CN112465231B - Method, apparatus and readable storage medium for predicting regional population health status - Google Patents
Method, apparatus and readable storage medium for predicting regional population health status Download PDFInfo
- Publication number
- CN112465231B CN112465231B CN202011385950.2A CN202011385950A CN112465231B CN 112465231 B CN112465231 B CN 112465231B CN 202011385950 A CN202011385950 A CN 202011385950A CN 112465231 B CN112465231 B CN 112465231B
- Authority
- CN
- China
- Prior art keywords
- population
- health state
- predicted
- health
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000003862 health status Effects 0.000 title claims description 167
- 230000036541 health Effects 0.000 claims abstract description 308
- 230000007704 transition Effects 0.000 claims abstract description 110
- 230000008859 change Effects 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 23
- 201000010099 disease Diseases 0.000 claims description 21
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 21
- 238000002372 labelling Methods 0.000 claims description 11
- 238000011084 recovery Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 17
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012546 transfer Methods 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 11
- 238000011156 evaluation Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 239000000654 additive Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses a regional population health state prediction method, a device and a readable storage medium, wherein the regional population health state prediction method comprises the following steps: the method comprises the steps of obtaining user data of an area to be predicted, carrying out overall health state recognition on the area to be predicted based on the user data to obtain overall health state data, further carrying out overall state transition probability prediction on the area to be predicted based on the overall health state data to obtain a health state transition decision model, and further generating a regional population health state prediction result based on population change data of the area to be predicted, the health state transition decision model and the overall health state data. In addition, the application also relates to a block chain technology, and user data of the area to be predicted can be stored in the block chain, so that the effect of predicting the population health state of the area can be improved.
Description
Technical Field
The present application relates to the field of medical technology, and in particular, to a method, device, and readable storage medium for predicting a health status of a regional population.
Background
With the continuous development of artificial intelligence and computer software, the application of artificial intelligence is more and more extensive, and in the field of medical technology, the health state of a single user is often evaluated based on a markov decision model.
Disclosure of Invention
The application mainly aims to provide a regional population health status prediction method, a device and a readable storage medium, and aims to solve the technical problem that the regional population health status prediction effect is poor in the prior art.
In order to achieve the above object, the present application provides a method for predicting a health status of a regional population, the method being applied to a device for predicting a health status of a regional population, the method comprising:
acquiring user data of an area to be predicted, and identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data;
based on the overall health state data, performing overall state transition probability prediction on the area to be predicted to obtain a health state transition decision model;
and generating a regional population health state prediction result based on the population change data of the region to be detected, the health state transition decision model and the overall health state data.
The present application further provides a device for predicting a health status of a population in a region, the device for predicting a health status of a population in a region is a virtual device, and the device for predicting a health status of a population in a region is applied to a device for predicting a health status of a population in a region, the device for predicting a health status of a population in a region includes:
the system comprises an identification module, a prediction module and a prediction module, wherein the identification module is used for acquiring user data of an area to be predicted, and identifying the overall health state of the area to be predicted based on the user data to acquire the overall health state data;
the prediction module is used for predicting the integral state transition probability of the area to be predicted based on the integral health state data to obtain a health state transition decision model;
and the generation module is used for generating a regional population health state prediction result based on the population change data of the region to be detected, the health state transition decision model and the overall health state data.
The present application further provides a device for predicting a health status of a population in a region, the device for predicting a health status of a population in a region being an entity device, the device for predicting a health status of a population in a region comprising: a memory, a processor, and a program of the regional population health status prediction method stored on the memory and executable on the processor, the program of the regional population health status prediction method when executed by the processor being operable to implement the steps of the regional population health status prediction method as described above.
The present application also provides a readable storage medium having stored thereon a program for implementing a method for predicting the health status of a population of a geographic area, the program implementing the method for predicting the health status of a population of a geographic area as described above when executed by a processor.
Compared with the technical means for predicting the health state of the population in the whole area based on the Markov model and the current health state data of each single user, the method, the device and the readable storage medium for predicting the health state of the population in the area have the advantages that after the user data of the area to be predicted is obtained, the overall health state of the area to be predicted is firstly identified based on the user data to obtain the overall health state data, so that the aim of converting the user data into the overall health state data of the area to be predicted is fulfilled, additionally, when the health state of the population in the whole area is predicted based on the Markov model and the current health state data of each single user in the prior art, the health state influence characteristic of the single user for prediction is used, and the prediction target is the overall health state of the area to be predicted, further, the characteristics used for prediction are not matched with the prediction target, further the prediction effect is poor, further the overall state transition probability prediction is carried out on the area to be predicted based on the overall health state data, so that the characteristic data used for decision analysis is matched with the prediction target of the overall health state of the area to be predicted, further a health state transition decision model with better prediction effect can be obtained, further population change data of the area to be detected, the health state transition decision model and the overall health state data are based, wherein the population change data comprises population birth rate, further the addition of the birth population rate as population characteristics on the basis of the health state transition decision model can be realized, and the matching degree of the characteristic data used for decision analysis and the prediction target of the overall health state of the area to be predicted is higher, the method can generate the prediction result of the population health state of the area with better prediction effect, and further overcome the technical defect that the prediction effect of the population health state of the area is poor due to the fact that the characteristics used for predicting the population health state of the area to be predicted are not matched with the prediction target when the health state of the population of the area is predicted based on the Markov model and the current health state data of each single user in the prior art, and the prediction target is the integral health state of the area to be predicted, and the prediction effect of the population health state of the area is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating a first embodiment of a method for predicting a population health status in a region of an application;
FIG. 2 is a schematic flow chart of a method for predicting the health status of a population in a region according to a second embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for predicting the health status of a population in a geographic area according to a second embodiment of the present invention;
fig. 4 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
The objectives, features, and advantages of the present application will be further described with reference to the accompanying drawings.
Detailed Description
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.
In a first embodiment of the method for predicting the health status of the regional population of the present application, referring to fig. 1, the method for predicting the health status of the regional population includes:
step S10, obtaining user data of an area to be predicted, and carrying out overall health state recognition on the area to be predicted based on the user data to obtain overall health state data;
in this embodiment, it should be noted that the area to be predicted is an area for performing overall health status evaluation on population of the area, where the area to be predicted includes a city, a cell, a town, and the like, where the overall health status of the population of the area is evaluated for the purpose of evaluating the overall health status of the population of the area to be detected, and is used to reflect medical insurance policy effect of the area to be detected, where the overall health status of the population of the area to be detected is better than the medical insurance policy effect of the area to be detected, where the overall health status may specifically represent prevalence rates of all population of the area to be detected for diseases and the like, the user data is user illness related characteristic data of all population of the area to be predicted, and is used to evaluate whether a user is a potential patient, for example, the age, sex, and existing medical history of the user and the like, and the potential patient is a target user whose illness probability exceeds a preset illness probability threshold but is not ill temporarily.
The method comprises the steps of obtaining user data of an area to be predicted, carrying out overall health state recognition on the area to be predicted based on the user data, obtaining overall health state data, specifically, obtaining illness related characteristic data of each population of the area to be predicted relative to a preset detection disease, inputting each illness related characteristic data into a preset area population classification model respectively, classifying target users corresponding to each illness related characteristic data based on the illness related characteristic data respectively, obtaining each health state type, wherein a health state type label is an identification of a health state type, the health state types comprise a non-potential illness risk type, a potential patient type, a death state type and the like, the non-potential illness risk type is the user type with illness probability lower than a preset illness probability threshold, the potential patient type is the user type with illness greater than or equal to a preset illness probability, the patient type is the user type with illness, the death state type is the death state type with illness due to illness, counting the number of population belonging to the health state types in the area to be predicted and the number of transition times of the population belonging to the health state in the area to be predicted, and the overall health state transition times between the other health state types, and counting the number of the other health state types, wherein the other health state types are not capable of being predicted area.
Further, the step of "acquiring the user data of the area to be predicted" in the step S10 further includes:
and acquiring user data of the area to be predicted from the block chain.
Specifically, for example, user data of a region to be predicted is extracted from a block of link points created by a worker in advance, and then, based on the user data, overall health state recognition is performed on the region to be predicted to obtain overall health state data.
In this embodiment, in order to ensure that the user data of the area to be predicted, which is required by the staff according to the actually applied service, is not erroneously modified or removed, the user data of the area to be predicted may be stored in a node of a block chain, so that not only the stability of the user data of the area to be predicted can be ensured, but also the response aggressiveness of the subsequent terminal device in extracting the user data of the area to be predicted can be ensured, and the accuracy of reading the user data of the area to be predicted can be ensured.
Step S20, based on the overall health state data, performing overall state transition probability prediction on the area to be predicted to obtain a health state transition decision model;
in this embodiment, it should be noted that the health state transition decision model is a decision model based on a markov chain, and is used for predicting the overall health state change condition of the population in the region to be predicted in a time span, that is, for predicting the change condition of the population number in each health state type in a time span.
Performing overall state transition probability prediction on the area to be predicted based on the overall health state data to obtain a health state transition decision model, specifically, obtaining state transition times between every two preset health state types in the overall health state data, further calculating state transition probabilities between every two preset health state types based on the state transition times and a preset state transition probability calculation formula to obtain a state transition probability matrix, and constructing the health state transition decision model by using the state transition probability matrix as a model parameter, wherein each bit value in the state transition probability matrix is the state transition probability of transferring from one health state type to another health state transition type, and the state transition probability matrix can use [ P [ P ] ] ij ]Where i is a row of the state transition probability matrix and j is a column of the state transition probability matrix. Wherein, the preset state transition probability calculation formula is as follows:
wherein i is in the value range of [0,n-1]Integer of (1), P ij Probability of state transition for transition from health state type i to health state type j, H ij Number of state transitions to transition from health state type i to health state type j, H ix Number of state transitions for transitioning from health state type i to health state type x, wherein0 represents a label of a type without potential disease risk, and n-1 represents a label of a death state type, wherein the closer the numerical value of the label of the state transition type is to 0, the lighter the disease degree of the user of the state transition type is, and the closer the numerical value of the label of the state transition type is to n-1, the heavier the disease degree of the user of the state transition type is.
The step of performing overall state transition probability prediction on the area to be predicted based on the overall health state data to obtain a health state transition decision model comprises the following steps:
step S21, determining the state transition times among the preset health state types based on the overall health state data;
step S22, generating state transition probability among the preset health state types based on the state transition times;
in this embodiment, based on each of the state transition times, a state transition probability between each of the preset health state types is generated, and specifically, for each of the preset health state types, the following steps are performed:
determining a to-be-transferred health state type and a transfer target health state type corresponding to the preset health state type, wherein the state transfer probability is a transfer probability of transferring the to-be-transferred health state type to the transfer target health state type, further calculating the sum of state transfer times of transferring the to-be-transferred health state type to each preset health state based on each state transfer time, determining a target state transfer time of transferring the to-be-transferred health state type to the transfer target health state type at each state transfer time, further calculating the quotient of the target state transfer time and the sum of the state transfer times, and obtaining the state transfer probability, wherein the state transfer times of transferring the to-be-transferred health state type to the self are times of not sending changes of the health state type.
And S23, generating the health state transition decision model based on the state transition probabilities.
In this embodiment, a state transition probability matrix is constructed based on each state transition probability, where the state transition probability matrix is a row corresponding to the type of the to-be-transferred health state, and the state transition probability matrix is a row corresponding to the type of the transfer target health state, and then the state transition probability matrix is used as the health state transition decision model.
And S30, generating a regional population health state prediction result based on the population change data of the region to be detected, the health state transition decision model and the overall health state data.
In this embodiment, it should be noted that the population change data is a birth rate of population of an area to be detected, and the health status prediction result of the population of the area can be represented by a health status evaluation index value, where the health status evaluation index value includes a disease prevalence rate, a disease detection rate, and the like of a disease.
Generating a regional population health status prediction result based on the population change data of the to-be-detected region, the health status transition decision model and the overall health status data, specifically, calculating a target population total of the to-be-predicted region after a preset time step based on the population birth rate and the current population total of the to-be-predicted region, further calculating a predicted population number belonging to each preset health status type after the preset time step based on the target population total, the population number belonging to each preset health status type and a status transition probability matrix, further calculating a health status evaluation index value based on each preset population number, and taking the health status evaluation index value as the regional population health status prediction result, for example, determining the patient population number of the patient type based on each preset population number, further calculating a prevalence rate as a health status evaluation index value based on the patient population number and the target population total, and further evaluating the medical insurance policy effect of the to-be-predicted region based on the health status evaluation index value.
Wherein the health state transition decision model comprises state transition probabilities between preset health state types, the population change data comprises population birth rates,
the step of generating the regional population health status prediction result based on the population change data of the region to be detected, the health status transition decision model and the overall health status data comprises the following steps:
step S31, determining the population number corresponding to each preset health state type based on the overall health state data;
in this embodiment, it should be noted that the population number is a population number belonging to the preset health status type at the current time point.
Step S32, predicting the predicted population number of each preset health state type after a preset unit time step length based on each state transition probability, each population number and the population birth rate;
in this embodiment, it should be noted that the sum of the population numbers is the current population number of the area to be predicted.
Predicting the predicted population number of each preset health state type after a preset unit time step based on each state transition probability, each population number and the population birth rate, and specifically, substituting each state transition probability, each population number and the population birth rate into a preset predicted population number calculation formula respectively to calculate the predicted population number belonging to each preset health state type after the preset unit time step, wherein the preset predicted population number calculation formula is as follows:
wherein, the time t is the current time point, the time t +1 is the time point after the current time point passes the preset unit time step length, P 0j As a state transition probability of a transition from a no potentially diseased risk type to a healthy state type j,
number of population belonging to the type of no potential risk of illness for time t, m t Is the current total population number at time t, B is the birth rate of the population, 1 to n-2 are type labels belonging to patient types with different degrees of illness, P ij For a state transition probability from health state type i to health state type j,
for the number of people belonging to health status type i at time t,
the predicted population number that belongs to health status type j at time t + 1.
Wherein each of the predetermined health status types includes a disease status, each of the population numbers includes a current non-disease population number, each of the predicted population numbers includes a predicted disease population number,
the step of predicting the predicted population number of each preset health state type after a preset unit time step based on each state transition probability, each population number and the population birth rate comprises:
step S321, calculating morbidity, mortality and recovery rate corresponding to the diseased state based on each state transition probability;
in this embodiment, it should be noted that the morbidity is a state transition probability from the non-potentially-diseased type and the potentially-diseased type to the patient type, and the mortality is a state transition probability from the non-mortality type to the mortality type, wherein the mortality includes a natural mortality from the non-potentially-diseased type and the potentially-diseased type and a disease mortality from the patient type to the mortality type, and the recovery is a state transition probability from the diseased type to the non-potentially-diseased type or the potentially-diseased type.
Step S322, calculating the number of newly-increased sick population after the preset unit time step length based on the morbidity, the population birth rate, the number of currently-unaffected population and the number of each population;
in this embodiment, based on the morbidity, the birth rate of the population, the number of currently unaffected population and the number of each population, the number of newly increased affected populations after the preset unit time step is calculated, specifically, the sum of the number of each population is calculated to obtain the number of currently total population, and then the birth rate of the population, the number of currently unaffected populations and the number of currently total population are substituted into a preset newly increased affected population number calculation formula to calculate the number of newly increased affected populations after the preset unit time step, where the preset newly increased affected population number calculation formula is as follows:
wherein m is 1 Is the newly increased number of patients, P D In order to be a measure of the incidence of disease,
m is the number of the currently unaffected population t Is the number of the currently unaffected population, B is the birth rate of the population, and P is D The value of (b) satisfies the following conditions:
wherein 1 to n-2 are each a signature for a patient type of different degree of illness, P D For the incidence, P 0j A state transition probability for transitioning from a non-diseased state type to a patient type, wherein the non-diseased state type comprises the non-potentially diseased risk type and the potentially diseased patient type.
Step S323, calculating the number of the patient mouths after the reduction after the preset unit time step length based on the mortality, the recovery rate and each population number;
in this embodiment, the mortality is a disease mortality due to disease death, and the number of patients who died after the reduction is the number of patients who died or recovered the remaining population of the patient type at time t.
Calculating the number of the reduced patient mouths after the preset unit time step length based on the death rate, the recovery rate and each population number, specifically, calculating the sum of each population number to obtain the current population number, substituting the disease death rate, the recovery rate and the current population number into a preset reduced patient mouth number calculation formula, and calculating the number of the reduced patient mouths after the preset unit time step length, wherein the preset reduced patient mouth number calculation formula is as follows:
wherein m is 2 M for said reduction of the number of patients' mouths t For the number of the currently non-diseased population,
population size, P, for time t belonging to health status type i 0j For the recovery rate, P i(n-1) Is the mortality rate.
And step S324, determining the predicted sick population number based on the newly increased sick population number and the reduced sick population number.
In this embodiment, the predicted diseased population number is determined based on the newly-added diseased population number and the reduced diseased patient population number, specifically, the sum of the newly-added diseased population number and the reduced diseased patient population number is calculated to obtain the predicted diseased population number, wherein the calculation formula of the predicted diseased population number is as follows:
wherein,
for the purpose of the prediction of the number of diseased population,
1 to n-2 are type labels for patient types of different degrees of morbidity, as are the number of predicted populations belonging to health status type i.
And step S33, generating a health state prediction result of the regional population based on each predicted population number.
In this embodiment, the health status prediction result of the regional population is generated based on each of the predicted population numbers, specifically, based on each of the predicted population numbers, the prediction of each of the predicted population numbers of the next preset unit time step is performed again until the variation width of the predicted population number of the remaining patient type in each of the obtained predicted population numbers is smaller than a preset variation width threshold value, the obtained each of the predicted population numbers is used as each of the target predicted population numbers, and based on each of the target predicted population numbers, a health status evaluation index value is calculated, and the health status evaluation index value is used as the health status prediction result of the regional population.
Wherein the step of generating the prediction of the health status of the population of the region based on each of the predicted population volumes comprises:
step S331, predicting each second predicted population number after the next preset unit time step length based on each predicted population number;
in this embodiment, each second predicted population number after the next preset unit time step is predicted based on each predicted population number, and specifically, each second predicted population number after the next preset unit time step is re-predicted based on each predicted population number, the state transition probability matrix, and the population birth rate.
Step S332 of calculating a predicted population variation range based on each of the second predicted population numbers and each of the predicted population numbers;
in this embodiment, the predicted population variation range is calculated based on each of the second predicted population numbers and each of the predicted population numbers, specifically, the predicted patient population number belonging to the patient type is selected from each of the predicted population numbers, the second predicted patient population number belonging to the patient type is selected from each of the second predicted population numbers, and the predicted population variation range is calculated based on the predicted patient population number and the second predicted patient population number.
Step S333, judging whether the predicted population variation amplitude is smaller than a preset population variation amplitude threshold value;
in this embodiment, it should be noted that the preset population variation amplitude threshold is a preset threshold for determining whether the population number of the patient type over the time length is stable.
In step S334, if yes, a region population health status index value is calculated based on each of the second predicted population numbers, and the region population health status index value is used as the region population health status prediction result.
In this embodiment, if so, calculating a region population health status index value based on each of the second predicted population numbers, and using the region population health status index value as the region population health status prediction result, specifically, if so, calculating a region population health status index value based on each of the second predicted population numbers, and using the region population health status index value as the region population health status prediction result, and if not, recalculating a target predicted population number belonging to each health status type after a next preset unit time step length based on each of the second predicted population numbers, the population birth rate, and the status transition probability matrix until a variation width of the population number belonging to the patient type in each target predicted population number is smaller than a preset population variation width threshold, calculating a region population health status index value based on each of the target predicted population numbers, and using the region population health status index value as the region population health status prediction result.
Compared with the technical means for predicting the health state of the population in the whole area based on the markov model and the current health state data of each single user, the method for predicting the health state of the population in the area provided by the embodiment firstly identifies the overall health state of the area to be predicted based on the user data after acquiring the user data of the area to be predicted to acquire the overall health state data, thereby achieving the purpose of converting the user data into the overall health state data of the area to be predicted, and additionally, it needs to be noted that when the health state of the population in the whole area is predicted based on the markov model and the current health state data of each single user in the prior art, the health state of the population in the area to be predicted is influenced by the health state of the single user for prediction, so that the prediction target is the overall health state of the area to be predicted, further, the characteristics used for prediction are not matched with the prediction target, further the prediction effect is poor, further the overall state transition probability prediction is carried out on the area to be predicted based on the overall health state data, so that the characteristic data used for decision analysis is matched with the prediction target of the overall health state of the area to be predicted, further a health state transition decision model with better prediction effect can be obtained, further population change data of the area to be detected, the health state transition decision model and the overall health state data are based, wherein the population change data comprises population birth rate, further the addition of the birth population rate as population characteristics on the basis of the health state transition decision model can be realized, and the matching degree of the characteristic data used for decision analysis and the prediction target of the overall health state of the area to be predicted is higher, the method can generate the prediction result of the population health state of the area with better prediction effect, and further overcome the technical defect that the prediction effect of the population health state of the area is poor due to the fact that the characteristics used for predicting the population health state of the area to be predicted are not matched with the prediction target when the health state of the population of the area is predicted based on the Markov model and the current health state data of each single user in the prior art, and the prediction target is the integral health state of the area to be predicted, and the prediction effect of the population health state of the area is improved.
Further, referring to fig. 2, in another embodiment of the present application, based on the first embodiment of the present application, each of the user data includes healthy user data, diseased user data, and diseased dead user data,
the step of identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data comprises the following steps:
step S11, respectively inputting the data of each healthy user into a preset label marking model so as to respectively identify the health state type of the healthy user corresponding to the data of each healthy user and obtain a target health state type label corresponding to each healthy user;
in this embodiment, it should be noted that the preset label labeling model is a preset machine learning model, and is configured to label population of an area to be predicted, where the target health status type label is an identifier of a health status type, the target health status type label at least includes a potential illness risk free type label and a potential patient type label, and the healthy user is population of the area to be predicted belonging to a non-illness user type.
Respectively inputting the data of each healthy user into a preset label marking model to respectively identify the health state type of the healthy user corresponding to the data of each healthy user, and obtaining a target health state type label corresponding to each healthy user, specifically, executing the following steps on the data of each healthy user:
inputting the healthy user data into a preset label labeling model, performing feature extraction on the healthy user data to obtain a feature extraction matrix corresponding to the healthy user data, then performing full connection on the feature extraction matrix to obtain classification vectors corresponding to the healthy user data, and then taking the classification labels in the classification vectors as target health state type labels of target users corresponding to the healthy user data.
The step of respectively performing health state type identification on the health users corresponding to the health user data to obtain the target health state type labels corresponding to the health users comprises the following steps:
step S111, respectively performing feature extraction on each healthy user data to obtain feature extraction results corresponding to each healthy user data;
in this embodiment, feature extraction is performed on each healthy user data to obtain a feature extraction result corresponding to each healthy user data, specifically, convolution and pooling alternation processing is performed on a user feature representation matrix corresponding to each healthy user data for a preset number of times to obtain a feature extraction matrix corresponding to each healthy user data, and each feature extraction matrix is used as each feature extraction result.
Step S112, respectively carrying out full connection on the feature extraction results to carry out health state classification on each healthy user so as to obtain a health state classification result corresponding to each healthy user;
in this embodiment, the feature extraction results are fully connected to classify the health status of each healthy user, so as to obtain a health status classification result corresponding to each healthy user, and specifically, the following steps are performed for each feature extraction result:
and carrying out full connection on the feature extraction matrix to obtain a full connection vector, wherein the full connection vector comprises health state classification information of the healthy user, and then the full connection vector is used as the health state classification result.
Step S113, labeling each healthy user based on each health status classification result, and obtaining each target health status type label.
In this embodiment, based on each health status classification result, label labeling is performed on each health user to obtain each target health status type label, specifically, each full-connection vector is mapped to a health status classification label within a preset value range, and each health status classification label is respectively assigned to a corresponding health user, so as to label each health user to obtain a target health status type label corresponding to each health user.
Step S12, classifying the target users corresponding to the user data based on the target health state type labels, the diseased user data and the diseased dead user data, and obtaining the overall health state data.
In this embodiment, based on each target health status type label, the diseased user data, and the diseased dead user data, target users corresponding to each user data are classified to obtain the overall health status data, specifically, based on each target health status type label, the diseased user data, and the diseased dead user data, health status classification is performed on each target user in an area to be predicted to obtain a health status classification result, where the health status classification result includes a type without a potential disease risk, a potential patient type, a patient type, and a death status type, and a population number belonging to each health status type and a state transition number between each two health status types in the health status classification result are collected, and then each population number and each state transition number are used as the overall health status data.
The embodiment provides a method for identifying the overall health state of an area to be predicted, namely, respectively inputting data of each healthy user into a preset label labeling model, so as to respectively identify the health state types of the healthy users corresponding to the data of each healthy user, thereby obtaining a target health state type label corresponding to each healthy user, and further classifying the target users corresponding to the data of each user based on the target health state type label, the data of the ill user and the data of the ill dead user, thereby obtaining the overall health state data, thereby achieving the purpose of converting the data of the users into the overall health state data of the area to be predicted In addition, the matching degree of the characteristic data used for decision analysis and the prediction target used as the overall health state of the area to be predicted is higher, the prediction result of the health state of the population in the area with better prediction effect can be generated, and further, the foundation is laid for overcoming the technical defect that when the health state of the population in the whole area is predicted based on the Markov model and the current health state data of each single user in the prior art, the diseased characteristic of the single user is used for prediction, the prediction target is the overall health state of the area to be predicted, and the characteristic used for prediction is not matched with the prediction target, so that the prediction effect is poorer.
Further, referring to fig. 3, based on the first embodiment of the present application, in another embodiment of the present application, the overall health status data corresponds to at least one health status influencing characteristic,
after the step of identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data, the method for predicting the population health state of the area further comprises the following steps:
step A10, inputting the overall health state data into a population health state prediction model of a preset area, and predicting the overall health state of the area to be predicted to obtain an overall health state prediction result;
in this embodiment, it should be noted that the overall health state data includes population age distribution data of an area to be predicted, current ratio of a diseased population, state transition probability data between health state types, and the like, and the corresponding health state influence characteristics include an age characteristic, a ratio characteristic of the diseased population, a health state transition frequency characteristic, and the like.
Inputting the overall health state data into a preset region population health state prediction model, performing overall health state prediction on the region to be predicted to obtain an overall health state prediction result, specifically, inputting a coding matrix corresponding to the overall health state data into the region population health state prediction model, performing feature extraction on the coding matrix to extract feature information in the coding matrix to obtain a feature extraction matrix, further performing full-joint vector on the feature extraction matrix, further mapping the full-joint vector to a value in a preset value range to obtain an overall health state prediction score, and taking the overall health state prediction score as the overall health state prediction result.
Step A20, performing model prediction and interpretation on the overall health state prediction result to calculate the feature contribution degree of each health state influence feature to the overall health state prediction result;
in this embodiment, it should be noted that the feature contribution degree is a degree of influence of the health status impact feature on the overall health status prediction result, where the feature contribution degree includes a positive feature contribution degree and a negative feature contribution degree, the positive feature contribution degree represents a positive influence on the overall health status prediction result, that is, supports a decision of the preset regional population health status prediction model for making the overall health status prediction result, and the negative feature contribution degree represents a negative influence on the overall health status prediction result, that is, opposes the preset regional population health status prediction model for making the decision of the overall health status prediction result.
Performing Model predictive interpretation on the overall health state prediction result to calculate a feature contribution degree of each health state influence feature to the overall health state prediction result, and specifically, based on the preset regional population health state prediction Model, calculating a feature contribution degree of each health state influence feature to the overall health state prediction result respectively in a preset feature contribution degree calculation mode, where the preset feature contribution degree calculation mode includes a SHAP (SHAP adaptive Additive explicit models interpretation) and a LIME (Local interactive Model-Additive models interpretation) and the like.
Step A30, determining a target health state influence factor in each health state influence characteristic based on each characteristic contribution degree;
in this embodiment, a target health status influencing factor is determined among the health status influencing factors based on the feature contribution degrees, and specifically, the health status influencing factor corresponding to the feature contribution degree with the largest absolute value is selected as the target health status influencing factor among the feature contribution degrees.
And A40, adjusting the medical insurance policy of the area to be predicted based on the target health state influence factors.
In this embodiment, it should be noted that the target health status influencing factor is a health status influencing feature that has the largest influence on the overall health status prediction result, and based on the target health status influencing factor, the medical insurance policy of the area to be predicted may be adjusted to improve the overall health status of the area to be predicted, for example, assuming that the target health status influencing factor is a population ratio feature, feature data corresponding to the population ratio feature is an elderly population ratio of the area to be predicted, and the overall health status prediction result is that the overall health status score of the area to be predicted is low, that is, the overall health status prediction result is an overall health status deviation, and a feature contribution degree corresponding to an age feature is a positive feature contribution degree, so that it is known that the overall health status deviation of the area to be predicted is caused by an excessively high elderly population ratio, and further, the medical insurance policy of the area to be predicted may be adjusted to be biased toward elderly population insurance, so as to achieve the purpose of improving the overall health status score of the area to be predicted to be low.
The embodiment provides a regional population health state prediction method based on model interpretation, that is, the overall health state data is input into a preset regional population health state prediction model, the regional to be predicted is subjected to overall health state prediction, an overall health state prediction result is obtained, then the overall health state prediction result is subjected to model prediction interpretation, so as to calculate the feature contribution degree of each health state influence feature to the overall health state prediction result, and thus the purpose of analyzing factors influencing the overall health state of the regional to be predicted is achieved, the reasons causing the overall health state prediction result can be explained, the confidence of the overall health state prediction result is higher, further, based on each feature contribution degree, a target health state influence factor is determined in each health state influence feature, the purpose of the factor influencing the overall health state of the regional to be predicted to the greatest extent can be achieved, further, based on the target health state influence factor, the medical insurance policy of the regional to be predicted is adjusted, and further, the purpose of specifically adjusting the medical insurance policy of the regional to be predicted can be achieved, and further, the purpose of improving the overall health state level of the regional to be predicted can be achieved.
Referring to fig. 4, fig. 4 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 4, the regional population health status prediction apparatus may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the regional population health status prediction device may further include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuitry, a sensor, audio circuitry, a WiFi module, and so on. The rectangular user interface may comprise a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the configuration of the regional population health status prediction device shown in fig. 4 does not constitute a limitation of the regional population health status prediction device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 4, the memory 1005, which is a type of computer storage medium, may include an operating system, a network communication module, and a regional population health status prediction program. The operating system is a program that manages and controls the local population health status prediction device hardware and software resources, supporting the operation of the local population health status prediction program as well as other software and/or programs. The network communication module is used to implement communication between the various components within the memory 1005 and with other hardware and software in the regional population health status prediction system.
In the device for predicting the health status of a local population shown in fig. 4, the processor 1001 is configured to execute a program for predicting the health status of a local population stored in the memory 1005, and implement the steps of the method for predicting the health status of a local population according to any one of the above-mentioned embodiments.
The specific implementation of the device for predicting the health status of the population in the area is basically the same as that of each embodiment of the method for predicting the health status of the population in the area, and is not described herein again.
The embodiment of the present application further provides a device for predicting a health status of a population in a region, where the device for predicting a health status of a population in a region is applied to a device for predicting a health status of a population in a region, and the device for predicting a health status of a population in a region includes:
the identification module is used for acquiring user data of an area to be predicted, and carrying out overall health state identification on the area to be predicted based on the user data to obtain overall health state data;
the prediction module is used for predicting the integral state transition probability of the area to be predicted based on the integral health state data to obtain a health state transition decision model;
and the generation module is used for generating a regional population health state prediction result based on the population change data of the region to be detected, the health state transition decision model and the overall health state data.
Optionally, the generating module includes:
the first determining unit is used for determining the population number corresponding to each preset health state type based on the overall health state data;
a prediction unit, configured to predict, based on each state transition probability, each population number, and the population birth rate, a predicted population number of each preset health state type after a preset unit time step;
and a second generation unit configured to generate a prediction result of the health status of the regional population based on each of the predicted population quantities.
Optionally, the prediction unit comprises:
a first calculating subunit, configured to calculate, based on each of the state transition probabilities, a morbidity rate, a mortality rate, and a recovery rate corresponding to the diseased state;
the second calculating subunit is used for calculating the newly increased sick population number after the preset unit time step length based on the morbidity, the population birth rate, the current sick population number and each population number;
a third calculating subunit, configured to calculate, based on the mortality rate, the recovery rate, and each of the population numbers, the number of patients suffering from reduction after the preset unit time step is performed;
and the determining subunit is used for determining the predicted diseased population number based on the newly increased diseased population number and the reduced diseased population number.
Optionally, the generating unit includes:
the predicting subunit is used for predicting each second predicted population number after the next preset unit time step length based on each predicted population number;
a fourth calculating subunit, configured to calculate a predicted population variation range based on each of the second predicted population numbers and each of the predicted population numbers;
the judging subunit is used for judging whether the predicted population variation amplitude is smaller than a preset population variation amplitude threshold value or not;
and if so, calculating a region population health state index value based on each second predicted population number, and taking the region population health state index value as the region population health state prediction result.
Optionally, the prediction module comprises:
the second determining unit is used for determining the state transition times among all preset health state types based on the overall health state data;
a second generation unit, configured to generate a state transition probability between the preset health state types based on each of the state transition times;
a third generating unit, configured to generate the health state transition decision model based on each of the state transition probabilities.
Optionally, the identification module comprises:
the label labeling unit is used for respectively inputting the data of each healthy user into a preset label labeling model so as to respectively identify the health state type of the healthy user corresponding to the data of each healthy user and obtain a target health state type label corresponding to each healthy user;
and the classification unit is used for classifying the target users corresponding to the user data based on the target health state type labels, the diseased user data and the diseased dead user data to obtain the overall health state data.
Optionally, the tag labeling unit includes:
the characteristic extraction subunit is used for respectively extracting the characteristics of the healthy user data to obtain characteristic extraction results corresponding to the healthy user data;
the full-connection subunit is used for respectively performing full connection on the feature extraction results so as to classify the health state of each healthy user and obtain a health state classification result corresponding to each healthy user;
and the label labeling subunit is used for labeling the labels of the health users respectively based on the health state classification results to obtain the target health state type labels.
Optionally, the apparatus for predicting the health status of the population in the region further comprises:
the health state prediction module is used for inputting the overall health state data into a preset area population health state prediction model, and performing overall health state prediction on the area to be predicted to obtain an overall health state prediction result;
the model interpretation module is used for carrying out model prediction interpretation on the overall health state prediction result so as to calculate the feature contribution degree of each health state influence feature to the overall health state prediction result;
a determination module, configured to determine a target health status influencing factor in each health status influencing feature based on each feature contribution degree;
and the adjusting module is used for adjusting the medical insurance policy of the area to be predicted based on the target health state influence factors.
The specific implementation of the device for predicting the health status of the population in the area is basically the same as that of each embodiment of the method for predicting the health status of the population in the area, and is not described herein again.
The embodiment of the application provides a readable storage medium, and the readable storage medium stores one or more programs, which can be further executed by one or more processors for implementing the steps of the regional population health status prediction method described in any one of the above.
The specific implementation of the readable storage medium of the present application is substantially the same as the embodiments of the method for predicting the population health status in the region, and is not described herein again.
It should be noted that the blockchain referred to in this application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
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 equivalent structures or equivalent processes, which are directly or indirectly applied to other related technical fields, and which are not limited by the present application, are also included in the scope of the present application.
Claims (9)
1. A regional population health status prediction method is characterized by comprising the following steps:
acquiring user data of an area to be predicted, and identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data;
determining the state transition times among preset health state types based on the overall health state data, generating the state transition probability among the preset health state types according to the state transition times, constructing a state transition probability matrix according to the state transition probability, and taking the state transition probability matrix as a health state transition decision model which is a decision model based on a Markov chain;
generating a regional population health state prediction result based on the population change data of the region to be predicted, the health state transition decision model and the overall health state data;
the overall health state data is the prevalence rate of all population of the area to be predicted for diseases, the user data is the user prevalence associated characteristic data of all population of the area to be predicted, and the health state types comprise a non-potential prevalence risk type, a potential patient type, a patient type and a death state type.
2. The method of predicting the health status of a population in a geographic area of claim 1, wherein the health status transition decision model comprises a probability of a state transition between preset health status types, wherein the population change data comprises a population birth rate,
the step of generating the regional population health status prediction result based on the population change data of the region to be predicted, the health status transition decision model and the overall health status data comprises:
determining the population number corresponding to each preset health state type based on the overall health state data;
predicting the predicted population number of each preset health state type after a preset unit time step length based on each state transition probability, each population number and the population birth rate;
and generating a prediction result of the health state of the population in the region based on each predicted population number.
3. The method of predicting the health status of a population in a geographic area of claim 2, wherein each of the predetermined health status types includes a disease status, each of the population quantities includes a current non-disease population quantity, each of the predicted population quantities includes a predicted disease population quantity,
the step of predicting the predicted population number of each preset health state type after a preset unit time step based on each state transition probability, each population number and the population birth rate comprises:
calculating morbidity, mortality and recovery rate corresponding to the diseased state based on each state transition probability;
calculating the number of newly-increased sick population after the preset unit time step length based on the morbidity, the population birth rate, the number of undiseased population and the population number;
calculating the number of the patient mouths after reduction after the preset unit time step length based on the mortality rate, the recovery rate and each population number;
and determining the predicted diseased population number based on the newly increased diseased population number and the reduced diseased population number.
4. The method for predicting the health status of the population of claim 2, wherein the step of generating the prediction of the health status of the population of the region based on each of the predicted population quantities comprises:
predicting each second predicted population number after the next preset unit time step length based on each predicted population number;
calculating a predicted population variation range based on each of the second predicted population quantities and each of the predicted population quantities;
judging whether the predicted population variation amplitude is smaller than a preset population variation amplitude threshold value or not;
if so, calculating a region population health state index value based on each second predicted population number, and taking the region population health state index value as a region population health state prediction result.
5. The method of predicting the health status of a population in a geographic area of claim 1, wherein each of said user data includes healthy user data, sick user data, and sick-dead user data,
the step of identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data comprises the following steps:
respectively inputting the data of each healthy user into a preset label marking model so as to respectively identify the health state type of the healthy user corresponding to the data of each healthy user and obtain a target health state type label corresponding to each healthy user;
classifying the target users corresponding to the user data based on the target health state type labels, the diseased user data and the diseased dead user data to obtain the overall health state data.
6. The method for predicting the population health status of the area according to claim 5, wherein the step of respectively performing health status type identification on the healthy users corresponding to the data of each healthy user to obtain the target health status type label corresponding to each healthy user comprises:
respectively carrying out feature extraction on each healthy user data to obtain a feature extraction result corresponding to each healthy user data;
respectively carrying out full connection on the feature extraction results to classify the health state of each health user to obtain a health state classification result corresponding to each health user;
and labeling labels for the health users respectively based on the health state classification results to obtain the target health state type labels.
7. The method of predicting the health status of a population of a geographic area of claim 1, wherein the overall health status data corresponds to at least one health status impact characteristic,
after the step of identifying the overall health state of the area to be predicted based on the user data to obtain the overall health state data, the method for predicting the population health state of the area further comprises the following steps:
inputting the overall health state data into a population health state prediction model of a preset area, and predicting the overall health state of the area to be predicted to obtain an overall health state prediction result;
performing model prediction interpretation on the overall health state prediction result to calculate the feature contribution degree of each health state influence feature to the overall health state prediction result;
determining a target state of health influencing factor in each of the state of health influencing features based on each of the feature contribution degrees;
and adjusting the medical insurance policy of the area to be predicted based on the target health state influence factors.
8. A regional population health status prediction device, the regional population health status prediction device comprising: a memory, a processor, and a program stored on the memory for implementing the method for predicting a state of population health in a region,
the memory is used for storing a program for realizing the regional population health state prediction method;
the processor is configured to execute a program implementing the method for predicting the health status of the population of the region, so as to implement the steps of the method for predicting the health status of the population of the region according to any one of claims 1 to 7.
9. A readable storage medium having stored thereon a program for implementing a method for predicting a health status of a population of a region, the program being executable by a processor to implement the steps of the method for predicting a health status of a population of a region according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011385950.2A CN112465231B (en) | 2020-12-01 | 2020-12-01 | Method, apparatus and readable storage medium for predicting regional population health status |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011385950.2A CN112465231B (en) | 2020-12-01 | 2020-12-01 | Method, apparatus and readable storage medium for predicting regional population health status |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465231A CN112465231A (en) | 2021-03-09 |
| CN112465231B true CN112465231B (en) | 2023-02-03 |
Family
ID=74805200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011385950.2A Active CN112465231B (en) | 2020-12-01 | 2020-12-01 | Method, apparatus and readable storage medium for predicting regional population health status |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465231B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160987B (en) * | 2021-04-28 | 2023-08-22 | 平安科技（深圳）有限公司 | Health state prediction method, apparatus, computer device and storage medium |
| CN115862888B (en) * | 2023-02-17 | 2023-05-16 | 之江实验室 | Method, system, device and storage medium for predicting infection condition of infectious disease |
| CN116884611B (en) * | 2023-07-11 | 2024-02-13 | 浙江万航信息科技有限公司 | Teenager physical health intervention method and device, storage medium and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462858A (en) * | 2014-12-30 | 2015-03-25 | 天津迈沃医药技术有限公司 | Health warning method based on multi-order hidden Markov model |
| CN105701330A (en) * | 2014-11-28 | 2016-06-22 | 薛海强 | Health information processing method and system |
| CN107910068A (en) * | 2017-11-29 | 2018-04-13 | 平安健康保险股份有限公司 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
| CN109712712A (en) * | 2018-12-13 | 2019-05-03 | 平安医疗健康管理股份有限公司 | A kind of health evaluating method, health evaluating device and computer readable storage medium |
| CN110752035A (en) * | 2019-09-06 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Health data processing method and device, computer equipment and storage medium |
| CN110826786A (en) * | 2019-10-28 | 2020-02-21 | 广州杰赛科技股份有限公司 | Method and device for predicting number of target place population and storage medium |
| CN111009328A (en) * | 2019-12-25 | 2020-04-14 | 新绎健康科技有限公司 | Regional population health condition assessment method and device |
| CN111652461A (en) * | 2020-04-13 | 2020-09-11 | 北京航空航天大学 | Aero-engine continuous health state evaluation method based on SAE-HMM |
| CN111798978A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | User health assessment method and device, storage medium and electronic equipment |
| CN111816312A (en) * | 2020-09-14 | 2020-10-23 | 杭州憶盛医疗科技有限公司 | Health state detection method and equipment based on model interpretation and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160365006A1 (en) * | 2015-06-11 | 2016-12-15 | Paul Ash Minturn | Quantified Well-Being Evaluations, Improvement Programs and Scientific Wellness Video Games |
| CN106407643A (en) * | 2016-08-03 | 2017-02-15 | 无锡金世纪国民体质与健康研究有限公司 | Method for establishing health risk assessment system |
| CN110265145A (en) * | 2019-05-21 | 2019-09-20 | 何泽仪 | A kind of personal health methods of risk assessment, device, electronic equipment and storage medium |
-
2020
- 2020-12-01 CN CN202011385950.2A patent/CN112465231B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701330A (en) * | 2014-11-28 | 2016-06-22 | 薛海强 | Health information processing method and system |
| CN104462858A (en) * | 2014-12-30 | 2015-03-25 | 天津迈沃医药技术有限公司 | Health warning method based on multi-order hidden Markov model |
| CN107910068A (en) * | 2017-11-29 | 2018-04-13 | 平安健康保险股份有限公司 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
| CN109712712A (en) * | 2018-12-13 | 2019-05-03 | 平安医疗健康管理股份有限公司 | A kind of health evaluating method, health evaluating device and computer readable storage medium |
| CN111798978A (en) * | 2019-04-09 | 2020-10-20 | Oppo广东移动通信有限公司 | User health assessment method and device, storage medium and electronic equipment |
| CN110752035A (en) * | 2019-09-06 | 2020-02-04 | 深圳壹账通智能科技有限公司 | Health data processing method and device, computer equipment and storage medium |
| CN110826786A (en) * | 2019-10-28 | 2020-02-21 | 广州杰赛科技股份有限公司 | Method and device for predicting number of target place population and storage medium |
| CN111009328A (en) * | 2019-12-25 | 2020-04-14 | 新绎健康科技有限公司 | Regional population health condition assessment method and device |
| CN111652461A (en) * | 2020-04-13 | 2020-09-11 | 北京航空航天大学 | Aero-engine continuous health state evaluation method based on SAE-HMM |
| CN111816312A (en) * | 2020-09-14 | 2020-10-23 | 杭州憶盛医疗科技有限公司 | Health state detection method and equipment based on model interpretation and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 黄枫.基于转移概率模型的老年人长期护理需求预测分析.《经济研究》.2012,第119-129页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465231A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465231B (en) | Method, apparatus and readable storage medium for predicting regional population health status | |
| WO2021017679A1 (en) | Address information parsing method and apparatus, system and data acquisition method | |
| CN112084383B (en) | Knowledge graph-based information recommendation method, device, equipment and storage medium | |
| WO2018108129A1 (en) | Method and apparatus for use in identifying object type, and electronic device | |
| CN109145245A (en) | Predict method, apparatus, computer equipment and the storage medium of clicking rate | |
| CN111739657A (en) | Epidemic infected person prediction method and system based on knowledge graph | |
| WO2023024411A1 (en) | Association rule assessment method and apparatus based on machine learning | |
| CN111800289B (en) | Communication network fault analysis method and device | |
| CN109948735A (en) | A kind of multi-tag classification method, system, device and storage medium | |
| CN113707323A (en) | Disease prediction method, device, equipment and medium based on machine learning | |
| CN116934385A (en) | Construction method of user loss prediction model, user loss prediction method and device | |
| CN115545103A (en) | Abnormal data identification method, label identification method and abnormal data identification device | |
| CN112420125A (en) | Molecular attribute prediction method and device, intelligent equipment and terminal | |
| CN109871866B (en) | Model training method, device, equipment and medium for hospital infection prediction | |
| CN116959099B (en) | Abnormal behavior identification method based on space-time diagram convolutional neural network | |
| CN116468043A (en) | Nested entity identification method, device, equipment and storage medium | |
| CN114360732B (en) | Medical data analysis method, device, electronic equipment and storage medium | |
| CN116502705A (en) | Knowledge distillation method and computer equipment for dual-purpose data set inside and outside domain | |
| CN113706019B (en) | Service capability analysis method, device, equipment and medium based on multidimensional data | |
| CN113537407B (en) | Image data evaluation processing method and device based on machine learning | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN114970727A (en) | Multi-label text classification method and system and computer equipment | |
| WO2021114626A1 (en) | Method for detecting quality of medical record data and related device | |
| CN114297235A (en) | Risk address identification method and system and electronic equipment | |
| JP2022129430A (en) | Assessment program, assessment method, and information processing device |
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 |
Effective date of registration: 20220524 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, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |