has some defects in the application of traditional Chinese medicine physique: (1) lack of unified standards: the infrared equipment in all parts of the world has large difference, and technicians in clinical operation are different in level and do not have perfect comprehensive judgment capability; (2) lack of unified scientific thinking: at present, the traditional Chinese medicine physique division still adopts a scale evaluation method published by the Chinese medical society in 2009, and has larger deviation on the target crowd physique division. Because of the difference of the detected objects in the subjective understanding of individuals of the scale items, the constitution evaluation result can generate larger deviation, the grouping of target crowd is inaccurate and the result repeatability is poor; (3) Lack of large sample, multi-directional, multi-angle scientific data: at present, the research of the infrared thermal imaging technology in the application of the physique of traditional Chinese medicine is only the small sample experience research of individuals, and the follow-up analysis of the data is supported by the better automatic analysis software; and (4) full cloud processing: the existing medical infrared equipment mainly adopts full cloud processing, data needs to be transmitted in a long distance, and has certain disadvantages in processing time lag.
Therefore, those skilled in the art are required to develop a new technical solution to solve the above problems.
Disclosure of Invention
In order to overcome the problems in the related art, the invention discloses a traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging.
According to a first aspect of the disclosed embodiments of the present invention, there is provided a method for identifying a constitution of a Chinese medicine by combining edge calculation with infrared imaging, which is applied to a system for identifying a constitution of a Chinese medicine by combining edge calculation with infrared imaging, the system comprising: the cloud server comprises a plurality of terminals, a preset number of edge terminals and a cloud server, wherein the plurality of terminals are respectively and electrically connected with the preset number of edge terminals, and the edge terminals are electrically connected with the cloud server, and the method comprises the following steps:
collecting infrared images of all parts of the body of a patient through the terminal, and sending the infrared images to the edge end;
analyzing the infrared image through the edge end according to a preset temperature analysis strategy to acquire temperature information of each part of the patient body;
determining the areas with abnormal temperature in each part of the patient body, and marking the areas with abnormal temperature on the infrared image to obtain a composite infrared image;
analyzing the temperature information of each part of the body of the patient according to the trained traditional Chinese medicine constitution identification model, and determining the traditional Chinese medicine constitution type of the patient;
and transmitting the composite infrared image of the patient and the traditional Chinese medicine physique type to the cloud server.
Optionally, the acquiring, by the terminal, infrared images of each part of the patient's body, and sending the infrared images to an edge end includes:
collecting infrared images of all parts of a patient through the terminal, and preprocessing the infrared images, wherein the preprocessing comprises at least one of filtering noise reduction processing, target enhancement processing and image segmentation processing;
and sending the preprocessed infrared image to an edge end so as to analyze the preprocessed infrared image through the edge end.
Optionally, the sending the infrared image to an edge includes:
respectively determining task scheduling parameters between a terminal for collecting infrared images of a patient and each edge, wherein the task scheduling parameters comprise: task energy consumption, task execution time, task resource consumption and task reliability;
according to a preset task execution sequence scoring strategy, task execution sequence scoring between the terminal and each edge is obtained, wherein the task execution sequence scoring strategy is as follows:
Score(i)＝α*TEC(i)+β*PEC(i)+γ*REC(i)+δ*AEC(i)，
wherein i represents an ith task, alpha, beta, gamma and delta are all weight coefficients, score (i) is a task execution sequence Score, TEC (i) is task energy consumption, PEC (i) is task execution time, REC (i) is task resource consumption, and AEC (i) is task reliability;
according to the task execution sequence scores between the terminal and each edge, determining the edge corresponding to the task execution sequence score with the highest score as a target edge;
and sending the infrared image to the target edge.
Optionally, the terminal includes an information collecting and storing module, and the sending the infrared image to an edge includes:
the collected infrared images are sent to an information collection and storage module;
and transmitting the infrared image of the patient to an edge end through an information collection and storage module.
Optionally, the information collecting and storing module is used for acquiring the composite infrared image and the traditional Chinese medicine physique type of the patient from the edge end and/or the cloud server.
Optionally, the terminal includes: the infrared thermal imager is used for collecting infrared images of all parts of the body of the patient;
the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
Optionally, the method further comprises:
acquiring body temperature distribution information of a preset number of sample patients and the type of Chinese medicine physique;
taking body temperature distribution information of a sample patient as input of a neural network model, taking a corresponding traditional Chinese medicine physique type as output of the neural network model, and training the neural network model;
obtaining a trained traditional Chinese medicine physique recognition model.
According to a second aspect of the disclosed embodiments of the present invention, there is provided an apparatus comprising: the device comprises a device body, a touch screen, a face recognition camera, an infrared camera and a processor, wherein the touch screen, the face recognition camera and the infrared camera are respectively and electrically connected with the processor;
the touch screen, the face recognition camera and the infrared camera are respectively arranged on the front surface of the equipment body, and the processor is arranged in the equipment body;
the face recognition camera is used for collecting face information of a patient;
the infrared camera is used for collecting infrared images of all parts of the body of the patient;
the processor is used for identifying the identity information of the patient according to the face information of the patient, acquiring the medical record information of the patient according to the identity information of the patient, acquiring infrared images of all parts of the body of the patient acquired by the infrared camera and preprocessing the infrared images;
the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
Optionally, a network cable jack and a power line jack are arranged on the back of the equipment body;
the network cable jack is used for connecting a network cable, and the equipment is electrically connected with the terminal through the network cable.
Optionally, the side of equipment body is provided with the button of focusing and shoots the button, the button of focusing and shoot the button respectively with infrared camera electricity is connected.
In summary, through the technical scheme in the disclosed embodiments of the present invention, the following beneficial effects can be brought:
(1) The operation is simple and convenient: the invention comprises hardware and software modules such as a thermal infrared imager, a touch screen and the like, and has simple equipment hardware structure, simple operation and lower cost;
(2) The application places are quite wide: the invention can be widely applied to various scenes such as hospitals, clinics, community health service centers, schools, office places and the like, is not only suitable for disease detection and diagnosis, but also can play an important role in the fields of health management, physical examination and the like;
(3) The data processing speed is faster: the invention discloses a method for allocating computing resources near the network edge side of a user and a data source by combining edge computing, and executing computing through a position closer to the data source, thereby providing high-bandwidth, low-delay, low-energy consumption and high-safety computing service for the user.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate the disclosure and together with the description serve to explain, but do not limit the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of recognition of a physical condition of a traditional Chinese medical science combining edge computing with infrared imaging, according to an exemplary embodiment;
FIG. 2 is a schematic diagram of a system for recognizing physical constitution of traditional Chinese medicine combining edge calculation and infrared imaging according to an exemplary embodiment;
FIG. 3 is a flow chart of a target edge determination method according to the one shown in FIG. 1;
FIG. 4 is a front view of an apparatus according to an exemplary embodiment;
FIG. 5 is a rear view of an apparatus according to the one shown in FIG. 4;
fig. 6 is a side view of an apparatus according to the one shown in fig. 4.
Detailed Description
The following describes in detail the embodiments of the present disclosure with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the disclosure, are not intended to limit the disclosure.
Fig. 1 is a flowchart illustrating a method for recognizing a constitution of a traditional Chinese medicine combining edge calculation and infrared imaging according to an exemplary embodiment, as shown in fig. 1, the method is applied to a system for recognizing a constitution of a traditional Chinese medicine combining edge calculation and infrared imaging, as shown in fig. 2, the system includes: the cloud server comprises a plurality of terminals, a preset number of edge terminals and a cloud server, wherein the plurality of terminals are respectively and electrically connected with the preset number of edge terminals, and the edge terminals are electrically connected with the cloud server, and the method comprises the following steps:
in step 101, an infrared image of each part of the patient's body is acquired by the terminal and sent to the edge.
In an exemplary embodiment of the present invention, a plurality of terminals and a preset number of edge terminals (typically, routers, base stations, etc.) together form a local area network, and after the terminals collect infrared images of all parts of a patient's body, the terminals send the infrared images to the edge terminals near the terminals due to limited data analysis processing capacity, and the edge terminals process the data and return the processed results to the terminals.
Optionally, the terminal collects infrared images of each part of the patient body, and sends the infrared images to the edge, including: collecting infrared images of all parts of a patient through the terminal, and preprocessing the infrared images, wherein the preprocessing comprises at least one of filtering noise reduction processing, target enhancement processing and image segmentation processing; and sending the preprocessed infrared image to an edge end so as to analyze the preprocessed infrared image through the edge end.
For example, before the terminal sends the infrared image to the edge, the terminal performs preprocessing (including at least one of filtering noise reduction processing, target enhancement processing and image segmentation processing) on the infrared image, so that the preprocessed infrared image received by the edge is not interfered by noise, the target image is more prominent relative to the background image, and the accuracy and processing speed of the edge in data processing are enhanced.
In addition, the terminal comprises an information collection and storage module, and the information collection and storage module is used for sending the infrared image to the edge end and comprises: the collected infrared images are sent to an information collection and storage module; and transmitting the infrared image of the patient to the edge end through an information collection and storage module.
The terminal comprises an information collection and storage module, the infrared thermal imager collects infrared images of all parts of the body of the patient, then the infrared images are sent to the information collection and storage module, the information collection and storage module backs up the infrared images and sends the infrared images to the edge end, and the edge end analyzes and processes the infrared images. The invention also stores the patient identity information, the history check record and the like in the information collecting and storing module.
In addition, the information collection and storage module is also used for acquiring the composite infrared image and the traditional Chinese medicine physique type of the patient from the edge end and/or the cloud server.
Optionally, the terminal includes: the infrared thermal imager is used for collecting infrared images of all parts of the body of the patient; the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
By way of example, it will be appreciated that the terminal is preferably comprised of a thermal infrared imager and a touch screen for a device that facilitates identification information and infrared image acquisition of a patient by a physician. The infrared thermal imager is a cold Wen Jixin high-precision infrared thermal imager and is used for collecting infrared images of all parts of the body of a patient. The thermal infrared imager can be provided with the functions of high-precision shooting mode, shooting angle adjustment, focusing and the like in the acquisition process, and the color band is adjusted according to the shot infrared image, so that the authenticity of data can be ensured, and the acquired image is rich in detail. Further, the thermal infrared imager parameters further include: detector resolution, thermal sensitivity, spatial resolution, field angle, spectral range, etc. The detector resolution refers to how many pixels the detector of the thermal imager has. Higher resolution means that each image contains more information, more pixels and more details, so that the temperature can be measured more accurately. Thermal sensitivity (NETD) (noise equivalent temperature difference) is a key parameter in evaluating mid-wave (MWIR) and long-wave (LWIR) thermal infrared imagers. It is a value representing the signal-to-noise ratio of the temperature difference, which is equivalent to the instantaneous noise of the thermal imager, i.e., approximately represents the minimum temperature difference that the thermal imager can resolve. Spatial resolution refers to the minimum distance that two adjacent features can be identified by a thermal infrared imager. The field of view (FOV) is determined by the thermal infrared imager lens. The field of view determines the distance and range that a thermal imager can capture. According to different use scenes, lenses with different view angles, such as a wide-angle (48 degrees) lens or a tele lens (12 degrees or 7 degrees), are selected. Specifically, the field angle is a horizontal field angle and a vertical field angle. Specifically, horizontal field angle= (image pitch/lens focal length)) × horizontal pixel count/17.45, and vertical field angle= (image pitch/lens focal length)) × vertical pixel count/17.45. The spectral range is the wavelength range in micrometers (μm) detected by the sensor in the thermal imager. Still further, the thermal infrared imager parameters displayed on the touch screen further include: the emissivity, before the thermal infrared imager is used for testing, also needs to set parameters of the thermal infrared imager, wherein the emissivity is set as the most critical, and the effect on the measurement shooting result is the greatest. In addition, the thermal infrared imager also comprises parameter setting options such as temperature, humidity, distance and the like.
In addition, the terminal can also comprise an identity information recognition module of the patient, which is used for collecting biological characteristic information such as face information of the patient and recognizing the identity information of the patient, so that medical staff can acquire medical record information of the patient according to the identity information of the patient. In another embodiment of the invention, the data sharing application can be realized through a cloud system, an APP, an applet and the like, so that the high efficiency and convenience of patient examination and report review are realized.
In step 102, the infrared image is analyzed by the edge according to a preset temperature analysis strategy, so as to obtain temperature information of each part of the patient body.
For example, the edge end determines the temperature information of each part of the patient body according to the infrared image, and in the embodiment of the invention, a dialogue-based hybrid artificial intelligence labeling method is adopted to label and analyze the infrared image data so as to assist doctors in analysis and diagnosis.
In step 103, determining the region with abnormal temperature in each part of the patient body, and marking the region with abnormal temperature on the infrared image to obtain a composite infrared image.
For example, after the edge obtains the temperatures of the parts of the patient's body as shown in step 102, it is determined whether there are abnormal temperature areas in the parts of the patient's body according to the pre-stored standard temperature information of the parts of the patient's body, and the abnormal temperature areas are marked (preferably, the marked composite infrared image may be obtained by deepening the color of the parts of the body in the infrared image of the patient). The composite infrared image can clearly show the abnormal temperature area and the normal temperature area in the body part of the patient, and helps doctors to quickly find and analyze the pathology.
