Nothing Special   »   [go: up one dir, main page]

CN110047564A - A kind of method and device embodying the accurate constitution conditioning of individuation - Google Patents

A kind of method and device embodying the accurate constitution conditioning of individuation Download PDF

Info

Publication number
CN110047564A
CN110047564A CN201910369971.6A CN201910369971A CN110047564A CN 110047564 A CN110047564 A CN 110047564A CN 201910369971 A CN201910369971 A CN 201910369971A CN 110047564 A CN110047564 A CN 110047564A
Authority
CN
China
Prior art keywords
target individual
information
individual
target
type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910369971.6A
Other languages
Chinese (zh)
Inventor
华伟
顾清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201910369971.6A priority Critical patent/CN110047564A/en
Publication of CN110047564A publication Critical patent/CN110047564A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other 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
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • 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
    • G16H20/90—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to alternative medicines, e.g. homeopathy or oriental medicines

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention discloses a kind of method and devices of the accurate constitution conditioning of embodiment individuation, it is related to data computing technique field, this method comprises: generating the first questionnaire according to the personal information of the target individual of acquisition, so that target individual generates the answer of the first questionnaire, and the answer of the first questionnaire according to acquisition, determine initial crowd's type belonging to target individual；Initial crowd's type according to belonging to target individual, determines the physical condition information of target individual；According to the physical condition information of target individual, target group's type belonging to target individual is determined；Target group's type according to belonging to target individual determines default constitution coordinating program corresponding with target group's type, and constitution coordinating program is sent to target individual.A kind of method and device embodying the accurate constitution conditioning of individuation provided by the present application, can be directed to everyone concrete condition, and the accurately crowd that carries out divides, and then can carry out personalized constitution conditioning.

Description

A kind of method and device embodying the accurate constitution conditioning of individuation
Technical field
This application involves data computing technique fields, more particularly, to a kind of method of the accurate constitution conditioning of embodiment individuation And device.
Background technique
Since everyone is unique individual, although existing system Opsonizing method is according to nine kinds of constitution classes of Chinese medicine Crowd has been carried out rough classification by type, and the somatotypes according to every kind of crowd gives constitution conditioning and maintenance.
However due to being limited by technological means, existing constitution Opsonizing method does not account for everyone medical information It is not careful enough to the judgement of crowd's type, not accurate enough with daily routines information, therefore, it is impossible to be directed to everyone specific feelings Condition, the accurately crowd that carries out divide, and then can not carry out personalized constitution conditioning.
Summary of the invention
In view of this, a kind of method and device for being designed to provide accurate constitution conditioning of embodiment individuation of the application, It can be directed to everyone concrete condition, the accurately crowd that carries out divides, and then can carry out personalized constitution conditioning.
In a first aspect, the embodiment of the present application provides a kind of method of accurate constitution conditioning of embodiment individuation, comprising:
The first questionnaire is generated according to the personal information of the target individual of acquisition, so that the target individual generates the first questionnaire Answer；
According to the answer of the first questionnaire of acquisition, initial crowd's type belonging to the target individual is determined；
Initial crowd's type according to belonging to the target individual generates the second questionnaire, so that the target individual generates The answer of second questionnaire；
According to the answer of the second questionnaire of acquisition, the medical physical condition information of the target individual is determined；
According to the daily routines information of the medical physical condition information of the target individual and the target individual of acquisition, Determine target group's type belonging to the target individual；
According to target group's type belonging to the target individual, default body corresponding with target group's type is determined Matter coordinating program, and the constitution coordinating program is sent to the target individual.
A kind of possible embodiment, wherein
The physical condition information according to the target individual, determines target group's type belonging to the target individual Determine target group's type of the target individual, comprising:
According to the physical condition information of each individual of sample of acquisition, the daily work of physical condition information of individual of sample is calculated The standard deviation of dynamic information；
According to the physical condition information daily routines information of the target individual, the physical condition of the target individual is determined Irrelevance between information daily routines information and the standard deviation；
According to the medical information of the target individual and the irrelevance, target group described in the target individual is determined Type.
A kind of possible embodiment, wherein crowd's type initial according to belonging to the target individual determines institute The physical condition information of target individual is stated, can be realized using following at least one method:
It obtains the answer of the second questionnaire generated according to initial crowd's type, obtain the daily work of the target individual Dynamic information, the medical information for obtaining the target individual and the history constitution coordinating program for obtaining the target individual.
A kind of possible embodiment, wherein in the physical condition information for obtaining the target individual including described in acquisition In the case where the daily routines information of target individual, the daily routines information includes human body attitude vector.
A kind of possible embodiment, wherein the method also includes:
Obtain the daily routines information of individual of sample；
Obtain the critical movements posture information in the daily routines information of individual of sample；Wherein, the critical movements posture Information is to meet the daily life information of preset condition；
Third questionnaire is generated, so that the individual of sample generates the answer of third questionnaire；
The third questionnaire of daily routines information, critical movements posture information and acquisition based on the individual of sample is answered Case is trained listener clustering model, obtains target group's disaggregated model；
Using target group's disaggregated model, according to the medical information of the target individual and the target of acquisition The critical movements posture information of body, determines target group's type belonging to the target individual.
A kind of possible embodiment, wherein before the training listener clustering model, further includes:
The daily routines information is filtered；
The mould for calculating each daily routines information, obtains multiple modulus evidences；
Remove noise of the multiple modulus in；
By the modulus according to decomposing multiple frequency ranges, and according to the frequency of the modulus evidence to the modulus according in multiple frequencies Section is sampled.
A kind of possible embodiment, wherein the daily routines information includes the direction attitude vectors of multiple directions；
Critical movements posture information in the daily routines information for obtaining individual of sample, specifically includes:
Respectively for the direction attitude vectors in each direction in daily routines information, each direction attitude vectors are calculated Mould obtains the modulus evidence of each direction attitude vectors；
It is bent according to the corresponding direction posture of each direction attitude vectors is drawn according to the modulus of each direction attitude vectors Line obtains critical movements posture according to the wave crest point and/or trough point of the corresponding direction posture curve in each direction Information.
A kind of possible embodiment, wherein it is described to obtain the critical movements posture information for meeting preset condition, also wrap It includes:
According to the trough point of the direction posture curve of vertical direction and/or time, it is aligned the direction appearance in each direction State curve；
From the direction posture curve after the alignment in each direction, frequency domain character data are extracted；
According to the wave crest point and/or trough point of the corresponding direction posture curve in each direction, each side is extracted To the direction posture curve in temporal signatures data；
According to the frequency domain character data and the temporal signatures data, critical movements posture information is determined.
It is described that listener clustering model is trained in a kind of possible embodiment, target group's disaggregated model is obtained, Include:
By the daily routines information of each individual of sample and critical movements posture information input listener clustering model, obtain every Crowd's type of a individual of sample；
According to the answer of the third questionnaire of acquisition and crowd's type of each individual of sample, epicycle listener clustering is determined The penalty values of model；
When the penalty values of calculating are greater than preset loss threshold value, the model parameter of the listener clustering model is adjusted, and It is described by the daily routines information of each individual of sample and critical movements posture information input listener clustering model to return to execution, directly Penalty values to calculating are less than preset loss threshold value；
When the penalty values of calculating are less than preset loss threshold value, the listener clustering model that last wheel iteration obtains is made For target group's disaggregated model.
Second aspect, the embodiment of the present application also provide a kind of device of accurate constitution conditioning of embodiment individuation, comprising:
Questionnaire information obtains module, and the personal information for the target individual according to acquisition generates the first questionnaire, so that institute The answer that target individual generates the first questionnaire is stated, is also used to obtain the answer of the first questionnaire；
Preliminary classification module determines initial belonging to the target individual for the answer according to the first questionnaire of acquisition Crowd's type；
Physical condition information determination module, for the initial crowd type according to belonging to the target individual, determine described in The physical condition information of target individual；
Listener clustering module determines belonging to the target individual for the physical condition information according to the target individual Target group's type；
Scheme determining module, for target group's type according to belonging to the target individual, the determining and target person The corresponding default constitution coordinating program of realm type, and the constitution coordinating program is sent to the target individual.
The third aspect, the embodiment of the present application also provide a kind of electronic equipment, comprising: processor, memory and bus, it is described Memory is stored with the executable machine readable instructions of the processor, when electronic equipment operation, the processor with it is described By bus communication between memory, the machine readable instructions executed when being executed by the processor it is above-mentioned in a first aspect, or Step in any possible embodiment of first aspect.
Fourth aspect, the embodiment of the present application also provide a kind of computer readable storage medium, the computer-readable storage medium Computer program is stored in matter, which executes above-mentioned in a first aspect, or first aspect when being run by processor Step in any possible embodiment.
A kind of method and device embodying the accurate constitution conditioning of individuation provided by the embodiments of the present application, for each target The physical condition information of individual, it is determined that target group's type described in target individual, so that it is determined that with target group's type pair The default constitution coordinating program answered, during carrying out listener clustering, the information of consideration is more comprehensive, so as to for every Personal concrete condition, the accurately crowd that carries out divide, and then can carry out personalized constitution conditioning.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of process for the method for embodying the accurate constitution conditioning of individuation provided by the embodiment of the present application Figure；
Fig. 2 shows the processes that another kind provided by the embodiment of the present application embodies the method for the accurate constitution conditioning of individuation Figure；
The structure that Fig. 3 shows the device that a kind of accurate constitution of embodiment individuation improves provided by the embodiment of the present application is shown It is intended to；
Fig. 4 shows the structural schematic diagram of a kind of electronic equipment provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work There are other embodiments, shall fall in the protection scope of this application.
It is accurate to a kind of embodiment individuation disclosed in the embodiment of the present application first for convenient for understanding the present embodiment The method of constitution conditioning describes in detail.
Embodiment one
The method provided by the embodiments of the present application for embodying the accurate constitution conditioning of individuation can be used for any crowd's type System conditioning is carried out, for example, providing system coordinating program to the crowd for needing traditional Chinese medicine to improve using the thinking of Chinese medical discrimination.
Chinese medicine passes through more than 2300 years Experiences, summarizes the syndrome development law and therapy system of various diseases, shape At unique mode of thinking and technology." diagnosis and treatment " is the basic principle of TCM knowledge disease and treatment disease, is traditional Chinese medicine One kind to disease special research and processing method, i.e., be divided into different constitutions for crowd, illness is divided into different disease types and gives Targetedly solve treatment and rehabilitation coordinating program.With the development of artificial intelligence and user's Portrait brand technology, especially artificial mind Development through network is drawn a portrait so that forming the user based on individual and population characteristic, to be formed for each target individual The conditioning model in " thousand people, thousand face " is possibly realized.The embodiment of the present application can be according to the own situation and body of each target individual Function feedback, science accurately customize corresponding health management scheme, provide Appropriate dietary guide plan, push health-preserving food product, And according to regular physique assessment and continuous feedback modifiers body Model.
As shown in Figure 1, the method for the accurate constitution conditioning of embodiment individuation that the embodiment of the present application one provides, comprising:
S101: generating the first questionnaire according to the personal information of the target individual of acquisition, so that the target individual generates the The answer of one questionnaire, and the answer of the first questionnaire according to acquisition determine initial crowd's type belonging to the target individual.
Here, the personal information of target individual, comprising: gender, age, height, weight, family's medical history etc..According to target The personal information of individual generates the first questionnaire, and here, the first questionnaire can be shown on human-computer interaction interface, so that the mesh Mark individual generates the answer of the first questionnaire.And the answer of the first questionnaire according to acquisition, it determines belonging to the target individual just Beginning crowd's type.
S102: initial crowd's type according to belonging to the target individual determines the physical condition letter of the target individual Breath.
Specifically, crowd's type initial according to belonging to the target individual, determines the body of the target individual Status information can be realized using following at least one method:
It obtains the answer of the second questionnaire generated according to initial crowd's type, obtain the daily work of the target individual Dynamic information, the medical information for obtaining the target individual and the history constitution coordinating program for obtaining the target individual.
If determining the mesh by the way of the answer for obtaining the second questionnaire generated according to initial crowd's type The physical condition information of individual is marked, can be realized using following step:
Step 1, initial crowd's type according to belonging to the target individual generate the second questionnaire, so that the target Body generates the answer of the second questionnaire.
Step 2, the answer according to the second questionnaire of acquisition, determine the medical information of the target individual.
Here, the medical information of target individual includes: the diet of target individual, and target individual is now ongoing External application coordinating program, such as massage, moxa-moxibustion, cupping etc., target individual ongoing drug coordinating program etc. now.
By the way of the daily routines information for obtaining the target individual, the physical condition of the target individual is determined In the case where information, the daily routines information of target individual includes human body attitude vector.Specifically for example, for needing Chinese medicine The crowd of conditioning is learned when classifying, the human body attitude vector include vector acceleration in human motion and angular speed to Amount.In the specific implementation, intelligent acquisition equipment can be used, acquire the daily routines information of target individual.It can be used for example Intelligent bracelet, smartwatch or intelligent shoe acquire the daily routines information of target individual.Also, in the human body attitude vector May include the direction attitude vectors of multiple directions, specifically, including front and rear, left and right, vertical six direction direction posture to Amount, respectively corresponds the x-axis in three-dimensional relationship, y-axis and z-axis.And it is possible to obtain multiple directions using intelligent acquisition equipment Direction attitude vectors, including the vector acceleration of six direction and the angular velocity vector of six direction can be obtained.
In addition to this it is possible to obtain the medical information of the target individual or obtain the history body of the target individual Matter coordinating program is having specifically, the medical information of target individual includes the medical history etc. of the various acute and chronic diseases of target individual When body is implemented, it can be obtained using the modes such as network case or input entity case.The history constitution conditioning side of target individual Case includes that the default constitution coordinating program corresponding with target group's type belonging to the target individual that history determines may be used also To include, application feedback of history constitution coordinating program etc..
Here, crowd's type initial according to belonging to the target individual, determines the body shape of the target individual State information, can be using answer, the acquisition target individual for obtaining the second questionnaire generated according to initial crowd's type Daily routines information, obtain the medical information of the target individual and obtain the history constitution coordinating program of the target individual In any method realize, can also be using any accomplished in many ways in the above method, can be using whole methods It realizes.
S103: according to the physical condition information of the target individual, target person realm belonging to the target individual is determined Type.
Here, target group's type of the determination target individual, specifically includes:
According to the physical condition information of each individual of sample of acquisition, the standard of the physical condition information of individual of sample is calculated Difference；According to the physical condition information of the target individual, the physical condition information and the standard deviation of the target individual are determined Between irrelevance；According to the irrelevance, target group's type described in the target individual is determined.
Specifically, determining the target individual by the way of the daily routines information for obtaining the target individual In the case where physical condition information, the method also includes:
Obtain the daily routines information of individual of sample；Obtain the critical movements posture in the daily routines information of individual of sample Information；Wherein, the critical movements posture information is to meet the daily life information of preset condition；Third questionnaire is generated, so that The individual of sample generates the answer of third questionnaire；Daily routines information, critical movements posture letter based on the individual of sample The answer of breath and the third questionnaire obtained, is trained listener clustering model, obtains target group's disaggregated model；Using institute Target group's disaggregated model is stated, according to the critical movements body of the medical information of the target individual and the target individual of acquisition State information determines target group's type belonging to the target individual.
Here, before the training listener clustering model, further includes:
The daily routines information is filtered；The mould for calculating everyone the daily routines information, obtains multiple moulds Data；Remove noise of the multiple modulus in；The modulus evidence is decomposed into multiple frequency ranges, and according to the modulus evidence Frequency is sampled the modulus according in multiple frequency ranges.
Here, the daily routines information includes the direction attitude vectors of multiple directions, specifically, including front and rear, left and right, The direction attitude vectors of vertical six direction, respectively correspond the x-axis in three-dimensional relationship, y-axis and z-axis；
Critical movements posture information in the daily routines information for obtaining individual of sample, specifically includes:
Respectively for the direction attitude vectors in each direction in daily routines information, each direction attitude vectors are calculated Mould obtains the modulus evidence of each direction attitude vectors；
It is bent according to the corresponding direction posture of each direction attitude vectors is drawn according to the modulus of each direction attitude vectors Line obtains critical movements posture according to the wave crest point and/or trough point of the corresponding direction posture curve in each direction Information.
It is here, described to obtain the critical movements posture information for meeting preset condition, further includes:
According to the trough point of the direction posture curve of vertical direction and/or time, it is aligned the direction appearance in each direction State curve, specifically, can trough point according to the direction posture curve in above-mentioned z-axis direction and/or time, be aligned each direction The direction posture curve；
From the direction posture curve after the alignment in each direction, frequency domain character data are extracted；
According to the wave crest point and/or trough point of the corresponding direction posture curve in each direction, each side is extracted To the direction posture curve in temporal signatures data；
According to the frequency domain character data and the temporal signatures data, critical movements posture information is determined.
And listener clustering model is trained using following step, obtains target group's disaggregated model:
By the daily routines information of each individual of sample and critical movements posture information input listener clustering model, obtain every Crowd's type of a individual of sample；
According to the answer of the third questionnaire of acquisition and crowd's type of each individual of sample, epicycle listener clustering is determined The penalty values of model；
When the penalty values of calculating are greater than preset loss threshold value, the model parameter of the listener clustering model is adjusted, and It is described by the daily routines information of each individual of sample and critical movements posture information input listener clustering model to return to execution, directly Penalty values to calculating are less than preset loss threshold value；
When the penalty values of calculating are less than preset loss threshold value, the listener clustering model that last wheel iteration obtains is made For target group's disaggregated model.
S104: according to target group's type belonging to the target individual, determination is corresponding with target group's type Default constitution coordinating program, and the constitution coordinating program is sent to the target individual.
Here, presetting constitution coordinating program may include: Meal regulation suggestion, the Chinese medicines such as massage, cupping, moxa-moxibustion, Chinese medicine Conditioning is suggested, or may include the medical treatment warning etc. for reminding target individual to see a doctor in time.
Embodiment two
For the ease of the understanding to the embodiment of the present application, to need the crowd of traditional Chinese medicine conditioning as target individual, with intelligence Energy shoes illustrate to the specific implementation process of the embodiment of the present application two as acquisition hardware.
As shown in Fig. 2, the disclosed method for embodying the accurate constitution conditioning of individuation of the embodiment of the present application two, comprising:
S201: generating the first questionnaire according to the personal information of the target individual of acquisition, so that the target individual generates the The answer of one questionnaire.
Here, the personal information of target individual, comprising: gender, age, height, weight, family's medical history etc..According to target The personal information of individual generates the first questionnaire, and here, the first questionnaire can be shown on human-computer interaction interface, so that the mesh Mark individual generates the answer of the first questionnaire.
Specifically for example, when for classifying to the crowd for needing traditional Chinese medicine to improve, believed according to the individual of target individual Breath is analyzed, and according to the dialectical theory of traditional Chinese medicine, crowd's type that the target individual obtained substantially belongs to knows target individual Corresponding crowd's type is easiest to the sub-health state occurred, to generate the first file according to the sub-health state.For example, If it is strong to determine that the corresponding crowd's type of target individual is relatively easy to generation obesity, constipation etc. according to the dialectical theory of traditional Chinese medicine Kang Wenti then generates the query message list in relation to fat or constipation.Specifically, to describe the problem convenience, by taking constipation as an example: Traditional Chinese medical science field, Qi deficiency physique crowd's constipation are usually expressed as ambassador and do not do not firmly, though there is awareness of defecation, difficult defecation is firmly exerted and earned Then sweating shortness of breath, makes rear out of strength, and colourless mind is tired, the tired lazy speech of limb, pale tongue with white fur, weak pulse etc..Therefore, according to the individual of target individual Information is analyzed, and when determining that the corresponding crowd's type of target individual is relatively easy to lead to the problem of constipation, generating includes stool shape State, whether difficult defecation, complexion state, tongue fur state the problems such as the first questionnaire first asked so that the target individual generates The answer of volume.
S202: according to the answer of the first questionnaire of acquisition, initial crowd's type belonging to the target individual is determined.
Specifically for example, when for classifying to the crowd for needing traditional Chinese medicine to improve, according to the first questionnaire of acquisition Answer determines initial crowd's type belonging to the target individual according to the dialectical theory of traditional Chinese medicine.Specifically, to illustrate to ask Topic is convenient, by taking the first questionnaire provided in step S201 as an example, according to target individual for include stool state, whether defecation is tired The answer of the first questionnaire of the problems such as hardly possible, complexion state, tongue fur state determines whether the target individual is Qi deficiency physique people Group.Certainly, it is merely given as a kind of embodiment here, when actual implementation, the first questionnaire can be further enriched, according to traditional Chinese medicine Dialectical theory determines initial crowd's type belonging to the target individual by the answer of the first questionnaire of acquisition.
S203: initial crowd's type according to belonging to the target individual generates the second questionnaire, so that the target individual Generate the answer of the second questionnaire.
Specifically for example, when for classifying to the crowd for needing traditional Chinese medicine to improve, according to the first questionnaire of acquisition Answer, initial crowd's type according to belonging to target individual obtain target individual common chronic disease situation and inferior health Situation generates the second questionnaire.For example, if initial crowd's type belonging to target individual is susceptible to suffer from diabetes, in the second questionnaire The problem of may include related glycemic index；If initial crowd's type belonging to target individual is susceptible to suffer from hypertension, asked second The problem of may include related blood pressure index in volume etc..
S204: according to the answer of the second questionnaire of acquisition, the medical information of the target individual is determined.
Here, the medical information of target individual includes: the diet of target individual, and target individual is now ongoing External application coordinating program, such as massage, moxa-moxibustion, cupping etc., target individual ongoing drug coordinating program now, target individual Glycemic index, the blood pressure index etc. of target individual.
S205: the daily routines information of the target individual is obtained.
For the embodiment of the present application is using intelligent shoe as acquisition hardware, the acquisition of the daily routines information of target individual is sketched Process.
Multiple sensors that intelligent shoe usually passes through vola obtain the daily routines information of target individual, here, target The daily routines information of body includes human body attitude vector.Specifically, such as when using intelligent shoe as acquisition hardware, human body appearance State vector includes: vector acceleration and angular velocity vector in human motion.Wherein, acceleration biography can be used in vector acceleration Sensor obtains；Angular-rate sensor, such as gyroscope can be used in angular velocity vector, obtains.
For example, the daily routines information of target individual, may include the human body attitude vector of six direction, six direction Human body attitude vector has respectively corresponded the human body attitude vector of x-axis, y-axis and z-axis in three-dimensional space.In the specific implementation, three-dimensional X-axis in space has corresponded to the front-rear direction in target individual direction of advance, before the y-axis in three-dimensional space has corresponded to target individual Into the left and right directions on direction, the z-axis in three-dimensional space has corresponded to target individual direction perpendicular to the ground.The people of six direction It is perpendicular to the ground that body attitude vectors have respectively corresponded front-rear direction in target individual direction of advance, left and right directions and target individual The human body attitude vector in direction.
Since using intelligent shoe as acquisition hardware, mainly the cadence of acquisition target individual and gait information are as target The daily routines information of body, generally in 110 steps/minute, i.e. 1.8Hz, frequency when people runs does not exceed the frequency of people's walking 5Hz, it is therefore possible to use the sample frequency of 70-500Hz samples the sensing data on acquisition hardware, thus adopting The collection accuracy of data, the collecting efficiency of acquisition hardware, energy consumption of acquisition hardware etc. reach best counterbalance effect.
Since using intelligent shoe as acquisition hardware, mainly the cadence of acquisition target individual and gait information are as target The daily routines information of body, and cadence and gait information have apparent regularity.For example, target individual is in horizontal movement, Cyclically-varying can be presented in vertical and two acceleration that advance.In the movement that foot is received in walking, due to center of gravity single foot touching upwards Ground, vertical direction acceleration are continued later forward, decentralization bipod bottoms out, and acceleration is opposite in positive increased trend. Horizontal acceleration reduces when receiving foot, the increase when taking a step.
Vector acceleration is suitable for the differentiation that direction explicitly moves, it can be determined that target individual is carrying out on foot also It is running, goes up a slope or go downstairs.But vector acceleration can not carry out fall detection to target user, period of motion link is examined Survey, splayfoot differentiation etc., this is to need to differentiate using angular velocity vector.Therefore, human body attitude vector also needs to include angle speed Spend vector.
Also, the vector acceleration in human motion includes: the vector acceleration of six direction, has respectively corresponded target The vector acceleration of front-rear direction, left and right directions and target individual direction perpendicular to the ground in body direction of advance.Human motion In angular velocity vector include: six direction angular velocity vector, respectively corresponded the front and back in target individual direction of advance To, the angular velocity vector of left and right directions and target individual direction perpendicular to the ground.
S206: the daily routines information of the target individual is pre-processed.
Since the data volume of the daily routines information of target individual is very big, using intelligent shoe as acquisition hardware for, intelligence Shoes acquire daily routines information of the plantar pressure data as target individual by the sensor of sole, it is assumed that sample rate is In the case where 100Hz, 3000 sensors are usually arranged in each vola, that is, acquire vola pressure of 3000 points on six direction Force data, thus it is interior every second, the original sampling data amount of each target individual is 3,600,000, in the field of data mining, That is for the dimension of initial data more than 3,600,000 dimensions, this can bring huge operand to subsequent data processing.Therefore in order to Operand and computational complexity are reduced, the daily routines information to target individual is needed to pre-process.To the day of target individual It includes: the noise reduced in daily routines data that normal activity data, which carries out pretreated main purpose,；Reduce original daily work The dimension of dynamic data；Original daily routines data are sampled.To lower group of participants's disaggregated model calculating process The calculation amount of daily routines data reduces the computational complexity of human body disaggregated model.
The daily routines information of target individual is filtered, high-pass filter and low-pass filter pair can be used for example The daily routines information progress that the daily routines information of target individual is filtered, low-pass filter can be used to target individual It filters or is filtered using daily routines information of the bandpass filter to target individual.
For using intelligent shoe as acquisition hardware, process that intelligent shoe is acquired the daily routines information of target individual In, the electromagnetic interference in circuit is main signal interference source, and since electromagnetic interference is high-frequency noise, and human motion is mainly Low frequency signal within 50Hz, therefore, it is possible to use low-pass filter filters out the electromagnetic interference noise of high frequency, for example, can be with Low-pass filter is realized using Wavelet Transform Threshold method, to filter out the electromagnetic interference noise of high frequency.
Due to, when acquisition hardware is acquired the horizontal movement of target individual, as shown in figure 4, obtained acceleration to Amount and a time substantially sine curve.It therefore, can be into one when the daily routines information to target individual is filtered Step considers the cadence of target individual, that is to say, that the time interval of adjacent two step should at least be greater than continuous two step of target individual Between time difference, usually with the time difference between continuous two step as unit of the second to describe target individual.Combining target individual Cadence carry out filter high frequency noise, can accuracy, hardware efficiency, in terms of obtain best counterbalance effect.
Similarly, the angular velocity vector that acquisition hardware obtains is also required to filter out high-frequency noise by filtering.
After filtering out high-frequency noise, the mould of each daily routines information is calculated separately, multiple modulus evidences are obtained, to reduce The dimension of human body attitude vector.Here, with ax, ay, az characterize respectively x-axis, y-axis, z-axis six direction vector acceleration, use Wx, wy, wz characterize respectively x-axis, y-axis, z-axis six direction angular velocity vector.
Next, removing noise of the multiple modulus in.
To the pressure data for collecting four regions, two-value profile is equalized in a gait cycle, as a result, each packet Gait video sequence containing a large amount of gait cycles is represented as a series of gray average pictures.
By the modulus according to decomposing multiple frequency ranges, and according to the frequency of the modulus evidence to the modulus according in multiple frequencies Section is sampled.
Any wavelet transform function can be used, using intelligent shoe as acquisition hardware for, wavelet decomposition, right can be carried out High-frequency wavelet coefficient processing, three steps of wavelet reconstruction wavelet transform function, by the time-domain signal discretization of modulus evidence.This When, the modulus is according to the mixed signal for being multi-frequency ingredient.By the modulus according to different frequency range is decomposed, then according to decomposition Different characteristic of each seed signal of the modulus after to different frequency range on frequency domain, to the modulus according to taking out Sample.
Then, the non_monitor algorithm based on matrix is used to removal noise and retains the information most represented.Finally, utilizing Supervision algorithm further increases resolution capability.Obtain the high gait data of signal-to-noise ratio.
Specifically, for using intelligent shoe as acquisition hardware, wavelet transform function can also be carried out using hard threshold method.
S207: the critical movements posture information in daily routines information is obtained.
For using intelligent shoe as acquisition hardware, since daily routines information includes the human body attitude vector of six direction, Therefore, the mould of each direction attitude vectors is calculated, is obtained for the direction attitude vectors in each direction in daily routines information respectively To the modulus evidence of each direction attitude vectors；According to the modulus of each direction attitude vectors according to draw each direction posture to Measure corresponding direction posture curve.As shown in figure 4, being the vector acceleration modular curve that acquisition hardware obtains.Here, according to described The wave crest point and/or trough point of the corresponding direction posture curve in each direction, obtain critical movements posture information.
Specifically, according to the trough point of the direction posture curve of vertical direction and/or time, it is aligned the described of each direction Direction posture curve.
In order to improve the uniformity, comparative of frequency domain character, improves and crowd is carried out to people's target individual according to frequency domain character The ability of classification.Be z-axis direction place to attitude vectors according to vertical direction place to attitude vectors, to direction posture to Amount is aligned.According to the trough point of the direction posture curve of the vertical direction of similar time, the side in each direction can be aligned To posture curve.
Specifically, for using intelligent shoe as acquisition hardware, by each direction attitude vectors with linear interpolation algorithm first Dimension normalizes to same value, is gone out after normalizing by first-order difference algorithm search on the direction attitude vectors curve of vertical direction Trough point, above-mentioned trough point is as a reference point, will be on the front and rear, left and right and vertical direction in active force with linear interpolation method The alignment of direction attitude vectors curve waveform, then with L layers of wavelet packet decomposition algorithm, from the direction after the alignment in each direction In posture curve, frequency domain character data are extracted.
According to the wave crest point and/or trough point of the corresponding direction posture curve in each direction, each side is extracted To the direction posture curve in temporal signatures data.
For using intelligent shoe as acquisition hardware, the wave crest point and trough point of Vertical Square upwardly direction posture curve are to mention Take the key point of the temporal signatures data in the posture curve of direction.
Temporal signatures data in the posture curve of direction include: at the key point of Vertical Square upwardly direction posture curve Force value, above-mentioned force value occur phase, adjacent key point active force change rate and momentum；The corresponding front and rear, left and right of key point The force value at wave crest point and/or trough point, driving momentum on square upwardly direction posture curve (occupy 0 on force-time curve Or more power and the integral of time) and braking momentum (occuping the integral of power below and time on force-time curve at 0 point of) Deng.
According to the frequency domain character data and the temporal signatures data, critical movements posture information is determined.
Above-mentioned temporal signatures and frequency domain character are combined, after being merged, obtain critical movements posture information.
S208: the listener clustering model is utilized, according to the target of the medical information of the target individual and acquisition The critical movements posture information of individual, determines target group's type belonging to the target individual.
Specifically, any common machine learning algorithm can be used in listener clustering model, comprising: non-supervisory engineering Practise algorithm, supervision machine learning algorithm, neural network algorithm etc..Specifically for example, for the crowd for needing traditional Chinese medicine to improve When being classified, support vector machines (Support Vector Machine, SVM) algorithm and/or neural network mould can be used Type.
The lower dimensional space of linearly inseparable is mapped to the higher-dimension of linear separability using Nonlinear Mapping Radial basis kernel function Space.The VC dimension of N-dimensional spatial linear function greatly reduces, and algorithm is made to be with good expansibility；Former problem is converted into antithesis After problem, algorithm operation quantity depends primarily on the supporting vector number in sample, and algorithm is made to be provided with lower complexity.These are special Point allows algorithm efficiently to solve the problems, such as higher-dimension.
Specifically, it can be handled first using medical information of the neural network model to target individual, by target Input layer of the medical information of body as neural network model, by the calculating of middle layer neuron, the target predicted is a The system classification constitution information of body.For example, according to the age of target individual, gender, weight, the course of disease, current glycemic index, when Calory count consumed by preceding blood pressure index and current kinetic, the glycemic index and blood pressure index of prediction target individual from now on, So that it is determined that whether target individual belongs to diabetic population or Hypertensive Population.
Later, target is determined according to the daily routines information of target individual according to the prediction result of neural network model Target group's type belonging to body, what is at this moment obtained is crowd's type of subdivision.
Calculate the standard deviation of the daily routines information of individual of sample.
For using intelligent shoe as acquisition hardware, a, b, c, d respectively indicate the left foot of intelligent shoe in four areas all around The daily routines information in four regions of the sensor acquisition on domain, such as crucial daily action message, to the sample obtained The daily action message of key of above-mentioned a, b, c, d of this individual integrally take standard deviation.
According to the daily routines information of the target individual, determine the target individual daily routines information and the mark Irrelevance between quasi- difference.
According to the medical information of the target individual and the irrelevance, target group described in the target individual is determined Type.
For example, left and right plantar pressure surge pressure distribution is essentially identical when normal person stands and walks；And patient of diabetes Person and critical person, range of motion, which becomes smaller, causes front foot/metapedes pressure to significantly increase, and pressure is unevenly distributed weighing apparatus.In this way as stood Vertical state, is further divided into normal stand and morbid state is stood.Which kind of morbid state can also be belonged to further division target individual Gait.Assuming that target individual belongs to diabetic population, and combines daily work in conjunction with the prediction result of above-mentioned neural network model The classification results of dynamic information, the gait of target individual are presented the ill gait of diabetes, target individual can be divided into glycosuria Disease hurts joint, to influence in a kind of crowd of daily exercise.
When classifying to the crowd for needing traditional Chinese medicine to improve, preferably classified using svm classifier model to crowd.
Svm classifier model needs seek optimal classification surface in higher dimensional space.The think of of optimal classification surface is sought in higher dimensional space Road can reduce the complexity of algorithm, but the conversion process of algorithm is very complicated, however by the optimizing function in dual problem Only need to calculate the inner product of training sample with classification function, therefore, transformed higher dimensional space is not necessarily to know variation And process, it is only necessary to calculate its inner product value using former spatial function.
Thus, suitable interior Product function is applied in optimal classification surface, linear point can be realized after nonlinear transformation Class, and computation complexity is reduced instead.
In the case where initial crowd's type is different with the medical information of target individual, according to the method described above respectively according to just The medical information of beginning crowd's type and target individual models, and forms different listener clustering models, can be used for so not Remote health with target individual detects, and forms the subdivision crowd's type for being directed to each target individual constitution.
Here, the irrelevance can be with crowd boundary center away from character representation, boundary center in machine learning algorithm Away from definition be distance of the boundary point to mass center.
Before determining target group's type described in the target individual, can also medical information to target individual, Principal component analysis technology is used to the temporal signatures data and frequency domain character data of the daily action message of key of target individual (principal component analysis, PCA) is pre-processed, thus further dimensionality reduction.In this way, both having used fixation Work samples set method in turn avoids the number when vector beyond work samples collection to have the advantages that calculating speed is fast When scale, listener clustering model only optimizes a part in supporting vector, thus the problem that bring is range-restricted.
By taking the daily action message of key of target individual as an example.
In order to eliminate the influence of different dimensions, different number grade between data, the crucial daily routines to target individual are needed Information and/or the initial data of irrelevance are standardized, and make it have comparativity, are subtracted by each element in putting to the proof The mean value of column is gone, then divided by the method for the standard deviation of column, so that it is 0 that each variable standard, which turns to mean value, variance For 1 matrix X.
Later, determine that correlation matrix, above-mentioned correlation matrix are real symmetric matrixes.Also, determine accumulative contribution Rate selects the sample set that target group's type is determined using listener clustering model according to contribution rate of accumulative total and correlation matrix.
When contribution rate of accumulative total reaches 50% or more, using than supreme people's court that the key of the target individual of highest contribution rate is more daily The temporal signatures data and frequency domain character data of action message leave, as fixed work sample set, remaining target individual The temporal signatures data and frequency domain character rejection of data of crucial daily action message.
Score matrix is finally calculated, principal component of the sample set selected by contribution rate of accumulative total as new variables.
In assorting process, according to the medical information of the target individual and the irrelevance, the target individual is determined Target group's type, if there is no the similarities between target group's type in the listener clustering model Greater than crowd's type of preset threshold, people's realm type is increased newly according to target group's type, and update the crowd point Class model.
S209: generating third questionnaire, so that the individual of sample generates the answer of third questionnaire.
Here, the main purpose of third questionnaire is to collect target individual for target group's type belonging to it Degree of recognition, to prove the accuracy of the method for embodiment individuation provided by the embodiments of the present application accurate constitution conditioning and correct Property.
S210: the third of daily routines information, critical movements posture information and acquisition based on the individual of sample is asked The answer of volume, training obtain listener clustering model.
With the increase of sample size, listener clustering model can adaptively be continued to optimize perfect, and this method is in genetic algorithm The beginning and end stage need selection rate appropriate.
By taking SVM algorithm as an example, the fitness function of SVM algorithm can be used to be characterized as SVM algorithm to divide correctly sample Rate.According to sample divide accuracy, the daily routines information of the individual of sample, critical movements posture information and acquisition the The answer of three questionnaires, training obtain listener clustering model.
Here, parallel implementation is simulated by keeping the interaction between multiple groups and properly control group, Even if can also improve the execution efficiency of algorithm to not use parallel computer.
Based on the same technical idea, the embodiment of the present application also provide a kind of constitution conditioning device based on crowd's type, Electronic equipment and computer storage medium etc., for details, reference can be made to following embodiments.
Embodiment three
It is a kind of device 300 for embodying the accurate constitution conditioning of individuation provided by the embodiments of the present application, packet as shown in Figure 3 It includes:
Questionnaire information obtains module 301, and the personal information for the target individual according to acquisition generates the first questionnaire, so that The target individual generates the answer of the first questionnaire, is also used to obtain the answer of the first questionnaire；
Preliminary classification module 302 determines belonging to the target individual just for the answer according to the first questionnaire of acquisition Beginning crowd's type；
Physical condition information determination module 303 determines institute for the initial crowd type according to belonging to the target individual State the physical condition information of target individual；
Listener clustering module 304 determines the target individual institute for the physical condition information according to the target individual Target group's type of category；
Scheme determining module 305, for target group's type according to belonging to the target individual, the determining and target The corresponding default constitution coordinating program of crowd's type, and the constitution coordinating program is sent to the target individual.
Example IV
As shown in figure 4, being the structural schematic diagram of a kind of electronic equipment 400 provided by the embodiment of the present application, including processing Device 401, memory 402, bus 403, the processor 401 and memory 402 are connected by bus 403；Processor 401 is used for Execute the executable module stored in memory 402, such as computer program.
Wherein, memory 402 may include high-speed random access memory (Random Access Memory, RAM), It may further include nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
It is total that bus 403 can be industry standard architecture (Industry Standard Architecture, ISA) Line, external equipment interconnection (Peripheral Component Interconnect, PCI) bus expand industrial standard summary Structure (Extended Industry Standard Architecture, EISA) bus etc..The bus can be divided into address Bus, data/address bus, control bus etc..Only to be indicated with a four-headed arrow in Fig. 4 convenient for indicating, it is not intended that only A piece bus or a type of bus.
Wherein, memory 402 is for storing program, and the processor 401 executes the journey after receiving and executing instruction Sequence, method performed by the device that the stream process that aforementioned any embodiment of the embodiment of the present invention discloses defines can be applied to handle In device 401, or realized by processor 401.
Processor 401 may be a kind of IC chip, the processing capacity with signal.It is above-mentioned during realization Each step of method can be completed by the integrated logic circuit of the hardware in processor 401 or the instruction of software form.On The processor 401 stated can be general processor, including central processing unit (Central Processing Unit, CPU), net Network processor (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing At programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete Door or transistor logic, discrete hardware components.It may be implemented or execute the disclosed each side in the embodiment of the present invention Method, step and logic diagram.General processor can be microprocessor or the processor is also possible to any conventional processing Device etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware decoding processor and execute completion, Or in decoding processor hardware and software module combination execute completion.Software module can be located at random access memory, dodge It deposits, read-only memory, this fields such as programmable read only memory or electrically erasable programmable memory, register are mature to deposit In storage media.The storage medium is located at memory 402, and processor 401 reads the information in memory 402, complete in conjunction with its hardware The step of at the above method.
A kind of device and electronic equipment embodying the accurate constitution conditioning of individuation provided in an embodiment of the present invention, with above-mentioned reality The method technical characteristic having the same that a kind of accurate constitution conditioning of embodiment individuation of example offer is provided, so also can solve identical The technical issues of, reach identical technical effect.
Embodiment five
Present embodiment discloses a kind of computer readable storage medium, calculating is stored on the computer readable storage medium Machine program, which executes the accurate constitution conditioning of embodiment individuation of above-described embodiment method when being run by processor In step.
The computer program of a kind of method of accurate constitution conditioning of embodiment individuation is carried out provided by the embodiment of the present application Product, the computer readable storage medium including storing the executable non-volatile program code of processor, described program generation The instruction that code includes can be used for executing previous methods method as described in the examples, and specific implementation can be found in embodiment of the method, This is repeated no more.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words The form of product embodies, which is stored in a storage medium, including some instructions use so that One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen It please be described in detail, those skilled in the art should understand that: anyone skilled in the art Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.

Claims (10)

1. a kind of method for embodying the accurate constitution conditioning of individuation characterized by comprising
The first questionnaire is generated according to the personal information of the target individual of acquisition, so that the target individual generates answering for the first questionnaire Case, and the answer of the first questionnaire according to acquisition determine initial crowd's type belonging to the target individual；
Initial crowd's type according to belonging to the target individual, determines the physical condition information of the target individual；
According to the physical condition information of the target individual, target group's type belonging to the target individual is determined；
According to target group's type belonging to the target individual, default constitution tune corresponding with target group's type is determined Reason scheme, and the constitution coordinating program is sent to the target individual.
2. the method according to claim 1, wherein the physical condition information according to the target individual, Determine target group's type belonging to the target individual, comprising:
According to the physical condition information of each individual of sample of acquisition, the standard deviation of the physical condition information of individual of sample is calculated；
According to the physical condition information of the target individual, the physical condition information and the standard deviation of the target individual are determined Between irrelevance；
According to the irrelevance, target group's type described in the target individual is determined.
3. the method according to claim 1, wherein crowd's class initial according to belonging to the target individual Type determines the physical condition information of the target individual, is realized using following at least one method:
The answer for obtaining the second questionnaire generated according to initial crowd's type, the daily routines for obtaining the target individual are believed It ceases, obtain the medical information of the target individual and obtain the history constitution coordinating program of the target individual.
4. according to the method described in claim 3, it is characterized in that, including in the physical condition information for obtaining the target individual In the case where the daily routines information for obtaining the target individual, the daily routines information includes human body attitude vector.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
Obtain the daily routines information of individual of sample；
Obtain the critical movements posture information in the daily routines information of individual of sample；Wherein, the critical movements posture information For the daily life information for meeting preset condition；
Third questionnaire is generated, so that the individual of sample generates the answer of third questionnaire；
The answer of the third questionnaire of daily routines information, critical movements posture information and acquisition based on the individual of sample, Listener clustering model is trained, target group's disaggregated model is obtained；
Using target group's disaggregated model, according to the medical information of the target individual and the target individual of acquisition Critical movements posture information determines target group's type belonging to the target individual.
6. according to the method described in claim 5, it is characterized in that, before the training listener clustering model, further includes:
The daily routines information is filtered；
The mould for calculating each daily routines information, obtains multiple modulus evidences；
Remove noise of the multiple modulus in；
By the modulus according to decomposing multiple frequency ranges, and according to the frequency of the modulus evidence to the modulus according to multiple frequency ranges into Line sampling.
7. according to the method described in claim 5, it is characterized in that, the daily routines information includes the direction appearance of multiple directions State vector；
Critical movements posture information in the daily routines information for obtaining individual of sample, specifically includes:
Respectively for the direction attitude vectors in each direction in daily routines information, the mould of each direction attitude vectors is calculated, is obtained To the modulus evidence of each direction attitude vectors；
According to the modulus of each direction attitude vectors according to the corresponding direction posture curve of each direction attitude vectors of drafting, root According to the wave crest point and/or trough point of the corresponding direction posture curve in each direction, critical movements posture information is obtained.
8. according to the method described in claim 5, it is characterized in that, obtaining the critical movements posture letter for meeting preset condition Breath, further includes:
According to the trough point of the direction posture curve of vertical direction and/or time, the direction posture for being aligned each direction is bent Line；
From the direction posture curve after the alignment in each direction, frequency domain character data are extracted；
According to the wave crest point and/or trough point of the corresponding direction posture curve in each direction, each direction is extracted Temporal signatures data in the direction posture curve；
According to the frequency domain character data and the temporal signatures data, critical movements posture information is determined.
9. according to the method described in claim 5, obtaining target it is characterized in that, described be trained listener clustering model Listener clustering model, comprising:
By the daily routines information of each individual of sample and critical movements posture information input listener clustering model, each sample is obtained Crowd's type of this individual；
According to the answer of the third questionnaire of acquisition and crowd's type of each individual of sample, epicycle listener clustering model is determined Penalty values；
When the penalty values of calculating are greater than preset loss threshold value, the model parameter of the listener clustering model is adjusted, and return It executes described by the daily routines information of each individual of sample and critical movements posture information input listener clustering model, Zhi Daoji The penalty values of calculation are less than preset loss threshold value；
When the penalty values of calculating are less than preset loss threshold value, the listener clustering model that last wheel iteration is obtained is as mesh Mark listener clustering model.
10. a kind of device for embodying the accurate constitution conditioning of individuation characterized by comprising
Questionnaire information obtains module, and the personal information for the target individual according to acquisition generates the first questionnaire, so that the mesh Mark individual generates the answer of the first questionnaire, is also used to obtain the answer of the first questionnaire；
Preliminary classification module determines initial crowd belonging to the target individual for the answer according to the first questionnaire of acquisition Type；
Physical condition information determination module determines the target for the initial crowd type according to belonging to the target individual The physical condition information of individual；
Listener clustering module determines mesh belonging to the target individual for the physical condition information according to the target individual Mark crowd's type；
Scheme determining module, for target group's type according to belonging to the target individual, the determining and target person realm The corresponding default constitution coordinating program of type, and the constitution coordinating program is sent to the target individual.
CN201910369971.6A 2019-05-06 2019-05-06 A kind of method and device embodying the accurate constitution conditioning of individuation Pending CN110047564A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910369971.6A CN110047564A (en) 2019-05-06 2019-05-06 A kind of method and device embodying the accurate constitution conditioning of individuation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910369971.6A CN110047564A (en) 2019-05-06 2019-05-06 A kind of method and device embodying the accurate constitution conditioning of individuation

Publications (1)

Publication Number Publication Date
CN110047564A true CN110047564A (en) 2019-07-23

Family

ID=67280794

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910369971.6A Pending CN110047564A (en) 2019-05-06 2019-05-06 A kind of method and device embodying the accurate constitution conditioning of individuation

Country Status (1)

Country Link
CN (1) CN110047564A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111599473A (en) * 2020-05-21 2020-08-28 北京因普乐健康科技有限公司 Blood glucose related index information processing method and device and electronic equipment
CN114005522A (en) * 2021-10-28 2022-02-01 平安国际智慧城市科技股份有限公司 Data processing method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160143578A1 (en) * 2013-06-06 2016-05-26 Valeriy Nasedkin System and method for functional state and/or performance assessment and training program adjustment
CN106991630A (en) * 2017-04-05 2017-07-28 苏华巍 A kind of diet balance instructs system and method
CN107015646A (en) * 2017-03-28 2017-08-04 北京犀牛数字互动科技有限公司 The recognition methods of motion state and device
CN107705848A (en) * 2017-11-07 2018-02-16 杭州八脉科技有限公司 A kind of method and system for recommending coordinating program according to user health situation
CN108887637A (en) * 2018-08-14 2018-11-27 四川固正保和健康管理有限责任公司 Improve the medicated food formula and conditioning health care product of constitution
CN109285594A (en) * 2018-09-11 2019-01-29 深圳众赢时代科技有限公司 Human body 3D scanning projection technology

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160143578A1 (en) * 2013-06-06 2016-05-26 Valeriy Nasedkin System and method for functional state and/or performance assessment and training program adjustment
CN107015646A (en) * 2017-03-28 2017-08-04 北京犀牛数字互动科技有限公司 The recognition methods of motion state and device
CN106991630A (en) * 2017-04-05 2017-07-28 苏华巍 A kind of diet balance instructs system and method
CN107705848A (en) * 2017-11-07 2018-02-16 杭州八脉科技有限公司 A kind of method and system for recommending coordinating program according to user health situation
CN108887637A (en) * 2018-08-14 2018-11-27 四川固正保和健康管理有限责任公司 Improve the medicated food formula and conditioning health care product of constitution
CN109285594A (en) * 2018-09-11 2019-01-29 深圳众赢时代科技有限公司 Human body 3D scanning projection technology

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111599473A (en) * 2020-05-21 2020-08-28 北京因普乐健康科技有限公司 Blood glucose related index information processing method and device and electronic equipment
CN114005522A (en) * 2021-10-28 2022-02-01 平安国际智慧城市科技股份有限公司 Data processing method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
Demrozi et al. Human activity recognition using inertial, physiological and environmental sensors: A comprehensive survey
Phinyomark et al. Navigating features: a topologically informed chart of electromyographic features space
Weng et al. Disease prediction with different types of neural network classifiers
Everson et al. BiometricNet: Deep learning based biometric identification using wrist-worn PPG
Sevil et al. Determining physical activity characteristics from wristband data for use in automated insulin delivery systems
Aqajari et al. Gsr analysis for stress: Development and validation of an open source tool for noisy naturalistic gsr data
Zhong Internet of things sensors assisted physical activity recognition and health monitoring of college students
Goyal et al. Classification, prediction, and monitoring of Parkinson’s disease using computer assisted technologies: a comparative analysis
Li et al. Deep learning of smartphone sensor data for personal health assistance
Tsinganos et al. Hilbert sEMG data scanning for hand gesture recognition based on deep learning
Diab et al. Embedded machine learning using microcontrollers in wearable and ambulatory systems for health and care applications: A review
Hsu Brain–computer interface: the next frontier of telemedicine in human–computer interaction
Mahoney et al. Methodology and validation for identifying gait type using machine learning on IMU data
CN110047564A (en) A kind of method and device embodying the accurate constitution conditioning of individuation
Aggarwal et al. A structured learning approach with neural conditional random fields for sleep staging
Soroushmojdehi et al. Transfer learning in hand movement intention detection based on surface electromyography signals
CN109285594A (en) Human body 3D scanning projection technology
Saranya et al. FIGS-DEAF: An novel implementation of hybrid deep learning algorithm to predict autism spectrum disorders using facial fused gait features
CN111916179A (en) Method for carrying out 'customized' diet nourishing model based on artificial intelligence self-adaption individual physical sign
Baldominos et al. Feature set optimization for physical activity recognition using genetic algorithms
Aziz et al. Machine learning based classification of normal, slow and fast walking by extracting multimodal features from stride interval time series
CN115394448B (en) Modeling method, model and equipment of coronary heart disease motion reactivity prediction model
CN116884615A (en) Hypertension risk prediction method, system, electronic equipment and storage medium
Gavrishchaka et al. Multi-complexity ensemble measures for gait time series analysis: Application to diagnostics, monitoring and biometrics
Sengupta et al. A Survey of Wearable Sensors and Machine Learning Algorithms for Automated Stroke Rehabilitation

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