CN110245960A - A kind of medical insurance antifraud system and method based on computer control - Google Patents
A kind of medical insurance antifraud system and method based on computer control Download PDFInfo
- Publication number
- CN110245960A CN110245960A CN201910424564.0A CN201910424564A CN110245960A CN 110245960 A CN110245960 A CN 110245960A CN 201910424564 A CN201910424564 A CN 201910424564A CN 110245960 A CN110245960 A CN 110245960A
- Authority
- CN
- China
- Prior art keywords
- medical insurance
- doctor
- prescription
- analysis module
- handler
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of medical insurance antifraud system and methods based on computer control, the medical insurance antifraud system includes medical insurance data input module, medical insurance data analysis module, medical insurance database and medical insurance data outputting module, the medical insurance data input module is for inputting this medical insurance data information, the medical insurance data analysis module is used for the fraud index of this medical insurance behavior, the medical insurance database is for storing medical insurance data information, the medical insurance data outputting module is for exporting whether this medical insurance behavior is fraud, the medical insurance data input module and medical insurance data analysis module, the connection of medical insurance database, the medical insurance data analysis module and medical insurance database, the connection of medical insurance data outputting module, the this time medical insurance data information includes medical insurance bill ID, insured person ID, this doctor ID that writes a prescription, this time cure Protect handler ID, this time medical insurance value, species name of this time writing a prescription.
Description
Technical field
The present invention relates to computer big data processing field, specifically a kind of medical insurance antifraud system based on computer control
System and method.
Background technique
Medical insurance refers to social medical insurance.Social medical insurance is state and society according to certain laws and regulations, is to guarantor
The social security system for hindering basic medical demand guarantee when the labourer in range provides illness and establishing.Basic medical insurance base
Gold is made of risk-pooling fund and personal account.The basic medical insurance expense that worker individual pays all is included in personal account；Employment
The basic medical insurance expense that unit is paid is divided into two parts, and a part is divided into personal account, and a part is for establishing risk-pooling fund
Medical insurance effectively controls the excessively rapid growth of medical expense, reduces the medical-risk of people generated by disease, alleviates people
Medical burden.But some criminals but medical insurance fraud, it is played one's own game using medical insurance, and nothing in existing technology
Effect effectively controls medical insurance fraud.
Summary of the invention
The purpose of the present invention is to provide a kind of medical insurance antifraud system and methods based on computer control, existing to solve
There is the problems in technology.
To achieve the above object, the invention provides the following technical scheme:
A kind of medical insurance antifraud system based on computer control, which includes medical insurance data input module,
Medical insurance data analysis module, medical insurance database and medical insurance data outputting module, medical insurance data input module are this time cured for inputting
Data information is protected, medical insurance data analysis module is used for the fraud index of this medical insurance behavior, and medical insurance database is for storing medical insurance
Data information, medical insurance data outputting module is for exporting whether this medical insurance behavior is fraud, medical insurance data input module
It is connect with medical insurance data analysis module, medical insurance database, medical insurance data analysis module and medical insurance database, medical insurance data export mould
Block connection.
Preferably, this time medical insurance data information include medical insurance bill ID, insured person ID, the doctor ID that this time writes a prescription,
This time medical insurance handler ID, this time medical insurance value, species name of this time writing a prescription, medical insurance database include insured person's module, doctor
Raw module, medical insurance handler's module, insured person's module includes the credit scoring of insured person's history medical insurance data and insured person, doctor
Module includes that the history of doctor is write a prescription data and the credit scoring of doctor, and medical insurance handler's module includes the history of medical insurance handler
The credit rating of data and medical insurance handler is examined, medical insurance data analysis module includes insured person's analysis module, doctor's analysis mould
Block, medical insurance handler analysis module and comprehensive analysis module, insured person's analysis module and medical insurance data input module, insured person's mould
Block connection, insured person's analysis module analyze mould for calculating fraud assessed value of the insured person in this medical insurance behavior, doctor
Block is connect with medical insurance data input module, client module, and doctor's analysis module is used for doctor's taking advantage of in this medical insurance behavior
Assessed value is cheated, medical insurance handler analysis module is connect with medical insurance data input module, medical insurance handler's module, medical insurance handler point
Analysis module is for calculating fraud assessed value of the medical insurance handler in this medical insurance behavior, comprehensive analysis module and insured person point
Module, doctor's analysis module, the connection of medical insurance handler's analysis module are analysed, comprehensive analysis module is for calculating this medical insurance behavior
Comprehensive assessment value is cheated, comprehensive analysis module is connect with data outputting module
Preferably, insured person's history medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription
Doctor ID, the history medical insurance handler ID of insured person and insured person's history are write a prescription species name, and the history of doctor is write a prescription data packet
The history for including doctor is write a prescription expense, and the history audit data of medical insurance handler include the history examination & approval reimbursement ratio of medical insurance handler
Example.
Preferably, insured person's analysis module include medical insurance analysis module, doctor's frequency analysis module of writing a prescription,
Medical insurance handler's frequency analysis module and write a prescription drugs analysis module, medical insurance analysis module be used for this medical insurance and
History medical insurance comparative analysis, for analyzing, the insured person is thus secondary to write a prescription what doctor write a prescription to doctor's frequency analysis module of writing a prescription
Frequency, medical insurance handler's frequency analysis module is used to analyze the insured person, and thus secondary medical insurance handler examines the frequency submitted an expense account, and opens
Drug variety comparative analysis that medicine drugs analysis module is used to this writing a prescription drug variety and history is write a prescription, doctor's analysis module are used
It writes a prescription expense comparative analysis in this history of write a prescription expense and doctor by doctor, medical insurance handler's analysis module will be for that will cure
Protect handler this examination & approval reimbursement ratio and medical insurance handler history submit an expense account ratio comparative analysis.
It is a kind of based on computer control medical insurance antifraud method, the medical insurance antifraud method the following steps are included:
(1) this medical insurance data information is inputted；
(2) this medical insurance data information is analyzed；
(3) export whether this medical insurance behavior is fraud.
Preferably, medical insurance antifraud method the following steps are included:
(1) medical insurance data input module inputs this medical insurance data information, and medical insurance data information includes medical insurance bill ID, insured person
ID, the doctor ID that this time writes a prescription, this time medical insurance handler ID, this time medical insurance value, species name of this time writing a prescription；
(2) medical insurance data analysis module reads this medical insurance data information from medical insurance data input module, and according to this doctor
It protects data information and reads history medical insurance data information from medical insurance database, calculate the fraud assessed value X of insured person, doctor takes advantage of
Cheat assessed value Y, the fraud assessed value Z of medical insurance handler and fraud comprehensive assessment value V；
(3) data outputting module from comprehensive analysis module read fraud comprehensive assessment value V, and compare fraud comprehensive assessment value V with
The size of threshold value V0 is cheated,
If cheating comprehensive assessment value V is less than V0, this non-fraud of medical insurance behavior is exported,
If cheating comprehensive assessment value V is more than or equal to V0, the secondary medical insurance behavior fraud is exported.
Preferably, step (2) the following steps are included:
1) according to insured person ID, insured person's analysis module reads insured person's history medical insurance data from insured person's module, insured person's
History medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription the history medical insurance of doctor ID, insured person
Handler ID and insured person's history are write a prescription species name,
Medical insurance analysis module reads N1 times before insured person medical insurance value each time, and by first N1 times medical insurance
Value by sequence arrangement from small to large, be denoted as a1, a2 ..., aN1, the maximum value and minimum of N1 middle medical insurance value before removing
It is worth, then medical insurance reference threshold are as follows:
a0=[a2+a3+…+a(N-1))]/(N-2),
Then medical insurance assessed value is A0=[abs (P-a0)]/a0, and P is this medical insurance value；
Doctor's frequency analysis module of writing a prescription reads N2 times before the insured person doctor ID that writes a prescription, if the doctor ID that this time writes a prescription is N2 times first
The doctor ID that writes a prescription in occur n1 times, then doctor's frequency of writing a prescription be B0=n1/N2；
Medical insurance handler's frequency analysis module reads N3 times before insured person medical insurance handler ID, if this time medical insurance handler ID exists
Occur n2 times in first N3 times medical insurance handler ID, then medical insurance handler frequency is C0=n2/N3；
Write a prescription drugs analysis module, if drug variety of this time writing a prescription is Q kind, the title of this Q kind drug variety be respectively M1, M2,
M3 ..., MQ, N4 drug variety of writing a prescription each time before reading, in drug of writing a prescription in N4 time before being located at, drug M1 appearance it is secondary
Number be D1, drug M2 occur number be D2 ..., drug MQ occur probability be DS, by D1, D2 ... DS and drug number threshold
Value R compares, and remembers in this Q kind drug variety, and type number of the drug variety frequency of occurrence greater than drug frequency threshold value R is d, then opens
Medicine drug evaluations value is D0=d/Q,
Then the fraud assessed value of insured person is
The credit scoring of X=x1*A0+x2*B0+x3*C0+x4*D0+x5* (1-x0), x0 insured person thus, x1, x2, x3, x4 are equal
For constant.
2) according to the ID of doctor of writing a prescription, doctor's analysis module from client module read the doctor that writes a prescription before N5 times each time
Write a prescription cost value, and first N5 times expense of writing a prescription arranged by sequence from small to large, note e1, e2 ..., eN5, remove preceding N5
Maximum value and minimum value in expense of writing a prescription in secondary, then expense of writing a prescription reference threshold are as follows:
E0=[e2+e3+ ...+e (N-1)]/(N-2),
Assessment of fees of then writing a prescription value is E0=[abs (R-e0)]/e0, and R is this expense of writing a prescription,
The fraud assessed value of doctor is Y=y1*E0+y2* (1-y0), and the credit scoring of y0 doctor thus, y1, y2 are constant
3) according to medical insurance handler ID, medical insurance handler analysis module is from N6 times before medical insurance handler's module reading medical insurance handler
Examination & approval each time submit an expense account ratio, and first N6 time examination & approval reimbursement ratio is arranged by sequence from small to large, remember f1,
F2 ..., fN6, the maximum value and minimum value in reimbursement ratio are examined before removing in N6 time, then examines reimbursement ratio reference threshold
Are as follows:
F0=(f2+f3+ ...+f (N-1))/(N-2),
Assessment of fees of then writing a prescription value is F0=[abs (S-f0)]/f0, and S is that ratio is submitted an expense account in this examination & approval,
The fraud assessed value of medical insurance handler is Z=z1*F0+z2* (1-z0), the credit scoring of z0 medical insurance handler thus, z1,
Z2 is constant；
4) comprehensive analysis module calculating fraud comprehensive assessment value V=v1*X+v2*Y+v3*Z, v1+v2+v3=1, v1, v2, v3 is
Constant.
Preferably, insured person's credit rating x0=0.6J0+0.2J1+O.2J2 in step 1), J0 are insured person
Initial credit grading, J1 be credit rating of the doctor to insured person, J2 be credit rating of the medical insurance handler to insured person；
O.2K2, K0 is that the initial credit of doctor is graded to step 2 doctor's credit rating y0=0.6K0+0.2K1+, and K1 is insured person
Credit rating to doctor, K2 are credit rating of the medical insurance handler to doctor；
O.2T1+ O.2T2, T0 is the initial credit of medical insurance handler by step 3) medical insurance handler's credit rating x0=O.2T0+
Grading, T1 are credit rating of the insured person to medical insurance handler, and T2 is credit rating of the doctor to medical insurance handler.
Compared with prior art, the beneficial effects of the present invention are: the present invention is from insured person, doctor, medical insurance handler three
The medical insurance data of aspect analyze medical insurance behavior, obtain fraud integrated value, when fraud comprehensive assessment value V is less than fraud threshold value
V0 then exports this non-fraud of medical insurance behavior, if exporting when fraud comprehensive assessment value V is more than or equal to fraud threshold value V0
The secondary medical insurance behavior fraud, so as to realize effective control to medical insurance antifraud behavior.
Detailed description of the invention
Fig. 1 is a kind of medical insurance antifraud system module schematic diagram based on computer control of the present invention；
Fig. 2 is a kind of connection schematic diagram of the medical insurance antifraud system based on computer control of the present invention；
Fig. 3 is a kind of flow diagram of the medical insurance antifraud method based on computer control of the present invention；
The flow diagram of the step of Fig. 4 is a kind of medical insurance antifraud method based on computer control of the invention (2).
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.
Please refer to Fig. 1~4, in the embodiment of the present invention, a kind of medical insurance antifraud system based on computer control, the medical insurance
Antifraud system includes medical insurance data input module, medical insurance data analysis module, medical insurance database and medical insurance data outputting module,
Medical insurance data input module is taken advantage of for inputting this medical insurance data information, medical insurance data analysis module for this medical insurance behavior
Index is cheated, medical insurance database is for exporting this medical insurance behavior for storing medical insurance data information, medical insurance data outputting module
No is fraud, and medical insurance data input module is connect with medical insurance data analysis module, medical insurance database, and medical insurance data analyze mould
Block is connect with medical insurance database, medical insurance data outputting module.
This time medical insurance data information includes medical insurance bill ID, insured person ID, the doctor ID that this time writes a prescription, this time medical insurance handler
ID, this time medical insurance value, species name of this time writing a prescription, medical insurance database include that insured person's module, client module, medical insurance are handled
People's module, insured person's module include the credit scoring of insured person's history medical insurance data and insured person, and client module includes doctor's
History is write a prescription data and the credit scoring of doctor, and medical insurance handler's module includes the history examination & approval data and medical insurance of medical insurance handler
The credit rating of handler, medical insurance data analysis module include insured person's analysis module, doctor's analysis module, medical insurance handler point
Analysis module and comprehensive analysis module, insured person's analysis module are connect with medical insurance data input module, insured person's module, insured person point
Analysis module is inputted for calculating fraud assessed value of the insured person in this medical insurance behavior, doctor's analysis module and medical insurance data
Module, client module connection, doctor's analysis module are used for fraud assessed value of the doctor in this medical insurance behavior, and medical insurance is handled
People's analysis module is connect with medical insurance data input module, medical insurance handler's module, and medical insurance handler's analysis module is for calculating doctor
Fraud assessed value of the handler in this medical insurance behavior is protected, comprehensive analysis module and insured person's analysis module, doctor analyze
Module, the connection of medical insurance handler's analysis module, comprehensive analysis module are used to calculate the fraud comprehensive assessment value of this medical insurance behavior,
Comprehensive analysis module is connect with data outputting module
Insured person's history medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription doctor ID, insured person
History medical insurance handler ID and insured person's history write a prescription species name, the history of doctor data of writing a prescription include that the history of doctor is opened
Expenses for medicine is used, and the history audit data of medical insurance handler include the history examination & approval reimbursement ratio of medical insurance handler.
Insured person's analysis module includes medical insurance analysis module, doctor's frequency analysis module of writing a prescription, medical insurance handler's frequency
Rate analysis module and drugs analysis module of writing a prescription, medical insurance analysis module are used for this medical insurance and history medical insurance
Comparative analysis, doctor's frequency analysis module of writing a prescription is for analyzing the insured person frequency that thus the secondary doctor that writes a prescription writes a prescription, medical insurance warp
Doing people's frequency analysis module, thus secondary medical insurance handler examines the frequency submitted an expense account, drugs analysis mould of writing a prescription for analyzing the insured person
Drug variety comparative analysis that block is used to this writing a prescription drug variety and history is write a prescription, doctor's analysis module are used for doctor this time
The history of write a prescription expense and doctor write a prescription expense comparative analysis, medical insurance handler's analysis module is used for medical insurance handler this time
Examination & approval reimbursement ratio and medical insurance handler history submit an expense account ratio comparative analysis.
It is a kind of based on computer control medical insurance antifraud method, the medical insurance antifraud method the following steps are included:
(1) medical insurance data input module inputs this medical insurance data information, and medical insurance data information includes that medical insurance bill ID is, is insured
Person ID is, the doctor ID that this time writes a prescription is, this time medical insurance handler ID is, this medical insurance value is, species name of this time writing a prescription；
(2) medical insurance data analysis module reads this medical insurance data information from medical insurance data input module, and according to this doctor
It protects data information and reads history medical insurance data information from medical insurance database, calculate the fraud assessed value X of insured person, doctor takes advantage of
Cheat assessed value Y, the fraud assessed value Z of medical insurance handler and fraud comprehensive assessment value V；
1) according to insured person ID, insured person's analysis module reads insured person's history medical insurance data from insured person's module, insured person's
History medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription the history medical insurance of doctor ID, insured person
Handler ID and insured person's history are write a prescription species name,
Medical insurance analysis module reads 5 times before insured person medical insurance values each time, and by first 5 times medical insurance values
By sequence arrangement from small to large, a1=12, a2=20, a3=28, a4=37, a5=46 are denoted as, medical insurance value in first 5 times is removed
Maximum value and minimum value, then medical insurance reference threshold are as follows:
a0=(a2+a3+a4)/3=28.3,
This medical insurance value P=33,
Then medical insurance assessed value is A0=/a0=0.166 [abs (P-a0)]；
Doctor's frequency analysis module of writing a prescription reads the previous doctor ID that writes a prescription of insured person, this doctor ID that writes a prescription is opened at first 10 times
Occur 2 times in medicine doctor ID, then doctor's frequency of writing a prescription is B0=1/5；
Medical insurance handler's frequency analysis module reads 10 times before insured person medical insurance handler ID, if this time medical insurance handler ID exists
Occur in first N3 times medical insurance handler ID 1 time, then medical insurance handler frequency is C0=1/10；
It writes a prescription drugs analysis module, this drug variety of writing a prescription is 2 kinds, and the title of this 2 kinds of drug varieties is respectively that feel cough double clear
Capsule and cefuroxime axetil tablets read preceding 10 drug varieties of writing a prescription each time, are located in first 10 times in drug of writing a prescription, and feel cough
The number that double clearing capsules occur is 1, and the number that cefuroxime axetil tablets occur is 2, by 1,2 compared with drug frequency threshold value R=4, then
Type number of the drug variety frequency of occurrence greater than drug frequency threshold value R is 0, then drug evaluations value of writing a prescription is D0=0,
The initial credit grading J0 of insured person is 0.7, and doctor is 0.95 to the credit rating J1 of insured person, and medical insurance handler is to ginseng
The credit rating J2 of guarantor person is 0.92,
Then insured person's credit rating x0=0.6J0+0.2J1+O.2J2=0.794,
Then the fraud assessed value of insured person is
X=x1*A0+x2*B0+x3*C0+x4*D0+x5*(1-x0)=0.1*0.166+0.3*1/5+0.3*1/10+0.2*0+0.1*
0.206=0.1272；
2) according to the ID of doctor of writing a prescription, doctor's analysis module from client module read the doctor that writes a prescription before 20 writing a prescription each time
Cost value, and by first 20 times write a prescription expense by from small to large sequence arrange, note 8,13.5,14.7,16.9,21.6,23.3,
24.2,25.1,27.3,28.9,30,31.6,33,35.7,36.2,37.9,38.3,39.8,42,46, remove and is opened in first 20 times
Maximum value and minimum value in expenses for medicine use, then expense of writing a prescription reference threshold are as follows:
E0=[e2+e3+ ...+e19]/18=28.89,
This expense of writing a prescription is 33
Assessment of fees of then writing a prescription value is E0=/e0=0.142 [abs (R-e0)],
The initial credit grading K0 of doctor is 0.7, and insured person is 0.9 to the credit rating K1 of doctor, and medical insurance handler is to doctor
Credit rating K2 be 0.98
Then doctor's credit rating y0=0.6K0+0.2K1+ is O.2K2=0.796
The fraud assessed value of doctor is
Y=y1*E0+y2*(1-y0)=0.3*0.142+0.1*0.204=0.063
3) according to medical insurance handler ID, medical insurance handler analysis module is from 10 times before medical insurance handler's module reading medical insurance handler
Examination & approval each time submit an expense account ratio, and first N6 time examination & approval reimbursement ratio is arranged by sequence from small to large, remember 0.4,
0.4,0.4,0.4,0.4,0.4,0.6,0.6,0.6,0.6, maximum value and minimum before removing in N6 times in examination & approval reimbursement ratio
Value, then examine reimbursement ratio reference threshold are as follows:
F0=(f2+f3+ ...+f9)/8=0.475,
This examination & approval reimbursement ratio is 0.4
Assessment of fees of then writing a prescription value is F0=/f0=0.158 [abs (S-f0)]
The initial credit grading T0 of medical insurance handler is 70, and insured person is 92 to the credit rating T1 of medical insurance handler, doctor couple
The credit rating T2 of medical insurance handler is 98,
O.2T1+ O.2T2=0.8 medical insurance handler's credit rating x0=O.2T0+.
The fraud assessed value of medical insurance handler is
Z=z1*F0+z2*(1-z0)=0.2*0.158+0.2*0.2=0.0716
4) comprehensive analysis module calculates fraud comprehensive assessment value
V=v1*X+v2*Y+v3*Z=0.2*0.1272+0.4*0.063+0.4*0.0716=0.07928。
(3) data outputting module reads fraud comprehensive assessment value V from comprehensive analysis module, and compares fraud comprehensive assessment value
The size of V=0.07984 and fraud threshold value V0=0.1,
It cheats comprehensive assessment value V and is less than V0, then export this non-fraud of medical insurance behavior.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.
Claims (8)
1. a kind of medical insurance antifraud system based on computer control, it is characterised in that: the medical insurance antifraud system includes doctor
Protect data input module, medical insurance data analysis module, medical insurance database and medical insurance data outputting module, the medical insurance data input
Module is used for the fraud index of this medical insurance behavior for inputting this medical insurance data information, the medical insurance data analysis module,
For storing medical insurance data information, the medical insurance data outputting module is used to export this medical insurance behavior is the medical insurance database
No is fraud, and the medical insurance data input module is connect with medical insurance data analysis module, medical insurance database, the medical insurance number
It is connect according to analysis module with medical insurance database, medical insurance data outputting module.
2. it is according to claim 1 it is a kind of based on computer control medical insurance antifraud system, it is characterised in that: it is described this
Secondary medical insurance data information includes medical insurance bill ID, insured person ID, the doctor ID that this time writes a prescription, this time medical insurance handler ID, this time doctor
Cost value, species name of this time writing a prescription are protected, the medical insurance database includes insured person's module, client module, medical insurance handler's mould
Block, insured person's module include the credit scoring of insured person's history medical insurance data and insured person, and the client module includes doctor
Raw history is write a prescription data and the credit scoring of doctor, and the medical insurance handler module includes the history examination & approval number of medical insurance handler
According to the credit rating with medical insurance handler, the medical insurance data analysis module include insured person's analysis module, doctor's analysis module,
Medical insurance handler analysis module and comprehensive analysis module, insured person's analysis module and medical insurance data input module, insured person
Module connection, insured person's analysis module are described for calculating fraud assessed value of the insured person in this medical insurance behavior
Doctor's analysis module is connect with medical insurance data input module, client module, doctor's analysis module for doctor this
Fraud assessed value in medical insurance behavior, the medical insurance handler analysis module and medical insurance data input module, medical insurance handler's mould
Block connection, the medical insurance handler analysis module are used to calculate fraud assessment of the medical insurance handler in this medical insurance behavior
Value, the comprehensive analysis module is connect with insured person's analysis module, doctor's analysis module, medical insurance handler's analysis module, described
Comprehensive analysis module is used to calculate the fraud comprehensive assessment value of this medical insurance behavior, and the comprehensive analysis module and data export mould
Block connection.
3. a kind of medical insurance antifraud system based on computer control according to claim 2, it is characterised in that: the ginseng
Guarantor person's history medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription the history of doctor ID, insured person
Medical insurance handler ID and insured person's history are write a prescription species name, and the history of doctor data of writing a prescription include that the history of doctor is write a prescription
Expense, the history audit data of the medical insurance handler include the history examination & approval reimbursement ratio of medical insurance handler.
4. a kind of medical insurance antifraud system based on computer control according to claim 3, it is characterised in that: the ginseng
Guarantor person's analysis module includes medical insurance analysis module, doctor's frequency analysis module of writing a prescription, medical insurance handler's frequency analysis module
With drugs analysis module of writing a prescription, the medical insurance analysis module is used to compare this medical insurance and history medical insurance point
Analysis, doctor's frequency analysis module of writing a prescription is for analyzing the insured person frequency that thus the secondary doctor that writes a prescription writes a prescription, the medical insurance
Handler's frequency analysis module is used to analyze the insured person, and thus secondary medical insurance handler examines the frequency submitted an expense account, the drug of writing a prescription
Drug variety comparative analysis that analysis module is used to this writing a prescription drug variety and history is write a prescription, doctor's analysis module are used for
By doctor, this history of write a prescription expense and doctor is write a prescription expense comparative analysis, and the medical insurance handler analysis module is used for will
Medical insurance handler this examination & approval reimbursement ratio and medical insurance handler history submit an expense account ratio comparative analysis.
5. it is a kind of based on computer control medical insurance antifraud method, it is characterised in that: the medical insurance antifraud method include with
Lower step:
(1) this medical insurance data information is inputted；
(2) this medical insurance data information is analyzed；
(3) export whether this medical insurance behavior is fraud.
6. a kind of medical insurance antifraud method based on computer control according to claim 5, it is characterised in that: the doctor
Protect antifraud method the following steps are included:
(1) medical insurance data input module inputs this medical insurance data information, and medical insurance data information includes medical insurance bill ID, insured person
ID, the doctor ID that this time writes a prescription, this time medical insurance handler ID, this time medical insurance value, species name of this time writing a prescription；
(2) medical insurance data analysis module reads this medical insurance data information from medical insurance data input module, and according to this doctor
It protects data information and reads history medical insurance data information from medical insurance database, calculate the fraud assessed value X of insured person, doctor takes advantage of
Cheat assessed value Y, the fraud assessed value Z of medical insurance handler and fraud comprehensive assessment value V；
(3) data outputting module from comprehensive analysis module read fraud comprehensive assessment value V, and compare fraud comprehensive assessment value V with
The size of threshold value V0 is cheated,
If cheating comprehensive assessment value V is less than V0, this non-fraud of medical insurance behavior is exported,
If cheating comprehensive assessment value V is more than or equal to V0, the secondary medical insurance behavior fraud is exported.
7. a kind of medical insurance antifraud method based on computer control according to claim 6, it is characterised in that: the step
Suddenly (2) the following steps are included:
1) according to insured person ID, insured person's analysis module reads insured person's history medical insurance data from insured person's module, insured person's
History medical insurance data include that insured person's history medical insurance value, the history of insured person are write a prescription the history medical insurance of doctor ID, insured person
Handler ID and insured person's history are write a prescription species name,
Medical insurance analysis module reads N1 times before insured person medical insurance value each time, and by first N1 times medical insurance
Value by sequence arrangement from small to large, be denoted as a1, a2 ..., aN1, the maximum value and minimum of N1 middle medical insurance value before removing
It is worth, then medical insurance reference threshold are as follows:
a0=[a2+a3+…+a(N-1))]/(N-2),
Then medical insurance assessed value is A0=[abs (P-a0)]/a0, and abs (P-a0) is the absolute value of (P-a0), and P is this doctor
Protect cost value；
Doctor's frequency analysis module of writing a prescription reads N2 times before the insured person doctor ID that writes a prescription, if the doctor ID that this time writes a prescription is N2 times first
The doctor ID that writes a prescription in occur n1 times, then doctor's frequency of writing a prescription be B0=n1/N2；
Medical insurance handler's frequency analysis module reads N3 times before insured person medical insurance handler ID, if this time medical insurance handler ID exists
Occur n2 times in first N3 times medical insurance handler ID, then medical insurance handler frequency is C0=n2/N3；
Write a prescription drugs analysis module, if drug variety of this time writing a prescription is Q kind, the title of this Q kind drug variety be respectively M1, M2,
M3 ..., MQ, N4 drug variety of writing a prescription each time before reading, in drug of writing a prescription in N4 time before being located at, drug M1 appearance it is secondary
Number be D1, drug M2 occur number be D2 ..., drug MQ occur probability be DS, by D1, D2 ... DS and drug number threshold
Value R compares, and remembers in this Q kind drug variety, and type number of the drug variety frequency of occurrence greater than drug frequency threshold value R is d, then opens
Medicine drug evaluations value is D0=d/Q,
Then the fraud assessed value of insured person is
The credit scoring of X=x1*A0+x2*B0+x3*C0+x4*D0+x5* (1-x0), x0 insured person thus, x1, x2, x3, x4 are equal
For constant
2) according to the ID of doctor of writing a prescription, doctor's analysis module from client module read the doctor that writes a prescription before N5 writing a prescription each time
Cost value, and first N5 times expense of writing a prescription is arranged by sequence from small to large, note e1, e2 ..., eN5, before removing in N5 times
Maximum value and minimum value in expense of writing a prescription, then expense of writing a prescription reference threshold are as follows:
E0=[e2+e3+ ...+e (N-1)]/(N-2),
Assessment of fees of then writing a prescription value is E0=[abs (R-e0)]/e0, and R is this expense of writing a prescription, and abs (R-e0) is (R-e0)
Absolute value
The fraud assessed value of doctor is Y=y1*E0+y2* (1-y0), and the credit scoring of y0 doctor thus, y1, y2 are constant
3) according to medical insurance handler ID, medical insurance handler analysis module is from N6 times before medical insurance handler's module reading medical insurance handler
Examination & approval each time submit an expense account ratio, and first N6 time examination & approval reimbursement ratio is arranged by sequence from small to large, remember f1,
F2 ..., fN6, the maximum value and minimum value in reimbursement ratio are examined before removing in N6 time, then examines reimbursement ratio reference threshold
Are as follows:
F0=(f2+f3+ ...+f (N-1))/(N-2),
Assessment of fees of then writing a prescription value is F0=[abs (S-f0)]/f0, and S is that ratio is submitted an expense account in this examination & approval, and abs (S-f0) is (S-
F0 absolute value),
The fraud assessed value of medical insurance handler is Z=z1*F0+z2* (1-z0), the credit scoring of z0 medical insurance handler thus, z1,
Z2 is constant；
4) comprehensive analysis module calculating fraud comprehensive assessment value V=v1*X+v2*Y+v3*Z, v1+v2+v3=1, v1, v2, v3 is
Constant.
8. a kind of medical insurance antifraud method based on computer control according to claim 7, it is characterised in that: the step
It is rapid 1) in insured person's credit rating x0=0.6J0+0.2J1+O.2J2, J0 be insured person initial credit grade, J1 is doctor
Credit rating to insured person, J2 are credit rating of the medical insurance handler to insured person；
O.2K2, K0 is that the initial credit of doctor is graded to the step 2 doctor credit rating y0=0.6K0+0.2K1+, and K1 is ginseng
Credit rating of the guarantor person to doctor, K2 are credit rating of the medical insurance handler to doctor；
O.2T1+ O.2T2, T0 is the initial of medical insurance handler by step 3) medical insurance handler's credit rating x0=O.2T0+
Credit rating, T1 are credit rating of the insured person to medical insurance handler, and T2 is credit rating of the doctor to medical insurance handler.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910424564.0A CN110245960A (en) | 2019-05-21 | 2019-05-21 | A kind of medical insurance antifraud system and method based on computer control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910424564.0A CN110245960A (en) | 2019-05-21 | 2019-05-21 | A kind of medical insurance antifraud system and method based on computer control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110245960A true CN110245960A (en) | 2019-09-17 |
Family
ID=67884712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910424564.0A Pending CN110245960A (en) | 2019-05-21 | 2019-05-21 | A kind of medical insurance antifraud system and method based on computer control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245960A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110957024A (en) * | 2019-10-25 | 2020-04-03 | 卫宁健康科技集团股份有限公司 | Medical credit evaluation method, device and storage medium |
| CN111325182A (en) * | 2020-03-19 | 2020-06-23 | 四川骏逸富顿科技有限公司 | OCR-based medical insurance reimbursement fraud detection method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN106600413A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Cheat recognition method and system |
| CN106874658A (en) * | 2017-01-18 | 2017-06-20 | 天津艾登科技有限公司 | A kind of medical insurance fraud recognition methods based on Principal Component Analysis Algorithm |
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| CN109360109A (en) * | 2018-09-26 | 2019-02-19 | 平安医疗健康管理股份有限公司 | Intelligent Claims Review householder method and system based on big data analysis and processing |
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
-
2019
- 2019-05-21 CN CN201910424564.0A patent/CN110245960A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN106600413A (en) * | 2015-10-19 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Cheat recognition method and system |
| CN106874658A (en) * | 2017-01-18 | 2017-06-20 | 天津艾登科技有限公司 | A kind of medical insurance fraud recognition methods based on Principal Component Analysis Algorithm |
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| CN109360109A (en) * | 2018-09-26 | 2019-02-19 | 平安医疗健康管理股份有限公司 | Intelligent Claims Review householder method and system based on big data analysis and processing |
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 夏宏等: "医疗保险中的欺诈与反欺诈问题", 《现代预防医学》 * |
| 陈亚琳等: "基于数据挖掘的医保欺诈预警模型研究", 《电脑知识与技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110957024A (en) * | 2019-10-25 | 2020-04-03 | 卫宁健康科技集团股份有限公司 | Medical credit evaluation method, device and storage medium |
| CN111325182A (en) * | 2020-03-19 | 2020-06-23 | 四川骏逸富顿科技有限公司 | OCR-based medical insurance reimbursement fraud detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Knack | Aid dependence and the quality of governance: Cross‐country empirical tests | |
| US20140297304A1 (en) | Determination of healthcare coverage using a payment account | |
| Nia | The effect of corona outbreak on the Indonesian stock market | |
| CN110245960A (en) | A kind of medical insurance antifraud system and method based on computer control | |
| CN102013084A (en) | System and method for detecting fraudulent transactions in medical insurance outpatient services | |
| CN106296391A (en) | A kind of assessment exceeds the time limit the method and apparatus of probability | |
| CN109544364B (en) | Data analysis-based illegal behavior detection method, device and terminal | |
| CN111784040B (en) | Optimization method and device for policy simulation analysis and computer equipment | |
| CN112801498A (en) | Risk identification model training method, risk identification device and risk identification equipment | |
| Patel et al. | Thirty-day readmission rate in acute heart failure patients discharged against medical advice in a matched cohort study | |
| Hu et al. | The fluctuations of bitcoin price during the hacks | |
| Akpoveta et al. | COVID-19 Pandemic: Nigeria’s economic and business disruptions | |
| CN107229605A (en) | The computational methods and device of text similarity | |
| Sarlis et al. | Sports Analytics and Text Mining NBA Data to Assess Recovery from Injuries and their Economic Impact | |
| Maurya et al. | Credit card fraud detection system using machine learning technique | |
| CN202084103U (en) | Electronic self-service card-issuing machine | |
| Khoirunnisa et al. | Comparative Analysis of the Efficiency of Islamic Banking in Indonesia Before and During Covid-19 Pandemic | |
| CN109472457B (en) | Loan application online reviewing method and terminal equipment | |
| Khoiri et al. | Disposition of Policy Implementers: Study on The Hospitals Payment System Change in The Indonesian National Health Insurance Era. | |
| Kang | Currency market efficiency revisited: Evidence from Korea | |
| Thorp et al. | COVID-19 & Disaster Capitalism–Part I | |
| CN112231420A (en) | Data analysis method, data analysis device, electronic device, and storage medium | |
| Singh | Are Cryptocurrency Markets, Efficient Markets? | |
| Hnatovska et al. | The Place of Cryptocurrency in the System of Financial Instruments | |
| Serván-Mori et al. | Changes in health care coverage, and catastrophic and impoverishing health expenditures in Mexico associated to the dissolution of Seguro popular |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 210000 No.6 Yuexiang Road, Xuanwu District, Nanjing City, Jiangsu Province Applicant after: He Jinxing Address before: 325600 Floor 1, Xicai Village Plaza, North Baixiang Town, Yueqing City, Wenzhou City, Zhejiang Province Applicant before: He Jinxing |