In step 104, the temperature information of each part of the patient's body is analyzed according to the trained traditional Chinese medicine physique recognition model, and the type of the traditional Chinese medicine physique of the patient is determined.
For example, a pre-trained traditional Chinese medicine physique recognition model is deployed in the edge end, so that temperature information of each part of the body of a patient input into the model can be analyzed, and the traditional Chinese medicine physique type of the patient can be output. It should be noted that the constitutions of traditional Chinese medicine include nine types, namely: mild physique, yang deficiency physique, yin deficiency physique, qi deficiency physique, phlegm-dampness physique, damp-heat physique, blood stasis physique, specific intrinsic physique and qi Yu Tizhi, wherein mild physique is a relatively healthy traditional Chinese medicine physique type, and the other eight traditional Chinese medicine physiques are all in a sub-health state.
In the embodiment of the invention, the traditional Chinese medicine physique type is obtained by analyzing the temperature information of each part of the body of the patient, and the metabolic level of each part of the body of the patient is also analyzed according to the temperature information of each part of the body of the patient, so that the traditional Chinese medicine physique type of the patient is analyzed according to the metabolic level.
It can be appreciated that in the embodiment of the disclosure, the terminal communicates with the edge terminal, so that low-latency performance and high-stability of traditional Chinese medicine physique type identification can be realized, and meanwhile, because the edge terminal is also located in a local area network, traditional Chinese medicine physique judgment with localized privacy data can be realized, and information leakage caused by uploading information of a patient to a cloud server when the traditional Chinese medicine physique type is judged through the cloud server is prevented.
In addition, the edge end performs data processing, so that the traditional Chinese medicine physique evaluation work in a large scale can be completed, and the accuracy of physique type judgment can be continuously improved through local training.
It should be noted that the method further includes: acquiring body temperature distribution information of a preset number of sample patients and the type of Chinese medicine physique; taking body temperature distribution information of a sample patient as input of a neural network model, taking a corresponding traditional Chinese medicine physique type as output of the neural network model, and training the neural network model; obtaining a trained traditional Chinese medicine physique recognition model.
The sample patient is sample data for training the traditional Chinese medicine constitution identification model in the disclosed embodiment of the invention, a large amount of temperature information and traditional Chinese medicine constitution types of all parts of the body of the sample patient are obtained, the information is respectively used as input and output of the neural network model, the neural network model is trained, and training is stopped and the traditional Chinese medicine constitution identification model is obtained until the loss function value of the trained neural network model is smaller than a preset value. The traditional Chinese medicine physique recognition model can continuously improve the accuracy of the model through updated sample data and local training.
In step 105, the composite infrared image and the traditional Chinese medicine physical type of the patient are transmitted to the cloud server.
By way of example, after the composite infrared image and the traditional Chinese medicine physique type of the patient are obtained, the information can be transmitted to the cloud server, so that medical staff can conveniently call the composite infrared image and the traditional Chinese medicine physique type information of the patient in the follow-up inquiry process of the patient, and diagnosis of the patient by the medical staff is facilitated. Furthermore, the information of the patient can be used as sample data for updating and training the traditional Chinese medicine physique recognition model so as to further improve the accuracy of the model recognition result.
Fig. 3 is a flowchart of a target edge determining method according to the method shown in fig. 1, and as shown in fig. 3, the method includes:
in step 301, task scheduling parameters between a terminal acquiring an infrared image of a patient and each edge are determined, respectively.
Wherein the task scheduling parameters include: task energy consumption, task execution time, task resource consumption, and task reliability.
Illustratively, a task scheduling line is formed between the terminal for collecting the infrared image of the patient and each edge, and task scheduling parameters of each task scheduling line include: task energy consumption index, task execution time index, task resource consumption index and task reliability index. The task energy consumption index is used for measuring energy consumed by the edge equipment in the task execution process, the task execution time index is used for measuring time required by completing the task, the task resource consumption index is used for representing resource occupation conditions of the edge equipment such as calculation, storage and network, and the task reliability index is used for describing the reliability requirement of the task in the edge environment.
In step 302, a task execution sequence score between the terminal and each edge is obtained according to a preset task execution sequence scoring policy.
Wherein, the task execution sequence scoring strategy is: score (i) =α TEC (i) +β PEC (i) +γ REC (i) +δ AEC (i), wherein i represents the ith task, α, β, γ, δ are all weight coefficients, score (i) is a task execution order Score, TEC (i) is task energy consumption, PEC (i) is task execution time, REC (i) is task resource consumption, AEC (i) is task reliability.
In step 303, according to the task execution sequence score between the terminal and each edge, the edge corresponding to the task execution sequence score with the highest score is determined as the target edge.
In step 304, the infrared image is sent to the target edge.
In the exemplary embodiment of the present invention, after the terminal collects the infrared image of the patient, the computing resource is deployed near the network edge side of the user and the data source, and the computing is performed by the edge end (such as the router and the base station) with the highest scoring of the task execution sequence, so as to provide the high-bandwidth, low-delay, low-energy consumption and high-safety computing service for the user. It can be understood that if the edge end with the highest task execution sequence score cannot receive the infrared image, the edge end corresponding to the task execution sequence score is sequentially selected as the target edge end to receive the infrared image according to the sequence from high to low of the task execution sequence score.
In addition, in other embodiments of the present disclosure, there are other edge computing task scheduling algorithms, such as genetic algorithm, particle swarm algorithm, greedy algorithm, etc., which select appropriate optimization objectives and strategies to perform task scheduling according to the specific situation.
It should be noted that the specific edge computing task scheduling formulas and algorithms may be different according to the actual application scenario and requirements. The above is only an example, and the actual application needs to be adjusted and optimized according to specific situations.
Fig. 4 is a front view of an apparatus according to an exemplary embodiment, the apparatus comprising: the device body, the face recognition camera 410, the infrared camera 420, the touch screen 430 and a processor (not shown in the figure), wherein the touch screen 430, the face recognition camera 410 and the infrared camera 420 are respectively and electrically connected with the processor; the touch screen 430, the face recognition camera 410 and the infrared camera 420 are respectively arranged on the front surface of the equipment body, and the processor is arranged in the equipment body; the face recognition camera 410 is used for collecting face information of a patient; the infrared camera 420 is used for collecting infrared images of various parts of the patient body; the processor is configured to identify identity information of a patient according to face information of the patient, acquire medical record information of the patient according to the identity information of the patient, acquire infrared images of all parts of the patient's body acquired by the infrared camera 420, and perform preprocessing on the infrared images; the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
Fig. 5 is a rear view of an apparatus according to fig. 4, as shown in fig. 5, the rear of the apparatus body being provided with a wire insertion hole 440 and a power wire insertion hole 450; the wire jack 440 is used to connect a wire through which the device is electrically connected to a terminal.
Fig. 6 is a side view of an apparatus according to fig. 4, as shown in fig. 6, a side of the apparatus body is provided with a focus button 460 and a photographing button 470, and the focus button 460 and the photographing button 470 are electrically connected to the infrared camera, respectively.
By way of example, the device in the embodiment of the invention inherits the thermal infrared imager, the face recognition module, the touch screen and the like, and medical staff can acquire the face information of a patient through the device and recognize the identity information of the patient, so that the medical record information of the patient is acquired. And then the infrared images of all parts of the body of the patient are acquired through the equipment, and the infrared images are sent to the edge end through a network cable (a wireless transmission module is also used) for data processing. In addition, still be provided with the button of focusing and shoot the button on this equipment, medical personnel also can be through the shooting angle of this equipment adjustment infrared camera, and the medical personnel of being convenient for gathers more clear infrared image.
In summary, the present invention discloses a method and apparatus for recognizing physique of traditional Chinese medicine by combining edge calculation and infrared imaging, the method comprising: the method comprises the steps of collecting infrared images of all parts of a patient body through a terminal, and sending the infrared images to an edge end; analyzing the infrared image through the edge end to acquire temperature information of each part of the patient body; determining the areas with abnormal temperature in each part of the patient body, and marking the areas with abnormal temperature on the infrared image to obtain a composite infrared image; analyzing the temperature information of each part of the body of the patient according to the trained traditional Chinese medicine constitution identification model, and determining the traditional Chinese medicine constitution type of the patient; and transmitting the composite infrared image of the patient and the type of the physique of the traditional Chinese medicine to the cloud server. The infrared image of the user can be obtained through the infrared thermal imager, the speed and accuracy of data processing are improved by combining edge calculation, the operation is simple and convenient, the cost is low, and the infrared thermal imaging system is widely applied to various places such as hospitals, clinics and physical examination centers.
The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and all the simple modifications belong to the protection scope of the present disclosure.
In addition, the specific features described in the foregoing embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, the present disclosure does not further describe various possible combinations.
Moreover, any combination between the various embodiments of the present disclosure is possible as long as it does not depart from the spirit of the present disclosure, which should also be construed as the disclosure of the present disclosure.

Claims (10)

1. The traditional Chinese medicine constitution identification method combining edge calculation and infrared imaging is characterized by being applied to a traditional Chinese medicine constitution identification system combining edge calculation and infrared imaging, and the system comprises the following steps: the cloud server comprises a plurality of terminals, a preset number of edge terminals and a cloud server, wherein the plurality of terminals are respectively and electrically connected with the preset number of edge terminals, and the edge terminals are electrically connected with the cloud server, and the method comprises the following steps:
collecting infrared images of all parts of the body of a patient through the terminal, and sending the infrared images to the edge end;
analyzing the infrared image through the edge end according to a preset temperature analysis strategy to acquire temperature information of each part of the patient body;
determining the areas with abnormal temperature in each part of the patient body, and marking the areas with abnormal temperature on the infrared image to obtain a composite infrared image;
analyzing the temperature information of each part of the body of the patient according to the trained traditional Chinese medicine constitution identification model, and determining the traditional Chinese medicine constitution type of the patient;
and transmitting the composite infrared image of the patient and the traditional Chinese medicine physique type to the cloud server.
2. The method for recognizing physique in TCM according to claim 1, wherein the step of acquiring infrared images of each part of the patient's body through the terminal and transmitting the infrared images to the edge terminal comprises:
collecting infrared images of all parts of a patient through the terminal, and preprocessing the infrared images, wherein the preprocessing comprises at least one of filtering noise reduction processing, target enhancement processing and image segmentation processing;
and sending the preprocessed infrared image to an edge end so as to analyze the preprocessed infrared image through the edge end.
3. The method for identifying a physical constitution of a traditional Chinese medicine by combining edge calculation and infrared imaging according to claim 1, wherein the step of transmitting the infrared image to an edge end comprises the steps of:
respectively determining task scheduling parameters between a terminal for collecting infrared images of a patient and each edge, wherein the task scheduling parameters comprise: task energy consumption, task execution time, task resource consumption and task reliability;
according to a preset task execution sequence scoring strategy, task execution sequence scoring between the terminal and each edge is obtained, wherein the task execution sequence scoring strategy is as follows:
Score(i)＝α*TEC(i)+β*PEC(i)+γ*REC(i)+δ*AEC(i)，
wherein i represents an ith task, alpha, beta, gamma and delta are all weight coefficients, score (i) is a task execution sequence Score, TEC (i) is task energy consumption, PEC (i) is task execution time, REC (i) is task resource consumption, and AEC (i) is task reliability;
according to the task execution sequence scores between the terminal and each edge, determining the edge corresponding to the task execution sequence score with the highest score as a target edge;
and sending the infrared image to the target edge.
4. The method for recognizing physique in TCM according to claim 1, wherein the terminal includes an information collecting and storing module, and the transmitting the infrared image to the edge terminal includes:
the collected infrared images are sent to an information collection and storage module;
and transmitting the infrared image of the patient to an edge end through an information collection and storage module.
5. The method for identifying the physique of the traditional Chinese medicine by combining edge calculation and infrared imaging according to claim 1, wherein the information collection and storage module is used for acquiring the composite infrared image and the physique type of the patient from an edge end and/or a cloud server.
6. The method for recognizing physique in combination with edge computing and infrared imaging according to claim 1, wherein the terminal comprises: the infrared thermal imager is used for collecting infrared images of all parts of the body of the patient;
the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
7. The method for identifying a physical constitution of a traditional Chinese medicine combining edge calculation and infrared imaging according to claim 1, wherein the method further comprises:
acquiring body temperature distribution information of a preset number of sample patients and the type of Chinese medicine physique;
taking body temperature distribution information of a sample patient as input of a neural network model, taking a corresponding traditional Chinese medicine physique type as output of the neural network model, and training the neural network model;
obtaining a trained traditional Chinese medicine physique recognition model.
8. An apparatus, the apparatus comprising: the device comprises a device body, a touch screen, a face recognition camera, an infrared camera and a processor, wherein the touch screen, the face recognition camera and the infrared camera are respectively and electrically connected with the processor;
the touch screen, the face recognition camera and the infrared camera are respectively arranged on the front surface of the equipment body, and the processor is arranged in the equipment body;
the face recognition camera is used for collecting face information of a patient;
the infrared camera is used for collecting infrared images of all parts of the body of the patient;
the processor is used for identifying the identity information of the patient according to the face information of the patient, acquiring the medical record information of the patient according to the identity information of the patient, acquiring infrared images of all parts of the body of the patient acquired by the infrared camera and preprocessing the infrared images;
the touch screen is used for displaying identity information, medical record information, thermal infrared imager parameter setting information and infrared image information of a patient.
9. The device of claim 8, wherein the back of the device body is provided with a network cable jack and a power cord jack;
the network cable jack is used for connecting a network cable, and the equipment is electrically connected with the terminal through the network cable.
10. The device of claim 8, wherein a focusing button and a photographing button are provided on a side surface of the device body, and the focusing button and the photographing button are electrically connected with the infrared camera, respectively.
CN202310967608.0A 2023-08-02 2023-08-02 Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging Pending CN116999026A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310967608.0A CN116999026A (en) 2023-08-02 2023-08-02 Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310967608.0A CN116999026A (en) 2023-08-02 2023-08-02 Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging

Publications (1)

Publication Number Publication Date
CN116999026A true CN116999026A (en) 2023-11-07

Family

ID=88570536

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310967608.0A Pending CN116999026A (en) 2023-08-02 2023-08-02 Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging

Country Status (1)

Country Link
CN (1) CN116999026A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117766103A (en) * 2023-12-29 2024-03-26 东莞市中医院 Digital system and equipment for evaluating curative effect of acupuncture and moxibustion treatment on dysmenorrhea by combining infrared imaging

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117766103A (en) * 2023-12-29 2024-03-26 东莞市中医院 Digital system and equipment for evaluating curative effect of acupuncture and moxibustion treatment on dysmenorrhea by combining infrared imaging

Similar Documents

Publication Publication Date Title
CN109190540B (en) Biopsy region prediction method, image recognition device, and storage medium
CN111524580B (en) Virus screening and epidemic prevention system and method based on neural network
US10127665B1 (en) Intelligent assistant judgment system for images of cervix uteri and processing method thereof
Bevilacqua et al. A novel approach to evaluate blood parameters using computer vision techniques
CN209029110U (en) Chinese medicine facial diagnosis is health management system arranged
CN109064469B (en) Sperm quality detector and sperm quality detection system
CN104217117B (en) A kind of wisdom hospital information system using user as core
CN116999026A (en) Traditional Chinese medicine physique identification method and equipment combining edge calculation and infrared imaging
CN111863216A (en) Vision screening and managing system and method
CN116189884B (en) Multi-mode fusion traditional Chinese medicine physique judging method and system based on facial vision
CN105678075A (en) Blood cell morphological analysis internet-of-things detection and diagnosis method and platform
CN109106333A (en) A kind of self-service vision drop system of automatic adjustable and device
CN211602181U (en) Integrated temperature measurement electronic class board
CN111524093A (en) Intelligent screening method and system for abnormal tongue picture
CN113537210A (en) Temperature detection method, device, system, computer equipment and storage medium
CN113724244A (en) Health monitoring method, device and system, health examination equipment and medium
CN108717872A (en) Health analysis method and system based on face, hard recognition and big data
Li et al. Lighting measurement with a 360° panoramic camera: Part 2–Applications
US20190371004A1 (en) System and method for determining skin color, method for generating icc profile, and image capturing device
CN113362951A (en) Human body infrared thermal structure attendance and health assessment and epidemic prevention early warning system and method
CN109145861A (en) Emotion identification device and method, head-mounted display apparatus, storage medium
CN111310717A (en) Intelligent screening and identity recognition device for non-sensible body temperature of sports people
CN112651270A (en) Gaze information determination method and apparatus, terminal device and display object
CN110321781A (en) A kind of signal processing method and device for heed contacted measure
CN110279406A (en) A kind of touchless pulse frequency measurement method and device based on camera

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination