CN112185561A - User portrait generation method and device and computer equipment - Google Patents
User portrait generation method and device and computer equipment Download PDFInfo
- Publication number
- CN112185561A CN112185561A CN202011043086.8A CN202011043086A CN112185561A CN 112185561 A CN112185561 A CN 112185561A CN 202011043086 A CN202011043086 A CN 202011043086A CN 112185561 A CN112185561 A CN 112185561A
- Authority
- CN
- China
- Prior art keywords
- user
- health
- disease
- data
- index data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
Landscapes
- Public Health (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application relates to the field of digital medical treatment, and discloses a user portrait generation method, which comprises the following steps: acquiring physiological index data of a detected user; analyzing the analysis result corresponding to each physiological index data through a medical model; generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases; and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease. And performing data analysis through the medical model according to the acquired detection value in the health file to obtain an analysis result, inputting the analysis result into the data calculation model to obtain a health description label set of the user, and designating a health portrait of the user and giving a health management suggestion through different health portraits.
Description
Technical Field
The present application relates to the field of digital medical technology, and more particularly, to a method, an apparatus, and a computer device for generating a user representation.
Background
With the continuous progress of society, people pay more and more attention to their health and pay more attention to the management of health. The health management of high-risk people such as chronic patients, middle-aged and old people, pregnant and lying-in women, infants and the like is urgent. Currently, health management mainly depends on the measurement terminal class: such as: electronic sphygmomanometers, blood glucose meters and the like, but after the measured health data is obtained, most users without scientific and medical knowledge cannot accurately master the current health portrait according to the measured data. Except for regular physical examination, the health monitoring and management process is not available, precaution before the onset of a disease cannot be achieved, or scientific and safety supervision and guidance is lacked, so that the negative influence on the personal health is caused. In short, the absence of a medical data analysis system compatible with the measurement data prevents the individual health data from being presented to the user visually.
Disclosure of Invention
The application mainly aims to provide generation of a user portrait and aims to solve the technical problem that no medical data analysis system which is connected with measurement data carries out data analysis.
The application provides a user portrait generation method, which comprises the following steps:
acquiring physiological index data of a detected user;
analyzing the analysis result corresponding to each physiological index data through a medical model;
generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases;
and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
Preferably, the step of analyzing the analysis result corresponding to each physiological index data through the medical model includes:
inputting specified index data into the medical model, wherein the specified index data is any index data in all the physiological index data;
obtaining a medical model, and analyzing the value distribution result of each disease type corresponding to the specified index data through a decision table and medical rules;
obtaining the value distribution results of the disease types corresponding to all the physiological index data one by one according to the calculation process of the value distribution results of the disease types corresponding to the specified index data;
and taking the value distribution result of each disease type corresponding to all the physiological index data one to one as the analysis result.
Preferably, the decision table includes a transverse decision table, the medical rule includes an evaluation probability of each disease caused by the specified index data, and the step of obtaining the score distribution result of each disease category corresponding to the specified index data by the medical model through the decision table and the medical rule includes:
inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in rows;
additionally filling an information column except the disease column, wherein the information column comprises a column in which the specified index data is positioned and a score distribution result column of each disease type;
according to the evaluation probability of each disease caused by the specified index data, deciding and calculating the score distribution result of each disease type corresponding to the specified index data;
and filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types in a one-to-one correspondence manner.
Preferably, the step of generating a health evaluation report from each analysis result through a data analysis model includes:
modeling each analysis result through a Gaussian process to obtain a confidence coefficient corresponding to each analysis result;
deducing the confidence corresponding to each analysis result through a kernel function to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease;
and generating the health evaluation report according to the risk probability evaluation of the user suffering from the disease, the label set describing the health of the user and the evaluation of factors causing the disease.
Preferably, the step of acquiring the physiological index data of the detected user is preceded by:
judging whether the health file of the current user reaches a preset standard of information perfection;
if not, generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user;
and updating the health record of the current user according to the feedback information of the current user to the intelligent question and answer sheet.
Preferably, the step of generating the intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health record of the current user includes:
acquiring information data in the health record of the current user;
inputting the information data in the health record of the current user into a decision table as an input item;
judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one;
and forming question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the appointed output item set.
Preferably, the step of generating a user representation according to the label set describing the health of the user, the risk probability assessment of the disease and the factor assessment of causing the disease is followed by:
determining a target item to be monitored according to the user portrait at the current moment;
sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment;
judging whether the uploaded data of the user is received in the monitoring time period;
if receiving uploaded data of a user, judging whether the uploaded data is new measurement data of the target project to be monitored;
and if the target item is the new measurement data of the target item to be monitored, updating the health evaluation report and the user portrait according to the new measurement data.
The present application further provides a user portrait generation apparatus, including:
the acquisition module is used for acquiring physiological index data of a detected user;
the analysis module is used for analyzing the analysis result corresponding to each physiological index data through a medical model;
the first generation module is used for generating a health evaluation report from each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of a user, risk probability evaluation of diseases and factor evaluation of causing diseases;
and the second generation module is used for generating a user portrait according to the label set for describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method as described above.
According to the health management method and the health management system, data analysis is carried out through a medical model according to the obtained detection numerical values in the health files to obtain analysis results, then the analysis results are input into a data calculation model, a health description label set of a user is obtained, the health portrait of the user is appointed, and health management suggestions are given through different health portraits.
