CN109712004A - A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision - Google Patents
A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision Download PDFInfo
- Publication number
- CN109712004A CN109712004A CN201811525770.2A CN201811525770A CN109712004A CN 109712004 A CN109712004 A CN 109712004A CN 201811525770 A CN201811525770 A CN 201811525770A CN 109712004 A CN109712004 A CN 109712004A
- Authority
- CN
- China
- Prior art keywords
- medical insurance
- slow
- insurance fund
- amount
- money
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013139 quantization Methods 0.000 claims abstract description 66
- 238000011002 quantification Methods 0.000 claims abstract description 26
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 154
- 201000010099 disease Diseases 0.000 claims description 152
- 238000007726 management method Methods 0.000 claims description 38
- 238000004590 computer program Methods 0.000 claims description 9
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 8
- 239000010931 gold Substances 0.000 claims description 8
- 229910052737 gold Inorganic materials 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 5
- 238000013497 data interchange Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 8
- 208000017667 Chronic Disease Diseases 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 206010007558 Cardiac failure chronic Diseases 0.000 description 1
- 206010018367 Glomerulonephritis chronic Diseases 0.000 description 1
- 201000003793 Myelodysplastic syndrome Diseases 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 208000021386 Sjogren Syndrome Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 208000019425 cirrhosis of liver Diseases 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003709 heart valve Anatomy 0.000 description 1
- 208000003532 hypothyroidism Diseases 0.000 description 1
- 230000002989 hypothyroidism Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 206010028417 myasthenia gravis Diseases 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 208000005069 pulmonary fibrosis Diseases 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 201000008827 tuberculosis Diseases 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Abstract
The embodiment of the invention discloses a kind of medical insurance fund Risk Forecast Method and device based on intelligent decision; it include: that slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, the first preset condition includes the first region and the first preset time period;Quantification treatment is carried out to driving factors, obtains slow sick information quantization value;The amount received and amount paid of medical insurance fund are predicted according to slow sick information quantization value and medical insurance fund revenue and expenditure model, obtain the expected revenue amount of money and the expectan amount of money;When the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determines that medical insurance fund has overdraw risk, risk management and control is carried out to medical insurance fund.It, can be by being predicted using slow sick information as revenue and expenditure of the driving factors of medical insurance fund to medical insurance fund using the present invention, and then the balance between revenue and expenditure of medical insurance fund is managed.Increase the specific aim of medical insurance fund management, and then promotes the efficiency of management of medical insurance fund.
Description
Technical field
The present invention relates to data processing fields, and in particular to a kind of medical insurance fund Risk Forecast Method based on intelligent decision
And device.
Background technique
Medical insurance is the important component of social insurance, to Medical Benefits Fund income and expenses predict can and
The control of Shi Jinhang Medical Benefits Fund or policy adjustment guarantee medical insurance fund revenue and expenditure to avoid there is medical insurance fund deficit risk
Balance.
Traditional medical insurance fund risk management and control not by medical insurance fund driving factors carry out dismantling and quantitative analysis, and according to
Quantitative analysis result determines these driving factors to the influence degree of medical insurance fund revenue and expenditure, leads to management to medical insurance fund very
It is coarse, it is difficult to useful information to be obtained from driving factors, so that the control to medical insurance fund is accurate to medical insurance
Links in whole flow process.Cause the risk management specific aim to medical insurance fund low in this way and inefficiency, is unable to satisfy
The demand of medical insurance fund management.
Summary of the invention
The embodiment of the present invention provides a kind of medical insurance fund Risk Forecast Method and device based on intelligent decision, can pass through
Quantification treatment is carried out using slow sick information as the driving factors of medical insurance fund, then according to slow sick information quantization value to medical insurance fund
Revenue and expenditure predicted, and then the balance between revenue and expenditure of medical insurance fund is managed.Increase the specific aim of medical insurance fund management, in turn
The efficiency of management for promoting medical insurance fund, enables medical insurance fund to carry out risk management and control in advance, guarantees that the revenue and expenditure of medical insurance fund is flat
Weighing apparatus.
The first aspect of the embodiment of the present invention provides a kind of medical insurance fund Risk Forecast Method based on intelligent decision, institute
Stating the medical insurance fund Risk Forecast Method based on intelligent decision includes:
Slow sick information is obtained as the relevant driving factors of medical insurance fund, the first default item according to the first preset condition
Part includes the first region and the first preset time period;
Quantification treatment is carried out to the driving factors, obtains slow sick information quantization value;
According to the slow sick quantized value and medical insurance fund revenue and expenditure model to the amount received of medical insurance fund and amount paid into
Row prediction, obtains the expected revenue amount of money and the expectan amount of money;
When the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, described in judgement
There is overdraw risk in medical insurance fund, carry out risk management and control to the medical insurance fund.
In an alternative scenario, described that slow sick information is obtained as the relevant driving of medical insurance fund according to the first preset condition
Factor, and quantification treatment is carried out to the driving factors, obtain slow sick information quantization value, comprising:
The first region is obtained in the slow sick information of the first preset time period;
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population;
The target the end of month slow disease population is determined as the slow sick information quantization value.
In an alternative scenario, described that formula calculating is carried out to the slow sick information, obtain the target the end of month slow disease population, packet
It includes:
The slow sick information got include before the first preset time period the end of last month slow disease population, non-slow disease the end of last month
Population, slow sick incidence and slow die of illness die population;
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, wherein the formula are as follows:
M1=M0,
M1 '=M1+ (Mn × p1)-Md;
Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate the target moon
The slow disease population in end, Mx indicate that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
In an alternative scenario, according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to medical insurance fund
Amount received and amount paid are predicted, before obtaining the expected revenue amount of money and the expectan amount of money, the method also includes
Medical insurance fund revenue and expenditure model is established, is specifically included:
Target area is obtained in the medical insurance policies and population structure of target time section;
According to the medical insurance policies and the population structure, determine that the target area is paid the fees in the medical insurance of target time section
Situation forms the medical insurance fund based revenue model;
Target area is obtained in the medical data of target time section, the medical data includes the moon of the target time section
Slow sick reimbursement number, slow sick reimbursed sum and total reimbursed sum;
It is established according to the medical data and pays model by the medical insurance fund of independent variable of the end of month slow disease population;
According to the medical insurance fund based revenue model and described using the end of month slow disease population as the medical insurance fund branch of independent variable
Model out obtains described using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable.
In an alternative case, it is described according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to medical insurance fund
Amount received and amount paid are predicted, the expected revenue amount of money and the expectan amount of money are obtained, comprising:
By slow sick corresponding first region of information and first preset time period respectively with the medical insurance base
The golden corresponding target area of revenue and expenditure model and the target time section are matched;
Determine that first region and the target area exactly match, when first preset time period is with the target
Between section be the period is identical but corresponding time is different period, and first preset time period the target time section it
Afterwards;
The slow sick information quantization value is imported in the medical insurance fund revenue and expenditure model, amount received to medical insurance fund and
Amount paid is predicted;
The amount received of the medical insurance fund revenue and expenditure model prediction out is obtained as the expected revenue amount of money, obtains prediction
The amount paid out is as the expectan amount of money.
In an alternative scenario, described to include: to medical insurance fund progress risk management and control
Slow disease population to first region in the first preset time period is verified, and determines that slow disease population growth rate is
It is no to be higher than the second preset threshold;
If so, calibrating to the slow disease population, accurately slow disease population growth rate is obtained.
The second aspect of the embodiment of the present invention provides a kind of medical insurance fund risk profile device, the medical insurance fund risk
Prediction meanss include:
Acquiring unit, for obtaining slow sick information as the relevant driving factors of medical insurance fund according to the first preset condition,
First preset condition includes the first region and the first preset time period;
Quantifying unit obtains slow sick information quantization value for carrying out quantification treatment to the driving factors;
Predicting unit, according to the slow sick quantized value and medical insurance fund revenue and expenditure model to the amount received and branch of medical insurance fund
The amount of money is predicted out, obtains the expected revenue amount of money and the expectan amount of money;
Risk management and control unit, for being more than first pre- when the difference of the expectan amount of money and the expected revenue amount of money
If when threshold value, determining that the medical insurance fund has overdraw risk, carrying out risk management and control to the medical insurance fund.
The third aspect of the embodiment of the present invention provides a kind of electronic device, including processor, memory, communication interface, with
And one or more programs, one or more of programs are stored in the memory, and are configured by the processing
Device executes, and described program is included the steps that for executing the instruction in first aspect either method.
Fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, and storage is used for electronic data interchange
Computer program, wherein the computer program make computer execute first aspect either method described in step finger
It enables.
As it can be seen that described in the embodiment of the present invention in the medical insurance fund Risk Forecast Method based on intelligent decision, root first
Slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, and the first preset condition includes the first region
With the first preset time period;Then quantification treatment is carried out to driving factors, obtains slow sick information quantization value;Further according to slow disease quantization
Value and medical insurance fund revenue and expenditure model, predict the amount received and amount paid of medical insurance fund, obtain the expected revenue amount of money
With the expectan amount of money;Finally when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine
There is overdraw risk in the medical insurance fund, carry out risk management and control to medical insurance fund.In this process, by making slow sick information
Quantification treatment is carried out for the driving factors of medical insurance fund, then the revenue and expenditure of medical insurance fund is carried out according to slow sick information quantization value pre-
It surveys, improves the accuracy of medical insurance fund income and expense projection, and then improve and have to what the balance between revenue and expenditure of medical insurance fund was managed
Effect property.Enable medical insurance fund to carry out risk management and control in advance, guarantees the balance between revenue and expenditure of medical insurance fund.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of medical insurance fund Risk Forecast Method process signal based on intelligent decision provided in an embodiment of the present invention
Figure;
Fig. 2 is the process of another medical insurance fund Risk Forecast Method based on intelligent decision provided in an embodiment of the present invention
Schematic diagram;
Fig. 3 is the process of another medical insurance fund Risk Forecast Method based on intelligent decision provided in an embodiment of the present invention
Schematic diagram;
Fig. 4 is the process of another medical insurance fund Risk Forecast Method based on intelligent decision provided in an embodiment of the present invention
Schematic diagram;
Fig. 5 is a kind of structural schematic diagram of electronic device provided in an embodiment of the present invention;
Fig. 6 is a kind of structural block diagram of medical insurance fund risk profile device provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
Containing at least one embodiment of the present invention.It is identical that each position in the description shows that the phrase might not be each meant
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
It describes in detail below to the embodiment of the present invention.
Referring to Fig. 1, Fig. 1 is a kind of medical insurance fund Risk Forecast Method stream based on intelligent decision in the embodiment of the present invention
Journey schematic diagram, as shown in Figure 1, the medical insurance fund Risk Forecast Method based on intelligent decision includes:
101, slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, described first in advance
If condition includes the first region and the first preset time period.
Medical insurance fund refers to that Medical Benefits Fund, Medical Benefits Fund are paid jointly by employing unit and individual, paid
The fund received is divided into overall social planning fund and personal account two parts, and risk-pooling fund is used for the Medical Consumption for patient according to doctor
Guarantor's policy is submitted an expense account, and personal account part carries out Medical Consumption for patient.
Slow disease is outpatient service chronic disease, such as chronic glomerulonephritis, myasthenia gravis, hypothyroidism, liver beans
Shape nuclear degeneration, pulmonary interstitial fibrosis, Sjogren syndrome, myelodysplastic syndrome, cardiac valve replacement and coronary artery are taken
Bridge is postoperative etc..It is characterized in that treatment cycle is longer, the state of an illness is relatively stable, can not cure in a short time.The harm of chronic disease is mainly
The damage for causing the important organs such as brain, the heart, kidney, easily causes disability, influences labour capacity and quality of life, and medical expense is extremely
Valuableness increases the financial burden of society and family.Therefore, country is subsidized for chronic disease, and slow disease application is stepped on
The medical insurance payment resident that note certification passes through, can get slow disease subsidy according to month, for of that month slow sick medical expense reimbursement.
Slow disease and its medical loan standard are as shown in table 1:
The medical loan standard (part) of the slow disease of watch 1
Outpatient service chronic disease disease | Month reimbursed sum |
1, chronic heart failure | 290 yuan/month |
2, Decompensated liver cirrhosis | 420 yuan/month |
3, tuberculosis | 160 yuan/month |
In different time sections, the population (referred to as slow disease population) for needing to carry out slow disease reimbursement is different for different regions, because
This, obtains slow sick information according to the first preset condition and is used as the relevant driving factors of medical insurance fund, and the first preset condition includes the
One region and the first preset time period.
102, quantification treatment is carried out to the driving factors, obtains slow sick information quantization value.
The driving factors information of acquisition, i.e., slow sick information, content are very abundant, including the beginning of the month slow disease population, the moon
Last slow disease population, slow sick disease incidence, die of illness and die population and increase slow disease population etc. newly, slowly wherein slow disease population indicates the hair of chronic disease
Disease population.These data only have progress quantification treatment just to can serve as the income and expense projection of medical benefits fund, determine driving factors to prediction
As a result influence power.
Optionally, quantification treatment is carried out to driving factors, obtains slow sick information quantization value, comprising: slow sick information is carried out
Formula calculates, and obtains the target the end of month slow disease population;The target the end of month slow disease population is determined as slow sick information quantization value.
The specific value of the slow disease of acquisition is only subjected to formula calculating, obtains the quasi- numerical value of variation, it can be quantitatively
Influence power of the slow disease of analysis to medical benefits fund prediction result.The end of month population in some month, i.e. the target the end of month slow disease population are sought,
Using the end of month slow disease population as slow sick information quantization value.
Optionally, formula calculating is carried out to slow sick information, obtains the target the end of month slow disease population, comprising: the slow disease got
Information include before the first preset time period the end of last month slow disease population, non-slow disease population the end of last month, slow sick incidence and die of illness slowly
Die population;Formula calculating is carried out to slow sick information, obtains the target the end of month slow disease population, wherein formula are as follows: M1=M0, M1 '=M1
+(Mn×p1)-Md;Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate mesh
The end of month slow disease population is marked, Mx indicates that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
Specifically, it to calculate and obtain the target the end of month slow disease population, such as the slow disease population at 1 the end of month in 2018, it is necessary first to
Determine slow disease population the end of last month, i.e., the end of month in December, 2017 slow disease population, in addition, according to the historical data of slow disease population, it can
To determine non-slow disease population the end of last month, i.e. the slow disease population of non-slow disease population the end of last month=medical insurance the end of last month population-the end of last month, equally
Can also according to history, sick data determine slow sick incidence slowly, the slow disease death rate, then known to: the end of month dies of illness slowly dies population=beginning of the month
Slow disease population × slow sick the death rate.
Having determined slow disease population M0 the end of last month, the end of last month non-slow disease population Mn, slow disease incidence p1 dies of illness die people slowly
It, can be according to formula under the premise of mouth Md:
The end of month in target month slow disease population M1 ' is determined, likewise, can seek under target month with iteration according to the formula
The one month the end of month slow disease population, or even acquire the end of month slow disease population in all months in the first preset time period.
As it can be seen that in embodiments of the present invention, by inciting somebody to action slow sick information as the relevant driving factors of medical insurance fund, and to slow
Sick information carries out quantification treatment, obtains slow sick information quantization value, can monitor under the first preset condition, slow disease information quantization value
Change the influence for medical insurance fund income expenditure, in the case where being lifted at slow sick INFORMATION DISCOVERY variation, medical benefits fund is taken in
The prediction accuracy of the amount of money and amount paid, and then promote the accuracy and validity that risk management is carried out to medical insurance fund.
103, according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to the amount received and branch of medical insurance fund
The amount of money is predicted out, obtains the expected revenue amount of money and the expectan amount of money.
Medical insurance fund revenue and expenditure model is that its dependent variable determines, the unknown model of only slow sick quantized value, therefore, by root
It imports in medical insurance fund revenue and expenditure model, is can be obtained under the first preset condition according to the slow sick quantized value that the first preset condition determines
The expected revenue amount of money and the expectan amount of money.
Optionally, golden to the amount received and expenditure of medical insurance fund in the slow sick quantized value of basis and medical insurance fund revenue and expenditure model
Before volume is predicted, this method further includes establishing medical insurance fund revenue and expenditure model, is specifically included: obtaining target area in target
Between section medical insurance policies and population structure;According to medical insurance policies and population structure, determine target area in the doctor of target time section
Payment situation is protected, medical insurance fund based revenue model is formed;Obtain medical data of the target area in target time section, medical data packet
Include monthly slow sick reimbursement number, slow sick reimbursed sum and the total reimbursed sum of target time section;According to medical data establish with
The end of month slow disease population is that the medical insurance fund of independent variable pays model;It is according to medical insurance fund based revenue model and with the end of month slow disease population
The medical insurance fund of independent variable pays model, obtains using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable.
It include that medical insurance fund based revenue model and medical insurance fund pay model in medical insurance fund revenue and expenditure model, wherein medical insurance base
Golden based revenue model is related with local medical insurance policies and population structure, includes different medical insurance payment class in medical insurance policies, with
And the corresponding payment amount of money of each class, it include urban and rural residents and worker in population structure, for urban and rural residents, payment frequency
Rate is paid for annual one, and payment time point is at the end of month the first month in medical insurance year, therefore urban and rural residents' medical insurance fund income formula is as follows:
Wherein, a R1 expression man-year payment volume, R2 indicate that year financial subsidies volume, Mz indicate that medical insurance payment population, p1 indicate
Urban and rural residents' population ratio, T1 indicate the medical insurance fund income of urban and rural residents, a man-year payment volume and year financial subsidies volume according to
Payment policy and subsidy policy in the medical insurance policies of each department determine.
For worker, payment frequency is monthly one to pay.Payment amount of money is payment standard paying multiplied by corresponding payment side
Take ratio, then by an account pro rate is divided into pool account and personal account, it is as follows that medical insurance fund takes in formula:
Wherein R3 indicates that personal payment standard, P1 indicate that personal Proportion of payment, P0 indicate to be divided into an account ratio, and P2 indicates single
Position Proportion of payment, p2 indicate worker's accounting.T2 indicates worker's medical insurance fund income, for medical insurance fund management, just for
Plan as a whole account, be not directed to personal account, therefore only obtains and plan as a whole account fund.Personal payment standard is according to personal wage water
Gentle local medical insurance system determines that personal Proportion of payment transfers an account ratio, unit Proportion of payment according to local medical treatment guarantor
Dangerous system determines.
It follows that in the case where the local constant medical insurance population structure of medical insurance policies determines, can the region doctor
Protect fund based revenue model are as follows:
Ts=T1+T2 (4)
Wherein Ts indicates medical insurance fund income.
Medical insurance fund expenditure model is related to local medical data, monthly slow including target time section in medical data
Sick reimbursement number, slow sick reimbursed sum and total reimbursed sum.Assuming that every numerical value in medical data is constant,
It can get and pay model by the medical benefits fund of independent variable of the end of month slow disease population:
Wherein, Tj indicates that monthly chronic disease reimbursed sum per capita, Tm indicate that monthly slow sick reimbursed sum, Mj indicate monthly slow
Sick reimbursement number, Tz indicate that medical insurance fund amount paid, mn ' indicate n-th of the end of month slow disease population in the target time period, T0
Indicate monthly total reimbursed sum of target time section.
Medical insurance fund based revenue model and medical insurance fund expenditure model are determined according to formula (4) and formula (5), in conjunction with can be true
Determine medical insurance fund revenue and expenditure model.And in other parameters it is known that and only slow sick information quantization value it is unknown in the case where, the medical insurance base
Golden revenue and expenditure model is using slow sick information quantization value as the medical insurance fund revenue and expenditure model of independent variable.According to the medical insurance fund revenue and expenditure mould
Type, in conjunction with the slow sick information quantization value having determined, can amount received to medical insurance fund and amount paid predict.
Optionally, according to slow sick quantized value and medical insurance fund revenue and expenditure model to the amount received and amount paid of medical insurance fund
Predicted, obtain the expected revenue amount of money and the expectan amount of money, comprising: will corresponding first region of slow sick information quantization value with
First preset time period target area corresponding with medical insurance fund revenue and expenditure model and target time section are matched;Determine described
One region and the target area exactly match, and first preset time period is that the period is identical but right with the target time section
The different period between seasonable, and first preset time period is after the target time section;It will slow sick information quantization value
It imports in medical insurance fund revenue and expenditure model, the amount received and amount paid of medical insurance fund is predicted;Medical insurance fund is obtained to receive
The amount received that branch model predicts obtains the amount paid predicted as the expectan amount of money as the expected revenue amount of money.
The quantitative information of driving factors is obtained according to the first preset condition, the first preset condition include the first region and
First preset time period, medical insurance fund revenue and expenditure model is established according to target area and target time section, it is therefore desirable to by
One region and target area are matched, and the first preset time period and target time section are matched.Region is matched, because
Can all there are larger difference, therefore corresponding first region of slow sick information quantization value and medical insurance base for the various data of different geographical
The corresponding target area of golden revenue and expenditure model must exactly match, can be by keyword match, and the keyword in each area,
Including provincial full name and provincial abbreviation.Such as the keyword in Guangdong Province includes: Guangdong, Guangdong Province, Guangdong.
The amount received and branch of medical insurance fund are predicted for time match, when quantized value due to obtaining driving factors
The amount of money out, therefore, corresponding first preset time period of driving factors target time section corresponding with medical insurance fund revenue and expenditure model is
The period that period is identical but the correspondence time is different, and the first preset time period is after target time section.Wherein the period can be with
It is 2 years, 1 year or half a year, be also possible to three months etc..It is as shown in table 1:
2 first preset time period of table and target time section
According to example shown in table 2 it is found that the period of the first preset time period and target time section is all 1~December, and
First preset time period is 2017, and target time section is 2016 or 2015, before 2017, because of target time section
Closer with the first preset time period, the Parameters variation in medical insurance fund revenue and expenditure model is smaller, and prediction result also can be more accurate, because
This, determines that the maximum difference of the first preset time period and target time section is 2 target time section periods.In addition, first is default
The matching accuracy of period and target time section can be month, is also possible to number of days, is also possible to hour.
After successful match, the slow sick information quantization value under the first preset condition of acquisition is imported into medical insurance fund revenue and expenditure model
In, the target area in former formula is replaced in the slow sick information quantization value of target time section, and it is as follows that formula can be obtained:
Tz=Tj × [M1 '+M2 '+... Mn ']+(T0-Tm) × n (5)
M1 '+m2 ' in formula (4)+...+mn ' is by the slow sick information under the first preset condition for getting in formula (1)
Quantized value replacement is remembered to obtain medical insurance fund amount paid.Medical insurance fund amount received can determine by formula (2)-(4).Finally
Obtain the expected revenue amount of money and the expectan amount of money.
104, when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine
There is overdraw risk in the medical insurance fund, carry out risk management and control to the medical insurance fund.
After determining expected revenue amount of money Ts and expectan amount of money Tz according to step 103, its difference is obtained are as follows: difference=
Tz-Ts, the first preset threshold are an amount of money values, such as 500,000 yuan etc., when difference is greater than the first preset threshold, illustrate medical insurance
There is a possibility that overdraw in fund, determining medical insurance fund, there are risks, carry out risk management and control to medical insurance fund.
Optionally, carrying out risk management and control to medical insurance fund includes: in the first preset time period to the first region to first
Region is verified in the slow disease population of the first preset time period, determines whether slow disease population growth rate is higher than the second default threshold
Value;If so, calibrating to slow disease population, accurately slow disease population growth rate is obtained.
Specifically, medical insurance fund revenue expenditure process in embodiments of the present invention because other data be all it is determining constant,
Only slow sick information quantization value changes with the variation of time, and therefore, in upper 1 year indices, there is no left
In the case where problem, if prediction result shows that medical insurance fund has overdraw risk, very maximum probability is slow sick information quantization value
The problem of.Such as slow disease population increases too fast, can calibrate to slow disease population growth rate, obtain more accurately slow disease population
Growth rate.Or source is occurred to slow disease and is investigated, the disease for improving people prevents consciousness, reduces the slow disease morbidity of people
Rate.
As it can be seen that in embodiments of the present invention, obtaining slow sick information as medical insurance fund phase according to the first preset condition first
The driving factors of pass, the first preset condition include the first region and the first preset time period;Then driving factors are quantified
Processing obtains slow sick information quantization value;Further according to slow sick quantized value and medical insurance fund revenue and expenditure model, to the income gold of medical insurance fund
Volume and amount paid are predicted, the expected revenue amount of money and the expectan amount of money are obtained;Finally when the expectan amount of money and expection
When the difference of amount received is more than the first preset threshold, determines that the medical insurance fund has overdraw risk, medical insurance fund is carried out
Risk management and control.In this process, by using slow sick information as the driving factors of medical insurance fund progress quantification treatment, then root
The revenue and expenditure of medical insurance fund is predicted according to slow sick information quantization value, improves the accuracy of medical insurance fund income and expense projection, in turn
Improve the validity being managed to the balance between revenue and expenditure of medical insurance fund.Medical insurance fund is enabled to carry out risk management and control in advance,
Guarantee the balance between revenue and expenditure of medical insurance fund.
Referring to Fig. 2, Fig. 2 is another medical insurance fund risk profile based on intelligent decision provided in an embodiment of the present invention
The flow diagram of method, as shown, the medical insurance fund Risk Forecast Method based on intelligent decision in the present embodiment includes:
201, slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, described first in advance
If condition includes the first region and the first preset time period;
202, the slow sick information got include before the first preset time period the end of last month slow disease population, the end of last month it is non-
Slow disease population, slow sick incidence and slow die of illness die population;
203, formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, wherein the formula are as follows:
M1=M0, M1 '=M1+ (Mn × p1)-Md;
Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate the target moon
The slow disease population in end, Mx indicate that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
204, the target the end of month slow disease population is determined as the slow sick information quantization value;
205, according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to the amount received and branch of medical insurance fund
The amount of money is predicted out, obtains the expected revenue amount of money and the expectan amount of money;
206, when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine
There is overdraw risk in the medical insurance fund, carry out risk management and control to the medical insurance fund.
In embodiments of the present invention, slow sick information is obtained as the relevant drive of medical insurance fund according to the first preset condition first
Then reason element carries out formula calculating to slow sick information, obtain the end of month slow disease population as slow sick information quantization value, in this way may be used
So that the driving factors of medical insurance fund income and expense projection are more specific, targetedly medical insurance fund is taken according to slow sick information
The amount of money and amount paid make more accurate prediction, improve the validity being managed to the balance between revenue and expenditure of medical insurance fund.Make
Risk management and control can be carried out in advance by obtaining medical insurance fund, guarantee the balance between revenue and expenditure of medical insurance fund.
Referring to Fig. 3, Fig. 3 is another medical insurance fund risk profile based on intelligent decision provided in an embodiment of the present invention
The flow diagram of method, as shown, the medical insurance fund Risk Forecast Method based on intelligent decision in the present embodiment includes:
301, slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, described first in advance
If condition includes the first region and the first preset time period;
302, formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, and by the target the end of month
Slow disease population is determined as the slow sick information quantization value;
303, target area is obtained in the medical insurance policies and population structure of target time section;
304, according to the medical insurance policies and the population structure, determine the target area in the medical insurance of target time section
Payment situation, forms the medical insurance fund based revenue model;
305, target area is obtained in the medical data of target time section, and the medical data includes the target time section
Monthly slow patient's number, slow sick reimbursed sum and total reimbursed sum;
306, it is established according to the medical data and pays model by the medical insurance fund of independent variable of the end of month slow disease population;
307, according to the medical insurance fund based revenue model and described using the end of month slow disease population as the medical insurance base of independent variable
Gold expenditure model obtains described using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable;
308, by slow sick corresponding first region of information and first preset time period respectively with the doctor
It protects the corresponding target area of fund revenue and expenditure model and the target time section is matched;
309, determine that first region and the target area exactly match, first preset time period and the mesh
Marking the period is identical but corresponding time in the period different period, and first preset time period is in the target time section
Later;
310, the slow sick information quantization value is imported in the medical insurance fund revenue and expenditure model, to the income gold of medical insurance fund
Volume and amount paid are predicted;
311, the amount received of the medical insurance fund revenue and expenditure model prediction out is obtained as the expected revenue amount of money, is obtained
The amount paid predicted is as the expectan amount of money;
312, when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine
There is overdraw risk in the medical insurance fund, carry out risk management and control to the medical insurance fund.
In embodiments of the present invention, according to history medical insurance policies and population structure, medical insurance fund based revenue model is established, is obtained
The expected revenue amount of money;Then it is established according to historical medical data using the end of month slow disease population as the medical insurance fund branch depanning of independent variable
Type, then the end of month acquired under the first preset condition predicted slow disease population is imported in medical insurance fund expenditure model,
Obtain the expectan amount of money, in this process, by the basis of other conditions are constant according to the pre- of the end of month slow disease population
Phase amount paid can more pass through driving factors quantitatively analyzing influence medical insurance fund branch so that prediction result is more targeted
Amount of money degree out improves the validity being managed to the balance between revenue and expenditure of medical insurance fund.Enable medical insurance fund shift to an earlier date into
Row risk management and control guarantees the balance between revenue and expenditure of medical insurance fund.
Referring to Fig. 4, Fig. 4 is another medical insurance fund risk profile based on intelligent decision provided in an embodiment of the present invention
The flow diagram of method, as shown, the medical insurance fund Risk Forecast Method based on intelligent decision in the present embodiment includes:
401, slow sick information is obtained as the relevant driving factors of medical insurance fund according to the first preset condition, described first in advance
If condition includes the first region and the first preset time period;
402, quantification treatment is carried out to the driving factors, obtains slow sick information quantization value;
403, according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to the amount received and branch of medical insurance fund
The amount of money is predicted out, obtains the expected revenue amount of money and the expectan amount of money;
404, when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine
There is overdraw risk in the medical insurance fund;
405, the slow disease population to first region in the first preset time period is verified, and determines that slow disease population increases
Whether rate is higher than the second preset threshold;
406, if so, calibrating to the slow disease population, accurately slow disease population growth rate is obtained.
In embodiments of the present invention, using slow sick information as the driving factors of medical insurance fund, then slow sick information is carried out
Quantification treatment obtains slow sick information quantization value, further according to slow sick information magnitude combination medical insurance fund income and expense projection model, to medical insurance
The amount received and amount paid of fund are predicted, the predictablity rate of medical insurance fund amount received and amount paid is improved
And effective percentage, finally, determining that medical insurance fund there are when risk, is verified and calibrated to slow disease population, cut down from source
The factor for causing medical insurance fund to be overdrawed promotes the validity being managed to the balance between revenue and expenditure of medical insurance fund.
Fig. 5 is a kind of structural schematic diagram of electronic device provided in an embodiment of the present invention, as shown in figure 5, the electronic device
Including processor, memory, communication interface and one or more programs, wherein said one or multiple programs are stored in
In above-mentioned memory, and it is configured to be executed by above-mentioned processor, above procedure includes the instruction for executing following steps:
Slow sick information is obtained as the relevant driving factors of medical insurance fund, the first default item according to the first preset condition
Part includes the first region and the first preset time period;
Quantification treatment is carried out to the driving factors, obtains slow sick information quantization value;
It is golden to the amount received and expenditure of medical insurance fund according to the slow sick information quantization value and medical insurance fund revenue and expenditure model
Volume is predicted, the expected revenue amount of money and the expectan amount of money are obtained;
When the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, described in judgement
There is overdraw risk in medical insurance fund, carry out risk management and control to the medical insurance fund.
As it can be seen that electronic device first according to the first preset condition obtain slow sick information as the relevant driving of medical insurance fund because
Element, the first preset condition include the first region and the first preset time period;Then quantification treatment is carried out to driving factors, obtained slow
Sick information quantization value;Amount received and expenditure gold further according to slow sick quantized value and medical insurance fund revenue and expenditure model, to medical insurance fund
Volume is predicted, the expected revenue amount of money and the expectan amount of money are obtained;Finally when the expectan amount of money and the expected revenue amount of money
When difference is more than the first preset threshold, determines that the medical insurance fund has overdraw risk, risk management and control is carried out to medical insurance fund.?
During this, by carrying out quantification treatment using slow sick information as the driving factors of medical insurance fund, then according to slow sick information
Quantized value predicts the revenue and expenditure of medical insurance fund, improves the accuracy of medical insurance fund income and expense projection, and then improve to doctor
Protect the validity that the balance between revenue and expenditure of fund is managed.Enable medical insurance fund to carry out risk management and control in advance, guarantees medical insurance base
The balance between revenue and expenditure of gold.
It is described that quantification treatment is carried out to the driving factors in a possible example, slow sick information quantization value is obtained,
Include:
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population;
The target the end of month slow disease population is determined as the slow sick information quantization value.
It is described that formula calculating is carried out to the slow sick information in a possible example, obtain the target the end of month slow patient
Mouthful, comprising:
The slow sick information got include before the first preset time period the end of last month slow disease population, non-slow disease the end of last month
Population, slow sick incidence and slow die of illness die population;
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, wherein the formula are as follows:
M1=M0,
M1 '=M1+ (Mn × p1)-Md;
Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate the target moon
The slow disease population in end, Mx indicate that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
In a possible example, according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to medical insurance base
The amount received and amount paid of gold are predicted that before obtaining the expected revenue amount of money and the expectan amount of money, the method is also
Including establishing medical insurance fund revenue and expenditure model, specifically include:
Target area is obtained in the medical insurance policies and population structure of target time section;
According to the medical insurance policies and the population structure, determine that the target area is paid the fees in the medical insurance of target time section
Situation forms the medical insurance fund based revenue model;
Target area is obtained in the medical data of target time section, the medical data includes the moon of the target time section
Slow patient's number, slow sick reimbursed sum and total reimbursed sum;
It is established according to the medical data and pays model by the medical insurance fund of independent variable of the end of month slow disease population;
According to the medical insurance fund based revenue model and described using the end of month slow disease population as the medical insurance fund branch of independent variable
Model out obtains described using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable.
In a possible example, it is described according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to medical insurance
The amount received and amount paid of fund are predicted, the expected revenue amount of money and the expectan amount of money are obtained, comprising:
By slow sick corresponding first region of information and first preset time period respectively with the medical insurance base
The golden corresponding target area of revenue and expenditure model and the target time section are matched;
Determine that first region and the target area exactly match, when first preset time period is with the target
Between section be the period is identical but corresponding time is different period, and first preset time period the target time section it
Afterwards;
The slow sick information quantization value is imported in the medical insurance fund revenue and expenditure model, amount received to medical insurance fund and
Amount paid is predicted;
The amount received of the medical insurance fund revenue and expenditure model prediction out is obtained as the expected revenue amount of money, obtains prediction
The amount paid out is as the expectan amount of money.
It is described to include: to medical insurance fund progress risk management and control in a possible example
Slow disease population to first region in the first preset time period is verified, and determines that slow disease population growth rate is
It is no to be higher than the second preset threshold;
If so, calibrating to the slow disease population, accurately slow disease population growth rate is obtained.
Fig. 6 is the functional unit composition block diagram of medical insurance fund risk profile device 600 involved in the embodiment of the present invention.
The medical insurance fund risk profile device 600 is applied to electronic device, and the medical insurance fund risk profile device includes:
Acquiring unit 601, for according to the first preset condition obtain slow sick information as the relevant driving of medical insurance fund because
Element, first preset condition include the first region and the first preset time period;
Quantifying unit 602 obtains slow sick information quantization value for carrying out quantification treatment to the driving factors;
Predicting unit 603, according to the slow sick quantized value and medical insurance fund revenue and expenditure model to the amount received of medical insurance fund
It is predicted with amount paid, obtains the expected revenue amount of money and the expectan amount of money;
Risk management and control unit 604 is more than for the difference when the expectan amount of money and the expected revenue amount of money
When one preset threshold, determines that the medical insurance fund has overdraw risk, risk management and control is carried out to the medical insurance fund.
Herein, it should be noted that above-mentioned acquiring unit 601, quantifying unit 602, predicting unit 603 and risk control list
Member 604 specific work process referring to above-mentioned steps 101-104 associated description.Details are not described herein.
As can be seen that in embodiments of the present invention, medical insurance fund risk profile device is obtained according to the first preset condition first
Take slow sick information as the relevant driving factors of medical insurance fund, the first preset condition includes the first region and the first preset time
Section;Then quantification treatment is carried out to driving factors, obtains slow sick information quantization value;It is received further according to slow sick quantized value and medical insurance fund
Branch model predicts the amount received and amount paid of medical insurance fund, obtains the expected revenue amount of money and the expectan amount of money;
Finally when the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, determine that the medical insurance fund exists
Overdraw risk carries out risk management and control to medical insurance fund.In this process, by using slow sick information as the driving of medical insurance fund
Factor carries out quantification treatment, is then predicted according to slow sick information quantization value the revenue and expenditure of medical insurance fund, improves medical insurance base
The accuracy of golden income and expense projection, and then improve the validity being managed to the balance between revenue and expenditure of medical insurance fund.So that medical insurance base
Gold can carry out risk management and control in advance, guarantee the balance between revenue and expenditure of medical insurance fund.
In an alternative case, quantification treatment is being carried out to the driving factors, it is described in terms of obtaining slow sick information quantization value
Acquiring unit 601 is specifically used for:
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population;
The target the end of month slow disease population is determined as the slow sick information quantization value.
In an alternative case, formula calculating is carried out to the slow sick information described, obtains the target the end of month slow disease population side
Face, the acquiring unit 601 are specifically used for:
The slow sick information got include before the first preset time period the end of last month slow disease population, non-slow disease the end of last month
Population, slow sick incidence and slow die of illness die population;
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, wherein the formula are as follows:
M1=M0, M1 '=M1+ (Mn × p1)-Md;
Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate the target moon
The slow disease population in end, Mx indicate that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
In an alternative case, the medical insurance fund risk profile device further includes model foundation unit 605, according to
Slow disease information quantization value and medical insurance fund revenue and expenditure model predict the amount received and amount paid of medical insurance fund, obtain pre-
Before phase amount received and the expectan amount of money, the model foundation unit 605 is specifically used for:
Target area is obtained in the medical insurance policies and population structure of target time section;
According to the medical insurance policies and the population structure, determine that the target area is paid the fees in the medical insurance of target time section
Situation forms the medical insurance fund based revenue model;
Target area is obtained in the medical data of target time section, the medical data includes the moon of the target time section
Slow patient's number, slow sick reimbursed sum and total reimbursed sum;
It is established according to the medical data and pays model by the medical insurance fund of independent variable of the end of month slow disease population;
According to the medical insurance fund based revenue model and described using the end of month slow disease population as the medical insurance fund branch of independent variable
Model out obtains described using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable.
In an alternative case, in the receipts according to the slow sick information quantization value and medical insurance fund revenue and expenditure model to medical insurance fund
Enter the amount of money and amount paid is predicted, in terms of obtaining the expected revenue amount of money and the expectan amount of money, the predicting unit 603 has
Body is used for:
By slow sick corresponding first region of information and first preset time period respectively with the medical insurance base
The golden corresponding target area of revenue and expenditure model and the target time section are matched;
Determine that first region and the target area exactly match, when first preset time period is with the target
Between section be the period is identical but corresponding time is different period, and first preset time period the target time section it
Afterwards;
The slow sick information quantization value is imported in the medical insurance fund revenue and expenditure model, amount received to medical insurance fund and
Amount paid is predicted;
The amount received of the medical insurance fund revenue and expenditure model prediction out is obtained as the expected revenue amount of money, obtains prediction
The amount paid out is as the expectan amount of money.
In an alternative case, in terms of carrying out risk management and control to the medical insurance fund, the risk management and control unit 604 is specific
For:
Slow disease population to first region in the first preset time period is verified, and determines that slow disease population growth rate is
It is no to be higher than the second preset threshold;
If so, calibrating to the slow disease population, accurately slow disease population growth rate is obtained.
The embodiment of the present invention also provides a kind of computer storage medium, wherein computer storage medium storage is for electricity
The computer program of subdata exchange, the computer program make computer execute any as recorded in above method embodiment
Some or all of method step, above-mentioned computer include mobile terminal.
The embodiment of the present invention also provides a kind of computer program product, and above-mentioned computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, above-mentioned computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of either record method step in method embodiment.The computer program product can be a software installation
Packet, above-mentioned computer includes mobile terminal.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of said units, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a memory, including some instructions are used so that a computer equipment (can
For personal computer, server or network equipment etc.) execute all or part of step of each embodiment above method of the application
Suddenly.And memory above-mentioned includes: USB flash disk, read-only memory (Read-Only Memory, ROM), random access memory
The various media that can store program code such as (Random Access Memory, RAM), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
It may include: flash disk, ROM, RAM, disk or CD etc..
The embodiment of the present invention has been described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas;
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the application
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (10)
1. a kind of medical insurance fund Risk Forecast Method based on intelligent decision, which is characterized in that the described method includes:
Slow sick information is obtained as the relevant driving factors of medical insurance fund, the first preset condition packet according to the first preset condition
Include the first region and the first preset time period;
Quantification treatment is carried out to the driving factors, obtains slow sick information quantization value;
According to the slow sick information quantization value and medical insurance fund revenue and expenditure model to the amount received of medical insurance fund and amount paid into
Row prediction, obtains the expected revenue amount of money and the expectan amount of money;
When the difference of the expectan amount of money and the expected revenue amount of money is more than the first preset threshold, the medical insurance is determined
There is overdraw risk in fund, carry out risk management and control to the medical insurance fund.
2. being obtained the method according to claim 1, wherein described carry out quantification treatment to the driving factors
Slow disease information quantization value, comprising:
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population;
The target the end of month slow disease population is determined as the slow sick information quantization value.
3. according to the method described in claim 2, it is characterized in that, described carry out formula calculating, acquisition to the slow sick information
The target the end of month slow disease population, comprising:
The slow sick information got include before the first preset time period the end of last month slow disease population, non-slow patient the end of last month
Mouth, slow sick incidence and slow die of illness die population;
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population, wherein the formula are as follows:
M1=M0,
M1 '=M1+ (Mn × p1)-Md;
Wherein, M0 indicates that slow disease population the end of last month, M1 indicate that the beginning of the month slow disease population in target month, M1 ' indicate that the target the end of month is slow
Disease population, Mx indicate that non-slow disease population the end of last month, p1 indicate slow sick incidence, and Md, which indicates to die of illness slowly, dies population.
4. according to the method described in claim 3, it is characterized in that, being received according to the slow sick information quantization value and medical insurance fund
Branch model predicts the amount received and amount paid of medical insurance fund, obtain the expected revenue amount of money and the expectan amount of money it
Before, the method also includes establishing medical insurance fund revenue and expenditure model, specifically include:
Target area is obtained in the medical insurance policies and population structure of target time section;
According to the medical insurance policies and the population structure, determine the target area in the medical insurance payment feelings of target time section
Condition forms the medical insurance fund based revenue model;
Target area is obtained in the medical data of target time section, the medical data includes the monthly slow of the target time section
Patient's number, slow sick reimbursed sum and total reimbursed sum;
It is established according to the medical data and pays model by the medical insurance fund of independent variable of the end of month slow disease population;
According to the medical insurance fund based revenue model and described using the end of month slow disease population as the medical insurance fund branch depanning of independent variable
Type obtains described using the end of month slow disease population as the medical insurance fund revenue and expenditure model of independent variable.
5. method described in -4 according to claim 1, which is characterized in that described according to the slow sick information quantization value and medical insurance base
Golden revenue and expenditure model predicts the amount received and amount paid of medical insurance fund, obtains the expected revenue amount of money and expectan gold
Volume, comprising:
Slow sick corresponding first region of information and first preset time period are received with the medical insurance fund respectively
The corresponding target area of branch model and the target time section are matched;
Determine that first region and the target area exactly match, first preset time period and the target time section
For the period that the period is identical but corresponding time is different, and first preset time period is after the target time section;
The slow sick information quantization value is imported in the medical insurance fund revenue and expenditure model, to the amount received and expenditure of medical insurance fund
The amount of money is predicted;
The amount received that the medical insurance fund revenue and expenditure model prediction goes out is obtained as the expected revenue amount of money, obtains and predicts
The amount paid is as the expectan amount of money.
6. according to the method described in claim 5, it is characterized in that, described include: to medical insurance fund progress risk management and control
Slow disease population to first region in the first preset time period is verified, and determines whether slow disease population growth rate is high
In the second preset threshold;
If so, calibrating to the slow disease population, accurately slow disease population growth rate is obtained.
7. a kind of medical insurance fund risk profile device, which is characterized in that the medical insurance fund risk profile device includes:
Acquiring unit, it is described as the relevant driving factors of medical insurance fund for obtaining sick information slowly according to the first preset condition
First preset condition includes the first region and the first preset time period;
Quantifying unit obtains slow sick information quantization value for carrying out quantification treatment to the driving factors;
Predicting unit, it is golden to the amount received and expenditure of medical insurance fund according to the slow sick quantized value and medical insurance fund revenue and expenditure model
Volume is predicted, the expected revenue amount of money and the expectan amount of money are obtained;
Risk management and control unit, for being more than the first default threshold when the difference of the expectan amount of money and the expected revenue amount of money
When value, determines that the medical insurance fund has overdraw risk, risk management and control is carried out to the medical insurance fund.
8. device according to claim 7, which is characterized in that carrying out quantification treatment to the driving factors, obtaining slow
In terms of sick information quantization value, the acquiring unit is specifically used for:
Formula calculating is carried out to the slow sick information, obtains the target the end of month slow disease population;
The target the end of month slow disease population is determined as the slow sick information quantization value.
9. a kind of electronic device, including processor, memory, communication interface, and one or more programs, one or more
A program is stored in the memory, and is configured to be executed by the processor, and described program includes being used for right of execution
Benefit requires the instruction of the step in 1-6 any means.
10. a kind of computer readable storage medium, storage is used for the computer program of electronic data interchange, wherein the calculating
Machine program makes the instruction of step described in any one of computer perform claim requirement 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811525770.2A CN109712004A (en) | 2018-12-13 | 2018-12-13 | A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811525770.2A CN109712004A (en) | 2018-12-13 | 2018-12-13 | A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109712004A true CN109712004A (en) | 2019-05-03 |
Family
ID=66256505
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811525770.2A Pending CN109712004A (en) | 2018-12-13 | 2018-12-13 | A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109712004A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008257310A (en) * | 2007-03-31 | 2008-10-23 | Nli Research Institute | Public pension finance forecasting system and public pension finance forecasting program |
US20110078073A1 (en) * | 2009-09-30 | 2011-03-31 | Suresh Kumar Annappindi | System and method for predicting consumer credit risk using income risk based credit score |
CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
WO2017157030A1 (en) * | 2016-03-18 | 2017-09-21 | 深圳市前海安测信息技术有限公司 | Medical insurance premium discount actuarial system and method |
CN107767009A (en) * | 2017-06-29 | 2018-03-06 | 平安医疗健康管理股份有限公司 | Medical Benefits Fund actuarial Forecasting Methodology and device |
-
2018
- 2018-12-13 CN CN201811525770.2A patent/CN109712004A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008257310A (en) * | 2007-03-31 | 2008-10-23 | Nli Research Institute | Public pension finance forecasting system and public pension finance forecasting program |
US20110078073A1 (en) * | 2009-09-30 | 2011-03-31 | Suresh Kumar Annappindi | System and method for predicting consumer credit risk using income risk based credit score |
WO2017157030A1 (en) * | 2016-03-18 | 2017-09-21 | 深圳市前海安测信息技术有限公司 | Medical insurance premium discount actuarial system and method |
CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
CN107767009A (en) * | 2017-06-29 | 2018-03-06 | 平安医疗健康管理股份有限公司 | Medical Benefits Fund actuarial Forecasting Methodology and device |
Non-Patent Citations (3)
Title |
---|
吴彬;罗仁夏;曹建平;: "等维新息灰色系统GM(1, 1)模型在福建省医保统筹基金风险预测中的应用", 中国卫生统计, no. 04, 25 August 2015 (2015-08-25), pages 63 - 65 * |
吴彬;罗仁夏;曹建平;: "等维新息灰色系统GM(1, 1)模型在福建省医保统筹基金风险预测中的应用", 中国卫生统计, no. 04, pages 63 - 65 * |
马桂峰;朱忠池;仇蕾洁;盛红旗;安洪庆;高倩倩;井淇;张惠卿;杨蕾;: "城镇职工基本医疗保险基金收支失衡风险预测研究", 中国卫生统计, no. 03, 25 June 2018 (2018-06-25), pages 105 - 107 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ferrier et al. | Analysis of uncompensated hospital care using a DEA model of output congestion | |
Vogt et al. | How has hospital consolidation affected the price and quality of hospital care? | |
McGuire | Demand for health insurance | |
Chomik et al. | Population Ageing and Social Security in A sia | |
Price | Optimal rotation with declining discount rate | |
Paulon et al. | Joint modeling of recurrent events and survival: a Bayesian non-parametric approach | |
Schmeiser et al. | A joint valuation of premium payment and surrender options in participating life insurance contracts | |
CN109559810A (en) | A kind of Optimizing Configuration System of hospital department fixing post quantity | |
Epstein et al. | Costs and prices for inpatient care in England: mirror twins or distant cousins? | |
WO2020070463A1 (en) | System for modelling financial information | |
O'Neill et al. | Discharges with surgical procedures performed less often than once per month per hospital account for two-thirds of hospital costs of inpatient surgery | |
CN109472710A (en) | A kind of medical insurance fund Risk Forecast Method and device | |
CN109712004A (en) | A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision | |
CN109785154A (en) | A kind of Risk Forecast Method and device based on intelligent decision | |
CN110210985A (en) | Basic medical insurance policies adjust the quantization method influenced on fund expenditure and system | |
Nandi et al. | Univariate time series forecasting: A study of monthly tax revenue of Bangladesh | |
Fugar et al. | Impact of chronic thrombocytopenia on in‐hospital outcomes and healthcare resource utilization after transcatheter aortic valve replacement | |
Suzuki | Sovereign risk and procyclical fiscal policy in emerging market economies | |
Nicholas | Will Medicare Advantage Benchmark Reforms Impact Plan Rebates and Enrollment? | |
Shahraki et al. | Projecting the shortages and surpluses of general practitioners in Iran | |
Xie et al. | Development of a novel hospital payment system–big data diagnosis & intervention Packet | |
CN109785150A (en) | A kind of medical insurance fund Risk Forecast Method and device based on intelligent decision | |
Li et al. | Information acquisition in new product introduction | |
JP2011054051A (en) | Order processing system, method for the same, and program | |
CN109615544A (en) | Submit an expense account processing method, device, terminal and computer readable storage medium |
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 |