CN107910068A - Insure health risk Forecasting Methodology, device, equipment and the storage medium of user - Google Patents
Insure health risk Forecasting Methodology, device, equipment and the storage medium of user Download PDFInfo
- Publication number
- CN107910068A CN107910068A CN201711222721.7A CN201711222721A CN107910068A CN 107910068 A CN107910068 A CN 107910068A CN 201711222721 A CN201711222721 A CN 201711222721A CN 107910068 A CN107910068 A CN 107910068A
- Authority
- CN
- China
- Prior art keywords
- user
- health
- health risk
- risk
- insures
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of health risk Forecasting Methodology, device, equipment and the storage medium of the user that insures, the described method includes：Obtain the individual health data information of the user to be predicted that insures and information of insuring；The individual health data information is extracted by preset rules, obtains target health characteristics data；According to the information of insuring, corresponding target health risk prediction model is determined from advance trained health risk prediction model；The target health characteristics data are sent in the target health risk prediction model, to obtain the corresponding health risk probability of the user to be predicted that insures；By determining corresponding target health risk prediction model thus according to health risk prediction model trained in advance, and calculate health risk probability, so as to relatively accurately determine the corresponding health risk grade of the user to be predicted that insures according to information of insuring, while ensure that health risk prediction effect, the workload of staff is also mitigated.
Description
Technical field
The present invention relates to data analysis technique field, more particularly to a kind of health risk Forecasting Methodology for the user that insures, dress
Put, equipment and storage medium.
Background technology
Insurance industry especially health insurance (using the body of insurant as insurance subject, make insurant in disease or
The expense or loss occurred during injury caused by contingency obtains a kind of insurance of compensation) in business, insurance company generally requires
The health risk for the user that insures is predicted, so as to judge the following Claims Resolution probability or number being likely to occur.
At present, insurance company usually relies on core guarantor, the personal experience of quotation personnel, medical knowledge, actuarial/statistical knowledge,
The past Claims Resolution information to the user that insured is analyzed, is judged that it is pre- then to carry out health risk to the user that insures to be predicted
Survey, but this prediction mode center is protected, the factor and individual subjective factor accounting of quotation personnel is higher, and the accuracy of prediction is relatively low.
The above is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that the above is existing skill
Art.
The content of the invention
It is a primary object of the present invention to provide a kind of health risk Forecasting Methodology for the user that insures, device, equipment and deposit
Storage media, it is intended to solve the prior art when the health risk to the user that insures is predicted, accuracy is relatively low, and effect is poor
Technical problem.
To achieve the above object, the present invention provides a kind of health risk Forecasting Methodology for the user that insures, the method bag
Include following steps:
Obtain the individual health data information of the user to be predicted that insures and information of insuring；
The individual health data information is extracted by preset rules, obtains target health characteristics data；
According to the information of insuring, corresponding target health wind is determined from advance trained health risk prediction model
Dangerous prediction model；
The target health characteristics data are sent in the target health risk prediction model, it is pre- to be treated described in acquisition
Survey is insured the corresponding health risk probability of user；
The corresponding healthy wind of the user to be predicted that insures is determined according to the health risk probability and the information of insuring
Dangerous grade.
Preferably, before the individual health data information for obtaining the user to be predicted that insures and information of insuring, the side
Method further includes：
The individual health data information of the user that insured of default quantity is obtained, is carried from the individual health data information
Take out the health characteristics data of preset kind；
Classified according to default classification of diseases rule to the health characteristics data, obtain different disease samples and
The corresponding sickness influence factor of each disease sample；
Preset model is carried out respectively according to different disease samples and the corresponding sickness influence factor of each disease sample
Training, obtains the corresponding health risk prediction model of each disease under various disease sample.
Preferably, it is described according to different disease samples and the corresponding sickness influence factor of each disease sample respectively to pre-
If model is trained, the corresponding health risk prediction model of each disease under various disease sample is obtained, is specifically included：
The corresponding sickness influence factor average value of each sickness influence factor in various disease sample is calculated respectively；
Survival rate of the corresponding sample population of each disease sample in different time points is obtained by presetting survival analysis method；
Preset model is trained according to the survival rate, the sickness influence factor and sickness influence factor average value,
Obtain the corresponding health risk prediction model of each disease under various disease sample.
Preferably, the preset model is：
Wherein, βiFor the corresponding regression coefficient of i-th of sickness influence factor；XiFor i-th of sickness influence factor；For disease
The average value of i-th of sickness influence factor in sick sample；S0(t) it is survival rate of the sample population in t time points；P is use to be predicted
Health risk probability of the family in t time points.
Preferably, the individual health data information of the user that insured for obtaining default quantity, from the personal health
The health characteristics data of preset kind are extracted in data message, are specifically included：
Obtain the individual health data information of the user that insured of default quantity；
The individual health data information is screened, using the user that insured with diseased history as targeted customer；
The health characteristics data of preset kind are extracted from the corresponding individual health data information of the targeted customer.
Preferably, it is described that the user couple to be predicted that insures is determined according to the health risk probability and the information of insuring
The health risk grade answered, specifically includes：
When the health risk probability exceedes predetermined probabilities, the user to be predicted that insures is determined as that excessive risk is used
Family；
The insured amount bought according to the excessive risk user described in acquisition of information that insures, exceedes pre- in the insured amount
If it is excessive risk Claims Resolution user by the excessive risk user's mark, to determine that the user to be predicted that insures is corresponding during the amount of money
Health risk grade.
Preferably, the insured amount that the excessive risk user described in acquisition of information of insuring described in the basis buys, in the guarantor
When the dangerous amount of money exceedes preset cost, by the excessive risk user's mark for excessive risk settle a claim user after, the method further includes：
The current individual health data information of the excessive risk Claims Resolution user is obtained every preset period of time；
According to the current individual health data information and the target health risk prediction model, the height is calculated
The current actual health risk probability of risk Claims Resolution user；
When the actual health risk probability is less than the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled
Note, and user's currently corresponding health risk grade to be predicted of insuring according to the actual health risk determine the probability.
In addition, to achieve the above object, the present invention also proposes the pre- measurement equipment of health risk of user that insures a kind of, described to set
It is standby to include：
The user's that insures that memory, processor and being stored in can be run on the memory and on the processor is strong
Health risk profile program, the health risk Prediction program of the user that insures be arranged for carrying out as described above insure user's
The step of health risk Forecasting Methodology.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, is stored with and insures on the storage medium
The health risk Prediction program of user, is realized as above when the health risk Prediction program of the user that insures is executed by processor
The step of health risk Forecasting Methodology of the user that insures.
In addition, to achieve the above object, the present invention also proposes a kind of health risk prediction meanss for the user that insures, the dress
Put including：
Data obtaining module, for the individual health data information for obtaining the user to be predicted that insures and information of insuring；
Information extraction modules, for being extracted by preset rules to the individual health data information, obtain target and are good for
Health characteristic；
Model chooses module, true from advance trained health risk prediction model for information of insuring according to
Fixed corresponding target health risk prediction model；
Risk profile module, for the target health characteristics data to be sent to the target health risk prediction model
In, to obtain the corresponding health risk probability of the user to be predicted that insures；
Risk evaluation module, for determining described to be predicted insure according to the health risk probability and the information of insuring
The corresponding health risk grade of user.
The present invention obtains the individual health data information of the user to be predicted that insures and information of insuring；By preset rules to described
Individual health data information is extracted, and obtains target health characteristics data；According to the information of insuring, from trained in advance
Corresponding target health risk prediction model is determined in health risk prediction model；The target health characteristics data are sent to
In the target health risk prediction model, to obtain the corresponding health risk probability of the user to be predicted that insures；According to institute
State health risk probability and the information of insuring determines the corresponding health risk grade of the user to be predicted that insures；So as to
It is relatively simple to determine corresponding health risk of the user to be predicted that insures etc. according to health risk probability and the information of insuring
Level, while ensure that health risk prediction effect accuracy, also mitigates the workload of staff.
Brief description of the drawings
Fig. 1 is the pre- measurement equipment of health risk of the user that insures for the hardware running environment that the embodiment of the present invention is related to
Structure diagram；
Fig. 2 is the flow diagram of the health risk Forecasting Methodology first embodiment of the user of the invention that insures；
Fig. 3 is the flow diagram of the health risk Forecasting Methodology second embodiment of the user of the invention that insures；
Fig. 4 is the flow diagram of the health risk Forecasting Methodology 3rd embodiment of the user of the invention that insures；
Fig. 5 is the structure diagram of the health risk prediction meanss first embodiment of the user of the invention that insures.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Embodiment
It should be appreciated that specific embodiment described herein is not intended to limit the present invention only to explain the present invention.
With reference to Fig. 1, the health risk that Fig. 1 is the user that insures for the hardware running environment that the embodiment of the present invention is related to is pre-
Measurement equipment structure diagram.
As shown in Figure 1, this is insured, the pre- measurement equipment of the health risk of user (the hereinafter referred to as pre- measurement equipment of health risk) can be with
Including：Processor 1001, such as CPU, communication bus 1002, user interface 1003, network interface 1004, memory 1005.Its
In, communication bus 1002 is used for realization the connection communication between these components.User interface 1003 can include display screen
(Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also connect including the wired of standard
Mouth, wave point.Network interface 1004 can optionally include standard wireline interface and wireless interface (such as WI-FI interfaces).Deposit
Reservoir 1005 can be high-speed RAM memory or the memory (non-volatile memory) of stabilization, such as magnetic
Disk storage.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
It will be understood by those skilled in the art that the structure shown in Fig. 1 does not form the limit to the pre- measurement equipment of health risk
It is fixed, it can include than illustrating more or fewer components, either combine some components or different components arrangement.
As shown in Figure 1, it can lead to as in a kind of memory 1005 of computer-readable storage medium including operating system, network
Believe module, Subscriber Interface Module SIM and the health risk Prediction program for the user that insures.
In the pre- measurement equipment of health risk shown in Fig. 1, network interface 1004 is mainly used for Connection Service device, with server
Into row data communication；User interface 1003 is mainly used for connecting client, with client into row data communication, the health risk
Pre- measurement equipment calls the health risk Prediction program of the user that insures stored in memory 1005 by processor 1001, and performs
Operate below：
Obtain the individual health data information of the user to be predicted that insures and information of insuring；
The individual health data information is extracted by preset rules, obtains target health characteristics data；
According to the information of insuring, corresponding target health wind is determined from advance trained health risk prediction model
Dangerous prediction model；
The target health characteristics data are sent in the target health risk prediction model, it is pre- to be treated described in acquisition
Survey is insured the corresponding health risk probability of user；
The corresponding healthy wind of the user to be predicted that insures is determined according to the health risk probability and the information of insuring
Dangerous grade.
Further, processor 1001 can call the pre- ranging of health risk of the user that insures stored in memory 1005
Sequence, also performs following operation：
The individual health data information of the user that insured of default quantity is obtained, is carried from the individual health data information
Take out the health characteristics data of preset kind；
Classified according to default classification of diseases rule to the health characteristics data, obtain different disease samples and
The corresponding sickness influence factor of each disease sample；
Preset model is carried out respectively according to different disease samples and the corresponding sickness influence factor of each disease sample
Training, obtains the corresponding health risk prediction model of each disease under various disease sample.
Further, processor 1001 can call the pre- ranging of health risk of the user that insures stored in memory 1005
Sequence, also performs following operation：
The corresponding sickness influence factor average value of each sickness influence factor in various disease sample is calculated respectively；
Survival rate of the corresponding sample population of each disease sample in different time points is obtained by presetting survival analysis method；
Preset model is trained according to the survival rate, the sickness influence factor and sickness influence factor average value,
Obtain the corresponding health risk prediction model of each disease under various disease sample.
Further, processor 1001 can call the pre- ranging of health risk of the user that insures stored in memory 1005
Sequence, also performs following operation：
Obtain the individual health data information of the user that insured of default quantity；
The individual health data information is screened, using the user that insured with diseased history as targeted customer；
The health characteristics data of preset kind are extracted from the corresponding individual health data information of the targeted customer.
Further, processor 1001 can call the pre- ranging of health risk of the user that insures stored in memory 1005
Sequence, also performs following operation：
When the health risk probability exceedes predetermined probabilities, the user to be predicted that insures is determined as that excessive risk is used
Family；
The insured amount bought according to the excessive risk user described in acquisition of information that insures, exceedes pre- in the insured amount
If it is excessive risk Claims Resolution user by the excessive risk user's mark, to determine that the user to be predicted that insures is corresponding during the amount of money
Health risk grade.
Further, processor 1001 can call the pre- ranging of health risk of the user that insures stored in memory 1005
Sequence, also performs following operation：
The current individual health data information of the excessive risk Claims Resolution user is obtained every preset period of time；
According to the current individual health data information and the target health risk prediction model, the height is calculated
The current actual health risk probability of risk Claims Resolution user；
When the actual health risk probability is less than the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled
Note, and user's currently corresponding health risk grade to be predicted of insuring according to the actual health risk determine the probability.
The present embodiment obtains target health characteristics by being extracted by preset rules to the individual health data information
Data；According to the information of insuring, corresponding target health risk is determined from advance trained health risk prediction model
Prediction model；The target health characteristics data are sent in the target health risk prediction model, to be treated described in acquisition
Predict the corresponding health risk probability of user of insuring；Treated according to determining the health risk probability and the information of insuring pre-
Survey is insured the corresponding health risk grade of user；It is relatively simple so as to according to health risk probability and the information of insuring
Determine the corresponding health risk grade of the user to be predicted that insures, ensure that the same of health risk prediction effect accuracy
When, also mitigate the workload of staff.
Based on above-mentioned hardware configuration, the health risk Forecasting Methodology embodiment of the proposition user of the invention that insures.
With reference to Fig. 2, Fig. 2 is the flow diagram of the health risk Forecasting Methodology first embodiment of the user of the invention that insures.
In the present embodiment, it the described method comprises the following steps：
Step S10：Obtain the individual health data information of the user to be predicted that insures and information of insuring；
It should be noted that the user to be predicted that insures can bought or Pre purchase health insurance or other classifications are protected
The user of danger；The individual health data information may include:Age, gender, physiological parameter (such as weight, blood group/blood pressure, the heart
Rate, lung capacity etc.), previously with regard to Biography of Medical Figures, familial inheritance medical history and occupation etc., essential information related to user's person.The throwing
It can be the information that user buys health insurance or the insurance of other classes to protect information, such as：The title of the insurer and insurant, insurance
Target, insured amount, insurance premium, insurance period, reparation or the Limitation on Liability of payment, history compensate record etc., certainly specific
The species for information of insuring can be set according to actual conditions, and the present embodiment is not any limitation as this.
In the concrete realization, the acquisition of the individual health data information and information of insuring can be by being carried out to user
Health Survey or according to being obtained in public security system, medical system and/or insurance system in the personal information of user.
Step S20：The individual health data information is extracted by preset rules, obtains target health characteristics number
According to；
It should be noted that the preset rules can be that individual subscriber health data information to be predicted of insuring is sieved
Choosing, with therefrom remove on health risk prediction result influence less or almost without influence information filtering rule or
The default information extraction list for being extracted to individual health data information, what specific information extraction list included
Information option or species, can be set according to actual conditions and additions and deletions, the present embodiment are not any limitation as this.
It should be understood that the target health characteristics data can reflect user's the past period to be predicted
The relevant data of physical condition, such as：Remove the number of hospital admission, the species of illnesses, nearly physical examination data several times,
The information datas such as age, occupation and familial inheritance disease.
In the concrete realization, can be by preset rules after the individual health data information of the user to be predicted that insures is got
The individual health data information is extracted, obtains target health characteristics data.
Step S30：According to the information of insuring, corresponding mesh is determined from advance trained health risk prediction model
Mark health risk prediction model；
It should be noted that the health risk model can be similar to the study mould for having supervision of supporting vector machine model
Type；It can also be analogous to the statistical models such as Cox proportional hazard models or Weibull regression models；Specific prediction model
Selection and training can be depending on actual conditions, the present embodiment is not any limitation as this.It is in addition, described in the present embodiment strong
Health risk forecast model for according to the health characteristics data of a large number of users are trained being capable of being good for user to be predicted
The model of health risk profile.In the present embodiment, different diseases is corresponding with corresponding health risk prediction model.
It will be appreciated that in the information of insuring of the user to be predicted that insures, insurance subject can generally indicate corresponding thing of insuring
, such as kinds of Diseases insured etc., therefore after the information of insuring is got, item of insuring that can be in information of insuring
Carry out from advance trained health risk prediction model to determine corresponding target health risk prediction model, such as：User throws
The disease of guarantor is heart disease, then can choose cardiopathic target health wind from advance trained health risk prediction model
Dangerous prediction model.
Step S40：The target health characteristics data are sent in the target health risk prediction model, to obtain
The corresponding health risk probability of the user to be predicted that insures.
In the present embodiment, the health risk probability can be user in current time (time point) or a period of time in future
It is interior generation health problem (such as：Sick, dead or unexpected injury etc.) probability.
Step S50：Determine that the user to be predicted that insures corresponds to according to the health risk probability and the information of insuring
Health risk grade.
It should be noted that health risk grade described in the present embodiment can be divided into excessive risk user, ordinary risk is used
Three ranks in family and low-risk user, the insured amount and risk subscribers of different stage can insure according to it in information
It is divided into high Claims Resolution user, common Claims Resolution user and low Claims Resolution three ranks of user, such as：Pass through the target of user A to be predicted
Health characteristics data and the health risk prediction model have calculated user A to be predicted may change high blood in following half a year
The probability for pressing disease was 80% (belonging to excessive risk user), and the insurance subject in the information of insuring of user A is personal insurance, and
Insured amount was 200,000 (belonging to high Claims Resolution user), then user A can be assert for excessive risk Claims Resolution user.Certainly, risk class with
The species division of Claims Resolution rank can be set according to actual conditions with judgment criteria, and the present embodiment is not any limitation as this.
In the concrete realization, the health risk probability of user to be predicted is being calculated according to the health risk prediction model
Afterwards, the corresponding health risk grade of the user to be predicted that insures can be determined with reference to the information of insuring of user to be predicted, with reality
Existing health risk prediction.
The present embodiment passes through the individual health data information for obtaining the user to be predicted that insures and information of insuring；By preset rules
The individual health data information is extracted, obtains target health characteristics data；The target health characteristics data are sent
Enter into advance trained health risk prediction model, it is general to obtain the corresponding health risk of the user to be predicted that insures
Rate；So as to according to health risk probability and the information of insuring, determine the user couple to be predicted that insures relatively simplely
The health risk grade answered, while ensure that health risk prediction effect accuracy, also mitigates the work of staff
Amount.
With reference to figure 3, Fig. 3 is the flow diagram of the health risk Forecasting Methodology second embodiment of the user of the invention that insures.
Based on above-mentioned first embodiment, the health risk Forecasting Methodology for the user that insures that the present embodiment proposes is in the step
Before S10, further include：
Step S01：The individual health data information of the user that insured of default quantity is obtained, from the individual health data
The health characteristics data of preset kind are extracted in information；
It should be noted that the user that insured is the user that have purchased various healthy class insurances.In order to ensure
The health risk prediction model subsequently obtained has higher accuracy rate, so as to improve the prediction level of health risk, is choosing
During model sample, model sample quantity can be determined according to actual conditions, such as：100000,500,000 or 1,000,000 etc..It is described default
Type can be pre-defined information category, such as：Physical examination data, age, medical treatment number, cost etc. of seeing a doctor, the present embodiment
This is not any limitation as.
It should be understood that see a doctor in numerous users that insured there may be a part in period insured without diseased
Record or the user for just buying insurance, and use meaning of the health characteristics data of these users that insure to model training is not
Greatly, it is contemplated that when carrying out model training, model sample quantity is larger, it is necessary to the individual subscriber collected and extracted under normal conditions
The scale of construction of health data information is also more huge, in order to ensure that the health characteristics data extracted are authentic and valid, in the present embodiment
Described in step S10 may particularly include：Obtain the individual health data information of the user that insured of default quantity；To the individual
Health data information is screened, using the user that insured with diseased history as targeted customer；Corresponded to from the targeted customer
Individual health data information in extract the health characteristics data of preset kind.
Step S02：Classified according to default classification of diseases rule to the health characteristics data, obtain different diseases
Sample and the corresponding sickness influence factor of each disease sample；
It should be noted that the default classification of diseases rule can be that the disease suffered to different user is classified
Rule, specific classifying rules can foundations《International Classification of Diseases》Or whole nation unification《In-patient classification of diseases》To make
Fixed, the present embodiment is not any limitation as this.
It will be appreciated that after the completion of corresponding classification of diseases rule (i.e. described default classification of diseases rule) is formulated, can
Classified according to the classification of diseases rule to the corresponding health characteristics data of the user that respectively insured, obtain different disease samples
(such as：Hypertension sample, hyperlipidemia sample, coronary heart disease sample etc.) and the corresponding sickness influence factor (example of each disease sample
Such as：Blood pressure, blood fat, heart rate, lung capacity etc.).
In a practical situation, the part user that insured may suffer from a variety of diseases, such as suffer from hypertension and hyperlipidemia
User, after the health characteristics data of this user are got, when carrying out classification of diseases, it is necessary to health characteristics by this kind of user
Data are included in hypertension sample and hyperlipidemia sample respectively, that is to say, that the health containing this user is special in hyperglycaemia sample
Data are levied, also health characteristics data containing this user in hyperlipidemia sample.
Step S03：According to different disease samples and the corresponding sickness influence factor pair preset model of each disease sample
It is trained, obtains the corresponding health risk prediction model of each disease under various disease sample；
, can be according to the corresponding sickness influence factor pair preset model of each disease sample after different disease samples is got
It is trained, obtains the corresponding health risk prediction model of each disease under various disease sample, such as：By hypertension sample with
And hypertension sample include the corresponding health risk prediction model of health characteristics data acquisition hypertension, by coronary heart disease sample
And corresponding health risk prediction model of health characteristics data acquisition coronary heart disease for including of coronary heart disease sample etc..
In the concrete realization, the step S03 may particularly include：Calculate each sickness influence factor in various disease sample
Corresponding sickness influence factor average value；The corresponding disease shadow of each sickness influence factor in various disease sample is calculated respectively
Ring factor average value；Existence of the corresponding sample population of each disease sample in different time points is obtained by presetting survival analysis method
Rate；Preset model is trained according to the survival rate, the sickness influence factor and sickness influence factor average value, is obtained not
The corresponding health risk prediction model with each disease under disease sample.
Further, it is contemplated that the health characteristics data of the user that insured got may be advised without certain distribution
Rule, preselects model selection to data distribution situation without desired model described in the present embodiment：
Wherein, βiFor the corresponding regression coefficient of i-th of sickness influence factor；XiFor i-th of sickness influence factor；For disease
The average value of i-th of sickness influence factor in sick sample；S0(t) it is survival rate of the sample population in t time points；P is use to be predicted
Health risk probability of the family in t time points.
The present embodiment presets the individual health data information of the user that insured of quantity by acquisition, from the personal health
The health characteristics data of preset kind are extracted in data message；According to default classification of diseases rule to the health characteristics data
Classify, obtain different disease samples and the corresponding sickness influence factor of each disease sample；According to different disease samples
This and the corresponding sickness influence factor of each disease sample are respectively trained preset model, obtain each under various disease sample
The corresponding health risk prediction model of disease, classifies health characteristics data by then passing through default classification of diseases rule,
Then it is directed to and all carries out model training per a kind of disease, obtains the corresponding health risk prediction mould of each disease under various disease sample
Type, so as to improve the reliability and accuracy of health risk prediction model prediction result.
With reference to figure 4, Fig. 4 is the flow diagram of the health risk Forecasting Methodology 3rd embodiment of the user of the invention that insures.
Based on the various embodiments described above, in the health risk Forecasting Methodology for the user that insures that the present embodiment proposes, the step
S50 may particularly include：
Step S501：When the health risk probability exceedes predetermined probabilities, the user to be predicted that insures is determined as
Excessive risk user；
Step S502：The insured amount bought according to the excessive risk user described in acquisition of information that insures, in the insurance
When the amount of money exceedes preset cost, the excessive risk user's mark is settled a claim user for excessive risk, to determine described to be predicted insure
The corresponding health risk grade of user.
It should be noted that the predetermined probabilities can set in advance judge whether user is the general of excessive risk user
Rate, when the health risk probability for finding user to be predicted exceedes the predetermined probabilities, then judgement user is excessive risk user, example
Such as：The predetermined probabilities are 60%, and the health risk probability for the user B for being computed drawing has exceeded described preset generally for 79%
Rate, then judge the user B for excessive risk user.
It is understood that since the age bracket for the user that insures, occupation, economic level are different, they buy
The insured amount bought during insurance is also not quite similar, and in order to further be distinguished to the excessive risk user crowd, facilitates industry
Business personnel intuitively and effectively confirm the grade belonging to each excessive risk user, and it is (i.e. pre- can also to preset an amount for which loss settled
If the amount of money) come to being determined as that the health risk grade of excessive risk user continues to divide.
In the concrete realization, by obtaining the information of insuring of excessive risk user, the insurance money of the excessive risk user is determined
Volume, then by the insured amount compared with the preset cost, when the insured amount exceedes preset cost, by described in
Excessive risk user's mark is excessive risk Claims Resolution user, to determine the corresponding health risk grade of the user to be predicted that insures.
Further, changing for physical condition may be brought due to the recovery of physical function for part excessive risk user
Kind, correspondingly health risk is greatly reduced, in order to be carried out in fact to the health risk grade of such excessive risk user as far as possible
When judge, the present embodiment method may also include after the step S501：The excessive risk is obtained every preset period of time
The current individual health data information of Claims Resolution user；It is pre- according to the current individual health data information and the health risk
Model is surveyed, calculates the current actual health risk probability of the excessive risk Claims Resolution user；In the actual health risk probability
During less than the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled, and according to the actual health risk probability
Determine user's currently corresponding health risk grade to be predicted of insuring.
The present embodiment is when the health risk probability calculated exceedes predetermined probabilities, by the user to be predicted that insures
It is determined as excessive risk user；The insured amount bought according to the excessive risk user described in acquisition of information that insures, in the insurance
When the amount of money exceedes preset cost, it is excessive risk Claims Resolution user by the excessive risk user's mark, is treated so as to realize to each
The corresponding health risk grade of prediction user is accurately divided.
With reference to Fig. 5, Fig. 5 is the structure diagram of the health risk prediction meanss first embodiment of the user of the invention that insures.
As shown in figure 5, the health risk prediction meanss 101 for the user that insures that the present embodiment proposes include：
Data obtaining module 1011, for the individual health data information for obtaining the user to be predicted that insures and information of insuring；
It should be noted that the user to be predicted that insures can bought or Pre purchase health insurance or other classifications are protected
The user of danger；The individual health data information may include:Age, gender, physiological parameter (such as weight, blood group/blood pressure, the heart
Rate, lung capacity etc.), previously with regard to Biography of Medical Figures, familial inheritance medical history and occupation etc., essential information related to user's person.The throwing
It can be the information that user buys health insurance or the insurance of other classes to protect information, such as：The title of the insurer and insurant, insurance
Target, insured amount, insurance premium, insurance period, reparation or the Limitation on Liability of payment, history compensate record etc., certainly specific
The species for information of insuring can be set according to actual conditions, and the present embodiment is not any limitation as this.
In the concrete realization, the acquisition of the individual health data information and information of insuring can obtain mould by described information
Block 1011 to user by carrying out Health Survey or according to user in public security system, medical system and/or insurance system
Personal information in obtain.
Information extraction modules 1012, for being extracted by preset rules to the individual health data information, obtain mesh
Mark health characteristics data；
It should be noted that the preset rules can be that individual subscriber health data information to be predicted of insuring is sieved
Choosing, with therefrom remove on health risk prediction result influence less or almost without influence information filtering rule or
The default information extraction list for being extracted to individual health data information, what specific information extraction list included
Information option or species, can be set according to actual conditions and additions and deletions, the present embodiment are not any limitation as this.
It should be understood that the target health characteristics data can reflect user's the past period to be predicted
The relevant data of physical condition, such as：Remove the number of hospital admission, the species of illnesses, nearly physical examination data several times,
The information datas such as age, occupation and familial inheritance disease.
Model chooses module 1013, true from advance trained health risk prediction model according to the information of insuring
Fixed corresponding target health risk prediction model；
It should be noted that the health risk model can be similar to the study mould for having supervision of supporting vector machine model
Type；It can also be analogous to the statistical models such as Cox proportional hazard models or Weibull regression models；Specific prediction model
Selection and training can be depending on actual conditions, the present embodiment is not any limitation as this.It is in addition, described in the present embodiment strong
Health risk forecast model for according to the health characteristics data of a large number of users are trained being capable of being good for user to be predicted
The model of health risk profile.In the present embodiment, different diseases is corresponding with corresponding health risk prediction model.
It will be appreciated that in the information of insuring of the user to be predicted that insures, insurance subject can generally indicate corresponding thing of insuring
, such as kinds of Diseases insured etc., therefore after the information of insuring is got, item of insuring that can be in information of insuring
Carry out from advance trained health risk prediction model to determine corresponding target health risk prediction model, such as：User throws
The disease of guarantor is heart disease, then can choose cardiopathic target health wind from advance trained health risk prediction model
Dangerous prediction model.
Risk profile module 1014, is predicted for the target health characteristics data to be sent to the target health risk
In model, to obtain the corresponding health risk probability of the user to be predicted that insures；
In the present embodiment, the health risk probability can be user in current time (time point) or a period of time in future
It is interior generation health problem (such as：Sick, dead or unexpected injury etc.) probability.
Risk evaluation module 1015, it is described to be predicted for being determined according to the health risk probability and the information of insuring
The corresponding health risk grade of the user that insures.
It should be noted that health risk grade described in the present embodiment can be divided into excessive risk user, ordinary risk is used
Three ranks in family and low-risk user, the insured amount and risk subscribers of different stage can insure according to it in information
It is divided into high Claims Resolution user, common Claims Resolution user and low Claims Resolution three ranks of user, such as：Pass through the target of user A to be predicted
Health characteristics data and the health risk prediction model have calculated user A to be predicted may change high blood in following half a year
The probability for pressing disease was 80% (belonging to excessive risk user), and the insurance subject in the information of insuring of user A is personal insurance, and
Insured amount was 200,000 (belonging to high Claims Resolution user), then user A can be assert for excessive risk Claims Resolution user.Certainly, risk class with
The species division of Claims Resolution rank can be set according to actual conditions with judgment criteria, and the present embodiment is not any limitation as this.
The present embodiment determines described to be predicted insure according to the health risk probability of acquisition and information of insuring relatively simplely
The corresponding health risk grade of user, while ensure that health risk prediction effect accuracy, also mitigates staff
Workload.
Health risk prediction meanss first embodiment based on the above-mentioned user that insures, insures user's described in the present embodiment
Health risk prediction meanss 101 further include：Data acquisition module, sample classification module and model training module.
The data acquisition module, the individual health data information of the user that insured for obtaining default quantity, from institute
State the health characteristics data that preset kind is extracted in individual health data information；
It should be noted that the user that insured is the user that have purchased various healthy class insurances.In order to ensure
The health risk prediction model subsequently obtained has higher accuracy rate, so as to improve the prediction level of health risk, is choosing
During model sample, model sample quantity can be determined according to actual conditions, such as：100000,500,000 or 1,000,000 etc..It is described default
Type can be pre-defined information category, such as：Physical examination data, age, medical treatment number, cost etc. of seeing a doctor, the present embodiment
This is not any limitation as.
It should be understood that see a doctor in numerous users that insured there may be a part in period insured without diseased
Record or the user for just buying insurance, and use meaning of the health characteristics data of these users that insure to model training is not
Greatly, it is contemplated that when carrying out model training, model sample quantity is larger, it is necessary to the individual subscriber collected and extracted under normal conditions
The scale of construction of health data information is also more huge, in order to ensure that the health characteristics data extracted are authentic and valid, in the present embodiment
Described in data acquisition module, be additionally operable to obtain the individual health data information of the user that insured of default quantity；To described
People's health data information is screened, using the user that insured with diseased history as targeted customer；From the targeted customer couple
The health characteristics data of preset kind are extracted in the individual health data information answered.
The sample classification module, for being classified according to default classification of diseases rule to the health characteristics data,
Obtain different disease samples and the corresponding sickness influence factor of each disease sample；
It should be noted that the default classification of diseases rule can be that the disease suffered to different user is classified
Rule, specific classifying rules can foundations《International Classification of Diseases》Or whole nation unification《In-patient classification of diseases》To make
Fixed, the present embodiment is not any limitation as this.
It will be appreciated that after the completion of corresponding classification of diseases rule (i.e. described default classification of diseases rule) is formulated, can
Classified according to the classification of diseases rule to the corresponding health characteristics data of the user that respectively insured, obtain different disease samples
(such as：Hypertension sample, hyperlipidemia sample, coronary heart disease sample etc.) and the corresponding sickness influence factor (example of each disease sample
Such as：Blood pressure, blood fat, heart rate, lung capacity etc.).
In a practical situation, the part user that insured may suffer from a variety of diseases, such as suffer from hypertension and hyperlipidemia
User, after the health characteristics data of this user are got, when carrying out classification of diseases, it is necessary to health characteristics by this kind of user
Data are included in hypertension sample and hyperlipidemia sample respectively, that is to say, that the health containing this user is special in hyperglycaemia sample
Data are levied, also health characteristics data containing this user in hyperlipidemia sample.
The model training module, for according to different disease samples and the corresponding sickness influence of each disease sample because
Son is trained preset model, obtains the corresponding health risk prediction model of each disease under various disease sample.
It is understood that after different disease samples is got, can be according to the corresponding sickness influence of each disease sample
Factor pair preset model is trained, and obtains the corresponding health risk prediction model of each disease under various disease sample, such as：It is logical
Cross the corresponding health risk prediction model of health characteristics data acquisition hypertension that hypertension sample and hypertension sample include,
The corresponding health risk prediction mould of health characteristics data acquisition coronary heart disease included by coronary heart disease sample and coronary heart disease sample
Type etc..
In the present embodiment, the model training module, is additionally operable to calculate each sickness influence factor in various disease sample
Corresponding sickness influence factor average value；Each disease is obtained by default survival analysis method (such as Kaplan-Meier analytic approach)
Survival rate of the corresponding sample population of sample in different time points；According to the survival rate, the sickness influence factor and sickness influence
Factor average value is trained preset model, obtains the corresponding health risk prediction model of each disease under various disease sample.
The health characteristics data of the user that insured in view of getting may be pre- described in the present embodiment without certain regularity of distribution
Select model selection to data distribution situation without desired model：
Wherein, βiFor the corresponding regression coefficient of i-th of sickness influence factor；XiFor i-th of sickness influence factor；For disease
The average value of i-th of sickness influence factor in sick sample；S0(t) it is survival rate of the sample population in t time points；P is use to be predicted
Health risk probability of the family in t time points.
Further, the risk evaluation module 1015, is additionally operable to when the health risk probability exceedes predetermined probabilities,
The user to be predicted that insures is determined as excessive risk user；Insure what excessive risk user described in acquisition of information bought according to described
Insured amount, is excessive risk Claims Resolution user by the excessive risk user's mark when the insured amount exceedes preset cost, with
Determine the corresponding health risk grade of the user to be predicted that insures.
It should be noted that the predetermined probabilities can set in advance judge whether user is the general of excessive risk user
Rate, when the health risk probability for finding user to be predicted exceedes the predetermined probabilities, then judgement user is excessive risk user, example
Such as：The predetermined probabilities are 60%, and the health risk probability for the user B for being computed drawing has exceeded described preset generally for 79%
Rate, then judge the user B for excessive risk user.
It is understood that since the age bracket for the user that insures, occupation, economic level are different, they buy
The insured amount bought during insurance is also not quite similar, and in order to further be distinguished to the excessive risk user crowd, facilitates industry
Business personnel intuitively and effectively confirm the grade belonging to each excessive risk user, and it is (i.e. pre- can also to preset an amount for which loss settled
If the amount of money) come to being determined as that the health risk grade of excessive risk user continues to divide.
Further, changing for physical condition may be brought due to the recovery of physical function for part excessive risk user
Kind, correspondingly health risk is greatly reduced, in order to be carried out in fact to the health risk grade of such excessive risk user as far as possible
When judge.Risk evaluation module 1015 described in the present embodiment, are additionally operable to obtain the excessive risk reason every preset period of time
Pay for the current individual health data information of user；According to the current individual health data information and health risk prediction
Model, calculates the current actual health risk probability of the excessive risk Claims Resolution user；It is low in the actual health risk probability
When the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled, and it is true according to the actual health risk probability
Fixed user's currently corresponding health risk grade to be predicted of insuring.
The present embodiment is when the health risk probability calculated exceedes predetermined probabilities, by the user to be predicted that insures
It is determined as excessive risk user；The insured amount bought according to the excessive risk user described in acquisition of information that insures, in the insurance
When the amount of money exceedes preset cost, it is excessive risk Claims Resolution user by the excessive risk user's mark, is treated so as to realize to each
The corresponding health risk grade of prediction user is accurately divided.
In addition, the present invention also provides a kind of storage medium, the health risk for the user that insures is stored with the storage medium
Prediction program, realizes following operation when the health risk Prediction program of the user that insures is executed by processor：
Obtain the individual health data information of the user to be predicted that insures and information of insuring；
The individual health data information is extracted by preset rules, obtains target health characteristics data；
According to the information of insuring, corresponding target health wind is determined from advance trained health risk prediction model
Dangerous prediction model；
The target health characteristics data are sent in the target health risk prediction model, it is pre- to be treated described in acquisition
Survey is insured the corresponding health risk probability of user；
The corresponding healthy wind of the user to be predicted that insures is determined according to the health risk probability and the information of insuring
Dangerous grade.
Further, following operation is also realized when the health risk Prediction program of the user that insures is executed by processor：
The individual health data information of the user that insured of default quantity is obtained, is carried from the individual health data information
Take out the health characteristics data of preset kind；
Classified according to default classification of diseases rule to the health characteristics data, obtain different disease samples and
The corresponding sickness influence factor of each disease sample；
It is trained according to different disease samples and the corresponding sickness influence factor pair preset model of each disease sample,
Obtain the corresponding health risk prediction model of each disease under various disease sample.
Further, following operation is also realized when the health risk Prediction program of the user that insures is executed by processor：
The corresponding sickness influence factor average value of each sickness influence factor in various disease sample is calculated respectively；
Survival rate of the corresponding sample population of each disease sample in different time points is obtained by presetting survival analysis method；
Preset model is trained according to the survival rate, the sickness influence factor and sickness influence factor average value,
Obtain the corresponding health risk prediction model of each disease under various disease sample.
Further, following operation is also realized when the health risk Prediction program of the user that insures is executed by processor：
Obtain the individual health data information of the user that insured of default quantity；
The individual health data information is screened, using the user that insured with diseased history as targeted customer；
The health characteristics data of preset kind are extracted from the corresponding individual health data information of the targeted customer.
Further, following operation is also realized when the health risk Prediction program of the user that insures is executed by processor：
When the health risk probability exceedes predetermined probabilities, the user to be predicted that insures is determined as that excessive risk is used
Family；
The insured amount bought according to the excessive risk user described in acquisition of information that insures, exceedes pre- in the insured amount
If it is excessive risk Claims Resolution user by the excessive risk user's mark, to determine that the user to be predicted that insures is corresponding during the amount of money
Health risk grade.
Further, following operation is also realized when the health risk Prediction program of the user that insures is executed by processor：
The current individual health data information of the excessive risk Claims Resolution user is obtained every preset period of time；
According to the current individual health data information and the target health risk prediction model, the height is calculated
The current actual health risk probability of risk Claims Resolution user；
When the actual health risk probability is less than the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled
Note, and user's currently corresponding health risk grade to be predicted of insuring according to the actual health risk determine the probability.
The present embodiment determines described to be predicted insure according to the health risk probability of acquisition and information of insuring relatively simplely
The corresponding health risk grade of user, while ensure that health risk prediction effect accuracy, also mitigates staff
Workload.
It should be noted that herein, term " comprising ", "comprising" or its any other variation are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And the other key elements being not explicitly listed are further included, or further include as this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Also there are other identical element in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, computer, takes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made, is directly or indirectly used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
- A kind of 1. health risk Forecasting Methodology for the user that insures, it is characterised in that the described method includes：Obtain the individual health data information of the user to be predicted that insures and information of insuring；The individual health data information is extracted by preset rules, obtains target health characteristics data；According to the information of insuring, determine that corresponding target health risk is pre- from advance trained health risk prediction model Survey model；The target health characteristics data are sent in the target health risk prediction model, to obtain the throwing to be predicted The corresponding health risk probability in warranty family；Corresponding health risk of the user to be predicted that insures etc. is determined according to the health risk probability and the information of insuring Level.
- 2. the method as described in claim 1, it is characterised in that the individual health data letter for obtaining the user to be predicted that insures Cease and information of insuring before, the method further includes：The individual health data information of the user that insured of default quantity is obtained, is extracted from the individual health data information The health characteristics data of preset kind；Classified according to default classification of diseases rule to the health characteristics data, obtain different disease samples and each disease The corresponding sickness influence factor of sick sample；Preset model is trained respectively according to different disease samples and the corresponding sickness influence factor of each disease sample, Obtain the corresponding health risk prediction model of each disease under various disease sample.
- 3. method as claimed in claim 2, it is characterised in that described according to different disease samples and each disease sample pair The sickness influence factor answered respectively is trained preset model, obtains the corresponding health risk of each disease under various disease sample Prediction model, specifically includes：The corresponding sickness influence factor average value of each sickness influence factor in various disease sample is calculated respectively；Survival rate of the corresponding sample population of each disease sample in different time points is obtained by presetting survival analysis method；Preset model is trained according to the survival rate, the sickness influence factor and sickness influence factor average value, is obtained The corresponding health risk prediction model of each disease under various disease sample.
- 4. method as claimed in claim 3, it is characterised in that the preset model is：<mrow> <mi>P</mi> <mo>=</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>S</mi> <mn>0</mn> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mi>exp</mi> <mrow> <mo>(</mo> <msubsup> <mi>&Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </msubsup> <msub> <mi>&beta;</mi> <mi>i</mi> </msub> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>-</mo> <msubsup> <mi>&Sigma;</mi> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </msubsup> <msub> <mi>&beta;</mi> <mi>i</mi> </msub> <msub> <mover> <mi>X</mi> <mo>&OverBar;</mo> </mover> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow>Wherein, βiFor the corresponding regression coefficient of i-th of sickness influence factor；XiFor i-th of sickness influence factor；For disease sample The average value of i-th of sickness influence factor in this；S0(t) it is survival rate of the sample population in t time points；P is user to be predicted in t The health risk probability of time point.
- 5. method as claimed in claim 4, it is characterised in that the personal health of the user that insured for obtaining default quantity Data message, the health characteristics data of preset kind are extracted from the individual health data information, are specifically included：Obtain the individual health data information of the user that insured of default quantity；The individual health data information is screened, using the user that insured with diseased history as targeted customer；The health characteristics data of preset kind are extracted from the corresponding individual health data information of the targeted customer.
- 6. method as claimed in claim 5, it is characterised in that described according to the health risk probability and the information of insuring Determine the corresponding health risk grade of the user to be predicted that insures, specifically include：When the health risk probability exceedes predetermined probabilities, the user to be predicted that insures is determined as excessive risk user；The insured amount bought according to the excessive risk user described in acquisition of information that insures, exceedes default gold in the insured amount It is excessive risk Claims Resolution user by the excessive risk user's mark during volume, to determine the corresponding health of the user to be predicted that insures Risk class.
- 7. method as claimed in claim 6, it is characterised in that insure excessive risk user described in acquisition of information described in the basis The insured amount of purchase, when the insured amount exceedes preset cost, the excessive risk user's mark is settled a claim for excessive risk User, after determining the corresponding health risk grade of the user to be predicted that insures, the method further includes：The current individual health data information of the excessive risk Claims Resolution user is obtained every preset period of time；According to the current individual health data information and the target health risk prediction model, the excessive risk is calculated The current actual health risk probability of Claims Resolution user；When the actual health risk probability is less than the predetermined probabilities, the mark to excessive risk Claims Resolution user is cancelled, And user's currently corresponding health risk grade to be predicted of insuring according to the actual health risk determine the probability.
- 8. a kind of health risk prediction meanss for the user that insures, it is characterised in that described device includes：Data obtaining module, for the individual health data information for obtaining the user to be predicted that insures and information of insuring；Information extraction modules, for being extracted by preset rules to the individual health data information, it is special to obtain target health Levy data；Model chooses module, according to the information of insuring, is determined from advance trained health risk prediction model corresponding Target health risk prediction model；Risk profile module, for the target health characteristics data to be sent to advance trained health risk prediction model In, to obtain the corresponding health risk probability of the user to be predicted that insures；Risk evaluation module, for determining the user to be predicted that insures according to the health risk probability and the information of insuring Corresponding health risk grade.
- 9. the pre- measurement equipment of health risk of a kind of user that insures, it is characterised in that the equipment includes：Memory, processor and The health risk Prediction program for the user that insures that can be run on the memory and on the processor is stored in, it is described to insure The health risk Prediction program of user is arranged for carrying out the healthy wind of the user that insures as any one of claim 1 to 7 The step of dangerous Forecasting Methodology.
- 10. a kind of storage medium, it is characterised in that the pre- ranging of health risk for the user that insures is stored with the storage medium Sequence, realizes such as claim 1 to 7 any one of them when the health risk Prediction program of the user that insures is executed by processor Insure user health risk Forecasting Methodology the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711222721.7A CN107910068A (en) | 2017-11-29 | 2017-11-29 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711222721.7A CN107910068A (en) | 2017-11-29 | 2017-11-29 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107910068A true CN107910068A (en) | 2018-04-13 |
Family
ID=61849089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711222721.7A Pending CN107910068A (en) | 2017-11-29 | 2017-11-29 | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107910068A (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510402A (en) * | 2018-06-06 | 2018-09-07 | 中国平安人寿保险股份有限公司 | Insurance kind information recommendation method, device, computer equipment and storage medium |
| CN108682457A (en) * | 2018-04-17 | 2018-10-19 | 中国医学科学院阜外医院 | Patient's long-term prognosis quantitative forecast and interfering system and method |
| CN108921707A (en) * | 2018-06-05 | 2018-11-30 | 中国平安人寿保险股份有限公司 | Core protects processing method, device, computer equipment and storage medium |
| CN109192306A (en) * | 2018-09-21 | 2019-01-11 | 广东工业大学 | A kind of judgment means of diabetes, equipment and computer readable storage medium |
| CN109345397A (en) * | 2018-09-17 | 2019-02-15 | 平安科技（深圳）有限公司 | Intelligent code insurance method, server and storage medium |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109377384A (en) * | 2018-09-03 | 2019-02-22 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of health insurance |
| CN109472711A (en) * | 2018-12-14 | 2019-03-15 | 平安健康保险股份有限公司 | The core of health insurance protects method, apparatus, equipment and computer readable storage medium |
| CN109493972A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Data processing method, device, server and storage medium based on prediction model |
| CN109493244A (en) * | 2018-11-07 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Method and Related product based on prediction model configuration demand for insurance |
| CN109523067A (en) * | 2018-10-30 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Cost Forecast method, apparatus, server and storage medium based on prediction model |
| CN109559243A (en) * | 2018-12-13 | 2019-04-02 | 泰康保险集团股份有限公司 | Adjuster method, apparatus, medium and electronic equipment |
| CN109620194A (en) * | 2018-12-12 | 2019-04-16 | 泰康保险集团股份有限公司 | Heart rate detection processing method, device, medium and electronic equipment |
| CN109727125A (en) * | 2019-01-25 | 2019-05-07 | 深圳乐信软件技术有限公司 | Borrowing balance prediction technique, device, server, storage medium |
| CN110110906A (en) * | 2019-04-19 | 2019-08-09 | 电子科技大学 | A kind of survival risk modeling method based on Efron near-optimal |
| CN110993103A (en) * | 2019-11-28 | 2020-04-10 | 阳光人寿保险股份有限公司 | Method for establishing disease risk prediction model and method for recommending disease insurance product |
| CN111105316A (en) * | 2019-11-13 | 2020-05-05 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment for long-term care insurance |
| CN111180065A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Insurance user evaluation method and device, electronic equipment and computer readable medium |
| CN111179095A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Health risk assessment-based underwriting method, system, equipment and storage medium |
| CN111179096A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Medical data auditing method and device, electronic equipment and computer readable medium |
| CN111275558A (en) * | 2020-01-13 | 2020-06-12 | 上海维跃信息科技有限公司 | Method and device for determining insurance data |
| WO2020119118A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Abnormal data processing method, apparatus and device, and computer readable storage medium |
| CN111462910A (en) * | 2020-03-31 | 2020-07-28 | 上海商汤智能科技有限公司 | Item matching method and device, electronic equipment and storage medium |
| CN111584084A (en) * | 2020-05-25 | 2020-08-25 | 泰康保险集团股份有限公司 | User information processing method and device, electronic equipment and storage medium |
| CN111666591A (en) * | 2020-06-09 | 2020-09-15 | 山东健康医疗大数据有限公司 | Online underwriting data security processing method, system, equipment and storage medium |
| WO2020207317A1 (en) * | 2019-04-09 | 2020-10-15 | Oppo广东移动通信有限公司 | User health assessment method and apparatus, and storage medium and electronic device |
| CN111986808A (en) * | 2020-07-30 | 2020-11-24 | 珠海中科先进技术研究院有限公司 | Method, device and medium for health insurance risk assessment and control |
| CN112017064A (en) * | 2020-08-26 | 2020-12-01 | 上海爱佰医疗科技发展有限公司 | Insurance application suggestion evaluation method and device suitable for assisted reproductive insurance |
| CN112117015A (en) * | 2020-10-28 | 2020-12-22 | 平安科技（深圳）有限公司 | Sepsis early warning device, method, apparatus and storage medium |
| CN112465231A (en) * | 2020-12-01 | 2021-03-09 | 平安医疗健康管理股份有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
| CN107146160A (en) * | 2016-02-26 | 2017-09-08 | 平安科技（深圳）有限公司 | Customer insured's analysis on the health status method and server |
-
2017
- 2017-11-29 CN CN201711222721.7A patent/CN107910068A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146160A (en) * | 2016-02-26 | 2017-09-08 | 平安科技（深圳）有限公司 | Customer insured's analysis on the health status method and server |
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN106874663A (en) * | 2017-01-26 | 2017-06-20 | 中电科软件信息服务有限公司 | Cardiovascular and cerebrovascular disease Risk Forecast Method and system |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108682457A (en) * | 2018-04-17 | 2018-10-19 | 中国医学科学院阜外医院 | Patient's long-term prognosis quantitative forecast and interfering system and method |
| CN108921707A (en) * | 2018-06-05 | 2018-11-30 | 中国平安人寿保险股份有限公司 | Core protects processing method, device, computer equipment and storage medium |
| CN108510402A (en) * | 2018-06-06 | 2018-09-07 | 中国平安人寿保险股份有限公司 | Insurance kind information recommendation method, device, computer equipment and storage medium |
| CN109377384A (en) * | 2018-09-03 | 2019-02-22 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of health insurance |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109377388B (en) * | 2018-09-13 | 2023-08-18 | 深圳平安医疗健康科技服务有限公司 | Medical insurance application method, medical insurance application device, computer equipment and storage medium |
| CN109345397A (en) * | 2018-09-17 | 2019-02-15 | 平安科技（深圳）有限公司 | Intelligent code insurance method, server and storage medium |
| CN109192306A (en) * | 2018-09-21 | 2019-01-11 | 广东工业大学 | A kind of judgment means of diabetes, equipment and computer readable storage medium |
| CN109493972A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Data processing method, device, server and storage medium based on prediction model |
| CN109523067A (en) * | 2018-10-30 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Cost Forecast method, apparatus, server and storage medium based on prediction model |
| CN109493244A (en) * | 2018-11-07 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Method and Related product based on prediction model configuration demand for insurance |
| CN111179095A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Health risk assessment-based underwriting method, system, equipment and storage medium |
| CN111180065A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Insurance user evaluation method and device, electronic equipment and computer readable medium |
| CN111179096A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Medical data auditing method and device, electronic equipment and computer readable medium |
| CN109620194A (en) * | 2018-12-12 | 2019-04-16 | 泰康保险集团股份有限公司 | Heart rate detection processing method, device, medium and electronic equipment |
| WO2020119118A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Abnormal data processing method, apparatus and device, and computer readable storage medium |
| CN109559243A (en) * | 2018-12-13 | 2019-04-02 | 泰康保险集团股份有限公司 | Adjuster method, apparatus, medium and electronic equipment |
| CN109472711A (en) * | 2018-12-14 | 2019-03-15 | 平安健康保险股份有限公司 | The core of health insurance protects method, apparatus, equipment and computer readable storage medium |
| CN109727125A (en) * | 2019-01-25 | 2019-05-07 | 深圳乐信软件技术有限公司 | Borrowing balance prediction technique, device, server, storage medium |
| WO2020207317A1 (en) * | 2019-04-09 | 2020-10-15 | Oppo广东移动通信有限公司 | User health assessment method and apparatus, and storage medium and electronic device |
| CN110110906A (en) * | 2019-04-19 | 2019-08-09 | 电子科技大学 | A kind of survival risk modeling method based on Efron near-optimal |
| CN111105316A (en) * | 2019-11-13 | 2020-05-05 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment for long-term care insurance |
| CN111105316B (en) * | 2019-11-13 | 2023-06-09 | 泰康保险集团股份有限公司 | Data processing method and device for long-term care insurance, medium and electronic equipment |
| CN110993103A (en) * | 2019-11-28 | 2020-04-10 | 阳光人寿保险股份有限公司 | Method for establishing disease risk prediction model and method for recommending disease insurance product |
| CN111275558A (en) * | 2020-01-13 | 2020-06-12 | 上海维跃信息科技有限公司 | Method and device for determining insurance data |
| CN111275558B (en) * | 2020-01-13 | 2024-02-27 | 上海维跃信息科技有限公司 | Method and device for determining insurance data |
| CN111462910A (en) * | 2020-03-31 | 2020-07-28 | 上海商汤智能科技有限公司 | Item matching method and device, electronic equipment and storage medium |
| CN111584084A (en) * | 2020-05-25 | 2020-08-25 | 泰康保险集团股份有限公司 | User information processing method and device, electronic equipment and storage medium |
| CN111666591A (en) * | 2020-06-09 | 2020-09-15 | 山东健康医疗大数据有限公司 | Online underwriting data security processing method, system, equipment and storage medium |
| CN111986808B (en) * | 2020-07-30 | 2023-12-12 | 珠海中科先进技术研究院有限公司 | Health insurance risk assessment and control method, device and medium |
| CN111986808A (en) * | 2020-07-30 | 2020-11-24 | 珠海中科先进技术研究院有限公司 | Method, device and medium for health insurance risk assessment and control |
| CN112017064A (en) * | 2020-08-26 | 2020-12-01 | 上海爱佰医疗科技发展有限公司 | Insurance application suggestion evaluation method and device suitable for assisted reproductive insurance |
| CN112117015A (en) * | 2020-10-28 | 2020-12-22 | 平安科技（深圳）有限公司 | Sepsis early warning device, method, apparatus and storage medium |
| CN112117015B (en) * | 2020-10-28 | 2023-09-05 | 平安科技（深圳）有限公司 | Sepsis early warning equipment, sepsis early warning method, sepsis early warning device and sepsis early warning storage medium |
| CN112465231A (en) * | 2020-12-01 | 2021-03-09 | 平安医疗健康管理股份有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
| CN112465231B (en) * | 2020-12-01 | 2023-02-03 | 深圳平安医疗健康科技服务有限公司 | Method, apparatus and readable storage medium for predicting regional population health status |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107910068A (en) | Insure health risk Forecasting Methodology, device, equipment and the storage medium of user | |
| US7640174B2 (en) | Method and system for gainsharing of physician services | |
| CN108256691A (en) | Refund Probabilistic Prediction Model construction method and device | |
| US20120271612A1 (en) | Predictive modeling | |
| CN108416664A (en) | Methods of risk assessment and system based on consumptive credit scene are realized | |
| CN108765176A (en) | Settlement of insurance claim case processing method, device, computer equipment and storage medium | |
| CN108346036A (en) | Insurance policy concentrates vouching method, electronic device and readable storage medium storing program for executing | |
| CN112529716B (en) | Method, device and computer readable storage medium for predicting credit | |
| CN107146160B (en) | Health condition analysis method for insurance client and server | |
| CN106971343A (en) | The risk analysis method and system of insurance data | |
| CN108197742A (en) | Continuation of insurance behavior prediction method, system and the computer readable storage medium of user | |
| CN109711424A (en) | A kind of rule of conduct acquisition methods, device and equipment based on decision tree | |
| CN113742492A (en) | Insurance scheme generation method and device, electronic equipment and storage medium | |
| CN111192133A (en) | Method and device for generating risk model after user loan and electronic equipment | |
| CN107844862A (en) | Order failure prediction method, apparatus, medium and electronic equipment | |
| CN111179095A (en) | Health risk assessment-based underwriting method, system, equipment and storage medium | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN109389511B (en) | Insurance product development method, insurance product development device, insurance product development terminal and computer-readable storage medium | |
| CN109711856B (en) | User classification method, device, server and storage medium based on big data | |
| CN112085517A (en) | Coupon issuing method and device, electronic equipment and readable storage medium | |
| CN109816470B (en) | Dangerous seed recommending method and device, electronic equipment and computer readable storage medium | |
| CN110706122A (en) | Method, device and readable medium for improving social security agent efficiency based on big data analysis | |
| CN110766559B (en) | Label configuration method and device | |
| JP6895912B2 (en) | Insurance design support system and insurance design support method | |
| CN110782361A (en) | Recommendation method and device for customized insurance |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180413 |
|
| RJ01 | Rejection of invention patent application after publication |