Drawings
FIG. 1 is a schematic flow chart illustrating a method for generating a user representation according to an embodiment of the present application;
FIG. 2 is a diagram illustrating the distribution of risk of disease according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an apparatus for generating a user representation according to an embodiment of the present application;
fig. 4 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, a method for generating a user portrait according to an embodiment of the present application includes:
s1: acquiring physiological index data of a detected user;
s2: analyzing the analysis result corresponding to each physiological index data through a medical model;
s3: generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases;
s4: and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
In the initial state of the application, the health file of the user is generated by collecting user information through an external system. The external systems include but are not limited to public health, hospital, pharmacy, health cabin, etc., and the user information includes but is not limited to name, age, height, weight, sex, etc. The physiological index data includes, but is not limited to, blood pressure, blood sugar, heart rate, etc., and when the physiological index data relates to a specific population field, the physiological index data can be adaptively expanded or replaced, for example, the sleep time, the milk drinking amount, the heat intake, etc., of infant population are increased. The medical model of the present application is a decision table model carrying medical rules. The decision table model comprises a transverse decision table or a longitudinal decision table corresponding to a single input item, and also comprises a cross decision table corresponding to two or more input items, and the transverse decision table is preferred in the application. The horizontal decision table refers to that the table head items are arranged in a centralized mode in a row mode, for example, the first row of the table is the name of each item such as age and weight. The analysis result comprises a risk evaluation score of a certain disease calculated according to medical rules in the decision table. And then obtaining a health evaluation report by means of a data analysis model according to analysis results corresponding to the plurality of physiological index data respectively. The data analysis model is a model comprising calculation modules such as a Gaussian function, a kernel function and a covariance matrix, so that through reasonable calculation deduction, a label set describing the health of a user, risk probability evaluation of diseases and factor evaluation of causing diseases are calculated according to analysis results corresponding to a plurality of physiological index data respectively, a health evaluation report is formed, a user portrait of the health of the user is obtained, the user can be assisted to more scientifically master the health condition according to detected physiological index data, and the health condition of the body can be reasonably monitored according to the health portrait of the user.
Further, the step S2 of analyzing the analysis result corresponding to each physiological index data by the medical model includes:
s21: inputting specified index data into the medical model, wherein the specified index data is any index data in all the physiological index data;
s22: obtaining a medical model, and analyzing the value distribution result of each disease type corresponding to the specified index data through a decision table and medical rules;
s23: obtaining the value distribution results of the disease types corresponding to all the physiological index data one by one according to the calculation process of the value distribution results of the disease types corresponding to the specified index data;
s24: and taking the value distribution result of each disease type corresponding to all the physiological index data one to one as the analysis result.
The input data of the medical model can be input through an input expression, and the input expression can expect that the input value is limited data or data in a limited value range. The important part of the medical model is to model the expected values, and the modeling rules cover all combinations of expected input values, i.e. can be combined into a complete decision table. The blood pressure data of the user is analyzed by a lateral decision table as in table 1 below.
TABLE 1
And then calculating according to medical rules to obtain a score distribution result of various diseases according to the blood pressure data of the user. As in table 2 below:
TABLE 2
According to the score distribution results of various diseases in table 2, a distribution state diagram of the disease risk as shown in fig. 2 is plotted as an analysis result.
Further, the decision table includes a transverse decision table, the medical rule includes an evaluation probability of each disease caused by the specified index data, and step S22 of obtaining the score distribution result of each disease category corresponding to the specified index data by the medical model through the decision table and the medical rule, includes:
s221: inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in rows;
s222: additionally filling an information column except the disease column, wherein the information column comprises a column in which the specified index data is positioned and a score distribution result column of each disease type;
s223: according to the evaluation probability of each disease caused by the specified index data, deciding and calculating the score distribution result of each disease type corresponding to the specified index data;
s224: and filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types in a one-to-one correspondence manner.
In the embodiment of the present application, the forming process of the above table 2 is a calculation process of the transverse decision table.
Further, the step S3 of generating a health evaluation report from each analysis result through a data analysis model includes:
s31: modeling each analysis result through a Gaussian process to obtain a confidence coefficient corresponding to each analysis result;
s32: deducing the confidence corresponding to each analysis result through a kernel function to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease;
s33: and generating the health evaluation report according to the risk probability evaluation of the user suffering from the disease, the label set describing the health of the user and the evaluation of factors causing the disease.
The data analysis model of the present application calculates the probability of the user suffering from a certain disease comprehensively according to the distribution state diagram of the disease risk corresponding to each physiological index data. The two-dimensional correlation between the user disease probability and the disease factor improves the correlation function
Assume that there is a set of continuous random variables, X0,X1,...,XTIf any finite set of this set of random variables:
and modeling the distribution of the correlation function by using a Gaussian process, and giving the confidence coefficient of the fitting result. Assume that an unknown function f (x) follows a gaussian process and is a smooth function. For two relatively close samples X1And X2Then, the function value f (x) is obtained1) And f (x)2) And also relatively close. If a finite number of samples X ═ X are sampled from the function f (X)1，X2...,XN]And then the N sample distribution points obey multivariate normal distribution and are recorded as: [ f (x)1),f(x2),...,f(xN)]TN (μ (X), K (X, X), where μ (X) ═ μ (X)1),μ(x2),...,μ(xN)]TDenotes a mean vector, K (X, X) ═ K (X)i,xj)]N.N is a covariance matrix, k (X)i,Xj) The similarity of two samples can be measured for the kernel function. By square exponential function of kernel function in gaussian process
And (3) deriving a calculation mode of deduction:
and deducing the confidence degrees corresponding to the analysis results respectively by the deduction calculation mode to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease. The health evaluation report is generated through the perfect health record. The health assessment report also contains the estimated diseases of the user and the associated assessment of other high risk factors, such as cardiovascular event assessment, ICVD risk assessment, complication risk assessment, and the like.
Further, before the step S1 of acquiring the physiological index data of the detected user, the method includes:
s11: judging whether the health file of the current user reaches a preset standard of information perfection;
s12: if not, generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user;
s13: and updating the health record of the current user according to the feedback information of the current user to the intelligent question and answer sheet.
The method and the device for judging the health record of the current user compare the information included in the health record of the current user with standard information included in a preset standard, and judge whether the information is perfect. If the health record is not perfect, the information included in the health record of the current user is used as an input item, then an intelligent question and answer sheet is generated through a transverse decision table, information interaction is carried out on the intelligent question and answer sheet and the user, and information data needed in the health record is complemented so as to avoid influencing the subsequent analysis process of a medical model and a data analysis model.
Further, the step S12 of generating the intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health record of the current user includes:
s121: acquiring information data in the health record of the current user;
s122: inputting the information data in the health record of the current user into a decision table as an input item;
s123: judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one;
s124: and forming question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the appointed output item set.
In the method, the output item set corresponding to the input item is determined through the input item, and according to the priority of the matching strategy of the input item and the output item, the information data with the highest priority is screened to be output as a problem until all the information data in the health file are supplemented. The intelligent questionnaire described above relates to questions asked including, but not limited to, the user's current diagnosis of disease, medication, family history, past history, diet, and the like. The set of test items includes, but is not limited to, a blood glucose monitoring data set, a heart rate monitoring data set, a blood pressure monitoring data set, a sleep time monitoring data set, a diet monitoring data set, a motion detection data set, a mental state monitoring data set, and the like.
Further, after the step S4 of generating a user profile according to the label set describing the health of the user, the risk probability assessment of the disease and the factor assessment of causing the disease, the method includes:
s41: determining a target item to be monitored according to the user portrait at the current moment;
s42: sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment;
s43: judging whether the uploaded data of the user is received in the monitoring time period;
s44: if receiving uploaded data of a user, judging whether the uploaded data is new measurement data of the target project to be monitored;
s44: and if the target item is the new measurement data of the target item to be monitored, updating the health evaluation report and the user portrait according to the new measurement data.
The new measurement data of the present application refers to measurement data of a new monitoring period after the last monitoring period. The health assessment report of the present application further includes a monitoring scheme for the next cycle determined for the current health representation, the monitoring scheme including one or more target items to be monitored, a first disease monitoring plan, a periodic follow-up plan, a medication plan, and the like. Based on the medical model and the data analysis model, the disease information and BMI index of the user are obtained through evaluation, and a health plan with accurate calorie calculation is provided by using a greedy algorithm, wherein the health plan comprises exercise suggestions, diet suggestions, life style guidance and the like. According to the health picture obtained by the medical model and the data analysis model, the monitoring plan of a new monitoring period is formulated, and the user is reminded to upload monitoring data such as blood sugar, blood pressure, heart rate, fetal movement times, infant sleeping time, milk drinking amount, intake heat and other measurement data on time, so that the health evaluation report of the user, the user picture and the monitoring plan of the next new monitoring period are updated in time according to the measurement data of the monitoring period, and the user is assisted in real time to carry out health management. The health management system formed by the medical model and the data analysis model has a perfect closed-loop flow, a scientific medical model algorithm and a high-quality monitoring management scheme.
According to the method and the system, a more targeted monitoring plan and a control target are provided according to different health portraits, so that a user can know the own health condition more clearly, and the health portraits are updated and a monitoring management scheme of the next period is adjusted continuously according to measurement data uploaded by the user in the last monitoring plan so as to adapt to the change of the health condition of the user. Each group of measurement data uploaded by the user is given real-time medical early warning feedback and guidance suggestions, so that the user can clearly know professional detection data, such as blood sugar: fasting, pre-meal, post-meal 2h, pre-sleep, etc., different user profiles and different periods of time have different control objectives.
The decision table can give early warning feedback of four colors of green, yellow, orange and red according to monitoring data uploaded by a user and corresponding control targets, so that the user can know whether the current monitoring data meet health standards, whether the current monitoring data need to be used for medical treatment in time or not, whether the current monitoring data need to be focused or not and whether the current monitoring data need to be closely observed in a future period or not. If the user triggers a serious early warning, the system can push a questionnaire to inquire other current conditions of the user, and take corresponding measures according to feedback information of the user, such as call return visit, timely call emergency call, door return visit and the like. And pushing follow-up questionnaires by a system user in a one-month period, comprehensively knowing the health condition of the user, automatically comparing the monitoring result of the last period with the improvement condition of the health condition, analyzing whether the medicine or the dosage needs to be adjusted, and updating the health file.
Referring to fig. 3, an apparatus for generating a user representation according to an embodiment of the present application includes:
the acquisition module 1 is used for acquiring physiological index data of a detected user;
the analysis module 2 is used for analyzing the analysis result corresponding to each physiological index data through a medical model;
the first generation module 3 is used for generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases;
and the second generation module 4 is used for generating a user portrait according to the label set for describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
In the initial state of the application, the health file of the user is generated by collecting user information through an external system. The external systems include but are not limited to public health, hospital, pharmacy, health cabin, etc., and the user information includes but is not limited to name, age, height, weight, sex, etc. The physiological index data includes, but is not limited to, blood pressure, blood sugar, heart rate, etc., and when the physiological index data relates to a specific population field, the physiological index data can be adaptively expanded or replaced, for example, the sleep time, the milk drinking amount, the heat intake, etc., of infant population are increased. The medical model of the present application is a decision table model carrying medical rules. The decision table model comprises a transverse decision table or a longitudinal decision table corresponding to a single input item, and also comprises a cross decision table corresponding to two or more input items, and the transverse decision table is preferred in the application. The horizontal decision table refers to that the table head items are arranged in a centralized mode in a row mode, for example, the first row of the table is the name of each item such as age and weight. The analysis result comprises a risk evaluation score of a certain disease calculated according to medical rules in the decision table. And then obtaining a health evaluation report by means of a data analysis model according to analysis results corresponding to the plurality of physiological index data respectively. The data analysis model is a model comprising calculation modules such as a Gaussian function, a kernel function and a covariance matrix, so that through reasonable calculation deduction, a label set describing the health of a user, risk probability evaluation of diseases and factor evaluation of causing diseases are calculated according to analysis results corresponding to a plurality of physiological index data respectively, a health evaluation report is formed, a user portrait of the health of the user is obtained, the user can be assisted to more scientifically master the health condition according to detected physiological index data, and the health condition of the body can be reasonably monitored according to the health portrait of the user.
Further, the analysis module 2 includes:
a first input unit, configured to input specified index data into the medical model, where the specified index data is any one of all the physiological index data;
the first acquisition unit is used for acquiring a score distribution result of the specified index data corresponding to each disease type through a decision table and a medical rule of the medical model;
an obtaining unit, configured to obtain, according to a calculation process of a score distribution result of each disease type corresponding to the specified index data, a score distribution result of each disease type corresponding to each physiological index data one to one;
and the unit is used for taking the value distribution results of all disease types corresponding to all the physiological index data one to one as the analysis results.
The input data of the medical model can be input through an input expression, and the input expression can expect that the input value is limited data or data in a limited value range. The important part of the medical model is to model the expected values, and the modeling rules cover all combinations of expected input values, i.e. can be combined into a complete decision table. The blood pressure data of the user is analyzed by a lateral decision table as in table 1 below.
TABLE 1
And then calculating according to medical rules to obtain a score distribution result of various diseases according to the blood pressure data of the user. As in table 2 below:
TABLE 2
According to the score distribution results of various diseases in table 2, a distribution state diagram of the disease risk as shown in fig. 2 is plotted as an analysis result.
Further, the decision table includes a transverse decision table, the medical rule includes an evaluation probability of each disease caused by the specified index data, and the obtaining unit includes:
the input subunit is used for inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in a row mode;
a supplementary subunit, configured to supplement and fill in information columns other than the disease column, where the information columns include a column in which the specified index data is located and a score distribution result column for each disease category;
the calculating subunit is used for deciding and calculating the score distribution result of the specified index data corresponding to each disease type according to the evaluation probability of each disease caused by the specified index data;
and the filling subunit is used for correspondingly filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types one by one.
In the embodiment of the present application, the forming process of the above table 2 is a calculation process of the transverse decision table.
Further, the first generating module 3 includes:
the modeling unit is used for modeling each analysis result through a Gaussian process to obtain the confidence corresponding to each analysis result;
the deduction unit is used for deducing the confidence degrees corresponding to the analysis results through kernel functions to obtain risk probability assessment of the diseases of the user, a label set describing the health of the user and factor assessment of causing the diseases;
and the generating unit is used for generating the health evaluation report according to the risk probability evaluation of the disease of the user, the label set describing the health of the user and the factor evaluation causing the disease.
The data analysis model of the present application calculates the probability of the user suffering from a certain disease comprehensively according to the distribution state diagram of the disease risk corresponding to each physiological index data. Probability of illness of user in the present applicationThe two-dimensional correlation according to the present application improves the correlation function in relation to the disease factor in two dimensions
Assume that there is a set of continuous random variables, X0,X1,...,XTIf any finite set of this set of random variables:
and modeling the distribution of the correlation function by using a Gaussian process, and giving the confidence coefficient of the fitting result. Assume that an unknown function f (x) follows a gaussian process and is a smooth function. For two relatively close samples X1And X2Then, the function value f (x) is obtained1) And f (x)2) And also relatively close. If a finite number of samples X ═ X are sampled from the function f (X)1，X2...,XN]And then the N sample distribution points obey multivariate normal distribution and are recorded as: [ f (x)1),f(x2),...,f(xN)]TN (μ (X), K (X, X), where μ (X) ═ μ (X)1),μ(x2),...,μ(xN)]TDenotes a mean vector, K (X, X) ═ K (X)i,xj)]N.N is a covariance matrix, k (X)i,Xj) The similarity of two samples can be measured for the kernel function. By square exponential function of kernel function in gaussian process
And (3) deriving a calculation mode of deduction:
and deducing the confidence degrees corresponding to the analysis results respectively by the deduction calculation mode to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease. The health evaluation report is generated through the perfect health record. The health assessment report also contains an assessment of the estimated user's disease, and associated risk factors that may trigger other high-risk factors, such as cardiovascular event assessment, ICVD risk assessment,risk assessment of complications, etc.
Further, a user representation generation apparatus, comprising:
the first judgment module is used for judging whether the health file of the current user reaches the preset standard of information perfection;
the third generation module is used for generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user if the preset standard of complete information is not met;
and the first updating module is used for updating the health record of the current user according to the feedback information of the current user on the intelligent question and answer sheet.
The method and the device for judging the health record of the current user compare the information included in the health record of the current user with standard information included in a preset standard, and judge whether the information is perfect. If the health record is not perfect, the information included in the health record of the current user is used as an input item, then an intelligent question and answer sheet is generated through a transverse decision table, information interaction is carried out on the intelligent question and answer sheet and the user, and information data needed in the health record is complemented so as to avoid influencing the subsequent analysis process of a medical model and a data analysis model.
Further, a third generation module comprising:
the second acquisition unit is used for acquiring information data in the health file of the current user;
the second input unit is used for inputting the information data in the health file of the current user into a decision table as an input item;
the judging unit is used for judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one;
and the forming unit is used for forming the question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the specified output item set.
In the method, the output item set corresponding to the input item is determined through the input item, and according to the priority of the matching strategy of the input item and the output item, the information data with the highest priority is screened to be output as a problem until all the information data in the health file are supplemented. The intelligent questionnaire described above relates to questions asked including, but not limited to, the user's current diagnosis of disease, medication, family history, past history, diet, and the like. The set of test items includes, but is not limited to, a blood glucose monitoring data set, a heart rate monitoring data set, a blood pressure monitoring data set, a sleep time monitoring data set, a diet monitoring data set, a motion detection data set, a mental state monitoring data set, and the like.
Further, a user representation generation apparatus, comprising:
the determining module is used for determining a target item to be monitored according to the user portrait at the current moment;
the sending module is used for sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment;
the second judgment module is used for judging whether the uploaded data of the user is received in the monitoring time period;
the third judgment module is used for judging whether the uploaded data is new measurement data of the target project to be monitored or not if the uploaded data of the user is received;
and the second updating module is used for updating the health evaluation report and the user portrait according to the new measurement data if the new measurement data is the new measurement data of the target project to be monitored.
The new measurement data of the present application refers to measurement data of a new monitoring period after the last monitoring period. The health assessment report of the present application further includes a monitoring scheme for the next cycle determined for the current health representation, the monitoring scheme including one or more target items to be monitored, a first disease monitoring plan, a periodic follow-up plan, a medication plan, and the like. Based on the medical model and the data analysis model, the disease information and BMI index of the user are obtained through evaluation, and a health plan with accurate calorie calculation is provided by using a greedy algorithm, wherein the health plan comprises exercise suggestions, diet suggestions, life style guidance and the like. According to the health picture obtained by the medical model and the data analysis model, the monitoring plan of a new monitoring period is formulated, and the user is reminded to upload monitoring data such as blood sugar, blood pressure, heart rate, fetal movement times, infant sleeping time, milk drinking amount, intake heat and other measurement data on time, so that the health evaluation report of the user, the user picture and the monitoring plan of the next new monitoring period are updated in time according to the measurement data of the monitoring period, and the user is assisted in real time to carry out health management. The health management system formed by the medical model and the data analysis model has a perfect closed-loop flow, a scientific medical model algorithm and a high-quality monitoring management scheme.
According to the method and the system, a more targeted monitoring plan and a control target are provided according to different health portraits, so that a user can know the own health condition more clearly, and the health portraits are updated and a monitoring management scheme of the next period is adjusted continuously according to measurement data uploaded by the user in the last monitoring plan so as to adapt to the change of the health condition of the user. Each group of measurement data uploaded by the user is given real-time medical early warning feedback and guidance suggestions, so that the user can clearly know professional detection data, such as blood sugar: fasting, pre-meal, post-meal 2h, pre-sleep, etc., different user profiles and different periods of time have different control objectives.
The decision table can give early warning feedback of four colors of green, yellow, orange and red according to monitoring data uploaded by a user and corresponding control targets, so that the user can know whether the current monitoring data meet health standards, whether the current monitoring data need to be used for medical treatment in time or not, whether the current monitoring data need to be focused or not and whether the current monitoring data need to be closely observed in a future period or not. If the user triggers a serious early warning, the system can push a questionnaire to inquire other current conditions of the user, and take corresponding measures according to feedback information of the user, such as call return visit, timely call emergency call, door return visit and the like. And pushing follow-up questionnaires by a system user in a one-month period, comprehensively knowing the health condition of the user, automatically comparing the monitoring result of the last period with the improvement condition of the health condition, analyzing whether the medicine or the dosage needs to be adjusted, and updating the health file.
Referring to fig. 4, a computer device, which may be a server and whose internal structure may be as shown in fig. 4, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required by the user representation generation process. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of generating a user representation.
The processor executing the method for generating the user portrait comprises: acquiring physiological index data of a detected user; analyzing the analysis result corresponding to each physiological index data through a medical model; generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases; and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
According to the computer equipment, data analysis is carried out through the medical model according to the detection values in the acquired health files to obtain analysis results, then the analysis results are input into the data calculation model to obtain a health description label set of a user, a health portrait of the user is appointed, and health management suggestions are given through different health portraits.
In an embodiment, the step of analyzing, by the processor, analysis results corresponding to the physiological index data through a medical model includes: inputting specified index data into the medical model, wherein the specified index data is any index data in all the physiological index data; obtaining a medical model, and analyzing the value distribution result of each disease type corresponding to the specified index data through a decision table and medical rules; obtaining the value distribution results of the disease types corresponding to all the physiological index data one by one according to the calculation process of the value distribution results of the disease types corresponding to the specified index data; and taking the value distribution result of each disease type corresponding to all the physiological index data one to one as the analysis result.
In one embodiment, the decision table includes a horizontal decision table, the medical rule includes an evaluation probability of each disease caused by the specified index data, and the step of analyzing the score distribution result of each disease category corresponding to the specified index data by the processor, which is obtained by the medical model through the decision table and the medical rule, includes: inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in rows; additionally filling an information column except the disease column, wherein the information column comprises a column in which the specified index data is positioned and a score distribution result column of each disease type; according to the evaluation probability of each disease caused by the specified index data, deciding and calculating the score distribution result of each disease type corresponding to the specified index data; and filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types in a one-to-one correspondence manner.
In one embodiment, the step of generating the health evaluation report by the processor through the data analysis model includes: modeling each analysis result through a Gaussian process to obtain a confidence coefficient corresponding to each analysis result; deducing the confidence corresponding to each analysis result through a kernel function to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease; and generating the health evaluation report according to the risk probability evaluation of the user suffering from the disease, the label set describing the health of the user and the evaluation of factors causing the disease.
In one embodiment, before the step of acquiring the physiological index data of the user, the processor includes: judging whether the health file of the current user reaches a preset standard of information perfection; if not, generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user; and updating the health record of the current user according to the feedback information of the current user to the intelligent question and answer sheet.
In one embodiment, the step of generating the intelligent question and answer sheet corresponding to the current user by the processor through a decision table algorithm according to the information data in the health record of the current user includes: acquiring information data in the health record of the current user; inputting the information data in the health record of the current user into a decision table as an input item; judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one; and forming question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the appointed output item set.
In one embodiment, the processor generates a user representation according to the label set describing the health of the user, the risk probability assessment of the disease and the factor assessment of causing the disease, and then comprises: determining a target item to be monitored according to the user portrait at the current moment; sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment; judging whether the uploaded data of the user is received in the monitoring time period; if receiving uploaded data of a user, judging whether the uploaded data is new measurement data of the target project to be monitored; and if the target item is the new measurement data of the target item to be monitored, updating the health evaluation report and the user portrait according to the new measurement data.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is only a block diagram of some of the structures associated with the present solution and is not intended to limit the scope of the present solution as applied to computer devices.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements a method for generating a user representation, including: acquiring physiological index data of a detected user; analyzing the analysis result corresponding to each physiological index data through a medical model; generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases; and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
The computer readable storage medium performs data analysis through the medical model according to the detected values in the acquired health file to obtain an analysis result, then inputs the analysis result into the data calculation model to obtain a health description label set of the user, and specifies the health portrait of the user and different health portraits to give health management suggestions.
In an embodiment, the step of analyzing, by the processor, analysis results corresponding to the physiological index data through a medical model includes: inputting specified index data into the medical model, wherein the specified index data is any index data in all the physiological index data; obtaining a medical model, and analyzing the value distribution result of each disease type corresponding to the specified index data through a decision table and medical rules; obtaining the value distribution results of the disease types corresponding to all the physiological index data one by one according to the calculation process of the value distribution results of the disease types corresponding to the specified index data; and taking the value distribution result of each disease type corresponding to all the physiological index data one to one as the analysis result.
In one embodiment, the decision table includes a horizontal decision table, the medical rule includes an evaluation probability of each disease caused by the specified index data, and the step of analyzing the score distribution result of each disease category corresponding to the specified index data by the processor, which is obtained by the medical model through the decision table and the medical rule, includes: inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in rows; additionally filling an information column except the disease column, wherein the information column comprises a column in which the specified index data is positioned and a score distribution result column of each disease type; according to the evaluation probability of each disease caused by the specified index data, deciding and calculating the score distribution result of each disease type corresponding to the specified index data; and filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types in a one-to-one correspondence manner.
In one embodiment, the step of generating the health evaluation report by the processor through the data analysis model includes: modeling each analysis result through a Gaussian process to obtain a confidence coefficient corresponding to each analysis result; deducing the confidence corresponding to each analysis result through a kernel function to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease; and generating the health evaluation report according to the risk probability evaluation of the user suffering from the disease, the label set describing the health of the user and the evaluation of factors causing the disease.
In one embodiment, before the step of acquiring the physiological index data of the user, the processor includes: judging whether the health file of the current user reaches a preset standard of information perfection; if not, generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user; and updating the health record of the current user according to the feedback information of the current user to the intelligent question and answer sheet.
In one embodiment, the step of generating the intelligent question and answer sheet corresponding to the current user by the processor through a decision table algorithm according to the information data in the health record of the current user includes: acquiring information data in the health record of the current user; inputting the information data in the health record of the current user into a decision table as an input item; judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one; and forming question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the appointed output item set.
In one embodiment, the processor generates a user representation according to the label set describing the health of the user, the risk probability assessment of the disease and the factor assessment of causing the disease, and then comprises: determining a target item to be monitored according to the user portrait at the current moment; sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment; judging whether the uploaded data of the user is received in the monitoring time period; if receiving uploaded data of a user, judging whether the uploaded data is new measurement data of the target project to be monitored; and if the target item is the new measurement data of the target item to be monitored, updating the health evaluation report and the user portrait according to the new measurement data.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (10)
1. A method for generating a user representation, comprising:
acquiring physiological index data of a detected user;
analyzing the analysis result corresponding to each physiological index data through a medical model;
generating a health evaluation report by each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of the user, risk probability evaluation of diseases and factor evaluation of causing diseases;
and generating a user portrait according to the label set describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
2. The method of generating a user representation according to claim 1, wherein the step of analyzing the analysis result corresponding to each of the physiological index data by the medical model includes:
inputting specified index data into the medical model, wherein the specified index data is any index data in all the physiological index data;
obtaining a medical model, and analyzing the value distribution result of each disease type corresponding to the specified index data through a decision table and medical rules;
obtaining the value distribution results of the disease types corresponding to all the physiological index data one by one according to the calculation process of the value distribution results of the disease types corresponding to the specified index data;
and taking the value distribution result of each disease type corresponding to all the physiological index data one to one as the analysis result.
3. The method of claim 2, wherein the decision table comprises a horizontal decision table, the medical rule comprises an evaluation probability of each disease caused by the specified index data, and the step of obtaining the score distribution result of the medical model corresponding to each disease type by the decision table and the medical rule comprises:
inputting various disease types related to the specified index data into corresponding disease columns in a transverse decision table in rows;
additionally filling an information column except the disease column, wherein the information column comprises a column in which the specified index data is positioned and a score distribution result column of each disease type;
according to the evaluation probability of each disease caused by the specified index data, deciding and calculating the score distribution result of each disease type corresponding to the specified index data;
and filling the score distribution results of the specified index data corresponding to the disease types into the score distribution result columns of the disease types in a one-to-one correspondence manner.
4. The method of generating a user representation as claimed in claim 2, wherein said step of generating a health assessment report from each of said analysis results using a data analysis model comprises:
modeling each analysis result through a Gaussian process to obtain a confidence coefficient corresponding to each analysis result;
deducing the confidence corresponding to each analysis result through a kernel function to obtain risk probability assessment of the disease of the user, a label set describing the health of the user and factor assessment causing the disease;
and generating the health evaluation report according to the risk probability evaluation of the user suffering from the disease, the label set describing the health of the user and the evaluation of factors causing the disease.
5. A method of generating a user representation as claimed in claim 1, wherein said step of obtaining physiological metric data indicative of a detected user is preceded by the steps of:
judging whether the health file of the current user reaches a preset standard of information perfection;
if not, generating an intelligent question and answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user;
and updating the health record of the current user according to the feedback information of the current user to the intelligent question and answer sheet.
6. The method of claim 5, wherein the step of generating the intelligent question-and-answer sheet corresponding to the current user through a decision table algorithm according to the information data in the health file of the current user comprises:
acquiring information data in the health record of the current user;
inputting the information data in the health record of the current user into a decision table as an input item;
judging whether the attribute of the detection item set to which the input item belongs has an incidence relation with a specified output item set in a database, wherein the number of the specified output item set is one or more than one;
and forming question output of the intelligent question and answer sheet corresponding to the current user according to the matching strategy priority of the appointed output item set.
7. The method of generating a user representation according to claim 1, wherein the step of generating a user representation based on the set of tags describing the health of the user, the risk probability assessment of the disease and the factor assessment of the disease comprises:
determining a target item to be monitored according to the user portrait at the current moment;
sending the target item to be monitored and the monitoring time period to a display end, wherein the display end is a display screen of the terminal corresponding to the user image at the current moment;
judging whether the uploaded data of the user is received in the monitoring time period;
if receiving uploaded data of a user, judging whether the uploaded data is new measurement data of the target project to be monitored;
and if the target item is the new measurement data of the target item to be monitored, updating the health evaluation report and the user portrait according to the new measurement data.
8. An apparatus for generating a user representation, comprising:
the acquisition module is used for acquiring physiological index data of a detected user;
the analysis module is used for analyzing the analysis result corresponding to each physiological index data through a medical model;
the first generation module is used for generating a health evaluation report from each analysis result through a data analysis model, wherein the health evaluation report comprises a label set describing the health of a user, risk probability evaluation of diseases and factor evaluation of causing diseases;
and the second generation module is used for generating a user portrait according to the label set for describing the health of the user, the risk probability evaluation of the disease and the factor evaluation of causing the disease.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011043086.8A CN112185561B (en) | 2020-09-28 | 2020-09-28 | User portrait generation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011043086.8A CN112185561B (en) | 2020-09-28 | 2020-09-28 | User portrait generation method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112185561A true CN112185561A (en) | 2021-01-05 |
| CN112185561B CN112185561B (en) | 2022-06-14 |
Family
ID=73946636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011043086.8A Active CN112185561B (en) | 2020-09-28 | 2020-09-28 | User portrait generation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112185561B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819548A (en) * | 2021-02-26 | 2021-05-18 | 泰康保险集团股份有限公司 | User portrait generation method and device, readable storage medium and electronic equipment |
| CN112908481A (en) * | 2021-03-18 | 2021-06-04 | 马尚斌 | Automatic personal health assessment and management method and system |
| CN113168919A (en) * | 2021-03-04 | 2021-07-23 | 曹庆恒 | System for performing health analysis by using personalized indexes and using method thereof |
| CN113643813A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Chronic disease follow-up supervision method and device based on artificial intelligence and computer equipment |
| CN113724878A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
| CN113782132A (en) * | 2021-08-31 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Dynamic updating method, device and medium for label information |
| CN114758781A (en) * | 2022-06-15 | 2022-07-15 | 武汉博科国泰信息技术有限公司 | Method, system and device for generating health portrait of user and storage medium |
| CN116092681A (en) * | 2023-03-28 | 2023-05-09 | 北京嘉和海森健康科技有限公司 | Method, system, electronic device and storage medium for determining health index score |
| CN116705337A (en) * | 2023-08-07 | 2023-09-05 | 山东第一医科大学第一附属医院(山东省千佛山医院) | Health data acquisition and intelligent analysis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150100344A1 (en) * | 2013-10-08 | 2015-04-09 | Chen Technology, Inc. | Patient health information analysis system |
| CN106446488A (en) * | 2015-08-07 | 2017-02-22 | 纬创资通股份有限公司 | Risk assessment system and data processing method |
| CN107273699A (en) * | 2017-07-07 | 2017-10-20 | 成都脉安科健生物科技有限公司 | Nutrition guide scheme acquisition methods, device and electronic equipment |
| CN107480721A (en) * | 2017-08-21 | 2017-12-15 | 上海中信信息发展股份有限公司 | A kind of ox only ill data analysing method and device |
-
2020
- 2020-09-28 CN CN202011043086.8A patent/CN112185561B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150100344A1 (en) * | 2013-10-08 | 2015-04-09 | Chen Technology, Inc. | Patient health information analysis system |
| CN106446488A (en) * | 2015-08-07 | 2017-02-22 | 纬创资通股份有限公司 | Risk assessment system and data processing method |
| CN107273699A (en) * | 2017-07-07 | 2017-10-20 | 成都脉安科健生物科技有限公司 | Nutrition guide scheme acquisition methods, device and electronic equipment |
| CN107480721A (en) * | 2017-08-21 | 2017-12-15 | 上海中信信息发展股份有限公司 | A kind of ox only ill data analysing method and device |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819548A (en) * | 2021-02-26 | 2021-05-18 | 泰康保险集团股份有限公司 | User portrait generation method and device, readable storage medium and electronic equipment |
| WO2022183460A1 (en) * | 2021-03-04 | 2022-09-09 | 曹庆恒 | System for performing health analysis by using personalized index, and use method thereof |
| CN113168919A (en) * | 2021-03-04 | 2021-07-23 | 曹庆恒 | System for performing health analysis by using personalized indexes and using method thereof |
| CN112908481A (en) * | 2021-03-18 | 2021-06-04 | 马尚斌 | Automatic personal health assessment and management method and system |
| CN112908481B (en) * | 2021-03-18 | 2024-04-16 | 马尚斌 | Automatic personal health assessment and management method and system |
| CN113643813A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Chronic disease follow-up supervision method and device based on artificial intelligence and computer equipment |
| CN113643813B (en) * | 2021-08-30 | 2024-07-09 | 平安医疗健康管理股份有限公司 | Chronic disease follow-up supervision method and device based on artificial intelligence and computer equipment |
| CN113782132B (en) * | 2021-08-31 | 2024-04-09 | 深圳平安智慧医健科技有限公司 | Dynamic updating method, device and medium of label information |
| CN113782132A (en) * | 2021-08-31 | 2021-12-10 | 平安国际智慧城市科技股份有限公司 | Dynamic updating method, device and medium for label information |
| CN113724878B (en) * | 2021-08-31 | 2024-05-10 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
| CN113724878A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
| CN114758781A (en) * | 2022-06-15 | 2022-07-15 | 武汉博科国泰信息技术有限公司 | Method, system and device for generating health portrait of user and storage medium |
| CN116092681A (en) * | 2023-03-28 | 2023-05-09 | 北京嘉和海森健康科技有限公司 | Method, system, electronic device and storage medium for determining health index score |
| CN116092681B (en) * | 2023-03-28 | 2023-08-08 | 北京嘉和海森健康科技有限公司 | Method, system, electronic device and storage medium for determining health index score |
| CN116705337A (en) * | 2023-08-07 | 2023-09-05 | 山东第一医科大学第一附属医院(山东省千佛山医院) | Health data acquisition and intelligent analysis method |
| CN116705337B (en) * | 2023-08-07 | 2023-10-27 | 山东第一医科大学第一附属医院(山东省千佛山医院) | Health data acquisition and intelligent analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112185561B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112185561B (en) | User portrait generation method and device and computer equipment | |
| Faust et al. | Automated detection of atrial fibrillation using long short-term memory network with RR interval signals | |
| CN104287706B (en) | A kind of health status real time monitor and diagnosis and treatment commending system | |
| Pappada et al. | Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes | |
| CN112365978B (en) | Method and device for establishing early risk assessment model of tachycardia event | |
| US8352408B2 (en) | System and methods for providing integrated wellness assessment | |
| CN109924965A (en) | A kind of cardiovascular and cerebrovascular rehabilitation training system | |
| CN112037922A (en) | Pathological data analysis method and device, computer equipment and storage medium | |
| US20220165417A1 (en) | Population-level gaussian processes for clinical time series forecasting | |
| Singh et al. | A unified non-linear approach based on recurrence quantification analysis and approximate entropy: application to the classification of heart rate variability of age-stratified subjects | |
| CN111951965B (en) | Panoramic health dynamic monitoring and predicting system based on time sequence knowledge graph | |
| CN113555107A (en) | Human body metabolic state quantitative management analysis system and method | |
| CN116864139A (en) | Disease risk assessment method, device, computer equipment and readable storage medium | |
| WO2023097780A1 (en) | Classification method and device for classifying patient‑ventilator asynchrony phenomenon in mechanical ventilation process | |
| US20210298625A1 (en) | System and method for detecting and predicting an occurrence of cardiac events from electrocardiograms | |
| CN113317783B (en) | Multimode personalized longitudinal and transverse calibration method | |
| Bahuguna et al. | Statistical Analysis and Prediction of Heart Disease Using Machine Learning | |
| CN114388089A (en) | Personal health management method and system based on artificial intelligence | |
| CN113990502A (en) | ICU heart failure prediction system based on heterogeneous graph neural network | |
| CN113057588A (en) | Disease early warning method, device, equipment and medium | |
| CN117379009B (en) | Early warning and monitoring system for critical cardiovascular and cerebrovascular diseases of old people in community | |
| Duchene et al. | An hybrid refinement methodology for multivariate simulation in home health telecare | |
| CN111883247B (en) | Analysis system for correlation between behavior data and medical outcome | |
| KR102380027B1 (en) | Patient health examination terminal using bio big-data visualization method | |
| Kaufman | Proportional-integral control in the evaluation of glucose homeostasis and Type 2 Diabetes |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220527 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |