CN117095835A - Intelligent medical health consultation system - Google Patents
Intelligent medical health consultation system Download PDFInfo
- Publication number
- CN117095835A CN117095835A CN202310906221.4A CN202310906221A CN117095835A CN 117095835 A CN117095835 A CN 117095835A CN 202310906221 A CN202310906221 A CN 202310906221A CN 117095835 A CN117095835 A CN 117095835A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- consultation
- user
- intelligent
- 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
- 230000036541 health Effects 0.000 title claims abstract description 144
- 238000003745 diagnosis Methods 0.000 claims abstract description 40
- 239000003814 drug Substances 0.000 claims abstract description 40
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 79
- 238000004891 communication Methods 0.000 claims description 54
- 238000007726 management method Methods 0.000 claims description 51
- 239000011159 matrix material Substances 0.000 claims description 44
- 238000013475 authorization Methods 0.000 claims description 40
- 238000007781 pre-processing Methods 0.000 claims description 38
- 238000013500 data storage Methods 0.000 claims description 31
- 230000001815 facial effect Effects 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 25
- 238000012512 characterization method Methods 0.000 claims description 23
- 238000007405 data analysis Methods 0.000 claims description 19
- 235000016709 nutrition Nutrition 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 239000008280 blood Substances 0.000 claims description 14
- 210000004369 blood Anatomy 0.000 claims description 14
- 230000035764 nutrition Effects 0.000 claims description 12
- 230000008451 emotion Effects 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 10
- 230000037081 physical activity Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 9
- 238000012550 audit Methods 0.000 claims description 8
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000011049 filling Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 5
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000036772 blood pressure Effects 0.000 claims description 4
- 230000036760 body temperature Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000003750 conditioning effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000004217 heart function Effects 0.000 claims description 4
- 238000002955 isolation Methods 0.000 claims description 4
- 235000012054 meals Nutrition 0.000 claims description 4
- 238000000554 physical therapy Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000012847 principal component analysis method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 210000002700 urine Anatomy 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims 1
- 210000001508 eye Anatomy 0.000 description 22
- 238000010586 diagram Methods 0.000 description 10
- 201000010099 disease Diseases 0.000 description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 9
- 230000007812 deficiency Effects 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 4
- 230000003862 health status Effects 0.000 description 4
- 206010062717 Increased upper airway secretion Diseases 0.000 description 3
- 208000031975 Yang Deficiency Diseases 0.000 description 3
- 208000031971 Yin Deficiency Diseases 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 3
- 210000001124 body fluid Anatomy 0.000 description 3
- 239000010839 body fluid Substances 0.000 description 3
- 208000026435 phlegm Diseases 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010014080 Ecchymosis Diseases 0.000 description 1
- 206010024561 Lip pain Diseases 0.000 description 1
- 206010037549 Purpura Diseases 0.000 description 1
- 210000004087 cornea Anatomy 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000000554 iris Anatomy 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006213 oxygenation reaction Methods 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 206010034754 petechiae Diseases 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000003786 sclera Anatomy 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- 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
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/60—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to nutrition control, e.g. diets
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- 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
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Probability & Statistics with Applications (AREA)
- Social Psychology (AREA)
- Psychology (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Nutrition Science (AREA)
- Physical Education & Sports Medicine (AREA)
Abstract
The invention discloses an intelligent medical health consultation system which comprises an intelligent terminal, a cloud server side and a multi-parameter health detection terminal; the intelligent terminal comprises a client and a consultant; the cloud server side comprises a central server and a server cluster; the client receives an intelligent consultation report transmitted by the central server; the consultant side performs health guidance service; the server cluster comprises, but is not limited to, a tongue diagnosis algorithm server, a face diagnosis algorithm server, a mesh diagnosis algorithm server and a traditional Chinese medicine physique identification algorithm server; the server cluster analyzes and processes the body image according to the user body image and then transmits the result to the central server; the central server comprises an intelligent consultation module; the intelligent consultation module is used for processing and analyzing result data transmitted by the client, the server cluster and the multi-parameter health detection terminal, and obtaining consultation scoring results through calculation. The invention provides a plurality of artificial intelligent diagnosis algorithms for realizing intelligent medical health consultation, which is convenient for users to perform personalized active health management anytime and anywhere.
Description
Technical Field
The invention relates to the field of intelligent medical health management, in particular to an intelligent medical health consultation system.
Background
The health status of a person is divided into three types: firstly, the human body is healthy and is not ill, namely, the human body is in a healthy state without any disease; secondly, the disease is not in a pathological state, namely, the stage that in vivo pathological information is hidden exists, or the small disease state with few premonitory symptoms or signs is not enough to be diagnosed as a certain disease; thirdly, the disease is not transmitted, namely, obvious pathological changes appear in a certain viscera of the human body. The proposal of treating the disease aims at the three states, and the disease is cured early. A large number of medical practices prove that the concept of "whole concept and diagnosis and treatment" of traditional Chinese medicine is used for curing the disease without curing, has unique advantages, can evaluate the health state of individuals on the whole, and is more suitable for health management. Therefore, the diagnosis and treatment means with the traditional Chinese medicine characteristics can make up for the shortages of modern health management means.
With the development of computer technology, more intelligent medical health systems exist in the field of medical health management, and can be summarized as that by means of digitalization, specialized equipment and computer algorithms are combined to replace manpower so as to realize disease diagnosis or health status identification. The main problems existing in the application field at present are that firstly, a large part of researches are aimed at the auxiliary diagnosis decision support of 'sick' without paying attention to the medical health management of 'sick', and the health state of a human body is lack to be grasped from the overall view; secondly, the artificial intelligence algorithm is trained according to the respectively established databases, and the merits of the artificial intelligence algorithm cannot be compared; thirdly, the reliability of the system is insufficient, and the analysis results of integrating a plurality of artificial intelligence algorithms and comprehensive health information are lacked to carry out comprehensive judgment and give out analysis results; fourthly, lack of dynamic health monitoring, namely failing to carry out comprehensive procedural supervision and evaluation on the health status of individuals or groups, and giving corresponding health guidance or human intervention according to the dynamic change process of the health status to achieve health intervention; fifthly, the individuation degree of the system functions is not high, and the participation, interactivity and enthusiasm of users are not strong.
Disclosure of Invention
The invention provides an intelligent medical health consultation system which comprises an intelligent terminal and a cloud server.
The intelligent terminal comprises a client. The cloud server side comprises a central server and a server cluster.
The client comprises an image acquisition module, an information input module, a display module and a login module, and is used for acquiring medical health data of a user, including but not limited to basic information, health indexes and body images.
The central server includes a data analysis module. The data analysis module comprises a data preprocessing module and an intelligent consultation module.
The data preprocessing module receives data from the client and the server cluster, obtains a feature subset after preprocessing, and transmits the feature subset to the intelligent consultation module.
The intelligent consultation module comprises a data characterization unit, a consultation scoring unit and a report generating unit.
And the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module to obtain a data vector, and transmits the data vector to the consultation scoring unit.
The consultation scoring unit includes a consultation scoring model. And the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit.
And the report generating unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client and the consultant.
The server cluster comprises a tongue diagnosis algorithm server, a face diagnosis algorithm server, a mesh diagnosis algorithm server and a traditional Chinese medicine physique identification algorithm server, and each server stores an independent algorithm. The server processes tongue image, facial image and eye image data of the user respectively through independent image processing algorithms to obtain return result data, and the return result data is transmitted to the central server. The returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
An intelligent medical health consultation system comprises an intelligent terminal and a cloud server.
The intelligent terminal comprises a client and a consultant. The cloud server side comprises a central server and a server cluster.
The client comprises an image acquisition module, an information input module, a display module, a login module and an authorization module, and is used for acquiring medical health data of a user, including but not limited to basic information, health indexes and body images.
The consultant terminal comprises a consultant registration login module, a occupation registration module, a comprehensive service module and a consultant personal information management module.
The central server includes a data analysis module. The data analysis module comprises a data preprocessing module and an intelligent consultation module.
The data preprocessing module receives data from the client and the server cluster, obtains a feature subset after preprocessing, and transmits the feature subset to the intelligent consultation module.
The intelligent consultation module comprises a data characterization unit, a consultation scoring unit and a report generating unit.
And the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module to obtain a data vector, and transmits the data vector to the consultation scoring unit.
The consultation scoring unit includes a consultation scoring model. And the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit.
And the report generating unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client and the consultant.
The server cluster comprises a tongue diagnosis algorithm server, a face diagnosis algorithm server, a mesh diagnosis algorithm server and a traditional Chinese medicine physique identification algorithm server, wherein each server stores an independent algorithm; the server processes tongue image, facial image and eye image data of the user respectively through an independent image processing algorithm to obtain return result data, and the return result data is transmitted to the central server; the returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
Further, the user terminal and the advisor terminal are packaged in an integrated module, and are installed and run on the intelligent terminal; an intelligent terminal comprises a user end and an advisor end, and the user end and the advisor end can be mutually switched through a switching module.
Further, the user terminal and the advisor terminal respectively exist on two different intelligent terminals, and the user terminal and the advisor terminal independently operate and respectively communicate with the cloud server terminal.
Further, the image acquisition module comprises a shooting module and an uploading module.
The shooting module shoots the body image of the user and transmits the body image to the uploading module. Including but not limited to tongue, face, and eye images.
And the uploading module performs data interaction with the central server through a network.
The information input module comprises a basic information input module, a inquiry information input module and a physical examination information input module.
The basic information input module is used for inputting basic information of a user. The user's basic information includes, but is not limited to, gender, age, height, weight, past medical history, marital status, job type, income situation.
The inquiry information input module is used for inputting inquiry information of a user. The questionnaire information includes, but is not limited to, traditional Chinese medicine questionnaire results, emotion self-questionnaire results, and physical activity questionnaire results. The traditional Chinese medicine questionnaire results, the emotion self-questionnaire results and the physical activity questionnaire results are obtained through an electronic questionnaire form.
And the physical examination information input module is used for inputting physical examination information of the user. The physical examination information includes, but is not limited to, physical examination results, blood routine examination results, urine routine examination results, and cardiac function evaluation results.
The display module comprises a history record display module, a consultation result display module, an intelligent intervention scheme pushing module and a professional guidance suggestion module.
The history record display module comprises a basic information history record display unit, a consultation information history record display unit, a physical examination information history record display unit and an image history record display unit.
The basic information history record display unit is used for counting and displaying basic information of the user.
The inquiry information history record display unit is used for counting and displaying inquiry information of the user.
And the physical examination information history record display unit is used for counting and displaying physical examination information of the user.
The image history display unit is used for counting and displaying body images of a user, including but not limited to tongue images, face images and eye images.
The consultation result display module is used for counting and displaying consultation reports of the user.
The intelligent intervention scheme pushing module comprises a nutrition prescription pushing unit, a sports prescription pushing unit, a traditional Chinese medicine prescription pushing unit and a music prescription pushing unit.
The nutrition recipe pushing unit is used for pushing the personalized nutrition recipe.
The sport prescription pushing unit is used for pushing the personalized sport prescriptions.
The traditional Chinese medicine prescription pushing unit is used for pushing personalized traditional Chinese medicine prescriptions.
The music prescription pushing unit is used for pushing personalized music prescriptions.
The specialized guidance suggestion module is used for displaying specialized guidance suggestions provided by the consultant according to the consultation report.
The login module comprises a user registration module, a user login module and an identity authentication module.
The user registration module is used for completing user registration operation.
The user login module is used for completing user login operation.
The identity authentication module is used for completing user identity authentication.
The authorization module comprises a privacy authorization module and a management authorization module.
The authorization module is used for providing corresponding personal privacy information to the system after the user agrees to authorization when the system needs the user to provide the privacy information.
The management authorization module is used for the consultant to acquire the access and the management authority of the user, and after the user agrees to the authorization, the consultant can check the user information and manage the information provided by the user.
Further, the client side also comprises an advisor module and a client terminal. The consultant module comprises a consultant selection module, an online communication module, an offline experience module and a consultant evaluation module, and is used for selecting a consultant, carrying out online communication and offline experience with the consultant and evaluating the consultant.
The client terminal comprises one or more of a smart phone, a tablet computer and a computer.
The image acquisition module, the information input module, the display module, the login module, the authorization module and the advisor module are integrated inside the client terminal.
The client terminal comprises a display module, an input interface and a communication module.
The display module is used for realizing a data display function.
The input interface is used for realizing a data acquisition function.
The communication module is used for realizing a data transmission function.
Further, the advisor registration login module comprises an advisor registration module, an advisor login module and an identity authentication module for registration login verification operation of the advisor.
The job registration module comprises a job information input module, a job information management module and a job audit certification display module, and is used for job title input and job information management of all consultants.
The comprehensive business module comprises a guiding suggestion module, an online service module and an offline service module.
The online service module is used for online communication between the target user and the consultant, including but not limited to graphic communication, voice communication and video communication.
The off-line service module is used for providing off-line health management services for target users, including but not limited to nutritional meal replacement, course training and physiotherapy conditioning.
The consultant personal information management module comprises a consultant personal information input module, a professional audit display module and a consultant history record management module, and is connected with a professional registration module to input and manage personal basic information and professional information of a consultant user.
The consultant terminal also comprises a consultant terminal, and the consultant registration login module, the occupation registration module, the comprehensive service module and the consultant personal information management module are integrated inside the consultant terminal.
The advisor terminal comprises a display module, an input interface and a communication module.
The display module is used for realizing a data display function.
The input interface is used for realizing a data acquisition function.
The communication module is used for realizing a data transmission function.
The advisor terminal may be one or more of a smart phone, a tablet computer, and a computer.
The safety authentication module is used for identity authentication when the consultant views and manages the user information, and comprises one or more of a password authentication unit, a fingerprint authentication unit, a face authentication unit, a USB hardware link authentication unit and an audio hole connection hardware authentication unit.
Further, the central server also comprises a data storage module and a data communication module.
The data storage module comprises a user data storage module, an advisor data storage module, a health knowledge database and a health intervention scheme database. The user data storage module is used for storing all data of users in the client. The advisor data storage module is used to store all data of the advisor. The health knowledge database is used for storing health knowledge data. The health intervention plan database is used for storing health intervention plan data.
And the central server performs data interaction with the client, the consultant and the server cluster through the data communication module.
Further, the system also comprises a multi-parameter health detection terminal.
The multi-parameter health detection terminal is used for acquiring real-time physical sign data of a user. Including but not limited to body temperature, heart rate, blood pressure, blood oxygen, including health management robots, medical devices.
And the multi-parameter health detection terminal performs data interaction with the central server through the data communication module.
All data of the user in the multi-parameter health detection terminal are stored in a user data storage module of the central server.
And the data of the multi-parameter health detection terminal are counted and displayed through a multi-parameter health detection terminal information history record display unit of the history record display module.
Further, the step of obtaining the feature subset by the data preprocessing module includes:
s11) filling the missing data automatically based on the mean filling method.
S12) detection of outliers using Isolation Forest.
S13) processing by SMOTE algorithm to obtain balanced data set.
S14) converting the non-numerical data, the sequencing data, the fixed type data and the character string type data into numerical data through category conversion, serial number coding, single thermal coding and word embedding models respectively.
S15) carrying out normalization processing on the numerical data by adopting a zero-mean normalization method.
S16) extracting the features by using a principal component analysis method to obtain a feature subset.
Further, the step of obtaining the data vector by the data characterization unit includes:
s22) converts the word information in the feature subset into one-dimensional tokensymbol codes.
S22) calculating the corresponding position codes and segment codes of each word.
S23) inputting TokenEmbeddins code, positionEmbeddins code and SegmentEmbeddins code into the BERT language characterization model to obtain the data vector after the global information is fused.
Further, the consultation scoring model comprises an input layer, a deep learning network layer, a full connection layer and an output layer:
the input layer is for receiving a data vector.
The deep learning network layer comprises a CNN layer and an LSTM layer.
And the CNN layer performs feature extraction on the data vector to obtain a feature matrix.
And the LSTM layer performs feature extraction on the data vector to obtain a feature sequence.
And the full connection layer weights the feature matrix and the feature sequence and maps the feature matrix and the feature sequence to a sample marking space to obtain a feature vector.
And the output layer performs inner product on the feature vector to obtain a consultation scoring result of the user.
The step of obtaining the consultation scoring result of the user by the consultation scoring model comprises the following steps:
s31) inputting the data vector into a CNN layer of a consultation scoring model to obtain a feature matrix U c And U a The method comprises the following steps:
U c ＝max(0,WF u +b) (1)
U a ＝max(0,WF a +b) (2)
wherein F is u 、F a Representing the feature subset and the returned result subset, respectively. W, b is the weight and bias;
S32) pair of feature matrices U c Feature matrix U a Global pooling operation is performed to obtain feature vectors (U' c ,U’ a ) The method comprises the following steps:
(U’ c ,U’ a )＝max(U c ,U a ) (3)
s33) inputting the data vector into the LSTM, and obtaining the characteristic sequence U through calculation of the input gate, the forget gate and the output gate l 。
S34) fitting the eigenvector U' c Characteristic sequence U l Performing full connection to obtain a new feature vector U F . Feature vector U' a Characteristic sequence U l Performing full connection to obtain a new feature vector U V 。
S35) pair of eigenvectors U F Feature vector U V Performing inner product operation to obtain consultation score M of user score The method comprises the following steps:
M score ＝U F ⊙U V (4)
in the formula, ++represents the inner product operation.
Further, the data analysis module further comprises an intelligent intervention module and a professional information auditing module.
The intelligent intervention module is used for generating an intelligent intervention scheme and returning a result to the intelligent intervention scheme pushing module.
The intelligent intervention module generates an intelligent intervention scheme comprising the following steps:
s41) acquiring a scoring matrix and a preference matrix of the user based on the feature subset and the consultation score;
s42) calculating the comprehensive similarity between the scoring matrix and the preference matrix by utilizing an SVD collaborative filtering algorithm based on the scoring matrix and the preference matrix;
s43) obtaining a predicted value of a user recommendation scheme according to the comprehensive similarity, and obtaining a preliminary recommendation scheme set based on the predicted value;
S44) excavating a characteristic value change curve by using the BP-DS neural network, and analyzing the characteristic value change curve to obtain an intervention scheme set;
s45) carrying out local adjustment on the intervention scheme set to obtain a complete intelligent intervention scheme;
s46) dynamically updating the intelligent intervention scheme based on the time-sequential update data resulting from executing the complete intelligent intervention scheme.
The intelligent medical health consultation system has the technical effects that the intelligent medical health consultation system is undoubted, the whole health state of a human body is analyzed based on the traditional Chinese medicine theory, health information of different dimensions is integrated, intelligent medical health consultation is realized by combining a plurality of artificial intelligent algorithms, a personalized intelligent intervention scheme is provided according to consultation results, on-line and off-line integrated health guidance is combined with a professional consultant, and personalized active health management is conveniently carried out by a user at any time and any place.
Drawings
FIG. 1 is a schematic diagram of the overall system structure 1 according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the overall system structure 2 according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the overall system structure of an embodiment of the present invention;
FIG. 4 is a schematic diagram of the overall system structure of an embodiment of the present invention 4;
FIG. 5 is a system architecture diagram of a client according to an embodiment of the present invention;
FIG. 6 is a system architecture diagram of an advisor side in accordance with an embodiment of the present invention;
FIG. 7 is a system configuration diagram of a central server according to an embodiment of the present invention;
FIG. 8 is a workflow diagram of generating feature subsets in an embodiment of the invention;
FIG. 9 is a flowchart of a process for generating data vectors in an embodiment of the invention;
FIG. 10 is a workflow diagram of generating consultation scoring results in an embodiment of the present invention;
FIG. 11 is a workflow diagram of generating a smart intervention scheme in an embodiment of the invention;
in the drawing the view of the figure, intelligent terminal 1000, cloud server side 2000, integration module 3000, multiparameter health detection terminal 4000, client side 1100, advisor side 1200, center server 2100, server cluster 2200, switching module 3100, image acquisition module 1110, information entry module 1120, display module 1130, login module 1140, authorization module 1150, advisor module 1160, client terminal 1170, shooting module 1111, uploading module 1112, basic information entry module 1121, inquiry information entry module 1122, physical examination information entry module 1123, history display module 1131, consultation result display module 1132, intelligent intervention scheme pushing module 1133, professional guiding suggestion module 1134, user registration module 1141, user login module 1142, user identity authentication module 1143, privacy authorization module 1151, management authorization module 1152, advisor selection module 1161, online communication module 1162, offline experience module 1163 advisor evaluation module 1164, display module 1171, input interface 1172, communication module 1173, advisor registration login module 1210, professional registration module 1220, integrated services module 1230, advisor personal information management module 1240, advisor terminal 1250, security authentication module 1260, advisor registration module 1211, advisor registration module 1212, advisor identity authentication module 1213, professional information entry module 1221, professional information management module 1222, professional audit authentication display module 1223, instruction suggestion module 1231, online service module 1232, offline service module 1233, display module 1251, input interface 1252, communication module 1253, data analysis module 2110, data storage module 2120, data communication module 2130, data preprocessing module 2111, intelligent consultation module 2112, intelligent intervention module 2113, user data storage module 2121, advisor data storage module 2122, health knowledge database 2123, A health intervention plan database 2124.
Detailed Description
The present invention is further described below with reference to examples, but it should not be construed that the scope of the above subject matter of the present invention is limited to the following examples. Various substitutions and alterations are made according to the ordinary skill and familiar means of the art without departing from the technical spirit of the invention, and all such substitutions and alterations are intended to be included in the scope of the invention.
Example 1:
referring to fig. 1 to 11, an intelligent medical health consultation system includes an intelligent terminal 1000 and a cloud server 2000;
the intelligent terminal 1000 includes a client 1100 and an advisor 1200; the cloud server side (1200) comprises a central server (2100) and a server cluster (2200);
the client 1100 includes an image acquisition module 1110, an information entry module 1120, a display module 1130, and a login module 1140, for acquiring medical health data of a user, including but not limited to basic information, health indicators, and body images;
the advisor side 1200 includes an advisor registration login module 1210, a professional registration module 1220, a comprehensive business module 1230, and an advisor personal information management module 1240, which provide professional health guidance comprehensive services for the target user;
the central server 2100 includes a data analysis module 2110; the data analysis module 2110 comprises a data preprocessing module 2111 and an intelligent consultation module 2112;
The data preprocessing module 2111 receives data from the client 1100 and the server cluster 2200, performs preprocessing to obtain a feature subset, and transmits the feature subset to the intelligent consultation module 2112;
the intelligent consultation module 2112 comprises a data characterization unit, a consultation scoring unit and a report generating unit;
the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module 2111 to obtain a data vector, and transmits the data vector to the consultation scoring unit;
the consultation scoring unit stores a consultation scoring model; the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit;
the report generating unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client 1100 and the consultant 1200;
the server cluster 2200 includes server a410, server B420, and server C430;
the server A410 comprises a server A411, a server A412 and a server A413, and different tongue diagnosis algorithms are respectively provided; the server A411 analyzes the tongue image of the user through an internal tongue diagnosis algorithm A1 to obtain return result data T1; server a412 analyzes the tongue image of the user by internal tongue diagnosis algorithm A2 to obtain return result data T2; the server A413 analyzes the tongue image of the user through an internal tongue diagnosis algorithm A3 to obtain return result data T3;
The tongue diagnosis algorithm comprises the following steps of: the tongue diagnosis algorithm analyzes tongue color, tongue coating quality, tongue shape, tongue body fluid and tongue appearance characteristics of sublingual collaterals and corresponding Chinese medicine physique according to tongue images of users. The returned result data T1, the returned result data T2 and the returned result data T3 are respectively transmitted to the data preprocessing module 2111 and combined into data Rt; the data Rt comprises tongue characteristic values and constitution characteristic values; the tongue manifestation characteristic values comprise tongue color characteristic values, tongue coating color characteristic values, tongue quality characteristic values, tongue shape characteristic values, body fluid characteristic values and sublingual collaterals characteristic values; the tongue color characteristic values comprise pale tongue, red tongue, dark red tongue and dark purple tongue; the characteristic values of the color of the moss comprise white moss, light yellow moss, burnt yellow moss, gray black moss and burnt black moss; the characteristic values of the moss comprise thin moss, thick moss, putrefaction, greasiness, flaking, no moss and little moss; the tongue-shaped characteristic values comprise fatness, thinness, old, tender, pricking, ecchymosis, petechiae, cracks and tooth marks; the body fluid characteristic value comprises moistening, lubricating and drying; the characteristic values of the sublingual collaterals comprise normal sublingual, sublingual deficiency, sublingual stasis and unclear sublingual graph; the constitution characteristic values comprise mild constitution, qi depression, qi deficiency, blood deficiency, yang deficiency, yin deficiency, phlegm dampness, damp heat, excessive heat, blood stasis and specific intrinsic properties.
The server B420 comprises a server B421, a server B422 and a server B423, and different facial diagnosis algorithms are respectively provided; the server B421 analyzes the facial image of the user through the internal facial algorithm B1 to obtain return result data F1; the server B422 analyzes the facial image of the user through the internal facial algorithm B2 to obtain return result data F2; the server B423 analyzes the facial image of the user through an internal facial diagnosis algorithm B3 to obtain return result data F3;
the facial image analysis processing step of the facial diagnosis algorithm comprises the following steps: the facial diagnosis algorithm analyzes facial image characteristics and corresponding Chinese medicine physique according to facial images of users. The returned result data F1, the returned result data F2 and the returned result data F3 are respectively transmitted to the data preprocessing module 2111 and combined into data Rf; the data Rf comprises a facial feature value and a physical feature value; the face image characteristic values include: a face color feature value, a face gloss feature value, a lip color feature value, and a lip texture lip state feature value; the face color feature value includes: cyan, yellow, red, white, and black; the face type characteristic value includes: superbroad, broad, medium, narrow, and supernarrow; the facial gloss characteristic values include: reddish, pale white and tarnish; the lip characteristic value includes: normal color, pale white, cyan, black, purple, dark red, and black; the lip texture lip state characteristic value comprises: normal lips, lip scraps, lip cocoons, lip shrinkage and lip sores; the constitution characteristic values comprise mild constitution, qi depression, qi deficiency, blood deficiency, yang deficiency, yin deficiency, phlegm dampness, damp heat, excessive heat, blood stasis and specific intrinsic properties.
The server C430 comprises a server C431, a server C432 and a server C433, and different diagnosis algorithms are respectively provided; the server C431 analyzes the eye images of the user through the internal diagnosis algorithm C1 to obtain return result data E1; the server C432 analyzes the eye images of the user through an internal diagnosis algorithm C2 to obtain return result data E2; the server C433 analyzes the eye image of the user through the internal diagnosis algorithm C3 to obtain the returned result data E3. The returned result data E1, the returned result data E2 and the returned result data E3 are respectively transmitted to the data preprocessing module 2111 and are combined into data Re; the data Re comprises characteristic values of the object and characteristic values of the constitution; the eye characteristic value comprises an eye characteristic value and a five-round area characteristic value; the eye color characteristic values include cyan, red, yellow, white, and black; the five rounds of regional feature values comprise cornea, inner and outer canthus, upper and lower eyelid, sclera and iris; the constitution characteristic values comprise mild constitution, qi depression, qi deficiency, blood deficiency, yang deficiency, yin deficiency, phlegm dampness, damp heat, excessive heat, blood stasis and specific intrinsic properties.
The image acquisition module 1110 includes a shooting module 1111 and an uploading module 1112;
The photographing module 1111 photographs body images of the user including, but not limited to, tongue, face and eyes, and transmits to the uploading module 1112;
the uploading module 1112 performs data interaction with the central server 1200 through a network;
the information input module 1120 includes a basic information input module 1121, an inquiry information input module 1122, and a physical examination information input module 1123;
the basic information input module 1121 is used for inputting basic information of a user; the user's basic information includes, but is not limited to, gender, age, height, weight, past medical history, marital status, occupation type, income situation;
the inquiry information input module 1122 is used for inputting inquiry information of the user; the questionnaire information includes, but is not limited to, traditional Chinese medicine questionnaire results, emotion self-questionnaire results and physical activity questionnaire results; the traditional Chinese medicine questionnaire results, the emotion self-questionnaire results and the physical activity questionnaire results are obtained through an electronic questionnaire form.
The traditional Chinese medicine questionnaire is shown in the following table 1:
table 1 Chinese medicine questionnaire
The emotion self-assessment roll is shown in table 2 below:
table 2 emotion self-questionnaire
The physical activity questionnaire is shown in table 3 below:
Table 3 physical Activity questionnaire
The physical examination information input module 1123 is used for inputting physical examination information of the user; the physical examination information includes, but is not limited to, physical examination results, blood routine examination results, urine routine examination results, and cardiac function assessment results;
the data Ri entered by the user through the information entry module 1120 is transmitted to the data preprocessing module 2111 through the client terminal 1170;
the display module 1130 comprises a history display module 1131, a consultation result display module 1132, an intelligent intervention scheme pushing module 1133 and a professional guidance suggestion module 1134;
the history display module 1131 includes a basic information history display unit, a consultation information history display unit, a physical examination information history display unit, and an image history display unit;
the basic information history record display unit is used for counting and displaying basic information of a user;
the inquiry information history record display unit is used for counting and displaying inquiry information of the user;
the physical examination information history record display unit is used for counting and displaying physical examination information of the user;
the image history record display unit is used for counting and displaying tongue images, face images and eye images of a user;
The consultation result display module 1132 is used for counting and displaying consultation reports of the user;
the intelligent intervention scheme pushing module 1133 comprises a nutrition prescription pushing unit, a sports prescription pushing unit, a traditional Chinese medicine prescription pushing unit and a music prescription pushing unit;
the nutrition recipe pushing unit is used for pushing personalized nutrition recipes;
the sport prescription pushing unit is used for pushing the personalized sport prescriptions;
the traditional Chinese medicine prescription pushing unit is used for pushing personalized traditional Chinese medicine prescriptions;
the music prescription pushing unit is used for pushing personalized music prescriptions;
the specialized guidance suggestion module 1134 is used for displaying specialized guidance suggestions provided by the consultant according to the consultation report; the specialized instruction advice includes, but is not limited to, providing functional training, dietary instruction and services, and rehabilitation advanced instruction for a particular group of people.
The login module 1140 includes a user registration module 1141, a user login module 1142, and a user identity authentication module 1143;
the user registration module 1141 is configured to complete a user registration operation;
the user login module 1142 is configured to complete a user login operation;
the user identity authentication module 1143 is configured to perform user identity authentication.
The authorization module 1150 includes a privacy authorization module 1151 and a management authorization module 1152;
the authorization module 1151 is configured to provide corresponding personal privacy information to the system after the user agrees to authorization when the system needs the user to provide privacy information;
the management authorization module 1152 is configured to obtain access and management rights of the user by the advisor, and after the user agrees to the authorization, the advisor can view information of the user and manage information provided by the user.
The client 1100 also includes an advisor module 1160; the advisor module 1160 includes an advisor selection module 1161, an online communication module 1162, an offline experience module 1163, and an advisor assessment module 1164 for selecting and assessing advisors, online communication, offline experiences.
The client 1100 also includes a client terminal 1170; the client terminal 1170 includes one or more of a smart phone, a tablet computer, and a computer;
the image acquisition module 1110, the information entry module 1120, the display module 1130, the login module 1140, the authorization module 1150, and the advisor module 1160 are integrated within the client terminal 1170;
the client terminal 1170 includes a display module 1171, an input interface 1172, and a communication module 1173;
The display module 1171 is configured to implement a data display function;
the input interface 1172 is used to implement a data acquisition function;
the communication module 1173 is configured to implement a data transmission function.
The advisor registration login module 1210 includes an advisor registration module 1211, an advisor login module 1212, and an advisor identity authentication module 1213 for the registration login verification operation of an advisor;
the job registration module 1220 comprises a job information input module 1221, a job information management module 1222 and a job audit certification display module 1223, which are used for job title input and job information management of all consultants;
the integrated service module 1230 includes a guide suggestion module 1231, an online service module 1232, and an offline service module 1233; the online service module is used for online communication between the target user and the consultant, including but not limited to graphic communication, voice communication and video communication; the off-line service module is used for providing off-line health management services performed by a target user, including but not limited to nutritional meal replacement, course training and physiotherapy conditioning;
the consultant personal information management module 1240 includes a consultant personal information input module, a occupation audit display module and a consultant history management module, and is connected with the occupation registration module 1220 to input and manage personal basic information and occupation information of the consultant user.
The advisor terminal 1200 further includes an advisor terminal 1250, and the advisor registration login module 1210, the professional registration module 1220, the integrated service module 1230, and the advisor personal information management module 1240 are integrated inside the advisor terminal 1250;
the advisor terminal 1250 includes a display module 1251, an input interface 1252, a communication module 1253;
the display module 1251 is used for realizing a data display function;
the input interface 1252 is used for realizing a data acquisition function;
the communication module 1253 is configured to implement a data transmission function;
the advisor terminal 1250 can be one or more of a smart phone, a tablet computer, and a computer.
The advisor side 1200 further includes a security authentication module 1260, the security authentication module 1260 is configured to perform identity authentication when the advisor views and manages user information, and the security authentication module includes one or more combinations of a password authentication unit, a fingerprint authentication unit, a face authentication unit, a USB hardware link authentication unit, and an audio hole connection hardware authentication unit.
The central server 2100 also includes a data storage module 2120 and a data communication module 2130;
the data storage module 2120 includes a user data storage module 2121, an advisor data storage module 2122, a health knowledge database 2123, and a health intervention plan database 2124; the user data storage module is used for storing all data of users in the client; the advisor data storage module is used for storing all data of the advisor; the health knowledge database 2123 is used for storing health knowledge data; the health intervention plan database 2124 is used for storing health intervention plan data;
The central server 2100 interacts with clients 1100, advisors 1200, and server cluster 2200 via data communication module 2130.
The data preprocessing module 2111 preprocesses the data Rt, the data Rf, the data Re, the data Ri and the data Rm to obtain a feature subset;
the step of obtaining the feature subset by the data preprocessing module 2111 includes:
s11) filling missing data automatically based on a mean filling method;
s12) detecting outliers by adopting an Isolation Forest;
s13) adopting an SMOTE algorithm to process to obtain a balanced data set;
s14) converting non-numerical data, sequencing data, fixed type data and character string type data into numerical data through category conversion, serial number coding, single-hot coding and word embedding models respectively;
s15) carrying out normalization processing on the numerical data by adopting a zero-mean normalization method;
s16) extracting the features by using a principal component analysis method to obtain a feature subset.
The step of obtaining the data vector by the data characterization unit comprises the following steps:
s21) converting word information in the feature subsets into one-dimensional TokenEmbedddings codes;
s22) calculating a position Embeddings code and a segment Embeddings code corresponding to each word;
S23) inputting TokenEmbeddins codes, positionEmbeddins codes and SegmentEmbeddins codes into the BERT language characterization model to obtain data vectors after global information fusion;
the consultation scoring model comprises an input layer, a deep learning network layer, a full connection layer and an output layer:
the input layer is used for receiving data vectors;
the deep learning network layer comprises a CNN layer and an LSTM layer;
the CNN layer performs feature extraction on the data vector to obtain a feature matrix;
the LSTM layer performs feature extraction on the data vector to obtain a feature sequence;
the full connection layer weights the feature matrix and the feature sequence and maps the feature matrix and the feature sequence to a sample marking space to obtain a feature vector;
and the output layer performs inner product on the feature vector to obtain a consultation scoring result of the user.
The step of obtaining the consultation scoring result of the user comprises the following steps:
s31) inputting the data vector into CNN, setting the number of convolution kernels to be 50, the convolution size to be 5 and the step length to be 1, and carrying out convolution operation according to the formula (1) to obtain a feature matrix U c Wherein F u Is a data vector V1 input to CNN;
U c ＝max(0,WF u +b) (1)
wherein W, b is the weight and bias;
inputting the data vector into CNN, setting the number of convolution kernels as 1100, the convolution size as 10 and the step length as 2, and performing convolution operation according to formula (2) to obtain a feature matrix U a Wherein F a Is a data vector V1 input to CNN;
U a ＝max(0,WF a +b) (2)
s32) carrying out global pooling operation according to a formula (3), and solving the maximum value of the whole data under the current dimension, so that the dimension is reduced, and a new feature vector is obtained;
(U’ c ,U’ a )＝max(U c ,U a ) (3)
s33) inputting the data vector into the LSTM, and obtaining the user characteristic U through the calculation of the input gate, the forget gate and the output gate l ；
S34) characterizing U' c ,U l Performing full connection to obtain a new feature vector U F ；
Characterization U' a ,U l Performing full connection to obtain a new feature vector U V ；
S35) performing inner product operation according to the formula (4) to obtain consultation scores M of the users score ；
M score ＝U F ⊙U V (4)
In the formula, ++represents the inner product operation.
The data analysis module 2110 also includes an intelligent intervention module 2113; the intelligent intervention module 2113 is configured to generate an intelligent intervention scheme, and return a result to the intelligent intervention scheme pushing module 1133;
the step of generating the intelligent intervention scheme by the intelligent intervention module 2113 includes:
s41) acquiring a scoring matrix and a preference matrix of the user based on the feature subset and the consultation score;
s42) calculating the comprehensive similarity between the scoring matrix and the preference matrix by utilizing an SVD collaborative filtering algorithm based on the scoring matrix and the preference matrix;
s43) obtaining a predicted value of a user recommendation scheme according to the comprehensive similarity, and obtaining a preliminary recommendation scheme set based on the predicted value;
S44) excavating a characteristic value change curve by using the BP-DS neural network, and analyzing the characteristic value change curve to obtain an intervention scheme set;
s45) carrying out local adjustment on the intervention scheme set to obtain a complete intelligent intervention scheme;
s46) dynamically updating the intelligent intervention scheme based on the time-sequential update data resulting from executing the complete intelligent intervention scheme.
Examples of the intelligent intervention scheme are shown in table 4 below:
table 4 Intelligent intervention scheme example
The system further includes a multi-parameter health detection terminal 4000;
the multi-parameter health detection terminal 4000 is used for acquiring real-time physical sign data of a user. Including but not limited to body temperature, heart rate, electrocardiograph, blood pressure, blood oxygenation, including health management robots, medical devices;
the multi-parameter health detection terminal 4000 performs data interaction with the central server 2100 through the data communication module 2130;
all data of the user in the multi-parameter health check terminal 4000 are stored in the user data storage module of the center server 2100;
the data of the multi-parameter health detection terminal 4000 is counted and displayed by a multi-parameter health detection terminal information history display unit of the history display module 1131.
Example 2:
an intelligent medical health consultation system comprises an intelligent terminal 1000 and a cloud server 2000;
the intelligent terminal 1000 includes a client 1100; the cloud server 1200 includes a central server 2100 and a server cluster 2200;
the client 1100 includes an image acquisition module 1110, an information entry module 1120, a display module 1130, a login module 1140, and an authorization module 1150, for acquiring medical health data of a user, including but not limited to basic information, health indicators, and body images;
the central server 2100 includes a data analysis module 2110; the data analysis module 2110 comprises a data preprocessing module 2111 and an intelligent consultation module 2112;
the data preprocessing module 2111 receives data from the client 1100 and the server cluster 2200, performs preprocessing to obtain a feature subset, and transmits the feature subset to the intelligent consultation module 2112;
the intelligent consultation module 2112 comprises a data characterization unit, a consultation scoring unit and a report generating unit;
the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module 2111 to obtain a data vector, and transmits the data vector to the consultation scoring unit;
the consultation scoring unit comprises a consultation scoring model; the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit;
The report generating unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client 1100;
the server cluster 2200 comprises a tongue diagnosis algorithm server 2210, a face diagnosis algorithm server 2220, a eye diagnosis algorithm server 2230 and a traditional Chinese medicine physique identification algorithm server 2240, wherein each server stores an independent algorithm; the server processes tongue image, facial image and eye image data of the user respectively through independent image processing algorithms to obtain return result data, and transmits the return result data to the central server 2100; the returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
Example 3:
an intelligent medical health consultation system comprises an intelligent terminal 1000 and a cloud server 1200;
the intelligent terminal 1000 includes a client 1100 and an advisor 1200; the cloud server 2000 includes a central server 2100 and a server cluster 2200;
the client 1100 includes an image acquisition module 1110, an information entry module 1120, a display module 1130, a login module 1140, and an authorization module 1150, for acquiring medical health data of a user, including but not limited to basic information, health indicators, and body images;
The advisor side 1200 includes an advisor registration login module 1210, a professional registration module 1220, a comprehensive business module 1230, and an advisor personal information management module 1240;
the central server 2100 includes a data analysis module 2110; the data analysis module 2110 comprises a data preprocessing module 2111 and an intelligent consultation module 2112;
the data preprocessing module 2111 receives data from the client 1100 and the server cluster 2200, performs preprocessing to obtain a feature subset, and transmits the feature subset to the intelligent consultation module 2112;
the intelligent consultation module 2112 comprises a data characterization unit, a consultation scoring unit and a report generating unit;
the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module 2111 to obtain a data vector, and transmits the data vector to the consultation scoring unit;
the consultation scoring unit comprises a consultation scoring model; the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit;
the report generating unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client 1100 and the consultant 1200;
the server cluster 2200 comprises a tongue diagnosis algorithm server 2210, a face diagnosis algorithm server 2230, a eye diagnosis algorithm server 2240 and a traditional Chinese medicine physique identification algorithm server 2250, wherein each server stores an independent algorithm; the server processes tongue image, facial image and eye image data of the user respectively through independent image processing algorithms to obtain return result data, and transmits the return result data to the central server 2100; the returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
Example 4:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-3, further, the user side 1100 and the consultant side 1200 are packaged in an integrated module 3000, installed and operated on the intelligent terminal 1000; an intelligent terminal 1000 includes both a client 1100 and an advisor 1200, which can be switched to each other by a switching module 3100.
Example 5:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-4, further, the user side 1100 and the consultant side 1200 exist on two different intelligent terminals respectively, and the two intelligent terminals operate independently and communicate with the cloud server side 2000 respectively.
Example 6:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-5, further, the image acquisition module 1110 includes a shooting module 1111 and an uploading module 1112;
the photographing module 1111 photographs the body image of the user and transmits to the uploading module 1112; including but not limited to tongue, face, and eye images;
the uploading module 1112 performs data interaction with the central server 1200 through a network;
example 7:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-6, further, the information input module 1120 includes a basic information input module 1121, an inquiry information input module 1122 and a physical examination information input module 1123;
The basic information input module 1121 is used for inputting basic information of a user; the user's basic information includes, but is not limited to, gender, age, height, weight, past medical history, marital status, occupation type, income situation;
the inquiry information input module 1122 is used for inputting inquiry information of the user; the questionnaire information includes, but is not limited to, traditional Chinese medicine questionnaire results, emotion self-questionnaire results and physical activity questionnaire results; the traditional Chinese medicine questionnaire results, the emotion self-questionnaire results and the physical activity questionnaire results are obtained through an electronic questionnaire form.
The physical examination information input module 1123 is used for inputting physical examination information of the user; the physical examination information includes, but is not limited to, physical examination results, blood routine examination results, urine routine examination results, and cardiac function assessment results; example 8:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-7, further, the display module 1130 includes a history display module 1131, a consultation result display module 1132, an intelligent intervention scheme pushing module 1133, and a professional guidance suggestion module 1134;
the history display module 1131 includes a basic information history display unit, a consultation information history display unit, a physical examination information history display unit, and an image history display unit;
The basic information history record display unit is used for counting and displaying basic information of a user;
the inquiry information history record display unit is used for counting and displaying inquiry information of the user;
the physical examination information history record display unit is used for counting and displaying physical examination information of the user;
the image history display unit is used for counting and displaying body images of a user, including but not limited to tongue images, face images and eye images;
the consultation result display module 1132 is used for counting and displaying consultation reports of the user;
example 9:
the technical content of the intelligent medical health consultation system is the same as any one of embodiments 2-8, further, the intelligent intervention scheme pushing module 1133 includes a nutrition prescription pushing unit, a sports prescription pushing unit, a traditional Chinese medicine prescription pushing unit and a music prescription pushing unit;
the nutrition recipe pushing unit is used for pushing personalized nutrition recipes;
the sport prescription pushing unit is used for pushing the personalized sport prescriptions;
the traditional Chinese medicine prescription pushing unit is used for pushing personalized traditional Chinese medicine prescriptions;
the music prescription pushing unit is used for pushing personalized music prescriptions;
the specialized guidance suggestion module 1134 is used for displaying specialized guidance suggestions provided by the consultant according to the consultation report;
Example 10:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-9, further, the login module 1140 includes a user registration module 1141, a user login module 1142, and a user identity authentication module 1143;
the user registration module 1141 is configured to complete a user registration operation;
the user login module 1142 is configured to complete a user login operation;
the user identity authentication module 1143 is configured to complete user identity authentication;
example 11:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-10, further, the authorization module 1150 includes a privacy authorization module 1151 and a management authorization module 1152;
the authorization module 1151 is configured to provide corresponding personal privacy information to the system after the user agrees to authorization when the system needs the user to provide privacy information;
the management authorization module 1152 is configured to obtain access and management rights of the user by the advisor, and after the user agrees to the authorization, the advisor can view information of the user and manage information provided by the user.
Example 12:
an intelligent medical health consultation system, the technical content of which is the same as in any one of embodiments 2-11, further, the client 1100 further comprises an advisor module 1160 and a client terminal 1170;
The advisor module 1160 includes an advisor selection module 1161, an online communication module 1162, an offline experience module 1163, and an advisor assessment module 1164 for selecting, communicating with, and assessing an advisor online.
The client terminal 1170 includes one or more of a smart phone, a tablet computer, and a computer;
example 13:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-12, further, the image acquisition module 1110, the information input module 1120, the display module 1130, the login module 1140, the authorization module 1150 and the consultant module 1160 are integrated in the client terminal 1170;
example 14:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-13, further, the client terminal 1170 includes a display module 1171, an input interface 1172, and a communication module 1173;
the display module 1171 is configured to implement a data display function;
the input interface 1172 is used to implement a data acquisition function;
the communication module 1173 is configured to implement a data transmission function.
Example 15:
an intelligent medical health consultation system, the technical content of which is the same as in any one of embodiments 2-14, further, the consultant registration login module 1210 includes a consultant registration module 1211, a consultant login module 1212 and a consultant identity authentication module 1213 for registration login verification operation of a consultant;
Example 16:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-15, further, the job registration module 1220 comprises a job information input module 1221, a job information management module 1222 and a job audit certification display module 1223, which are used for job title input and job information management of all consultants;
example 17:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-16, further, the integrated service module 1230 includes a guidance suggestion module 1231, an online service module 1232, and an offline service module 1233;
the online service module is used for online communication between the target user and the consultant, including but not limited to graphic communication, voice communication and video communication;
the off-line service module is used for providing off-line health management services performed by a target user, including but not limited to nutritional meal replacement, course training and physiotherapy conditioning;
example 18:
an intelligent medical health consultation system has technical contents similar to any one of embodiments 2-17, further, the consultant personal information management module 1240 includes a consultant personal information input module, a occupation auditing display module and a consultant history management module, and is connected with the occupation registration module 1220 to input and manage personal basic information and occupation information of a consultant user.
Example 19:
an intelligent medical health consultation system, the technical content of which is the same as that of any one of embodiments 2-18, further, the consultant terminal 1200 further comprises a consultant terminal 1250, a security authentication module 1260, and a consultant registration login module 1210, a occupation registration module 1220, a comprehensive business module 1230, and a consultant personal information management module 1240 are integrated inside the consultant terminal 1250;
example 20:
an intelligent medical health consultation system, the technical content of which is the same as in any one of embodiments 2-19, further, the consultant terminal 1250 comprises a display module 1251, an input interface 1252 and a communication module 1253;
the display module 1251 is used for realizing a data display function;
the input interface 1252 is used for realizing a data acquisition function;
the communication module 1253 is configured to implement a data transmission function;
the advisor terminal 1250 can be one or more of a smart phone, a tablet computer, and a computer; example 21:
an intelligent medical health consultation system, the technical content of which is the same as any one of embodiments 2-20, further comprising a security authentication module 1260 for performing secondary identity authentication when a consultant views and manages user information, wherein the security authentication module comprises one or more of a password authentication unit, a fingerprint authentication unit, a face authentication unit, a USB hardware link authentication unit and an audio hole connection hardware authentication unit.
Example 22:
an intelligent medical health consultation system having the technical content as in any one of embodiments 2-21, further, the central server 2100 further includes a data storage module 2120 and a data communication module 2130;
the data storage module 2120 includes a user data storage module 2121, an advisor data storage module 2122, a health knowledge database 2123, and a health intervention plan database 2124; the user data storage module is used for storing all data of users in the client; the advisor data storage module is used for storing all data of the advisor; the health knowledge database 2123 is used for storing health knowledge data; the health intervention plan database 2124 is used for storing health intervention plan data;
the central server 2100 interacts with clients 1100, advisors 1200, and server cluster 2200 via data communication module 2130.
Example 23:
an intelligent medical health consultation system, the technical content of which is the same as any one of embodiments 2-22, further comprising a multi-parameter health detection terminal 4000;
the multi-parameter health detection terminal 4000 is used for acquiring real-time physical sign data of a user, including but not limited to body temperature, heart rate, electrocardio, blood pressure and blood oxygen, including health management robots and medical equipment;
The multi-parameter health detection terminal 4000 performs data interaction with the central server 2100 through the data communication module 2130;
all data of the user in the multi-parameter health check terminal 4000 are stored in the user data storage module of the center server 2100;
the data of the multi-parameter health detection terminal 4000 are counted and displayed through a multi-parameter health detection terminal information history record display unit of a history record display module 1131;
example 24:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-23, further, the step of obtaining the feature subset by the data preprocessing module 2111 includes:
s11) filling missing data automatically based on a mean filling method;
s12) detecting outliers by adopting an Isolation Forest;
s13) adopting an SMOTE algorithm to process to obtain a balanced data set;
s14) converting non-numerical data, sequencing data, fixed type data and character string type data into numerical data through category conversion, serial number coding, single-hot coding and word embedding models respectively;
s15) carrying out normalization processing on the numerical data by adopting a zero-mean normalization method;
s16) extracting the features by using a principal component analysis method to obtain a feature subset.
Example 25:
an intelligent medical health consultation system, the technical content of which is the same as any one of embodiments 2-24, further comprising the step of obtaining a data vector by the data characterization unit:
s21) converting word information in the feature subsets into one-dimensional TokenEmbedddings codes;
s22) calculating a position Embeddings code and a segment Embeddings code corresponding to each word;
s23) inputting TokenEmbeddins code, positionEmbeddins code and SegmentEmbeddins code into the BERT language characterization model to obtain the data vector after the global information is fused.
Example 26:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-23, further, the consultation scoring model comprises an input layer, a deep learning network layer, a full connection layer and an output layer:
the input layer is used for receiving data vectors;
the deep learning network layer comprises a CNN layer and an LSTM layer;
the CNN layer performs feature extraction on the data vector to obtain a feature matrix;
the LSTM layer performs feature extraction on the data vector to obtain a feature sequence;
the full connection layer weights the feature matrix and the feature sequence and maps the feature matrix and the feature sequence to a sample marking space to obtain a feature vector;
And the output layer performs inner product on the feature vector to obtain a consultation scoring result of the user.
Example 27:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-26, further, the step of obtaining a consultation scoring result of the user by the consultation scoring model includes:
s31) inputting the data vector into a CNN layer of a consultation scoring model to obtain a feature matrix U c And U a The method comprises the following steps:
U c ＝max(0,WF u +b) (1)
U a ＝max(0,WF a +b) (2)
wherein F is u 、F a Respectively representing a feature subset and a returned result subset;
s32) pair of feature matrices U c Feature matrix U a Global pooling operation is performed to obtain feature vectors (U' c ,U’ a ) The method comprises the following steps:
(U’ c ,U’ a )＝max(U c ,U a ) (4)
s33) inputting the data vector into the LSTM, and obtaining the characteristic sequence U through calculation of the input gate, the forget gate and the output gate l ；
S34) fitting the eigenvector U' c Characteristic sequence U l Performing full connection to obtain a new feature vector U F The method comprises the steps of carrying out a first treatment on the surface of the Feature vector U' a Characteristic sequence U l Performing full connection to obtain a new feature vector U V ；
S35) pair of eigenvectors U F Feature vector U V Performing inner product operation to obtain the userM_score, i.e.:
M score ＝U F ⊙U V (5)
in the formula, ++represents the inner product operation.
Example 28:
an intelligent medical health consultation system, the technical content of which is the same as in any one of embodiments 2-27, further, the data analysis module 2110 further comprises an intelligent intervention module 2113;
The intelligent intervention module 2113 is configured to generate an intelligent intervention scheme, and return a result to the intelligent intervention scheme pushing module 1133;
example 29:
the intelligent medical health consultation system has the technical content as in any one of embodiments 2-28, further, the step of generating an intelligent intervention scheme by the intelligent intervention module 2113 includes:
s41) acquiring a scoring matrix and a preference matrix of the user based on the feature subset and the consultation score;
s42) calculating the comprehensive similarity between the scoring matrix and the preference matrix by utilizing an SVD collaborative filtering algorithm based on the scoring matrix and the preference matrix;
s43) obtaining a predicted value of a user recommendation scheme according to the comprehensive similarity, and obtaining a preliminary recommendation scheme set based on the predicted value;
s44) excavating a characteristic value change curve by using the BP-DS neural network, and analyzing the characteristic value change curve to obtain an intervention scheme set;
s45) carrying out local adjustment on the intervention scheme set to obtain a complete intelligent intervention scheme;
s46) dynamically updating the intelligent intervention scheme based on the time-sequential update data resulting from executing the complete intelligent intervention scheme.
Claims (10)
1. An intelligent medical health consultation system, which is characterized in that: the intelligent terminal (1000) and the cloud server (2000) are included.
The intelligent terminal (1000) comprises a client (1100); the cloud server side (1200) includes a central server (2100) and a server cluster (2200).
The client (1100) comprises an image acquisition module (1110), an information input module (1120), a display module (1130), a login module (1140) and an authorization module (1150) for acquiring medical health data of a user, including but not limited to basic information, health indexes and body images;
the central server (2100) comprises a data analysis module (2110); the data analysis module (2110) comprises a data preprocessing module (2111) and an intelligent consultation module (2112);
the data preprocessing module (2111) receives data from the client (1100) and the server cluster (2200), performs preprocessing to obtain a feature subset, and transmits the feature subset to the intelligent consultation module (2112);
the intelligent consultation module (2112) comprises a data characterization unit, a consultation scoring unit and a report generating unit;
the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module (2111) to obtain a data vector, and transmits the data vector to the consultation scoring unit;
the consultation scoring unit comprises a consultation scoring model; the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit;
The report generation unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client (1100);
the server cluster (2200) comprises a tongue diagnosis algorithm server (2210), a face diagnosis algorithm server (2220), a mesh diagnosis algorithm server (2230) and a traditional Chinese medicine physique identification algorithm server (2240), wherein each server stores an independent algorithm; the server processes tongue image, facial image and eye image data of the user respectively through independent image processing algorithms to obtain return result data, and the return result data is transmitted to a central server (2100); the returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
2. An intelligent medical health consultation system, which is characterized in that: the cloud server comprises an intelligent terminal (1000) and a cloud server (1200);
the intelligent terminal (1000) comprises a client (1100) and a consultant (1200); the cloud server side (2000) comprises a central server (2100) and a server cluster (2200);
the client (1100) comprises an image acquisition module (1110), an information input module (1120), a display module (1130), a login module (1140) and an authorization module (1150) for acquiring medical health data of a user, including but not limited to basic information, health indexes and body images;
The consultant end (1200) comprises a consultant registration login module (1210), a occupation registration module (1220), a comprehensive business module (1230) and a consultant personal information management module (1240);
the central server (2100) comprises a data analysis module (2110); the data analysis module (2110) comprises a data preprocessing module (2111) and an intelligent consultation module (2112);
the data preprocessing module (2111) receives data from the client (1100) and the server cluster (2200), performs preprocessing to obtain a feature subset, and transmits the feature subset to the intelligent consultation module (2112);
the intelligent consultation module (2112) comprises a data characterization unit, a consultation scoring unit and a report generating unit;
the data characterization unit performs comprehensive processing analysis on the feature subset obtained by the data preprocessing module (2111) to obtain a data vector, and transmits the data vector to the consultation scoring unit;
the consultation scoring unit comprises a consultation scoring model; the consultation scoring model analyzes the data vector to obtain a consultation scoring result of the user and transmits the consultation scoring result to the report generating unit;
the report generation unit generates a consultation report according to the consultation scoring result of the user and transmits the consultation report to the client (1100) and the consultant (1200);
The server cluster (2200) comprises a tongue diagnosis algorithm server (2210), a face diagnosis algorithm server (2230), a mesh diagnosis algorithm server (2240) and a traditional Chinese medicine physique identification algorithm server (2250), wherein each server stores an independent algorithm; the server processes tongue image, facial image and eye image data of the user respectively through independent image processing algorithms to obtain return result data, and the return result data is transmitted to a central server (2100); the returned result data includes, but is not limited to, tongue image features, facial image features, eye image features, and traditional Chinese medicine physique features.
3. The intelligent medical health consultation system according to claim 2, wherein the user side (1100) and the consultant side (1200) are packaged in an integrated module (3000), installed and operated on the intelligent terminal (1000); an intelligent terminal (1000) comprises a user terminal (1100) and an advisor terminal (1200) which can be mutually switched through a switching module (3100).
4. The intelligent medical health consultation system according to claim 2, wherein the user terminal (1100) and the consultant terminal (1200) respectively exist on two different intelligent terminals, and the two terminals independently operate and respectively communicate with the cloud server terminal (2000).
5. The intelligent medical health consultation system according to any one of claims 1, 2, wherein the image acquisition module (1110) includes a shooting module (1111) and an uploading module (1112);
the shooting module (1111) shoots a body image of a user and transmits the body image to the uploading module (1112); including but not limited to tongue, face, and eye images;
the uploading module (1112) performs data interaction with the central server (1200) through a network;
the information input module (1120) comprises a basic information input module (1121), an inquiry information input module (1122) and a physical examination information input module (1123);
the basic information input module (1121) is used for inputting basic information of a user; the user's basic information includes, but is not limited to, gender, age, height, weight, past medical history, marital status, occupation type, income situation;
the inquiry information input module (1122) is used for inputting inquiry information of a user; the questionnaire information includes, but is not limited to, traditional Chinese medicine questionnaire results, emotion self-questionnaire results and physical activity questionnaire results; the traditional Chinese medicine questionnaire results, the emotion self-questionnaire results and the physical activity questionnaire results are obtained through an electronic questionnaire form.
The physical examination information input module (1123) is used for inputting physical examination information of the user; the physical examination information includes, but is not limited to, physical examination results, blood routine examination results, urine routine examination results, and cardiac function assessment results;
the display module (1130) comprises a history record display module (1131), a consultation result display module (1132), an intelligent intervention scheme pushing module (1133) and a professional guidance suggestion module (1134);
the history display module (1131) comprises a basic information history display unit, a consultation information history display unit, a physical examination information history display unit and an image history display unit;
the basic information history record display unit is used for counting and displaying basic information of a user;
the inquiry information history record display unit is used for counting and displaying inquiry information of the user;
the physical examination information history record display unit is used for counting and displaying physical examination information of the user;
the image history display unit is used for counting and displaying body images of a user, including but not limited to tongue images, face images and eye images;
the consultation result display module (1132) is used for counting and displaying consultation reports of the users;
The intelligent intervention scheme pushing module (1133) comprises a nutrition prescription pushing unit, a sports prescription pushing unit, a traditional Chinese medicine prescription pushing unit and a music prescription pushing unit;
the nutrition recipe pushing unit is used for pushing personalized nutrition recipes;
the sport prescription pushing unit is used for pushing the personalized sport prescriptions;
the traditional Chinese medicine prescription pushing unit is used for pushing personalized traditional Chinese medicine prescriptions;
the music prescription pushing unit is used for pushing personalized music prescriptions;
the specialized guidance suggestion module (1134) is used for displaying specialized guidance suggestions provided by the consultant according to the consultation report;
the login module (1140) comprises a user registration module (1141), a user login module (1142) and a user identity authentication module (1143);
the user registration module (1141) is configured to complete a user registration operation;
the user login module (1142) is used for completing user login operation;
the user identity authentication module (1143) is used for completing user identity authentication;
the authorization module (1150) includes a privacy authorization module (1151) and a management authorization module (1152);
the authorization module (1151) is configured to provide corresponding personal privacy information to the system after the user agrees to authorization when the system needs the user to provide privacy information;
The management authorization module (1152) is used for the consultant to obtain the access and the management authority of the user, and after the user agrees to the authorization, the consultant can check the user information and manage the information provided by the user.
6. The intelligent medical health consultation system according to any one of claims 1, 2, wherein the client (1100) further comprises an advisor module (1160), a client terminal (1170);
the advisor module (1160) includes an advisor selection module (1161), an online communication module (1162), an offline experience module (1163), and an advisor assessment module (1164) for selecting, online communicating with, and offline experiencing an advisor, and assessing the advisor.
The client terminal (1170) comprises one or more of a smart phone, a tablet computer and a computer;
the image acquisition module (1110), the information input module (1120), the display module (1130), the login module (1140), the authorization module (1150) and the advisor module (1160) are integrated inside the client terminal (1170);
the client terminal (1170) comprises a display module (1171), an input interface (1172) and a communication module (1173);
the display module (1171) is used for realizing a data display function;
-said input interface (1172) for implementing a data acquisition function;
The communication module (1173) is configured to implement a data transfer function.
7. The intelligent medical health consultation system according to any one of claims 1, 2, wherein the consultant registration login module (1210) includes a consultant registration module (1211), a consultant login module (1212) and a consultant identity authentication module (1213) for a registration login verification operation of the consultant;
the job registration module (1220) comprises a job information input module (1221), a job information management module (1222) and a job audit certification display module (1223) which are used for job title input and job information management of all consultants;
the integrated service module (1230) comprises a guide suggestion module (1231), an online service module (1232) and an offline service module (1233);
the online service module is used for online communication between the target user and the consultant, including but not limited to graphic communication, voice communication and video communication;
the off-line service module is used for providing off-line health management services performed by a target user, including but not limited to nutritional meal replacement, course training and physiotherapy conditioning;
the consultant personal information management module (1240) comprises a consultant personal information input module, a professional audit display module and a consultant history management module, and is connected with the professional registration module (1220) to input and manage personal basic information and professional information of the consultant user.
The advisor terminal (1200) further comprises an advisor terminal (1250), a security authentication module (1260), and an advisor registration login module (1210), a professional registration module (1220), a comprehensive business module (1230) and an advisor personal information management module (1240) are integrated inside the advisor terminal (1250);
the advisor terminal (1250) includes a display module (1251), an input interface (1252), a communication module (1253);
the display module (1251) is used for realizing a data display function;
the input interface (1252) is used for realizing a data acquisition function;
the communication module (1253) is used for realizing a data transmission function;
the advisor terminal (1250) may be one or more of a smart phone, a tablet computer, and a computer;
the security authentication module (1260) is used for performing secondary identity authentication when the consultant views and manages the user information, and comprises one or more of a password authentication unit, a fingerprint authentication unit, a face authentication unit, a USB hardware link authentication unit and an audio hole connection hardware authentication unit.
8. An intelligent medical health consultation system according to either of claims 1, 2 characterised in that the central server (2100) further includes a data storage module (2120) and a data communications module (2130);
The data storage modules (2120) include a user data storage module (2121), an advisor data storage module (2122), a health knowledge database (2123), and a health intervention plan database (2124); the user data storage module is used for storing all data of users in the client; the advisor data storage module is used for storing all data of the advisor; the health knowledge database (2123) is used for storing health knowledge data; the health intervention plan database (2124) is for storing health intervention plan data;
the central server (2100) performs data interaction with the client (1100), the advisor (1200) and the server cluster (2200) through the data communication module (2130).
The intelligent medical health consultation system also comprises a multi-parameter health detection terminal (4000);
the multi-parameter health detection terminal (4000) is used for acquiring real-time sign data of a user, including but not limited to body temperature, heart rate, electrocardio, blood pressure and blood oxygen, including a health management robot and medical equipment;
the multi-parameter health detection terminal (4000) performs data interaction with the central server (2100) through a data communication module (2130);
all data of the user in the multi-parameter health detection terminal (4000) are stored in a user data storage module of a central server (2100);
And the data of the multi-parameter health detection terminal (4000) are counted and displayed through a multi-parameter health detection terminal information history record display unit of a history record display module (1131).
9. The intelligent medical health consultation system according to any one of claims 1, 2, wherein the step of the data preprocessing module (2111) obtaining the feature subset includes:
s11) filling missing data automatically based on a mean filling method;
s12) detecting outliers by adopting an Isolation Forest;
s13) adopting an SMOTE algorithm to process to obtain a balanced data set;
s14) converting non-numerical data, sequencing data, fixed type data and character string type data into numerical data through category conversion, serial number coding, single-hot coding and word embedding models respectively;
s15) carrying out normalization processing on the numerical data by adopting a zero-mean normalization method;
s16) extracting the features by using a principal component analysis method to obtain a feature subset.
The step of obtaining the data vector by the data characterization unit comprises the following steps:
s21) converting word information in the feature subsets into one-dimensional TokenEmbedddings codes;
s22) calculating a position Embeddings code and a segment Embeddings code corresponding to each word;
S23) inputting TokenEmbeddins code, positionEmbeddins code and SegmentEmbeddins code into the BERT language characterization model to obtain the data vector after the global information is fused.
10. The intelligent medical health consultation system according to any one of claims 1 and 2, wherein the consultation scoring model includes an input layer, a deep learning network layer, a full connection layer and an output layer:
the input layer is used for receiving data vectors;
the deep learning network layer comprises a CNN layer and an LSTM layer;
the CNN layer performs feature extraction on the data vector to obtain a feature matrix;
the LSTM layer performs feature extraction on the data vector to obtain a feature sequence;
the full connection layer weights the feature matrix and the feature sequence and maps the feature matrix and the feature sequence to a sample marking space to obtain a feature vector;
and the output layer performs inner product on the feature vector to obtain a consultation scoring result of the user.
The step of obtaining the consultation scoring result of the user by the consultation scoring model comprises the following steps:
s31) inputting the data vector into a CNN layer of a consultation scoring model to obtain a feature matrix U c And U a The method comprises the following steps:
U c ＝max(0，WF u +b) (1)
U a ＝max(0，WF a +b) (2)
wherein F is u 、F a Respectively representing a feature subset and a returned result subset; w, b is the weight and bias;
S32) pair of feature matrices U c Feature matrix U a Global pooling operation is performed to obtain feature vectors (U' c ，U’ a ) The method comprises the following steps:
(U’ c ，U’ a )＝max(U c ，U a ) (4)
s33) inputting the data vector into the LSTM, and obtaining the special by calculation of the input gate, the forget gate and the output gateCharacterization sequence U l ；
S34) fitting the eigenvector U' c Characteristic sequence U l Performing full connection to obtain a new feature vector U F The method comprises the steps of carrying out a first treatment on the surface of the Feature vector U' a Characteristic sequence U l Performing full connection to obtain a new feature vector U V ；
S35) pair of eigenvectors U F Feature vector U V Performing inner product operation to obtain consultation score M of user score The method comprises the following steps:
M score ＝U F ⊙U V (5)
in the formula, ++represents the inner product operation.
The data analysis module (2110) further includes an intelligent intervention module (2113);
the intelligent intervention module (2113) is used for generating an intelligent intervention scheme and returning a result to the intelligent intervention scheme pushing module (1133);
the step of the intelligent intervention module (2113) generating an intelligent intervention scheme includes:
s41) acquiring a scoring matrix and a preference matrix of the user based on the feature subset and the consultation score;
s42) calculating the comprehensive similarity between the scoring matrix and the preference matrix by utilizing an SVD collaborative filtering algorithm based on the scoring matrix and the preference matrix;
s43) obtaining a predicted value of a user recommendation scheme according to the comprehensive similarity, and obtaining a preliminary recommendation scheme set based on the predicted value;
S44) excavating a characteristic value change curve by using the BP-DS neural network, and analyzing the characteristic value change curve to obtain an intervention scheme set;
s45) carrying out local adjustment on the intervention scheme set to obtain a complete intelligent intervention scheme;
s46) dynamically updating the intelligent intervention scheme based on the time-sequential update data resulting from executing the complete intelligent intervention scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310906221.4A CN117095835A (en) | 2023-07-21 | 2023-07-21 | Intelligent medical health consultation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310906221.4A CN117095835A (en) | 2023-07-21 | 2023-07-21 | Intelligent medical health consultation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117095835A true CN117095835A (en) | 2023-11-21 |
Family
ID=88776120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310906221.4A Pending CN117095835A (en) | 2023-07-21 | 2023-07-21 | Intelligent medical health consultation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117095835A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118471541A (en) * | 2024-07-12 | 2024-08-09 | 四川师范大学 | Method and device for detecting disease stage based on data dimension rising and deep learning |
-
2023
- 2023-07-21 CN CN202310906221.4A patent/CN117095835A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118471541A (en) * | 2024-07-12 | 2024-08-09 | 四川师范大学 | Method and device for detecting disease stage based on data dimension rising and deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110507335B (en) | Multi-mode information based criminal psychological health state assessment method and system | |
| US10806390B1 (en) | System and method for detecting physiological state | |
| US20210248656A1 (en) | Method and system for an interface for personalization or recommendation of products | |
| Kanawong et al. | Automated tongue feature extraction for ZHENG classification in traditional Chinese medicine | |
| CN110464366A (en) | A kind of Emotion identification method, system and storage medium | |
| CN105426695B (en) | A kind of health status detecting system based on iris | |
| CN108597621B (en) | Health state monitoring device, system and method based on traditional Chinese medicine theory | |
| Huan et al. | Deep convolutional neural networks for classifying body constitution based on face image | |
| CN107633876A (en) | A kind of internet medical information processing system and method based on mobile platform | |
| CN109920535A (en) | A kind of mobile Chinese medical discrimination analysis method and device | |
| CN117095835A (en) | Intelligent medical health consultation system | |
| CN113707305A (en) | Health scheme recommendation method, device, equipment and medium based on deep learning | |
| CN111048216A (en) | Early screening and intervention system for community senile dementia | |
| WO2020169214A1 (en) | Machine-implemented beauty assistant for predicting face aging | |
| WO2022011448A1 (en) | Method and system for an interface for personalization or recommendation of products | |
| CN108937967A (en) | A kind of psychology data memory promotion detection method and system based on VR technology | |
| CN110310737A (en) | A kind of intelligent mobile terminal of tcm constitution health | |
| Lian et al. | An Ear Wearable Device System for Facial Emotion Recognition Disorders | |
| CN117100270A (en) | Psychological health risk early warning evaluation system | |
| KR100915922B1 (en) | Methods and System for Extracting Facial Features and Verifying Sasang Constitution through Image Recognition | |
| CN114974254A (en) | Child depression emotion recognition method based on multi-mode artificial intelligence technology | |
| CN114582467A (en) | Personal education information management platform based on Internet | |
| de J Lozoya-Santos et al. | Current and future biometrics: technology and applications | |
| Hong | Spatial–Spectral–Temporal Framework for Emotion Recognition | |
| TWI852643B (en) | Artificial intelligence facial emotion recognition system |
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 |