CN113539486A - Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change - Google Patents
Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change Download PDFInfo
- Publication number
- CN113539486A CN113539486A CN202111077108.7A CN202111077108A CN113539486A CN 113539486 A CN113539486 A CN 113539486A CN 202111077108 A CN202111077108 A CN 202111077108A CN 113539486 A CN113539486 A CN 113539486A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- data
- medical record
- tongue
- 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
- 230000001815 facial effect Effects 0.000 title claims abstract description 48
- 239000003814 drug Substances 0.000 title claims abstract description 33
- 230000036541 health Effects 0.000 title claims abstract description 26
- 230000008859 change Effects 0.000 title claims abstract description 25
- 230000003862 health status Effects 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 29
- 208000024891 symptom Diseases 0.000 claims description 68
- 238000000034 method Methods 0.000 claims description 36
- 208000011580 syndromic disease Diseases 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000010219 correlation analysis Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 18
- 208000017667 Chronic Disease Diseases 0.000 claims description 17
- 238000011835 investigation Methods 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 239000011248 coating agent Substances 0.000 claims description 7
- 238000000576 coating method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 206010060926 abdominal symptom Diseases 0.000 claims description 4
- 208000027407 head symptom Diseases 0.000 claims description 4
- 230000009885 systemic effect Effects 0.000 claims description 4
- 230000005284 excitation Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 201000010099 disease Diseases 0.000 abstract description 33
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 33
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000007774 longterm Effects 0.000 abstract description 4
- 238000003745 diagnosis Methods 0.000 description 13
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 210000004072 lung Anatomy 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 230000007812 deficiency Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 229940079593 drug Drugs 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 206010062717 Increased upper airway secretion Diseases 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 208000026435 phlegm Diseases 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 208000006820 Arthralgia Diseases 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 2
- 208000008454 Hyperhidrosis Diseases 0.000 description 2
- 206010024264 Lethargy Diseases 0.000 description 2
- 206010028735 Nasal congestion Diseases 0.000 description 2
- 206010041235 Snoring Diseases 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 210000000038 chest Anatomy 0.000 description 2
- 238000003759 clinical diagnosis Methods 0.000 description 2
- 238000003748 differential diagnosis Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 210000003734 kidney Anatomy 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 206010041232 sneezing Diseases 0.000 description 2
- 230000035900 sweating Effects 0.000 description 2
- 206010007558 Cardiac failure chronic Diseases 0.000 description 1
- 206010010774 Constipation Diseases 0.000 description 1
- 206010061819 Disease recurrence Diseases 0.000 description 1
- 206010015137 Eructation Diseases 0.000 description 1
- 208000031361 Hiccup Diseases 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 240000000543 Pentas lanceolata Species 0.000 description 1
- 241001282135 Poromitra oscitans Species 0.000 description 1
- 208000023146 Pre-existing disease Diseases 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 206010041956 Stasis syndrome Diseases 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 206010048232 Yawning Diseases 0.000 description 1
- 208000031971 Yin Deficiency Diseases 0.000 description 1
- 238000001467 acupuncture Methods 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 208000027687 belching Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000005634 blind loop syndrome Diseases 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 208000020832 chronic kidney disease Diseases 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 208000035850 clinical syndrome Diseases 0.000 description 1
- 208000010877 cognitive disease Diseases 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 210000002249 digestive system Anatomy 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000002124 endocrine Effects 0.000 description 1
- 210000000750 endocrine system Anatomy 0.000 description 1
- 206010016256 fatigue Diseases 0.000 description 1
- 230000002550 fecal effect Effects 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008376 long-term health Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000002485 urinary effect Effects 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 230000008673 vomiting Effects 0.000 description 1
Images
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
本发明涉及健康管理领域，特别是一种基于中医面舌象动态变化的健康状态辨识系统。包括面舌象采集模块、信息录入模块以及服务器，所述服务器包括用户管理单元、病历管理单元以及数据处理单元。本发明通过基于长期样本数据之间的关联性，对录入的问诊信息、采集到的面舌象图片信息、声音信息进行分析，将动态采集数据的结果进行可视化展示，也可为构建知识图谱提供个体健康状态动态数据源，能够有效的对人体的疾病、健康状态进行诊断，且具备便于推广、使用方便、形式新颖、结果精确的优点。
The invention relates to the field of health management, in particular to a health state identification system based on the dynamic change of the facial and tongue images of traditional Chinese medicine. It includes a face and tongue image acquisition module, an information input module and a server. The server includes a user management unit, a medical record management unit and a data processing unit. Based on the correlation between long-term sample data, the present invention analyzes the entered consultation information, the collected face and tongue image information, and the sound information, and visualizes the results of the dynamic collection of data, which can also be used to construct a knowledge map. Provides a dynamic data source of individual health status, which can effectively diagnose the disease and health status of the human body, and has the advantages of easy promotion, convenient use, novel form and accurate results.
Description
技术领域technical field
本发明涉及健康管理领域，特别是一种基于中医面舌象动态变化的健康状态辨识系统。The invention relates to the field of health management, in particular to a health state identification system based on the dynamic change of the facial and tongue images of traditional Chinese medicine.
背景技术Background technique
中医在“治未病”方面优势显著。中医“治未病”最早源于《黄帝内经》所注：“上工治未病，不治已病，此之谓也”。“治未病”有四要点：未病先防、欲病救萌、既病防变、瘥后防复。一是指要防病于未然，指身体处于健康状态；二指疾病还处于萌芽状态或将发未发之时，就采取有效措施；三指疾病的发生后，既病后要防其传变，需及时诊断治疗；四指预防疾病复发。中医辨证讲究望、闻、问、切四诊合参，推断出病因、病位和病性等。Traditional Chinese medicine has significant advantages in "preventing disease". The "preventive disease treatment" of traditional Chinese medicine originated from the annotation in "The Yellow Emperor's Classic of Internal Medicine": "Shanggong treats pre-existing diseases, but does not treat already-existing diseases, this is what is called." There are four main points in "treating the disease before it": prevention before the disease, saving the sprout from the disease, preventing the disease after the disease, and preventing the relapse after the disease. The first refers to preventing the disease before it occurs, which means that the body is in a healthy state; the second refers to taking effective measures when the disease is still in its infancy or about to develop; the third refers to the occurrence of the disease, and it is necessary to prevent its spread after the disease. , need timely diagnosis and treatment; four fingers to prevent disease recurrence. TCM syndrome differentiation pays attention to looking, smelling, asking, and diagnosing the four factors together, and infers the etiology, location and nature of the disease.
随着计算机技术的发展，在面舌诊方面，目前已经有许多治未病的健康管理系统，也有相应的智能医疗系统，通过智能医疗系统采集用户图像，根据智能镜对图像上面部面型、面色、唇色、舌苔、舌形等特征进行分析，得出相应的症状信息等等。With the development of computer technology, in terms of face and tongue diagnosis, there are already many health management systems for pre-disease treatment, and corresponding intelligent medical systems. The complexion, lip color, tongue coating, tongue shape and other characteristics are analyzed to obtain corresponding symptom information and so on.
近年来面诊、舌诊客观化研究成果显著，但是还存在很多不足。其中的关键问题就是面部、舌部信息跟个体差异关系紧密，仅仅从统一面诊、舌诊客观化标准的角度出发无法真正发挥望诊在临床诊断中的作用。当前国内外学者关于望诊标准化的研究没有结合当时的外界环境特点和病人的个体差异，也没有针对疾病的发生、发展和变化这一动态过程进行深入分析。更没有一种基于中医的动态思维、使用便捷、结果准确适用于慢性病的健康状态辨识系统。In recent years, the research on the objectification of face diagnosis and tongue diagnosis has achieved remarkable results, but there are still many deficiencies. The key problem is that face and tongue information are closely related to individual differences. Only from the perspective of unifying the objective standards of face diagnosis and tongue diagnosis cannot really play the role of inspection in clinical diagnosis. The current research on the standardization of inspection by domestic and foreign scholars has not taken into account the characteristics of the external environment at that time and the individual differences of patients, and has not conducted in-depth analysis of the dynamic process of the occurrence, development and change of the disease. There is also no health status identification system based on traditional Chinese medicine, which is easy to use, and has accurate results for chronic diseases.
发明内容SUMMARY OF THE INVENTION
本发明的目的在于克服现有技术中所存在的没有一种基于中医的动态思维、使用便捷、结果准确适用于慢性病的健康状态辨识系统，提供一种基于中医面舌象动态变化的健康状态辨识系统。The purpose of the present invention is to overcome the existing in the prior art that there is no dynamic thinking based on traditional Chinese medicine, a health state identification system that is easy to use, and has accurate results for chronic diseases, and provides a health state identification system based on the dynamic changes of the face and tongue image of traditional Chinese medicine. system.
为了实现上述发明目的，本发明提供了以下技术方案：In order to achieve the above-mentioned purpose of the invention, the present invention provides the following technical solutions:
一种基于中医面舌象动态变化的健康状态辨识系统，包括面舌象采集模块、信息录入模块以及服务器，所述服务器包括用户管理单元、病历管理单元以及数据处理单元；A health state identification system based on the dynamic changes of Chinese medicine facial and tongue images, comprising a facial and tongue image acquisition module, an information input module and a server, the server comprising a user management unit, a medical record management unit and a data processing unit;
所述面舌象采集模块用于采集用户的面舌像数据，并上传到所述病历管理单元；The face and tongue image collection module is used to collect the user's face and tongue image data and upload it to the medical record management unit;
所述信息录入模块用于录入所述用户的症状调查信息以及所述用户的个人信息，并将所述症状调查信息上传到所述病历管理单元，所述个人信息上传到所述用户管理单元；The information input module is used to input the symptom investigation information of the user and the personal information of the user, and upload the symptom investigation information to the medical record management unit, and the personal information is uploaded to the user management unit;
所述用户管理单元用于增删、修改以及管理所述用户的账号信息，所述账号信息包括所述个人信息；The user management unit is used for adding, deleting, modifying and managing the account information of the user, and the account information includes the personal information;
所述病历管理单元用于存储管理所述用户的病历信息，所述病历信息包括多个时间周期采集的所述面舌像数据以及所述症状调查信息；The medical record management unit is used for storing and managing the medical record information of the user, the medical record information including the facial and tongue image data and the symptom survey information collected in multiple time periods;
所述数据处理单元用于对所述病历信息进行综合分析，并输出所述用户的健康状态。本发明通过基于长期样本数据之间的关联性，对录入的问诊信息、采集到的面舌象图片信息、声音信息进行分析，将动态采集数据的结果进行可视化展示，也可为构建知识图谱提供个体健康状态动态数据源，能够有效的对人体的疾病、健康状态进行诊断，且具备便于推广、使用方便、形式新颖、结果精确的优点。The data processing unit is used for comprehensively analyzing the medical record information and outputting the health status of the user. Based on the correlation between long-term sample data, the present invention analyzes the entered consultation information, the collected face and tongue image information, and voice information, and visualizes the results of the dynamic collection of data, which can also be used for building a knowledge map. Provides a dynamic data source of individual health status, which can effectively diagnose the disease and health status of the human body, and has the advantages of easy promotion, convenient use, novel form and accurate results.
作为本发明的优选方案，所述数据处理单元执行以下流程：As a preferred solution of the present invention, the data processing unit executes the following procedures:
S01：获取待辨识用户的病历信息；S01: Obtain the medical record information of the user to be identified;
S02：通过神经网络对所述病历信息进行预处理，获取分析数据；S02: preprocessing the medical record information through a neural network to obtain analysis data;
S03：采用灰色关联分析法将所述分析数据与各个慢性病中医证型进行关联性分析，输出所述用户与各个中医证型的关联度；S03: Use the grey correlation analysis method to carry out correlation analysis between the analysis data and each TCM syndrome type of chronic diseases, and output the correlation degree between the user and each TCM syndrome type;
S04：根据所述关联度，输出所述用户的健康状态。本发明以与个体关系密切的面象、舌象信息为基础，结合问诊等相关信息，通过动态监测不同时期面象、舌象及其他症状信息，分析面舌象状态与症状的关联规律；可实现基于量表法慢病信息的动态、客观化采集；同时采用灰色关联分析可对量化后的健康状态信息经过计算关联度和关联度排序探究望诊关键影响因子，实现基于中医面象舌象动态变化规律的健康状态辨识系统，为中医望诊治未病提供科学有效的数据支撑和指导。S04: According to the correlation degree, output the health status of the user. Based on the facial and tongue information closely related to the individual, the present invention analyzes the association law between the facial and tongue state and symptoms by dynamically monitoring facial, tongue and other symptom information in different periods in combination with relevant information such as inquiries; It can realize the dynamic and objective collection of chronic disease information based on the scale method; at the same time, the gray correlation analysis can be used to calculate the correlation degree and the correlation degree of the quantified health status information to explore the key influencing factors of inspection and diagnosis, and realize the basis of traditional Chinese medicine face like tongue. The health status identification system, which is like a dynamic change law, provides scientific and effective data support and guidance for traditional Chinese medicine for the diagnosis and treatment of pre-diseases.
作为本发明的优选方案，所述步骤S02包括以下流程：As a preferred solution of the present invention, the step S02 includes the following procedures:
S021：对所述病历信息中的所述面舌象数据进行图像增强处理，对所述病历信息中的所述症状调查信息进行归类、筛选、标记、清洗、补全、离散化处理；并在归一化处理后生成症状数据表；S021: Perform image enhancement processing on the face and tongue image data in the medical record information, and classify, filter, mark, clean, complete, and discretize the symptom investigation information in the medical record information; and Generate a symptom data table after normalization;
S022：将所述症状数据表导入到神经网络模型中进行处理，并生成分析数据。S022: Import the symptom data table into a neural network model for processing, and generate analysis data.
作为本发明的优选方案，所述症状数据表包括所述面舌像数据中所述用户的面色、唇色、光泽、舌色、舌质、苔色和/或苔质，以及所述症状调查信息中所述用户的全身症状、头项症状、耳鼻喉科症状、胸腹症状、四肢症状和/或二便性状的症状信息。As a preferred solution of the present invention, the symptom data table includes the user's complexion, lip color, gloss, tongue color, tongue quality, coating color and/or coating quality in the facial and tongue image data, and the symptom survey Symptom information of the user's systemic symptoms, head symptoms, ENT symptoms, chest and abdominal symptoms, limb symptoms and/or fecal symptoms described in the information.
作为本发明的优选方案，所述神经网络模型包括输入层、隐含层和输出层；As a preferred solution of the present invention, the neural network model includes an input layer, a hidden layer and an output layer;
所述输入层的神经元的个数与变量的个数相同；The number of neurons in the input layer is the same as the number of variables;
所述隐含层采用双曲正切传递函数，所述隐含层的输出
其中，
所述输出层采用线性传递函数，所述输出层的输出
其中，
所述权重以及所述偏置的初始化及更新公式为：The initialization and update formulas of the weight and the bias are:
其中，
作为本发明的优选方案，所述步骤S03包括以下流程：As a preferred solution of the present invention, the step S03 includes the following processes:
S031：将所述分析数据转换为比较序列
S032：采用均值化法对所述比较序列
S033：根据下式计算所述比较序列
其中
S034：根据下式求取所述比较序列
S035：将所述关联度
作为本发明的优选方案，所述面舌象采集模块设有麦克风传感器，用于采集所述用户的语音数据，并输入到所述数据处理单元进行分析。本发明通过对语音数据的采集和分析，扩大了分析数据的范围，也有效地提高了本发明辨识结果的准确性和可靠性。As a preferred solution of the present invention, the face and tongue image collection module is provided with a microphone sensor, which is used to collect the user's voice data and input it to the data processing unit for analysis. By collecting and analyzing the voice data, the present invention expands the scope of the analyzed data, and also effectively improves the accuracy and reliability of the identification result of the present invention.
作为本发明的优选方案，所述系统包括以下执行流程：As a preferred solution of the present invention, the system includes the following execution flow:
S11：所述用户在所述信息录入模块输入对应的账号密码进行登录；若所述用户未注册账号则进行账号注册流程；所述账号注册流程包括个人信息录入以及密码设置；S11: the user enters the corresponding account password in the information entry module to log in; if the user does not register an account, perform an account registration process; the account registration process includes personal information entry and password setting;
S12：通过所述面舌象采集模块采集面舌像数据，采集完成后将所述面舌像数据上传至所述病历管理单元；S12: collecting facial and tongue image data by the facial and tongue image acquisition module, and uploading the facial and tongue image data to the medical record management unit after the collection is completed;
S13：通过所述麦克风传感器采集语音数据，采集完成后将所述语音数据上传至所述病历管理单元；S13: Collect voice data through the microphone sensor, and upload the voice data to the medical record management unit after the collection is completed;
S14：通过所述信息录入模块填写症状调查信息，采集完成后将所述症状调查信息上传至所述病历管理单元；S14: Fill in the symptom investigation information through the information input module, and upload the symptom investigation information to the medical record management unit after the collection is completed;
S15：所述数据处理单元用于对所述病历信息进行综合分析，并输出所述用户的健康状态。S15: The data processing unit is configured to comprehensively analyze the medical record information, and output the health status of the user.
作为本发明的优选方案，所述执行流程按照1周1次的频率采集数据，并按时间标签存入所述病历管理单元。As a preferred solution of the present invention, the execution process collects data at a frequency of once a week, and stores the data in the medical record management unit according to a time tag.
本发明按1周1次的频率采集数据，为构建知识图谱提供个体健康状态动态数据源，也使得输出结果更加准确可靠。The present invention collects data at a frequency of once a week, provides a dynamic data source of individual health status for building a knowledge map, and also makes the output result more accurate and reliable.
作为本发明的优选方案，所述系统还包括结果可视化模块，用于展示所述用户的健康状态，并显示对应的健康提示。As a preferred solution of the present invention, the system further includes a result visualization module for displaying the health status of the user and displaying corresponding health prompts.
与现有技术相比，本发明的有益效果：Compared with the prior art, the beneficial effects of the present invention:
1.本发明通过基于长期样本数据之间的关联性，对录入的问诊信息、采集到的面舌象图片信息、声音信息进行分析，将动态采集数据的结果进行可视化展示，也可为构建知识图谱提供个体健康状态动态数据源，能够有效的对人体的疾病、健康状态进行诊断，且具备便于推广、使用方便、形式新颖、结果精确的优点。1. The present invention analyzes the entered consultation information, the collected face and tongue image information, and the sound information based on the correlation between long-term sample data, and visualizes the results of the dynamic collection of data, which can also be used for constructing. The knowledge graph provides a dynamic data source of individual health status, which can effectively diagnose the disease and health status of the human body, and has the advantages of easy promotion, convenient use, novel form and accurate results.
2.本发明以与个体关系密切的面象、舌象信息为基础，结合问诊等相关信息，通过动态监测不同时期面象、舌象及其他症状信息，分析面舌象状态与症状的关联规律；可实现基于量表法慢病信息的动态、客观化采集；同时采用灰色关联分析可对量化后的健康状态信息经过计算关联度和关联度排序探究望诊关键影响因子，实现基于中医面象舌象动态变化规律的健康状态辨识系统，为中医望诊治未病提供科学有效的数据支撑和指导。2. The present invention is based on facial and tongue information closely related to the individual, combined with relevant information such as inquiries, and analyzes the relationship between facial and tongue status and symptoms by dynamically monitoring facial, tongue and other symptom information in different periods. It can realize the dynamic and objective collection of chronic disease information based on the scale method; at the same time, the gray correlation analysis can be used to calculate the correlation degree and the correlation degree of the quantified health status information to explore the key influencing factors of inspection and diagnosis. The health status identification system of the dynamic change law of elephant tongue image provides scientific and effective data support and guidance for TCM observation, diagnosis and treatment of pre-disease.
3.本发明通过对语音数据的采集和分析，扩大了分析数据的范围，也有效地提高了本发明辨识结果的准确性和可靠性。3. The present invention expands the scope of the analyzed data by collecting and analyzing the voice data, and also effectively improves the accuracy and reliability of the identification result of the present invention.
4.本发明按1周1次的频率采集数据，为构建知识图谱提供个体健康状态动态数据源，也使得输出结果更加准确可靠。4. The present invention collects data at a frequency of once a week, provides a dynamic data source of individual health status for building a knowledge map, and also makes the output results more accurate and reliable.
附图说明Description of drawings
图1为本发明实施例1所述的一种基于中医面舌象动态变化的健康状态辨识系统的结构示意图；1 is a schematic structural diagram of a health state identification system based on the dynamic change of the facial and tongue image of traditional Chinese medicine according to Embodiment 1 of the present invention;
图2为本发明实施例1所述的一种基于中医面舌象动态变化的健康状态辨识系统中症候辨识的神经网络模型的结构示意图；2 is a schematic structural diagram of a neural network model for symptom identification in a health state identification system based on the dynamic change of TCM facial and tongue images according to Embodiment 1 of the present invention;
图3为本发明实施例1所述的一种基于中医面舌象动态变化的健康状态辨识系统的辨识工作流程示意图；3 is a schematic diagram of the identification workflow of the health status identification system based on the dynamic change of the facial and tongue image in traditional Chinese medicine according to Embodiment 1 of the present invention;
图4为本发明实施例1所述的一种基于中医面舌象动态变化的健康状态辨识系统中所述数据处理单元的工作流程；4 is the workflow of the data processing unit in the health state identification system based on the dynamic change of the Chinese medicine face and tongue image according to Embodiment 1 of the present invention;
图5为本发明实施例1所述的一种基于中医面舌象动态变化的健康状态辨识系统中舌体图片分割示意图。FIG. 5 is a schematic diagram of the segmentation of a tongue body image in a health state identification system based on the dynamic change of the facial and tongue image in traditional Chinese medicine according to Embodiment 1 of the present invention.
具体实施方式Detailed ways
下面结合试验例及具体实施方式对本发明作进一步的详细描述。但不应将此理解为本发明上述主题的范围仅限于以下的实施例，凡基于本发明内容所实现的技术均属于本发明的范围。The present invention will be further described in detail below in conjunction with test examples and specific embodiments. However, it should not be construed that the scope of the above-mentioned subject matter of the present invention is limited to the following embodiments, and all technologies realized based on the content of the present invention belong to the scope of the present invention.
实施例1Example 1
如图1所示，一种基于中医面舌象动态变化的健康状态辨识系统，包括面舌象采集模块、信息录入模块以及服务器（所述服务器可采用云端服务器），所述服务器包括用户管理单元、病历管理单元以及数据处理单元；As shown in Figure 1, a health status identification system based on the dynamic changes of Chinese medicine facial and tongue images includes a facial and tongue image acquisition module, an information input module and a server (the server can be a cloud server), and the server includes a user management unit , medical record management unit and data processing unit;
所述面舌象采集模块用于采集用户的面舌像数据，并上传到所述病历管理单元；其中，面象采集时需要满足以下要求：（1）露出完整面部，面部正面完整位于采集面罩内；（2）最好不要化妆，以免影响面色信息及唇色信息的采集。舌象采集时需要满足以下要求：（1）露出完整口腔，舌头正面完全伸出；（2）最好不要吃可以影响舌头颜色的食物。完成采集后在所述信息录入模块上点击提交按钮将面舌象数据上传到服务器的病历管理单元。The facial and tongue image collection module is used to collect the user's facial and tongue image data and upload it to the medical record management unit; wherein, the facial image collection needs to meet the following requirements: (1) The complete face is exposed, and the front of the face is completely located in the collection mask (2) It is best not to wear makeup, so as not to affect the collection of complexion information and lip color information. When collecting tongue images, the following requirements should be met: (1) the entire mouth is exposed, and the front of the tongue is fully extended; (2) it is best not to eat food that can affect the color of the tongue. After the collection is completed, click the submit button on the information input module to upload the facial and tongue image data to the medical record management unit of the server.
同时，所述面舌象采集模块还包括麦克风传感器，通过数字硅晶麦克风传感器进行声音信息的采集，并在所述数据测量模块进行分析，判断是否存在病变声音。病变声音是疾病反映于声音和语言上的变化。听病变的声音，主要是辨别用户的语声、鼻鼾、咳嗽、喷嚏、呵欠、太息等异常声音。语言的辨别，则主要分析用户语言的表达与应答能力有无异常以及吐字是否清晰等。病变声音包括辨语声、语言、呼吸、咳嗽、呕吐、呃逆、嗳气、叹息、鼻鼾、喷嚏、肠鸣与振水声等内容。音频数据处理过程中将wav格式的音频文件导入Praat语音分析软件，提取用户发声时声腔的共鸣频率，即第一共振峰（First Formant，F1）、第二共振峰（Second Formant，F2）、第三共振峰（Third Formant，F3）、第四共振峰（Fourth Formant，F4），共计四个反映语音特征的指标。语音信号的预处理可以针对一段声音波形，精确选择起始端点与结束端点，从而准确地截取语音信号的有效部分，良好的预处理不仅能够去除不必要的噪音，同时能保证截取语音信息的一致性。At the same time, the face and tongue image acquisition module also includes a microphone sensor, and the digital silicon crystal microphone sensor is used to collect sound information, and the data measurement module is analyzed to determine whether there is a lesion sound. Lesion voice is the change in voice and language reflected by the disease. Listening to the sound of lesions is mainly to identify abnormal sounds such as the user's voice, snoring, coughing, sneezing, yawning, and breathing. Language identification mainly analyzes whether the user's language expression and response ability are abnormal and whether the pronunciation is clear. The sound of lesions includes speech recognition, language, breathing, coughing, vomiting, hiccups, belching, sighing, snoring, sneezing, bowel sounds and vibrations. In the process of audio data processing, the audio file in wav format is imported into the Praat speech analysis software, and the resonance frequency of the vocal cavity when the user is vocalized is extracted, that is, the first formant (First Formant, F1), the second formant (Second Formant, F2), the second formant (F2), the Three formants (Third Formant, F3), fourth formant (Fourth Formant, F4), a total of four indicators reflecting the characteristics of speech. The preprocessing of the voice signal can accurately select the start and end points of a sound waveform, so as to accurately intercept the effective part of the voice signal. Good preprocessing can not only remove unnecessary noise, but also ensure the consistency of the intercepted voice information. sex.
所述信息录入模块用于录入所述用户的症状调查信息以及所述用户的个人信息，并将所述症状调查信息上传到所述病历管理单元，所述个人信息上传到所述用户管理单元；其中，所述症状调查信息以50-60道选择题的形式给出可能出现的症状，用户根据严重程度进行如实填写，这些问题根据常见慢病中医诊疗指南和姚乃礼老师主编的第二版《中医症状鉴别诊断学》进行制定，覆盖全身症状、头项症状、胸腹症状、四肢症状、二便情况等方面。The information input module is used to input the symptom investigation information of the user and the personal information of the user, and upload the symptom investigation information to the medical record management unit, and the personal information is uploaded to the user management unit; Among them, the symptom survey information gives possible symptoms in the form of 50-60 multiple-choice questions, and the user fills in truthfully according to the severity. Symptoms Differential Diagnosis" was formulated, covering systemic symptoms, head symptoms, chest and abdominal symptoms, limb symptoms, and two stools.
所述用户管理单元用于增删、修改以及管理所述用户的账号信息，所述账号信息包括所述个人信息；用户需要以有效的电话号码进行注册，并设置对应的密码，登录时以注册时登记的电话号码及密码进行登录。所述个人信息包括个人基本信息和个人生活习惯信息两大类。个人基本信息包括姓名、年龄、性别、联系电话、常驻地址、职业、学历、有无过敏史等内容。个人生活习惯信息包括疾病状态、特殊期类型、饮食睡眠习惯、运动习惯、情绪状态、家庭氛围、等内容、加班出差情况、身高、体重等内容。且所述个人信息可在登录后根据实际情况选择修改。The user management unit is used to add, delete, modify and manage the account information of the user, and the account information includes the personal information; the user needs to register with a valid phone number and set a corresponding password. Login with the registered phone number and password. The personal information includes two categories of personal basic information and personal living habit information. Basic personal information includes name, age, gender, contact number, permanent address, occupation, education, and allergies. Personal living habits information includes disease state, type of special period, eating and sleeping habits, exercise habits, emotional state, family atmosphere, etc., overtime travel, height, weight, etc. And the personal information can be modified according to the actual situation after logging in.
所述病历管理单元用于存储管理所述用户的病历信息，所述病历信息包括多个时间周期采集的所述面舌像数据以及所述症状调查信息；The medical record management unit is used for storing and managing the medical record information of the user, the medical record information including the facial and tongue image data and the symptom survey information collected in multiple time periods;
所述数据处理单元用于对所述病历信息进行综合分析，并输出所述用户的健康状态。如图2所示，所述数据处理单元通过深度学习技术构建症候辨识的神经网络模型，即通过数据驱动的方式训练并得到以“分类后面舌象+中医其它四诊信息”为输入向量、“症候分类”为输出标签的症候辨识模型（例如对于慢性阻塞性肺疾病（Chronic ObstructivePulmoriary Disease，COPD）的中医证型分为风寒袭肺证、外寒内饮证、痰热壅肺证、痰浊阻肺证、痰蒙神窍证、肺气虚证、肺脾气虚证、肺肾气虚证、肺肾气阴两虚证、兼证-血瘀证这10种类型，通过神经网络算法进行不同中医证型的识别分类）。并采用灰色关联分析法完成面舌象与慢性病症状的关联性分析，通过横向和纵向双向比较对个性化数据和共通性数据进行不同分析。在个人横向数据中，当面舌象出现频率高于第一预设值（例如70%）时，恒定不变的面色、舌色、苔色以及其他症状信息，则认为是常色或者常态的表现，当面舌象出现频率低于第二预设值（例如30%）时，则认为是客色或者异态的表现，需要根据疾病中医指南给与健康警告。而对于不同人群的纵向数据的处理采用灰色关联分析法进行完成面舌象与慢性病中医证型的关联性分析。本系统辨识工作流程如图3所示。The data processing unit is used for comprehensively analyzing the medical record information and outputting the health status of the user. As shown in Figure 2, the data processing unit constructs a neural network model for symptom identification through deep learning technology, that is, it is trained in a data-driven manner and obtains the input vector with "tongue image after classification + other four diagnostic information of traditional Chinese medicine" as the input vector, " Syndrome classification" is the output label of the syndrome identification model (for example, for chronic obstructive pulmonary disease (COPD), the TCM syndrome types are divided into wind-cold attacking the lung syndrome, external cold and internal drinking syndrome, phlegm-heat blocking the lung syndrome, phlegm-turbid syndrome There are 10 types of lung obstruction syndrome, phlegm blocking Shen orifice syndrome, lung qi deficiency syndrome, lung spleen deficiency syndrome, lung and kidney qi deficiency syndrome, lung and kidney qi and yin deficiency syndrome, and concurrent syndrome-blood stasis syndrome. identification and classification of evidence types). And the gray correlation analysis method was used to complete the correlation analysis between facial and tongue appearance and chronic disease symptoms, and the individualized data and common data were analyzed differently by horizontal and vertical two-way comparison. In personal horizontal data, when the frequency of facial and tongue appearance is higher than the first preset value (for example, 70%), the constant facial color, tongue color, moss color and other symptom information are considered to be normal color or normal performance. , when the frequency of facial and tongue appearance is lower than the second preset value (for example, 30%), it is considered to be a manifestation of objective color or abnormal state, and a health warning needs to be given according to the guidelines of traditional Chinese medicine for diseases. For the processing of longitudinal data of different populations, the grey relational analysis method was used to complete the correlation analysis between facial and tongue images and TCM syndrome types of chronic diseases. The identification workflow of this system is shown in Figure 3.
如图4所示，所述数据处理单元执行以下流程：As shown in Figure 4, the data processing unit executes the following procedures:
S01：获取待辨识用户的病历信息；S01: Obtain the medical record information of the user to be identified;
S02：通过神经网络对所述病历信息进行预处理，获取分析数据；S02: preprocessing the medical record information through a neural network to obtain analysis data;
S021：对所述病历信息预处理后，归一化生成症状数据表；面舌象数据的预处理包括基于传统形态学的处理、基于水平翻转平移等图像增强处理，增强样本容量；症状调查信息的预处理包括原始样本进行归类、筛选、标记、清洗、补全、离散化，去除内容不完整、有误的数据。输入向量的归一化处理主要针对中医四诊信息进行标准化，拟参照中华人民共和国国家标准《中医基础理论术语》并结合姚乃礼老师主编的第二版《中医症状鉴别诊断学》对原始样本中的舌象症状进行规范。输出标签的归一化处理主要针对舌象证候分类进行规范化，拟参照行业标准《ZY/T001.1.94中医病证诊断与疗效标准》。所述症状数据表包括所述面舌像数据中所述用户的面色、唇色、光泽、舌色、舌质、苔色和/或苔质，以及所述症状调查信息中所述用户的全身症状、头项症状、耳鼻喉科症状、胸腹症状、四肢症状和/或二便性状的症状信息。S021: After preprocessing the medical record information, normalize to generate a symptom data table; the preprocessing of the facial and tongue image data includes processing based on traditional morphology, image enhancement processing based on horizontal flipping and translation, etc., to enhance the sample capacity; symptom investigation information The preprocessing includes classifying, screening, marking, cleaning, completing, discretizing the original samples, and removing incomplete and erroneous data. The normalization of the input vector is mainly aimed at standardizing the information of the four diagnosis of traditional Chinese medicine. It is planned to refer to the national standard of the People's Republic of China "Basic Theory and Terminology of Traditional Chinese Medicine" and combine with the second edition of "The Differential Diagnosis of Traditional Chinese Medicine Symptoms" edited by Mr. Yao Naili to analyze the information in the original sample. Tongue symptoms were standardized. The normalization processing of output labels is mainly aimed at standardizing the classification of tongue syndromes, and it is planned to refer to the industry standard "ZY/T001.1.94 TCM Diseases and Syndrome Diagnosis and Efficacy Standards". The symptom data table includes the complexion, lip color, gloss, tongue color, tongue texture, coating color and/or coating texture of the user in the facial and tongue image data, and the user's whole body in the symptom survey information Symptom information for symptoms, head symptoms, ENT symptoms, thoracic and abdominal symptoms, extremity symptoms, and/or constipation traits.
S022：将所述症状数据表导入到神经网络模型中进行处理，并生成分析数据（所述神经网络模型采用历史标注样本训练得到，所述历史标注样本随机分组为80%训练集与20%测试集）；如图5所示，为本发明进行舌体图片分割示意图，在卷积神经网络和ReLU函数之间进行批归一化（Batch Normalization），使得训练深层网络模型更加容易和稳定。如果实际应用的样本与训练样本分布不同，即发生了协方差偏移，则一般是要对模型重新进行训练的。在神经网络，尤其是深度神经网络中，协方差偏移会导致模型预测效果变差，重新的训练模型各隐藏层的和均产生偏移和变化。而批归一化（Batch Normalization）减少了各层权重之间的耦合性，对个隐藏层输出进行均值和方差的归一化处理，让各层更加独立，实现自我训练学习的效果，让模型变得更加健壮，鲁棒性更强。S022: Import the symptom data table into a neural network model for processing, and generate analysis data (the neural network model is obtained by training with historically labeled samples, and the historically labeled samples are randomly grouped into 80% training set and 20% test set As shown in Figure 5, it is a schematic diagram of the present invention for segmentation of tongue images. Batch normalization is performed between the convolutional neural network and the ReLU function, which makes the training of the deep network model easier and more stable. If the actual application samples are distributed differently from the training samples, that is, a covariance shift occurs, the model is generally retrained. In neural networks, especially deep neural networks, the covariance shift will cause the model prediction effect to deteriorate, and the sum of each hidden layer of the retrained model will shift and change. Batch normalization reduces the coupling between the weights of each layer, normalizes the mean and variance of the output of each hidden layer, makes each layer more independent, realizes the effect of self-training and learning, and makes the model Become more robust and robust.
其中，所述神经网络模型包括输入层、隐含层和输出层；Wherein, the neural network model includes an input layer, a hidden layer and an output layer;
所述输入层的神经元的个数与变量的个数相同；The number of neurons in the input layer is the same as the number of variables;
所述隐含层采用双曲正切传递函数，所述隐含层的输出
其中，
所述输出层采用线性传递函数，所述输出层的输出
其中，
所述权重以及所述偏置的初始化及更新公式为：The initialization and update formulas of the weight and the bias are:
其中，
S03：采用灰色关联分析法将所述分析数据（本发明选用10项数据进行分析）与某慢性病中医证型进行关联性分析，输出所述用户与各个中医证型的关联度；其中，灰色关联分析法是根据系统内部各因素之间的相似或相异程度来衡量因素之间的关联程度，是一种量化比较分析。进行灰色关联分析首先要指定参考序列。基于灰色关联分析的面舌象动态变化规律分析算法包括如下几个步骤：S03: Use the grey correlation analysis method to carry out correlation analysis between the analysis data (10 items of data are selected for analysis in the present invention) and a certain chronic disease TCM syndrome type, and output the correlation degree between the user and each TCM syndrome type; wherein, the grey correlation The analysis method is to measure the degree of correlation between factors according to the degree of similarity or dissimilarity between factors within the system, which is a quantitative comparative analysis. The first step to perform grey relational analysis is to specify a reference sequence. The dynamic change law analysis algorithm of facial and tongue image based on grey relational analysis includes the following steps:
S031：将所述分析数据转换为比较序列
表1 面舌象特征与COPD中医证型关联分析数值内容Table 1 Numerical content of correlation analysis between facial and tongue characteristics and TCM syndrome types of COPD
S032：由于系统中各因素列中的数据可能因量纲不同，不便于比较或在比较时难以得到正确的结论。因此在进行灰色关联度分析时，一般都要进行数据的无量纲化处理。本发明采用均值化法，即将各个序列的统计值与整条序列的均值作比值进行预处理，计算式如下：S032: Since the data in each factor column in the system may be different in dimension, it is inconvenient to compare or it is difficult to get a correct conclusion during comparison. Therefore, in the analysis of grey relational degree, it is generally necessary to carry out dimensionless processing of the data. The present invention adopts the mean value method, that is, the statistical value of each sequence and the mean value of the whole sequence are preprocessed as a ratio, and the calculation formula is as follows:
S033：根据下式计算所述比较序列
其中
S034：因为关联系数是比较数列与参考数列在各个时刻（即曲线中的各点）的关联程度值，所以它的数不止一个，而信息过于分散不便于进行整体性比较。因此有必要将各个时刻（即曲线中的各点）的关联系数集中为一个值，即求其平均值，作为比较数列与参考数列间关联程度的数量表示，关联度
S035：将所述关联度
S04：根据所述关联度，输出所述用户的健康状态。S04: According to the correlation degree, output the health status of the user.
其中，灰色关联分析是根据各因素变化曲线几何形状的相似程度，来判断因素之间关联程度的方法。此方法通过对动态过程发展态势的量化分析，完成对系统内时间序列有关统计数据几何关系的比较，求出参考数列与各比较数列之间的灰色关联度。与参考数列关联度越大的比较数列，其发展方向和速率与参考数列越接近，与参考数列的关系越紧密。灰色关联分析方法要求样本容量可以少到4个，对数据无规律同样适用，不会出现量化结果与定性分析结果不符的情况。其基本思想是将评价指标原始观测数进行无量纲化处理，计算关联系数、关联度以及根据关联度的大小对待评指标进行排序。Among them, gray correlation analysis is a method to judge the degree of correlation between factors according to the similarity of the geometric shapes of the change curves of each factor. This method completes the comparison of the geometric relationship of the statistical data of the time series in the system through the quantitative analysis of the development trend of the dynamic process, and obtains the grey correlation degree between the reference sequence and each comparison sequence. The greater the correlation with the reference sequence, the closer the development direction and speed of the comparison sequence to the reference sequence, and the closer the relationship with the reference sequence. The gray correlation analysis method requires that the sample size can be as small as 4, and it is also applicable to irregular data, and there will be no discrepancy between the quantitative results and the qualitative analysis results. The basic idea is to perform dimensionless processing on the original observations of the evaluation index, calculate the correlation coefficient, the correlation degree, and sort the indicators to be evaluated according to the size of the correlation degree.
实施例2Example 2
本实施例与实施例1的区别在于，所述步骤S031采用灰色关联分析法将所述分析数据（约10项）与某慢性病典型其他症状（如COPD的典型症状有嗜睡、多汗、鼻塞、关节疼痛等，约40种症状）进行关联性分析，输出所述用户与各典型症状的关联度，所述步骤具体为：The difference between this embodiment and Embodiment 1 is that the step S031 adopts the gray correlation analysis method to compare the analysis data (about 10 items) with other typical symptoms of a chronic disease (for example, typical symptoms of COPD include lethargy, sweating, nasal congestion, Joint pain, etc., about 40 symptoms), perform correlation analysis, and output the correlation between the user and each typical symptom. The steps are as follows:
S031：将所述分析数据转换为比较序列
表2 面舌象特征与COPD其他典型症状关联分析数值内容Table 2 Numerical content of correlation analysis between facial and tongue features and other typical symptoms of COPD
实施例3Example 3
本实施例与实施例1的区别在于，所述系统还包括结果可视化模块，用于展示所述用户的健康状态，并显示对应的健康提示。且该模块还能够通过实体抽取、属性识别、关系抽取、知识评估等步骤进行相关数据知识库的构建，并在实现过程中不断进行知识库的更新。通过几何图、星团图等形式对上述关联分析结果进行可视化。The difference between this embodiment and Embodiment 1 is that the system further includes a result visualization module, which is used to display the health status of the user and display corresponding health prompts. And this module can also construct the relevant data knowledge base through the steps of entity extraction, attribute recognition, relation extraction, knowledge evaluation, etc., and continuously update the knowledge base in the implementation process. The above-mentioned correlation analysis results are visualized in the form of geometric diagrams, star cluster diagrams, etc.
实施例4Example 4
本实施例为实施例1或实施例2所述系统的执行流程：This embodiment is the execution flow of the system described in Embodiment 1 or Embodiment 2:
S11：所述用户在所述信息录入模块输入对应的账号密码进行登录；若所述用户未注册账号则进行账号注册流程；所述账号注册流程包括个人信息录入以及密码设置；S11: the user enters the corresponding account password in the information entry module to log in; if the user does not register an account, perform an account registration process; the account registration process includes personal information entry and password setting;
S12：通过所述面舌象采集模块采集面舌像数据，采集完成后将所述面舌像数据上传至所述病历管理单元；S12: collecting facial and tongue image data by the facial and tongue image acquisition module, and uploading the facial and tongue image data to the medical record management unit after the collection is completed;
S13：通过所述麦克风传感器采集语音数据，采集完成后将所述语音数据上传至所述病历管理单元；S13: Collect voice data through the microphone sensor, and upload the voice data to the medical record management unit after the collection is completed;
S14：通过所述信息录入模块填写症状调查信息，采集完成后将所述症状调查信息上传至所述病历管理单元；S14: Fill in the symptom investigation information through the information input module, and upload the symptom investigation information to the medical record management unit after the collection is completed;
S15：所述数据处理单元用于对所述病历信息进行综合分析，并输出所述用户的健康状态。S15: The data processing unit is configured to comprehensively analyze the medical record information, and output the health status of the user.
且所述执行流程按照1周1次的频率采集数据，并按时间标签存入所述病历管理单元。且本系统可应用于以下情况：And the execution process collects data according to the frequency of once a week, and stores the data in the medical record management unit according to the time tag. And this system can be applied to the following situations:
（1）用于家庭及各类医疗机构常规提示性检测设备。可作为家庭、各级医院、社区医疗机构、乡镇诊所的检测设备。(1) Routine suggestive testing equipment for families and various medical institutions. It can be used as testing equipment for families, hospitals at all levels, community medical institutions, and township clinics.
（2）为中医临床辨证提供量化依据。采集面舌象图片、音频数据、问诊信息作为针灸经穴及补泻手法的选择提供量化依据，提供面象和舌象信息与中医证型之间的关联性，辅助临床精确诊断。(2) Provide quantitative basis for TCM clinical syndrome differentiation. The collection of facial and tongue images, audio data, and consultation information provides a quantitative basis for the selection of acupuncture meridians and reinforcing and reducing techniques, and provides the correlation between facial and tongue information and TCM syndromes, and assists accurate clinical diagnosis.
（3）为普通慢性病患者提供疾病变化预警。对于慢性病患者，长期进行病情稳定性控制，而面象和舌象的变化早于疾病的恶化，长期健康监测有助于患者提前掌握自身病情，及时就医治疗。(3) Provide early warning of disease changes for ordinary chronic disease patients. For patients with chronic diseases, long-term disease stability control is carried out, and the changes of facial and tongue images are earlier than the deterioration of the disease. Long-term health monitoring helps patients to grasp their own conditions in advance and seek medical treatment in time.
（4）早期疾病提示。对神经系统、消化系统、内分泌系统、循环系统、泌尿系统、排泄系统、呼吸系统、运动系统等各类易患疾病有较准确的提示与判断。特别对高血压、糖尿病、慢性心力衰竭、慢性肺阻病、慢性肾功能不全、认知功能障碍等常见慢性疾病有一定的前瞻性提示或警示作用。(4) Early disease prompts. It has more accurate prompts and judgments for various susceptible diseases such as the nervous system, digestive system, endocrine system, circulatory system, urinary system, excretory system, respiratory system, and motor system. In particular, it has a certain prospective prompt or warning effect for common chronic diseases such as hypertension, diabetes, chronic heart failure, chronic pulmonary obstructive disease, chronic renal insufficiency, and cognitive dysfunction.
（5）病情疗效评价观察。对临床治疗效果，包括药品、保健品应用效果进行客观评估，并能跟踪观察疾病转归化数据变化的动态过程。(5) Evaluation and observation of the curative effect of the disease. It can objectively evaluate the clinical treatment effect, including the application effect of drugs and health products, and can track and observe the dynamic process of the change of disease transformation data.
（6）界定人体亚健康。对人体的精神活动、心理活动、植物神经活动、疲劳综合症等亚健康的状态提供的准确的量化数据，并做出提示性判断。(6) Define human sub-health. It provides accurate quantitative data on sub-health states such as mental activity, mental activity, autonomic nervous activity, fatigue syndrome, etc. of the human body, and makes suggestive judgments.
（7）全身检。可用于人群健康筛查或某些系统疾病的筛查。提示人体体能、神经、循环、消化代谢、免疫、内分泌、骨骼、运动系统及内脏器官生理病理状况。也可作为心理疾病诊断的参考指标。(7) General examination. It can be used for population health screening or screening of certain systemic diseases. Indicates the physiological and pathological conditions of human physical fitness, nerves, circulation, digestion and metabolism, immunity, endocrine, bone, motor system and internal organs. It can also be used as a reference index for the diagnosis of mental illness.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included in the protection of the present invention. within the range.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077108.7A CN113539486A (en) | 2021-09-15 | 2021-09-15 | Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111077108.7A CN113539486A (en) | 2021-09-15 | 2021-09-15 | Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113539486A true CN113539486A (en) | 2021-10-22 |
Family
ID=78092625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111077108.7A Pending CN113539486A (en) | 2021-09-15 | 2021-09-15 | Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113539486A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114242243A (en) * | 2021-12-21 | 2022-03-25 | 中科麦迪人工智能研究院(苏州)有限公司 | User health assessment method, device, equipment and storage medium |
| CN115206523A (en) * | 2022-08-10 | 2022-10-18 | 重庆乾坤济实业集团有限公司 | Health management evaluation system and method thereof |
| CN115429228A (en) * | 2022-09-20 | 2022-12-06 | 广东省中医院（广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院） | Tongue picture recognition auxiliary diagnosis system based on AI technology |
| CN116784804A (en) * | 2023-07-19 | 2023-09-22 | 湖南云医链生物科技有限公司 | No-disease analysis and evaluation system |
| CN119314690A (en) * | 2024-12-12 | 2025-01-14 | 合肥云诊信息科技有限公司 | Analysis method of tongue image characteristics change rules based on the rehabilitation process of chronic disease patients |
| CN120032195A (en) * | 2025-04-24 | 2025-05-23 | 安徽智侒信信息技术有限公司 | Auxiliary diagnosis and treatment system based on traditional Chinese medicine large model |
| CN120032195B (en) * | 2025-04-24 | 2025-08-01 | 安徽智侒信信息技术有限公司 | Auxiliary diagnosis and treatment system based on traditional Chinese medicine large model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295139A (en) * | 2016-07-29 | 2017-01-04 | 姹ゅ钩 | A kind of tongue body autodiagnosis health cloud service system based on degree of depth convolutional neural networks |
| CN106446533A (en) * | 2016-09-12 | 2017-02-22 | 北京和信康科技有限公司 | Processing system of human body health data and method thereof |
| CN107330889A (en) * | 2017-07-11 | 2017-11-07 | 北京工业大学 | A kind of traditional Chinese medical science tongue color coating colour automatic analysis method based on convolutional neural networks |
| CN110299193A (en) * | 2019-06-27 | 2019-10-01 | 合肥云诊信息科技有限公司 | Chinese medicine health cloud service method based on artificial intelligence lingual diagnosis |
| CN110432864A (en) * | 2019-07-19 | 2019-11-12 | 成都中医药大学 | A kind of tcm constitution dynamic change discrimination method and system |
-
2021
- 2021-09-15 CN CN202111077108.7A patent/CN113539486A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295139A (en) * | 2016-07-29 | 2017-01-04 | 姹ゅ钩 | A kind of tongue body autodiagnosis health cloud service system based on degree of depth convolutional neural networks |
| CN106446533A (en) * | 2016-09-12 | 2017-02-22 | 北京和信康科技有限公司 | Processing system of human body health data and method thereof |
| CN107330889A (en) * | 2017-07-11 | 2017-11-07 | 北京工业大学 | A kind of traditional Chinese medical science tongue color coating colour automatic analysis method based on convolutional neural networks |
| CN110299193A (en) * | 2019-06-27 | 2019-10-01 | 合肥云诊信息科技有限公司 | Chinese medicine health cloud service method based on artificial intelligence lingual diagnosis |
| CN110432864A (en) * | 2019-07-19 | 2019-11-12 | 成都中医药大学 | A kind of tcm constitution dynamic change discrimination method and system |
Non-Patent Citations (3)
| Title |
|---|
| 周霞等: "灰色关联分析在医学中的应用", 《辽宁中医杂志》 * |
| 宋海贝等: "基于 AI 的中医舌象面象辅助诊疗系统构建", 《时珍国医国药》 * |
| 章浩伟等: "基于灰色关联分析的中医肝炎肝硬化诊断方法", 《计算机工程与应用》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114242243A (en) * | 2021-12-21 | 2022-03-25 | 中科麦迪人工智能研究院(苏州)有限公司 | User health assessment method, device, equipment and storage medium |
| CN115206523A (en) * | 2022-08-10 | 2022-10-18 | 重庆乾坤济实业集团有限公司 | Health management evaluation system and method thereof |
| CN115429228A (en) * | 2022-09-20 | 2022-12-06 | 广东省中医院（广州中医药大学第二附属医院、广州中医药大学第二临床医学院、广东省中医药科学院） | Tongue picture recognition auxiliary diagnosis system based on AI technology |
| CN116784804A (en) * | 2023-07-19 | 2023-09-22 | 湖南云医链生物科技有限公司 | No-disease analysis and evaluation system |
| CN119314690A (en) * | 2024-12-12 | 2025-01-14 | 合肥云诊信息科技有限公司 | Analysis method of tongue image characteristics change rules based on the rehabilitation process of chronic disease patients |
| CN120032195A (en) * | 2025-04-24 | 2025-05-23 | 安徽智侒信信息技术有限公司 | Auxiliary diagnosis and treatment system based on traditional Chinese medicine large model |
| CN120032195B (en) * | 2025-04-24 | 2025-08-01 | 安徽智侒信信息技术有限公司 | Auxiliary diagnosis and treatment system based on traditional Chinese medicine large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113539486A (en) | Health state identification system based on traditional Chinese medicine facial and tongue manifestation dynamic change | |
| Shi et al. | Theory and Application of Audio‐Based Assessment of Cough | |
| Chen et al. | Deep neural network for automatic classification of pathological voice signals | |
| CN112166475A (en) | Respiratory system based sound management of respiratory conditions | |
| US20050033121A1 (en) | Diagnostic information systems | |
| JP2015514456A (en) | Method and apparatus for processing patient sounds | |
| Dar et al. | Design and development of hybrid optimization enabled deep learning model for COVID-19 detection with comparative analysis with DCNN, BIAT-GRU, XGBoost | |
| Heitmann et al. | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries | |
| Hafke-Dys et al. | Artificial intelligence approach to the monitoring of respiratory sounds in asthmatic patients | |
| CN113658697B (en) | Psychological assessment system based on video fixation difference | |
| Zou et al. | Artificial neural network to assist psychiatric diagnosis | |
| Krishnamoorthy et al. | Diagnosis of pneumonia using deep learning techniques | |
| Huang et al. | A contrastive embedding-based domain adaptation method for lung sound recognition in children community-acquired pneumonia | |
| Chen et al. | Heart function grading evaluation based on heart sounds and convolutional neural networks | |
| Sajid et al. | IoMT-Enabled Noninvasive Lungs Disease Detection and Classification Using Deep Learning-Based Analysis of Lungs Sounds. | |
| CN113409938A (en) | Modeling method and system of traditional Chinese medicine syndrome type prediction model of systemic lupus erythematosus | |
| Patel et al. | Performance analysis of deep learning algorithms for classifying chronic obstructive pulmonary disease | |
| Riad | IoT-based intelligent system For Alzheimer's Disease Detection & Monitoring | |
| Jiang et al. | Integrated analyzer and classifier of glottographic signals | |
| Sahu et al. | Optimized 1D CNNs for Enhanced Early Detection and Accurate Prediction of COPD and Other Pulmonary Diseases | |
| Joshi Manisha et al. | Computerized pragmatic assessment of Prakriti Dosha using tongue images-Pilot study | |
| CN115273176A (en) | Pain multi-algorithm objective assessment method based on vital signs and expressions | |
| CN111524563A (en) | A method for establishing a physiological sound database and its database | |
| CN119649972B (en) | Clinical medicine research evaluation system and method based on AI | |
| Jha et al. | Enhanced Predictive Modeling Techniques for Early Detection of COPD Utilizing 1D Convolutional Neural Networks |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211022 |
|
| RJ01 | Rejection of invention patent application after publication |