CN108597621B - Health state monitoring device, system and method based on traditional Chinese medicine theory - Google Patents
Health state monitoring device, system and method based on traditional Chinese medicine theory Download PDFInfo
- Publication number
- CN108597621B CN108597621B CN201810747015.2A CN201810747015A CN108597621B CN 108597621 B CN108597621 B CN 108597621B CN 201810747015 A CN201810747015 A CN 201810747015A CN 108597621 B CN108597621 B CN 108597621B
- Authority
- CN
- China
- Prior art keywords
- module
- monitoring
- health
- chinese medicine
- traditional chinese
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 71
- 239000003814 drug Substances 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012806 monitoring device Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 116
- 238000003745 diagnosis Methods 0.000 claims abstract description 43
- 230000003862 health status Effects 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 230000001815 facial effect Effects 0.000 claims abstract description 13
- 238000011835 investigation Methods 0.000 claims abstract description 10
- 201000010099 disease Diseases 0.000 claims abstract description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 9
- 230000002787 reinforcement Effects 0.000 claims abstract description 7
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 37
- 239000008280 blood Substances 0.000 claims description 37
- 210000004369 blood Anatomy 0.000 claims description 37
- 239000008103 glucose Substances 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 32
- 230000036772 blood pressure Effects 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 24
- 230000001502 supplementing effect Effects 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 239000007789 gas Substances 0.000 description 13
- 230000004044 response Effects 0.000 description 10
- 108010015776 Glucose oxidase Proteins 0.000 description 8
- 239000004366 Glucose oxidase Substances 0.000 description 8
- 229940116332 glucose oxidase Drugs 0.000 description 8
- 235000019420 glucose oxidase Nutrition 0.000 description 8
- 238000000691 measurement method Methods 0.000 description 8
- 241000282414 Homo sapiens Species 0.000 description 7
- 108010050375 Glucose 1-Dehydrogenase Proteins 0.000 description 6
- 210000000056 organ Anatomy 0.000 description 4
- 230000010355 oscillation Effects 0.000 description 4
- 210000002784 stomach Anatomy 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 241001504424 Zosteropidae Species 0.000 description 3
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000004072 lung Anatomy 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 210000000952 spleen Anatomy 0.000 description 3
- 101100054292 Arabidopsis thaliana ABCG36 gene Proteins 0.000 description 2
- 101100351526 Arabidopsis thaliana PEN3 gene Proteins 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000003928 nasal cavity Anatomy 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 206010061218 Inflammation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 210000000867 larynx Anatomy 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009278 visceral effect Effects 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
- 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
- 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
- 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
Abstract
The health state monitoring device, system and method based on the traditional Chinese medicine theory are used for acquiring facial image data and tongue image data of a monitoring user through a camera; acquiring smell information of a monitoring user through a smell scanner; acquiring sound information of a monitoring user through an electroacoustical instrument; invoking a display module to conduct health questionnaire investigation on a monitoring user through a touch display screen; acquiring pulse wave data of a monitoring user through a pulse diagnosis instrument; invoking a data coding module, and coding data characteristics through a neural network data coding algorithm; performing disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; invoking a result identification module to identify the health state monitoring result through a countermeasure reinforcement learning algorithm; and calling a result evaluation module to evaluate the health state monitoring result according to expert preset rules. The invention realizes the health status monitoring of the user, does not need the whole participation of traditional Chinese medicine personnel, has low cost and ensures that more people can enjoy the traditional Chinese medicine service.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a health state monitoring device, system and method based on a traditional Chinese medicine theory.
Background
The theory of traditional Chinese medicine is systematic rational knowledge of the relationship between human and nature, the vital activity, pathological changes and regulation rules and rules of human body; is the guiding thought and principle of traditional Chinese medicine health care and disease prevention and treatment, and is the centralized expression of unique natural, life, disease and methodology in China. With the development of social economy, people pay more attention to the health status of themselves. Health management is a process and method aiming at preventing and controlling occurrence and development of diseases, reducing medical cost and improving life quality, carrying out health education on individuals and groups, improving self-management consciousness and level, and continuously improving health risk factors related to life style by means of health information acquisition, health detection, health assessment, personalized monitoring management scheme, health intervention and the like.
Health management is the process of comprehensively managing health risk factors of individuals or groups of people. At present, traditional Chinese medicine health preservation and traditional Chinese medicine diagnosis and treatment are popular among people, people need to communicate face to face with medical staff engaged in traditional Chinese medicine when carrying out medical health consultation, for example, the traditional Chinese medicine staff is required to observe the spirit, color, shape, state, tongue picture and the like of a user purposefully so as to detect visceral lesions, for example, the white eyes correspond to heart lung, white eyes if red, heart fire is explained, and capillary inflammation and congestion of the white eyes are caused. The margin of the tongue reflects heart problems, and red tongue indicates heart fire heat, and is required to reduce fire and nourish the heart. The tongue coating reflects the problems of the spleen and stomach, yellow tongue coating, large fire in the spleen and stomach and white tongue coating, which indicates that the spleen and stomach are cold and the stomach is to be nourished. At present, users need to participate in the whole process of traditional Chinese medicine diagnosis and treatment, health state monitoring is carried out by traditional Chinese medicine personnel, so that the cost is high, the number of the personnel capable of receiving traditional Chinese medicine services is limited, and most of the personnel cannot monitor the health state by the traditional Chinese medicine theory.
Disclosure of Invention
The invention aims to provide a health state monitoring device, system and method based on the traditional Chinese medicine theory, which are combined with the traditional Chinese medicine theory of looking and asking, realize the health state monitoring of a user based on a machine learning technology, do not need the whole participation of traditional Chinese medicine personnel, have low cost and enable more people to enjoy the service based on the traditional Chinese medicine theory.
In order to achieve the above purpose, the technical scheme of the invention is as follows: the health state monitoring device based on the traditional Chinese medicine theory comprises a central processing unit, and further comprises a voiceprint recognition module, a voice playing module, an odor acquisition module, a display module, a pulse diagnosis module, an image acquisition module, a light source detection module and a light supplementing module; the voiceprint recognition module establishes a connection relation with the central processing unit, and is configured with an electroacoustic device, and the voiceprint recognition module is used for acquiring sound information of a monitoring user through the electroacoustic device; the voice playing module establishes a connection relation with the central processing unit, is provided with a voice player and is used for playing voice information through the voice player; the odor acquisition module is connected with the central processor, is configured with an odor scanner and is used for acquiring odor information of a monitoring user through the odor scanner; the display module establishes a connection relation with the central processing unit, is provided with a touch display screen, and is used for monitoring health questionnaires by users through the touch display screen, and the display module is also used for feeding back health state data information to the monitoring users; the pulse-taking module establishes a connection relation with the central processing unit, is provided with a pulse-taking instrument and is used for acquiring pulse wave data of a monitoring user through the pulse-taking instrument; the image acquisition module establishes a connection relation with the central processing unit, is provided with a camera and is used for acquiring facial image data and tongue image data of a monitoring user through the camera; the light source detection module is connected with the central processing unit, is provided with a light source detector and is used for acquiring light source information of the shooting environment where the camera is positioned; the light supplementing module establishes a connection relation with the central processing unit, the light supplementing module is provided with a light supplementing lamp, and the light supplementing module is used for supplementing light to a shooting object of the camera through the light supplementing lamp.
The health state monitoring device based on the traditional Chinese medicine theory is characterized in that the central processing unit adopts a Cortex-R series processor of ARM company; the electroacoustical instrument adopts a CRY6125 electroacoustical device; the odor scanner was model AIRSENSE PEN3. The central processing unit, the electroacoustics appearance and the air-gas scanner that this technical scheme adopted belong to prior art. The voiceprint of the voiceprint recognition module is that an electroacoustical instrument is used for displaying the sound wave spectrum carrying speech information, the generation of human language is a complex physiological and physical process between the human language center and the pronunciation organs, and the pronunciation organs used by a person when speaking, namely the tongue, the teeth, the larynx, the lung and the nasal cavity, are greatly different in size and form, so that the voiceprint patterns of any two persons are different. The odor scanning is composed of three functional devices of an odor sampling manipulator, a gas sensor array and a signal processing system, and the main mechanism for identifying the odor is that each sensor in the array has different sensitivity to the detected gas, for example, a first gas can generate high response on one sensor and low response on other sensors, a second gas generates high response sensor is insensitive to the first gas, the response patterns of the whole sensor array to different gases are different, and the odor can be identified according to the response patterns of the sensors based on the differences.
The health state monitoring device based on the traditional Chinese medicine theory further comprises a blood pressure acquisition module, wherein the blood pressure acquisition module is provided with a blood pressure instrument, and the blood pressure acquisition module is used for acquiring and monitoring blood pressure parameters of a user through the blood pressure instrument. The sphygmomanometer is an instrument for measuring blood pressure, and the oscillometric sphygmomanometer can acquire oscillation waves generated in the deflation process and convert the oscillation waves into blood pressure values.
The health state monitoring device based on the traditional Chinese medicine theory, as described above, further comprises a blood glucose collecting module, wherein the blood glucose collecting module is configured with a blood glucose meter, and the blood glucose collecting module is used for collecting and monitoring blood glucose parameters of a user through the blood glucose meter. Examples of the blood glucose meter include a glucose oxidase electrode measurement method and a glucose dehydrogenase electrode measurement method. The glucose oxidase electrode measurement method is a method for measuring blood glucose by measuring the amount of current generated by the reaction of glucose in blood with glucose oxidase in test paper, and most of the mainstream types are glucose oxidase measurement methods. Glucose dehydrogenase electrode measurement measures blood glucose by measuring the amount of current produced by the reaction of glucose in blood with glucose dehydrogenase in test paper.
The invention also provides a health state monitoring system based on the traditional Chinese medicine theory, which comprises the monitoring device, and further comprises a management server, wherein the management server establishes a connection relation with the monitoring device, the management server comprises a questionnaire storage module, a data coding module, a diagnosis and treatment decision module, a result identification module and a result evaluation module, and the questionnaire storage module is used for storing health state measurement questionnaires; the data coding module is used for carrying out data characteristic coding on the acquired monitoring data of the monitoring user through a neural network data coding algorithm; the diagnosis and treatment decision module is used for carrying out disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; the result identification module is used for identifying the health state monitoring result through a countermeasure reinforcement learning algorithm; and the result evaluation module is used for evaluating the health state monitoring result according to expert preset rules.
The invention further provides a health state monitoring method based on the traditional Chinese medicine theory, the monitoring method is realized by the monitoring system by adopting the monitoring device, and the monitoring method comprises the following steps:
an image acquisition module is called to acquire facial image data and tongue image data of a monitoring user through a camera;
calling an odor acquisition module to acquire odor information of a monitoring user through an odor scanner;
calling a voiceprint recognition module to acquire the voice information of the monitoring user through an electroacoustical instrument; invoking a display module to conduct health questionnaire investigation on a monitoring user through a touch display screen;
a pulse diagnosis module is called to acquire pulse wave data of a monitoring user through a pulse diagnosis instrument;
invoking a data encoding module to encode the data characteristics of the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data through a neural network data encoding algorithm;
invoking a diagnosis and treatment decision module to perform disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; invoking a result identification module to identify the health state monitoring result through a countermeasure reinforcement learning algorithm; and calling a result evaluation module to evaluate the health state monitoring result according to expert preset rules.
The health state monitoring method based on the traditional Chinese medicine theory further comprises the step of calling a blood pressure acquisition module to acquire and monitor blood pressure parameters of a user through a blood pressure instrument; and calling a blood glucose acquisition module to acquire and monitor blood glucose parameters of the user through the blood glucose meter.
According to the health state monitoring method based on the traditional Chinese medicine theory, the BP network is adopted in the neural network data encoding algorithm, the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data images are layered into n small blocks, n neurons are input correspondingly, m neurons are input correspondingly to the compressed data, m is smaller than or equal to n, the weight of the network is adjusted in the network learning process through the training algorithm, so that the reconstruction error E= ||X-Z||average value of the training set image is minimum, X is an input layer sample set, and Z is an output layer sample set.
According to the health state monitoring method based on the traditional Chinese medicine theory, the neural network data coding algorithm adopts a self-organizing mapping neural network, and the input layer neuron (x 1 ,x 2 ,…,x n ) In the output layer, m neurons are arranged in a two-dimensional network, where each neuron j receives two types of inputs: input x from input layer neuron i i The weight is w ij Fixed weights from output layer neurons, for each ambient input vector x= (x) 1 ,x 2 ,…,x n ) With a distance d from the input i =f(x,w j ),w j =(w 1j ,w 2j ,…,w nj ) The neuron j that is the smallest is fired.
The health state monitoring method based on the traditional Chinese medicine theory further comprises a result identification module and a result evaluation module which measure the result predicted by the data coding module model through a loss function and a penalty factor; the loss function is a log-log loss function, a square loss function, an exponential loss function, a range loss function, a 0-1 loss function, or an absolute value loss function.
The invention has the following advantages: the traditional Chinese medicine theory of looking at the inquiry is combined, the health state of the user is monitored based on the machine learning technology, the whole participation of Chinese medicine personnel is not needed, the automatic diagnosis and treatment and prescription recommendation combined with the Chinese medicine theory are realized, the effect of combining four Chinese medicine diagnoses and parameters for health monitoring is achieved, the service cost is low, more people can enjoy the service based on the Chinese medicine theory, and the health monitoring is beneficial to human beings.
Drawings
Fig. 1 is a schematic diagram of a health status monitoring device based on the theory of traditional Chinese medicine in an embodiment;
fig. 2 is a schematic diagram of a health status monitoring system based on the theory of traditional Chinese medicine in an embodiment;
FIG. 3 is a flowchart of a health status monitoring method based on the theory of traditional Chinese medicine in an embodiment;
fig. 4 is a schematic diagram of a health status monitoring method based on the theory of traditional Chinese medicine in an embodiment.
Detailed Description
The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1, the health status monitoring device based on the theory of traditional Chinese medicine comprises a central processing unit 1, and further comprises a voiceprint recognition module 2, a voice playing module 3, an odor acquisition module 4, a display module 5, a pulse diagnosis module 6, an image acquisition module 7, a light source detection module 8 and a light supplementing module 9; the voiceprint recognition module 2 establishes a connection relationship with the central processing unit 1, the voiceprint recognition module 2 is configured with an electroacoustical instrument 10, and the voiceprint recognition module 2 is used for acquiring sound information of a monitoring user through the electroacoustical instrument 10; the voice playing module 3 establishes a connection relationship with the central processing unit 1, the voice playing module 3 is configured with a voice player 11, and the voice playing module 3 is used for playing voice information through the voice player 11; the odor acquisition module 4 establishes a connection relationship with the central processor 1, the odor acquisition module 4 is configured with an odor scanner 12, and the odor acquisition module 4 is used for acquiring odor information of a monitoring user through the odor scanner 12; the display module 5 establishes a connection relationship with the central processing unit 1, the display module 5 is configured with a touch display screen 13, the display module 5 is used for monitoring health questionnaires by users through the touch display screen 13, and the display module 5 is also used for feeding back health state data information to the monitoring users; the pulse-taking module 6 establishes a connection relationship with the central processing unit 1, the pulse-taking module 6 is configured with a pulse-taking instrument 14, and the pulse-taking module 6 is used for acquiring pulse wave data of a monitoring user through the pulse-taking instrument 14; the image acquisition module 7 establishes a connection relationship with the central processing unit 1, the image acquisition module 7 is provided with a camera 15, and the image acquisition module 7 is used for acquiring facial image data and tongue image data of a monitoring user through the camera 15; the light source detection module 8 establishes a connection relationship with the central processing unit 1, the light source detection module 8 is configured with a light source detector 16, and the light source detection module 8 is used for acquiring light source information of an imaging environment in which the camera 15 is positioned; the light supplementing module 9 establishes a connection relationship with the central processing unit 1, the light supplementing module 9 is configured with a light supplementing lamp 17, and the light supplementing module 9 is configured to supplement light to a shooting object of the camera 15 through the light supplementing lamp 17.
In one embodiment of the health status monitoring device based on the theory of traditional Chinese medicine, the central processing unit 1 adopts a Cortex-R series processor of ARM company; the electroacoustical instrument 10 adopts a CRY6125 electroacoustical device; the odor scanner 12 is model AIRSENSE PEN3. The central processing unit 1, the electroacoustical instrument 10 and the smell scanner 12 adopted by the technical scheme belong to the prior art. The voiceprint of the voiceprint recognition module 2 is that the electroacoustic device 10 is used for displaying the sound wave spectrum carrying speech information, the generation of human language is a complex physiological and physical process between the human language center and the pronunciation organs, and the pronunciation organs used by people when speaking, namely the tongue, the teeth, the throat, the lungs and the nasal cavity, are greatly different in size and shape, so that the voiceprint patterns of any two people are different. The odor scanning is composed of three functional devices of an odor sampling manipulator, a gas sensor array and a signal processing system, and the main mechanism for identifying the odor is that each sensor in the array has different sensitivity to the detected gas, for example, a first gas can generate high response on one sensor and low response on other sensors, a second gas generates high response sensor is insensitive to the first gas, the response patterns of the whole sensor array to different gases are different, and the odor can be identified according to the response patterns of the sensors based on the differences.
In one embodiment of the health status monitoring device based on the theory of traditional Chinese medicine, the monitoring device further comprises a blood pressure acquisition module 18, wherein the blood pressure acquisition module 18 is configured with a blood pressure meter 19, and the blood pressure acquisition module 18 is used for acquiring and monitoring blood pressure parameters of a user through the blood pressure meter 19. The sphygmomanometer 19 is an instrument for measuring blood pressure, and the oscillometric sphygmomanometer can acquire an oscillation wave generated during deflation and convert the oscillation wave into a blood pressure value.
In one embodiment of the health status monitoring device based on the theory of traditional Chinese medicine, the monitoring device further comprises a blood glucose collecting module 20, wherein the blood glucose collecting module 20 is configured with a blood glucose meter 21, and the blood glucose collecting module 20 is used for collecting and monitoring blood glucose parameters of a user through the blood glucose meter 21. The blood glucose meter 21 is realized by a glucose oxidase electrode measurement method, a glucose dehydrogenase electrode measurement method, or the like. The glucose oxidase electrode measurement method is a method for measuring blood glucose by measuring the amount of current generated by the reaction of glucose in blood with glucose oxidase in test paper, and most of the mainstream types are glucose oxidase measurement methods. Glucose dehydrogenase electrode measurement measures blood glucose by measuring the amount of current produced by the reaction of glucose in blood with glucose dehydrogenase in test paper.
Referring to fig. 2, the invention further provides a health status monitoring system based on the traditional Chinese medicine theory, the monitoring system comprises the monitoring device, the monitoring system further comprises a management server 22, the management server 22 establishes a connection relationship with the monitoring device, the management server 22 comprises a questionnaire storage module 23, a data coding module 24, a diagnosis and treatment decision module 25, a result identification module 26 and a result evaluation module 27, and the questionnaire storage module 23 is used for storing a health status assessment questionnaire; the data encoding module 24 is configured to perform data feature encoding on the obtained monitoring data of the monitoring user through a neural network data encoding algorithm; the diagnosis and treatment decision module 25 is used for performing disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; the result identification module 26 is configured to identify the health status monitoring result by using an countermeasure reinforcement learning algorithm; the result evaluation module 27 is configured to evaluate the health status monitoring result according to an expert preset rule.
Referring to fig. 3 and 4, the present invention further provides a health status monitoring method based on the theory of traditional Chinese medicine, wherein the monitoring method is implemented by the monitoring system using the monitoring device, and the monitoring method includes the following steps:
s1: the image acquisition module 7 is called to acquire facial image data and tongue image data of the monitoring user through the camera 15;
s2: the smell acquisition module 4 is called to acquire smell information of the monitoring user through the smell scanner 12;
s3: calling a voiceprint recognition module 2 to acquire the voice information of the monitoring user through the electroacoustical instrument 10; invoking a display module 5 to conduct health questionnaire investigation on a monitoring user through a touch display screen 13;
s4: invoking pulse diagnosis module 6 to obtain pulse wave data of the monitoring user through pulse diagnosis instrument 14;
s5: invoking a data encoding module 24 to perform data feature encoding on the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data through a neural network data encoding algorithm;
s6: invoking a diagnosis and treatment decision module 25 to perform disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; invoking the result discrimination module 26 to discriminate the health status monitoring result by the challenge reinforcement learning algorithm; the call result evaluation module 27 evaluates the health status monitoring result according to expert preset rules.
In one embodiment of the health status monitoring method based on the theory of traditional Chinese medicine, the monitoring method further comprises the steps of calling a blood pressure acquisition module 18 to acquire and monitor blood pressure parameters of a user through a blood pressure meter 19; the blood glucose collection module 20 is invoked to collect and monitor blood glucose parameters of the user via the blood glucose meter 21.
In one embodiment of the health status monitoring method based on the traditional Chinese medicine theory, the neural network data encoding algorithm adopts a BP network, firstly, the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data images are layered into n small blocks, corresponding to the n neurons which are input, the compressed data corresponds to m neurons of an hidden layer, m is less than or equal to n, the weight of the network is adjusted in the network learning process through the training algorithm, so that the average value of reconstruction errors E= ||X-Z|| of the training set images is minimum, X is an input layer sample set, and Z is an output layer sample set.
In one embodiment of the health status monitoring method based on the theory of traditional Chinese medicine, the neural network data coding algorithm adopts a self-organizing mapping neural network, and inputs layer neurons (x 1 ,x 2 ,…,x n ) In the output layer, m neurons are arranged in a two-dimensional network, where each neuron j receives two types of inputs: input x from input layer neuron i i The weight is w ij Fixed weights from output layer neurons, for each ambient input vector x= (x) 1 ,x 2 ,…,x n ) With a distance d from the input i =f(x,w j ),w j =(w 1j ,w 2j ,…,w nj ) The neuron j that is the smallest is fired.
In one embodiment of the health status monitoring method based on the theory of traditional Chinese medicine, the monitoring method further comprises a result identification module 26 and a result evaluation module 27 for measuring the result predicted by the model of the data encoding module 24 through a loss function and a penalty factor; the loss function is a log-log loss function, a square loss function, an exponential loss function, a range loss function, a 0-1 loss function, or an absolute value loss function.
The invention uses the health status self-evaluating practical questionnaires as the basis of various questionnaires and interfaces of the knowledge base and the sensor, wherein the knowledge base is various Chinese medicine health and diagnosis decision knowledge bases developed by Chinese medical science college of Chinese medical science, and the knowledge of the knowledge base is called through the interfaces to support the early warning and decision of the monitoring device. The sensor comprises a sensor for four diagnosis of traditional Chinese medicine, a camera for tongue diagnosis, a pulse diagnosis instrument for pulse diagnosis and an electroacoustical instrument for diagnosis. The invention combines the traditional Chinese medicine theory of looking at the inquiry, realizes the health status monitoring of the user based on the machine learning technology, does not need the whole participation of Chinese medicine staff, realizes the automatic diagnosis and treatment and prescription recommendation combined with the Chinese medicine theory, achieves the effects of combining four Chinese medicine diagnoses and parameters and carrying out health monitoring, has low service cost, and ensures that more people can enjoy the service based on the Chinese medicine theory and benefit the mankind.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (6)
1. The health state monitoring method based on the traditional Chinese medicine theory comprises a monitoring device, a voice print recognition module (2), a voice playing module (3), an odor acquisition module (4), a display module (5), a pulse diagnosis module (6), an image acquisition module (7), a light source detection module (8) and a light supplementing module (9), wherein the monitoring device comprises a central processing unit (1); the voiceprint recognition module (2) establishes a connection relation with the central processing unit (1), the voiceprint recognition module (2) is provided with an electroacoustical instrument (10), and the voiceprint recognition module (2) is used for acquiring sound information of a monitoring user through the electroacoustical instrument (10); the voice playing module (3) establishes a connection relation with the central processing unit (1), the voice playing module (3) is configured with a voice player (11), and the voice playing module (3) is used for playing voice information through the voice player (11); the odor acquisition module (4) is connected with the central processing unit (1), the odor acquisition module (4) is provided with an odor scanner (12), and the odor acquisition module (4) is used for acquiring odor information of a monitoring user through the odor scanner (12); the display module (5) is connected with the central processing unit (1), the display module (5) is provided with a touch display screen (13), the display module (5) is used for monitoring health questionnaires by users through the touch display screen (13), and the display module (5) is also used for feeding back health state data information to the monitoring users; the pulse-taking module (6) is connected with the central processing unit (1), the pulse-taking module (6) is provided with a pulse-taking instrument (14), and the pulse-taking module (6) is used for acquiring pulse wave data of a monitoring user through the pulse-taking instrument (14); the image acquisition module (7) is connected with the central processing unit (1), the image acquisition module (7) is provided with a camera (15), and the image acquisition module (7) is used for acquiring facial image data and tongue image data of a monitoring user through the camera (15); the light source detection module (8) is connected with the central processing unit (1), the light source detection module (8) is provided with a light source detector (16), and the light source detection module (8) is used for acquiring light source information of a shooting environment where the camera (15) is positioned; the light supplementing module (9) is connected with the central processing unit (1), the light supplementing module (9) is provided with a light supplementing lamp (17), the light supplementing module (9) is used for supplementing light to a shooting object of the camera (15) through the light supplementing lamp (17), the light supplementing module is realized through a monitoring system, the monitoring system further comprises a management server (22), the management server (22) is connected with a monitoring device, the management server (22) comprises a questionnaire storage module (23), a data encoding module (24), a diagnosis and treatment decision module (25), a result identification module (26) and a result evaluation module (27), and the questionnaire storage module (23) is used for storing a health state assessment questionnaire; the data coding module (24) is used for carrying out data feature coding on the acquired monitoring data of the monitoring user through a neural network data coding algorithm; the diagnosis and treatment decision module (25) is used for carrying out disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; the result identification module (26) is used for identifying the health state monitoring result through a countermeasure reinforcement learning algorithm; the result evaluation module (27) is used for evaluating the health state monitoring result according to expert preset rules; the method is characterized in that: the monitoring method comprises the following steps:
an image acquisition module (7) is called to acquire facial image data and tongue image data of a monitoring user through a camera (15);
the odor acquisition module (4) is called to acquire odor information of a monitoring user through the odor scanner (12);
calling a voiceprint recognition module (2) to acquire the sound information of a monitoring user through an electroacoustical instrument (10); invoking a display module (5) to conduct health questionnaire investigation on a monitoring user through a touch display screen (13);
invoking a pulse diagnosis module (6) to acquire pulse wave data of a monitoring user through a pulse diagnosis instrument (14);
invoking a data encoding module (24), and performing data feature encoding on the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data through a neural network data encoding algorithm;
invoking a diagnosis and treatment decision module (25) to perform disease diagnosis and prescription recommendation on the monitoring user according to the traditional Chinese medicine health and diagnosis and treatment decision knowledge base; invoking a result identification module (26) to identify the health state monitoring result through a countermeasure reinforcement learning algorithm; a calling result evaluation module (27) evaluates the health state monitoring result according to expert preset rules;
the neural network data coding algorithm adopts a BP network, firstly, the obtained facial image data, tongue image data, smell information, sound information, health questionnaire investigation information and pulse wave data images are layered into n small blocks, corresponding to n neurons which are input, the compressed data corresponds to m neurons of an hidden layer, m is smaller than or equal to n, the weight of the network is adjusted in the network learning process through a training algorithm, so that the reconstruction error E= |X-Z|average value of the training set image is minimum, X is an input layer sample set, and Z is an output layer sample set;
the neural network data coding algorithm adopts a self-organizing mapping neural network, and inputs layer neurons (x) 1 ,x 2 ,…,x n ) In the output layer, m neurons are arranged in a two-dimensional network, where each neuron j receives two types of inputs: input x from input layer neuron i i The weight is w ij Fixed weights from output layer neurons, for each ambient input vector x= (x) 1 ,x 2 ,…,x n ) With a distance d from the input i =f(x,w j ),w j =(w 1j ,w 2j ,…,w nj ) The neuron j that is the smallest is fired.
2. The health status monitoring method based on the theory of traditional Chinese medicine according to claim 1, wherein: the monitoring method further comprises the steps of calling a blood pressure acquisition module (18) to acquire blood pressure parameters of a monitoring user through a blood pressure instrument (19); and calling a blood glucose acquisition module (20) to acquire and monitor blood glucose parameters of a user through a blood glucose meter (21).
3. The health status monitoring method based on the theory of traditional Chinese medicine according to claim 1, wherein: the monitoring method further comprises the steps that a result identification module (26) and a result evaluation module (27) measure the result predicted by the data coding module (24) through a loss function and a penalty factor; the loss function is a log-log loss function, a square loss function, an exponential loss function, a range loss function, a 0-1 loss function, or an absolute value loss function.
4. The health status monitoring method based on the theory of traditional Chinese medicine according to claim 1, wherein: the central processing unit (1) adopts a Cortex-R series processor of ARM company; the electroacoustical instrument (10) adopts a CRY6125 electroacoustical device; the odor scanner (12) is model AIRSENSE PEN.
5. The health status monitoring method based on the theory of traditional Chinese medicine according to claim 1, wherein: the monitoring device further comprises a blood pressure acquisition module (18), wherein the blood pressure acquisition module (18) is provided with a blood pressure instrument (19), and the blood pressure acquisition module (18) is used for acquiring blood pressure parameters of a monitoring user through the blood pressure instrument (19).
6. The health status monitoring method based on the theory of traditional Chinese medicine according to claim 1, wherein: the monitoring device further comprises a blood glucose collection module (20), wherein the blood glucose collection module (20) is provided with a blood glucose meter (21), and the blood glucose collection module (20) is used for collecting blood glucose parameters of a monitoring user through the blood glucose meter (21).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810747015.2A CN108597621B (en) | 2018-07-09 | 2018-07-09 | Health state monitoring device, system and method based on traditional Chinese medicine theory |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810747015.2A CN108597621B (en) | 2018-07-09 | 2018-07-09 | Health state monitoring device, system and method based on traditional Chinese medicine theory |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108597621A CN108597621A (en) | 2018-09-28 |
CN108597621B true CN108597621B (en) | 2024-03-22 |
Family
ID=63617821
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810747015.2A Active CN108597621B (en) | 2018-07-09 | 2018-07-09 | Health state monitoring device, system and method based on traditional Chinese medicine theory |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108597621B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109346179B (en) * | 2018-12-10 | 2022-08-26 | 山东管理学院 | Coronary heart disease interventional postoperative recurrence prediction model and modeling method and device thereof |
TWI718504B (en) | 2019-03-22 | 2021-02-11 | 台灣奈米碳素股份有限公司 | Gas sensing tattoo sticker |
CN110558966A (en) * | 2019-08-12 | 2019-12-13 | 平安科技(深圳)有限公司 | Pulse detection device |
CN110772235A (en) * | 2019-08-22 | 2020-02-11 | 天津森宇科技股份有限公司 | Traditional Chinese medicine intelligent health analysis system based on cloud computing and mobile platform |
CN111048202A (en) * | 2019-12-12 | 2020-04-21 | 苏州杰胜通信息技术有限公司 | Intelligent traditional Chinese medicine diagnosis system and method thereof |
CN111753543B (en) * | 2020-06-24 | 2024-03-12 | 北京百度网讯科技有限公司 | Medicine recommendation method, device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200120A (en) * | 2014-09-18 | 2014-12-10 | 上海中医药大学 | System and method for health status monitoring based on traditional Chinese medicine diagnosis information |
CN105528526A (en) * | 2016-01-15 | 2016-04-27 | 胡广芹 | Traditional Chinese medicine inheritance and big data mining-based dynamic health management system for life cycle |
CN107887024A (en) * | 2017-12-14 | 2018-04-06 | 华子昂 | Intelligent diagnosis system and traditional Chinese medical science robot based on traditional Chinese medical science robot |
CN208422436U (en) * | 2018-07-09 | 2019-01-22 | 中国中医科学院中医药信息研究所 | Health status monitoring device and system based on theory of traditional Chinese medical science |
-
2018
- 2018-07-09 CN CN201810747015.2A patent/CN108597621B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200120A (en) * | 2014-09-18 | 2014-12-10 | 上海中医药大学 | System and method for health status monitoring based on traditional Chinese medicine diagnosis information |
CN105528526A (en) * | 2016-01-15 | 2016-04-27 | 胡广芹 | Traditional Chinese medicine inheritance and big data mining-based dynamic health management system for life cycle |
CN107887024A (en) * | 2017-12-14 | 2018-04-06 | 华子昂 | Intelligent diagnosis system and traditional Chinese medical science robot based on traditional Chinese medical science robot |
CN208422436U (en) * | 2018-07-09 | 2019-01-22 | 中国中医科学院中医药信息研究所 | Health status monitoring device and system based on theory of traditional Chinese medical science |
Also Published As
Publication number | Publication date |
---|---|
CN108597621A (en) | 2018-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108597621B (en) | Health state monitoring device, system and method based on traditional Chinese medicine theory | |
CN110507335B (en) | Multi-mode information based criminal psychological health state assessment method and system | |
US10219736B2 (en) | Methods and arrangements concerning dermatology | |
CN105393252B (en) | Physiological data collection and analysis | |
US11904224B2 (en) | System and method for client-side physiological condition estimations based on a video of an individual | |
JP6272308B2 (en) | Sound-based spirometry device, system and method | |
WO2019229543A1 (en) | Managing respiratory conditions based on sounds of the respiratory system | |
US20170007126A1 (en) | System for conducting a remote physical examination | |
CN110584601B (en) | Old man cognitive function monitoring and evaluation system | |
US20190013092A1 (en) | System and method for facilitating determination of a course of action for an individual | |
CN109313931A (en) | For providing system, the method and computer program product of feedback related with medical inspection | |
CN109124655A (en) | State of mind analysis method, device, equipment, computer media and multifunctional chair | |
EP2874539A1 (en) | A method and system for determining the state of a person | |
CN208422436U (en) | Health status monitoring device and system based on theory of traditional Chinese medical science | |
CN115517681A (en) | Method and system for monitoring mood fluctuation and evaluating emotional disorder state of MD (MD) patient | |
CN116807476A (en) | Multi-mode psychological health assessment system and method based on interface type emotion interaction | |
JP2003079602A (en) | Mind and body diagnosing system | |
CN111640496A (en) | Traditional Chinese medicine remote consultation system based on artificial intelligence | |
Pessoa et al. | BRACETS: Bimodal repository of auscultation coupled with electrical impedance thoracic signals | |
Vatanparvar et al. | Speechspiro: Lung function assessment from speech pattern as an alternative to spirometry for mobile health tracking | |
CN113647973A (en) | Portable nondestructive testing device based on convolutional neural network | |
CN113040773A (en) | Data acquisition and processing method | |
Su et al. | An Automatic Sleep Arousal Detection Method by Enhancing U-Net with Spatial-channel Attention | |
WO2023150575A2 (en) | Cyber-physical system to enhance usability and quality of telehealth consultation | |
US11882237B1 (en) | Apparatus and methods for monitoring human trustworthiness |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |