CN119963343B - Medical insurance anti-fraud intelligent management system and management method thereof - Google Patents
Medical insurance anti-fraud intelligent management system and management method thereofInfo
- Publication number
- CN119963343B CN119963343B CN202510075719.XA CN202510075719A CN119963343B CN 119963343 B CN119963343 B CN 119963343B CN 202510075719 A CN202510075719 A CN 202510075719A CN 119963343 B CN119963343 B CN 119963343B
- Authority
- CN
- China
- Prior art keywords
- fraud
- medical insurance
- coefficient
- case
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本发明公开了一种医保反欺诈智能管理系统及其管理方法，涉及反诈监督管理技术领域，包括如下模块：欺诈案例分析模块，获取欺诈案例建立案例数据库，分别通过每个欺诈历史案例获取信息值，分别通过每个欺诈历史案例获取方式值，分别通过每个欺诈案例的信息值与方式值得到每个欺诈历史案例的欺诈系数；通过医保报销人员的欺诈系数与历史系数得到筛选参考范围，再根据医保报销人员的筛选参考范围与欺诈系数参考范围得到相似重合度，从而便于将医保报销人员的真实情况与案例数据库中的欺诈案例进行相似度比较，进而有益于提高医保欺诈行为的预警效果，也有益于避免团伙作案采用类似手法骗取医保费用。
The present invention discloses an intelligent medical insurance anti-fraud management system and a management method thereof, which relate to the technical field of anti-fraud supervision management, and include the following modules: a fraud case analysis module, which obtains fraud cases to establish a case database, obtains information values through each fraud history case, obtains method values through each fraud history case, and obtains the fraud coefficient of each fraud history case through the information value and method value of each fraud case; obtains a screening reference range through the fraud coefficient and the historical coefficient of the medical insurance reimbursement personnel, and then obtains a similarity overlap based on the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement personnel, thereby facilitating a similarity comparison between the actual situation of the medical insurance reimbursement personnel and the fraud cases in the case database, thereby being beneficial to improving the early warning effect of medical insurance fraud and also beneficial to preventing gangs from committing crimes by using similar methods to defraud medical insurance expenses.
Description
Technical Field
The invention relates to the technical field of anti-fraud supervision and management, in particular to an intelligent management system and method for medical insurance anti-fraud.
Background
Medical insurance fraud includes false reimbursement, fictional illness, over-standard charging, repeated charging, and the like. These actions can lead to wastage and abuse of medical insurance funds, severely affecting fairness and sustainability of the medical insurance regime.
The anti-fraud of the medical insurance big data is to identify medical insurance fraud by utilizing a large amount of data in a medical insurance system through a data analysis and mining technology, and take corresponding processes of preventing and striking measures, wherein the medical insurance big data anti-fraud mainly adopts a data mining and machine learning technology, and doctors, medical institutions and patients with possible fraud are identified through analysis and modeling of the data in the medical insurance system.
The implementation of the anti-fraud of the medical insurance big data can effectively improve the supervision capability and the anti-fraud level of the medical insurance management department, reduce the occurrence of medical insurance fraud, provide powerful guarantee for the sustainable development of the medical insurance system, but the anti-fraud supervision management of the big data only depends on education and prevention of blacklist personnel at present, but the mode has the defects that when the medical insurance fraud personnel have fraud illegal laws, the medical insurance fraud personnel can be marked, hysteresis exists in the check, loss is easy to cause, the follow-up medical insurance fraud behavior is difficult to fundamentally avoid by carrying out blacklist marking on the medical insurance fraud related participants, and the unlabeled related personnel still can take the same method for carrying out the medical insurance fraud.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides an intelligent management system and a management method for medical insurance anti-fraud, which are used for solving the problems in the prior art.
(II) technical scheme
In order to achieve the purpose, the intelligent management system for medical insurance anti-fraud is realized by the following technical scheme that the intelligent management system comprises the following modules:
The fraud case analysis module is used for acquiring fraud case establishment case databases, acquiring information values through each fraud history case, acquiring mode values through each fraud history case, acquiring fraud coefficients of each fraud history case through the information values and the mode values of each fraud case, and acquiring fraud coefficient reference ranges through the dispersion conditions of all fraud coefficients by taking the fraud coefficients of each fraud case into the case databases;
the fraud similarity analysis module is used for acquiring fraud coefficients of medical insurance reimbursement staff, acquiring history coefficients of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficients and the history coefficients of the medical insurance reimbursement staff, and acquiring a similarity coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
And the suspicious early warning module judges whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judges whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel.
Preferably, the fraud case analysis module obtains a fraud case creation case database, specifically:
Acquiring medical insurance fraud cases through a medical insurance bureau network, acquiring medical insurance fraud cases through a court judge document database, and acquiring medical insurance fraud cases through a news website and an academic journal;
and step two, summarizing all acquired medical insurance fraud cases, deleting duplicate medical insurance fraud cases, establishing a case database and incorporating all deleted medical insurance fraud cases into the case database.
Preferably, in the fraud case analysis module, the information value is obtained through each fraud history case, specifically:
The method comprises the steps of firstly, obtaining provinces of the participants in a fraud history case, respectively marking all nationwide provinces with different numbers, obtaining numbers corresponding to the provinces of the participants in the fraud history case, marking the numbers as provinces, obtaining the cities of the participants in the fraud history case, respectively marking all nationwide cities with different numbers, obtaining numbers corresponding to the cities of the participants in the fraud history case, marking the numbers as city numbers, and carrying out weighted summation on the provincial numbers and the city numbers to obtain position information;
Step two, acquiring the age of the underwriting person in the fraud history case, acquiring the underwriting person in the fraud history case, marking the underwriting person in the fraud history case as 5 if the underwriting person in the fraud history case is male, marking the underwriting person in the fraud history case as 10 if the underwriting person in the fraud history case is female, and obtaining underwriting person information through weighted summation of the age and sex of the underwriting person in the fraud history case;
step three, obtaining the fraud amount of the participant in the fraud history case, and obtaining an information value through the fraud amount, the position information and the participant information;
The information value is calculated in the following manner:
wherein Xn is represented as an information value, je is represented as a fraud amount, wx is represented as location information, cx is represented as attendee information, 、AndAre all the weights of the materials,,,。
Preferably, in the fraud case analysis module, the mode value is obtained through each fraud history case, specifically:
Judging whether a fraud history case has a hanging hospitalization, if so, marking the hanging hospitalization as 1, and if not, marking the hanging hospitalization as 0;
Step two, acquiring medical notes in fraud history cases, judging whether the medical notes in the fraud history cases are suspicious notes according to the paper quality, the printing quality and the format standardization degree, if the medical notes are suspicious notes, marking the medical notes as 1, and if the medical notes are not suspicious notes, marking the medical notes as 0;
Step three, acquiring identity card information of a participant in a fraud history case and used medical insurance card information, judging whether the identity card information of the participant in the fraud history case is consistent with the used medical insurance card information, if the identity card information is inconsistent with the used medical insurance card information, marking the medical insurance card as 1, and if the identity card information is consistent with the used medical insurance card information, marking the medical insurance card as 0;
Step four, obtaining mode values through hanging hospital, medical bill and medical insurance card of fraud history cases;
The mode value calculation mode specifically includes:
wherein Fs is expressed as a mode value, gc is expressed as a hospital stay, yp is expressed as a medical bill, yb is expressed as a medical insurance card, 、AndAre all the weights of the materials,,,。
Preferably, the calculating mode of the fraud coefficient in the fraud case analysis module is specifically as follows:
Where Qz is denoted as a fraud coefficient, xn is denoted as an information value, fs is denoted as a mode value, AndAre all the weights of the materials,,。
Preferably, the fraud coefficient reference range is obtained in the fraud case analysis module through the dispersion condition of all fraud coefficients, specifically:
Obtaining all fraud coefficients, summing and averaging all fraud coefficients to obtain fraud average coefficients, obtaining a plurality of fraud coefficient differences by making differences between each fraud coefficient and the fraud average coefficient, and obtaining a plurality of fraud coefficient variances by squaring each fraud coefficient difference;
And secondly, summing all fraud coefficient variances to average to obtain a fraud coefficient variance average, squaring the fraud coefficient variance average to obtain a fraud coefficient standard deviation, setting a range preset threshold value, summing the fraud coefficient standard deviation with the range preset threshold value to obtain a range maximum value, obtaining a range minimum value by summing the fraud coefficient standard deviation with the range preset threshold value, and defining a fraud coefficient reference range between the range minimum value and the range maximum value.
Preferably, the historical coefficient of the medical insurance reimbursement personnel is obtained from the fraud similarity analysis module, and the screening reference range is obtained through the fraud coefficient and the historical coefficient of the medical insurance reimbursement personnel, specifically:
Acquiring the last medical insurance reimbursement date of medical insurance reimbursement staff, acquiring the current date, obtaining interval time by making a difference between the current date and the last medical insurance reimbursement date of the medical insurance reimbursement staff, setting a time correlation preset threshold value, and obtaining a history coefficient by multiplying the interval time by the time correlation preset threshold value;
Obtaining a fraud coefficient of the medical insurance reimbursement personnel, summing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient to obtain a fraud coefficient maximum value, and obtaining a fraud coefficient minimum value by differencing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient, wherein the fraud coefficient minimum value and the fraud coefficient maximum value are defined as a screening reference range.
Preferably, in the fraud similarity analysis module, the similarity coincidence degree is obtained through a screening reference range of medical insurance reimbursement personnel and a fraud coefficient reference range, specifically:
Step one, acquiring a screening reference range of medical insurance reimbursement personnel, acquiring a fraud coefficient reference range, judging whether the fraud coefficient reference range and the screening reference range have overlapping parts, if the fraud coefficient reference range and the screening reference range have no overlapping parts, marking the similar overlapping ratio as 0, and if the fraud coefficient reference range and the screening reference range have overlapping parts, executing step two;
Obtaining the minimum value and the maximum value of the overlapping part, obtaining the overlapping value by making a difference between the maximum value and the minimum value of the overlapping part, obtaining the maximum value and the minimum value of the screening reference range, obtaining the reference range value by making a difference between the maximum value and the minimum value of the screening reference range, and obtaining the similar overlapping ratio by using the overlapping value and the reference range value as a quotient.
Preferably, the suspicious early warning module specifically comprises:
step one, obtaining the similarity of medical insurance reimbursement staff, setting a similarity preset threshold, judging whether the similarity of the medical insurance reimbursement staff is larger than the similarity preset threshold, and if the similarity of the medical insurance reimbursement staff is larger than or equal to the similarity preset threshold, starting an alarm to remind a manager to carry out repeated auditing on the information of the medical insurance reimbursement staff;
and step two, obtaining repeated auditing results of the information of the medical insurance reimbursement personnel by the management personnel, and obtaining the fraud coefficient of the medical insurance reimbursement personnel and incorporating the fraud coefficient into the case database if the medical insurance reimbursement personnel has medical insurance fraud.
An intelligent management method for medical insurance anti-fraud comprises the following steps:
S1, acquiring fraud cases, establishing a case database, acquiring information values through each fraud history case, acquiring mode values through each fraud history case, acquiring fraud coefficients of each fraud history case through the information values and the mode values of each fraud case, and acquiring fraud coefficient reference ranges through the dispersion conditions of all fraud coefficients by taking the fraud coefficients of each fraud case into the case database;
S2, acquiring a fraud coefficient of a medical insurance reimbursement staff, acquiring a history coefficient of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficient and the history coefficient of the medical insurance reimbursement staff, and acquiring a similar coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
And S3, judging whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judging whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel.
(III) beneficial effects
The invention provides an intelligent management system and a management method for medical insurance anti-fraud, and the intelligent management system has the following beneficial effects:
(1) According to the scheme, the screening reference range is obtained through the fraud coefficient and the history coefficient of the medical insurance reimbursement personnel in the fraud similarity analysis module, and the similarity degree is obtained according to the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement personnel, so that the real situation of the medical insurance reimbursement personnel can be conveniently compared with the fraud case in the case database in similarity, and the early warning effect of medical insurance fraudulent activity can be improved.
(2) According to the scheme, the alarm is controlled to be started through the similarity of the medical insurance reimbursement personnel in the suspicious early warning module, so that a manager is conveniently reminded to carry out strict examination on the medical insurance reimbursement personnel, economic loss caused by medical insurance fraud is avoided, whether the fraud coefficient of the medical insurance reimbursement personnel is brought into the case database is judged through the examination result of the medical insurance reimbursement personnel, the case database is conveniently updated in a supplementing mode according to the real-time fraud case, and the accuracy of the fraud coefficient reference range is improved, so that the accuracy of medical insurance frauds early warning is improved.
Drawings
FIG. 1 is a schematic diagram of a medical insurance anti-fraud intelligent management system;
fig. 2 is a flow chart of a medical insurance anti-fraud intelligent management method of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the invention provides an intelligent management system for medical insurance anti-fraud, which comprises the following modules:
The fraud case analysis module is used for acquiring fraud case establishment case databases, acquiring information values through each fraud history case, acquiring mode values through each fraud history case, acquiring fraud coefficients of each fraud history case through the information values and the mode values of each fraud case, and acquiring fraud coefficient reference ranges through the dispersion conditions of all fraud coefficients by taking the fraud coefficients of each fraud case into the case databases;
the fraud similarity analysis module is used for acquiring fraud coefficients of medical insurance reimbursement staff, acquiring history coefficients of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficients and the history coefficients of the medical insurance reimbursement staff, and acquiring a similarity coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
The suspicious early warning module judges whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judges whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel;
the calculating mode of the fraud coefficient in the fraud case analysis module is specifically as follows:
Where Qz is denoted as a fraud coefficient, xn is denoted as an information value, fs is denoted as a mode value, AndAre all the weights of the materials,,。
In the embodiment, the fraud coefficient is obtained through the information value and the mode value of the fraud case in the fraud case analysis module, so that the information and the scheme of the crime are conveniently dataized according to the real situation of the fraud case, the probability of the fraud of the medical insurance reimbursement personnel is conveniently judged according to the fraud case, and the early warning effect of the medical insurance fraud is improved;
According to the scheme, a screening reference range is obtained through the fraud coefficient and the history coefficient of the medical insurance reimbursement personnel in the fraud similarity analysis module, and then the similarity is obtained according to the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement personnel, so that the real situation of the medical insurance reimbursement personnel can be conveniently compared with the fraud case in the case database in similarity, and the early warning effect of medical insurance fraud is improved;
The method and the system control the alarm to be started through the similarity of the medical insurance reimbursement personnel in the suspicious early warning module, so that a manager is conveniently reminded to carry out strict examination on the medical insurance reimbursement personnel, economic loss caused by medical insurance fraud is avoided, whether the fraud coefficient of the medical insurance reimbursement personnel is brought into a case database is judged through the examination result of the medical insurance reimbursement personnel, so that the case database is conveniently updated in a supplementing mode according to the real-time fraud case, the accuracy of the fraud coefficient reference range is improved, and the accuracy of medical insurance fraudster early warning is improved;
it should be noted that, the weight value in the scheme can be obtained through an analytic hierarchy process, and the value of the preset threshold can be obtained through the weight analysis process, which is not described in detail herein.
Obtaining fraud cases in a fraud case analysis module to establish a case database, specifically:
Acquiring medical insurance fraud cases through a medical insurance bureau network, acquiring medical insurance fraud cases through a court judge document database, and acquiring medical insurance fraud cases through a news website and an academic journal;
and step two, summarizing all acquired medical insurance fraud cases, deleting duplicate medical insurance fraud cases, establishing a case database and incorporating all deleted medical insurance fraud cases into the case database.
In the embodiment, the medical insurance fraud cases are acquired through the medical insurance bureau network, the court judge document database and the news website and the academic journal, so that the authenticity and diversity of the acquired medical insurance fraud cases are improved, and the similarity prediction of medical insurance reimbursement personnel according to the medical insurance fraud cases is facilitated.
In the fraud case analysis module, information values are obtained through each fraud history case respectively, specifically:
The method comprises the steps of firstly, obtaining provinces of the participants in a fraud history case, respectively marking all nationwide provinces with different numbers, obtaining numbers corresponding to the provinces of the participants in the fraud history case, marking the numbers as provinces, obtaining the cities of the participants in the fraud history case, respectively marking all nationwide cities with different numbers, obtaining numbers corresponding to the cities of the participants in the fraud history case, marking the numbers as city numbers, and carrying out weighted summation on the provincial numbers and the city numbers to obtain position information;
Step two, acquiring the age of the underwriting person in the fraud history case, acquiring the underwriting person in the fraud history case, marking the underwriting person in the fraud history case as 5 if the underwriting person in the fraud history case is male, marking the underwriting person in the fraud history case as 10 if the underwriting person in the fraud history case is female, and obtaining underwriting person information through weighted summation of the age and sex of the underwriting person in the fraud history case;
step three, obtaining the fraud amount of the participant in the fraud history case, and obtaining an information value through the fraud amount, the position information and the participant information;
The information value is calculated in the following manner:
wherein Xn is represented as an information value, je is represented as a fraud amount, wx is represented as location information, cx is represented as attendee information, 、AndAre all the weights of the materials,,,。
In this embodiment, the information value is obtained through the fraud amount, the position information and the information of the sponsor, so that the data analysis and classification are performed on the medical insurance fraudsters according to the information of the medical insurance fraudsters, the fraud coefficient of the medical insurance reimbursement personnel is obtained in the fraud similarity analysis module, and the fraud amount of the medical insurance reimbursement personnel is 0 when the fraud coefficient is calculated through the information value and the mode value because the fraud amount of the medical insurance reimbursement personnel is not available.
The fraud case analysis module obtains mode values through each fraud history case respectively, specifically:
Judging whether a fraud history case has a hanging hospitalization, if so, marking the hanging hospitalization as 1, and if not, marking the hanging hospitalization as 0;
Step two, acquiring medical notes in fraud history cases, judging whether the medical notes in the fraud history cases are suspicious notes according to the paper quality, the printing quality and the format standardization degree, if the medical notes are suspicious notes, marking the medical notes as 1, and if the medical notes are not suspicious notes, marking the medical notes as 0;
Step three, acquiring identity card information of a participant in a fraud history case and used medical insurance card information, judging whether the identity card information of the participant in the fraud history case is consistent with the used medical insurance card information, if the identity card information is inconsistent with the used medical insurance card information, marking the medical insurance card as 1, and if the identity card information is consistent with the used medical insurance card information, marking the medical insurance card as 0;
Step four, obtaining mode values through hanging hospital, medical bill and medical insurance card of fraud history cases;
The mode value calculation mode specifically includes:
wherein Fs is expressed as a mode value, gc is expressed as a hospital stay, yp is expressed as a medical bill, yb is expressed as a medical insurance card, 、AndAre all the weights of the materials,,,。
In this embodiment, the mode value is obtained through the on-bed hospitalization of the fraud history case, the medical bill and the medical insurance card, so that the mode value is conveniently obtained by combining the history fraud mode of the medical insurance fraud personnel, the fraud mode of the history case is conveniently dataized, the similarity of medical insurance reimbursement personnel is conveniently predicted and compared later, whether the medical bill in the fraud history case is a suspicious bill is judged through the quality of paper, the printing quality and the format standard degree, the quality of paper can be judged specifically through the parameters such as the weight toughness of the paper, the printing quality can be judged through the parameters such as the color brightness of printing ink, the format standard degree can be judged through the modes such as the signature condition, finally, the bill condition is obtained through the mode of weighted summation of the quality of the paper, the printing quality and the format standard degree, finally, whether the bill is a suspicious bill is judged according to the condition of the bill, and whether the bill is a suspicious bill can be judged through naked eyes and touch feeling by experience.
Obtaining a fraud coefficient reference range through the dispersion condition of all fraud coefficients in a fraud case analysis module, wherein the fraud coefficient reference range is specifically as follows:
Obtaining all fraud coefficients, summing and averaging all fraud coefficients to obtain fraud average coefficients, obtaining a plurality of fraud coefficient differences by making differences between each fraud coefficient and the fraud average coefficient, and obtaining a plurality of fraud coefficient variances by squaring each fraud coefficient difference;
And secondly, summing all fraud coefficient variances to average to obtain a fraud coefficient variance average, squaring the fraud coefficient variance average to obtain a fraud coefficient standard deviation, setting a range preset threshold value, summing the fraud coefficient standard deviation with the range preset threshold value to obtain a range maximum value, obtaining a range minimum value by summing the fraud coefficient standard deviation with the range preset threshold value, and defining a fraud coefficient reference range between the range minimum value and the range maximum value.
The fraud similarity analysis module obtains the historical coefficient of medical insurance reimbursement personnel, and the screening reference range is obtained through the fraud coefficient and the historical coefficient of the medical insurance reimbursement personnel, specifically:
Acquiring the last medical insurance reimbursement date of medical insurance reimbursement staff, acquiring the current date, obtaining interval time by making a difference between the current date and the last medical insurance reimbursement date of the medical insurance reimbursement staff, setting a time correlation preset threshold value, and obtaining a history coefficient by multiplying the interval time by the time correlation preset threshold value;
Obtaining a fraud coefficient of the medical insurance reimbursement personnel, summing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient to obtain a fraud coefficient maximum value, and obtaining a fraud coefficient minimum value by differencing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient, wherein the fraud coefficient minimum value and the fraud coefficient maximum value are defined as a screening reference range.
Obtaining the similarity coincidence degree through the screening reference range of medical insurance reimbursement personnel and the fraud coefficient reference range in the fraud similarity analysis module, wherein the similarity coincidence degree is specifically as follows:
Step one, acquiring a screening reference range of medical insurance reimbursement personnel, acquiring a fraud coefficient reference range, judging whether the fraud coefficient reference range and the screening reference range have overlapping parts, if the fraud coefficient reference range and the screening reference range have no overlapping parts, marking the similar overlapping ratio as 0, and if the fraud coefficient reference range and the screening reference range have overlapping parts, executing step two;
Obtaining the minimum value and the maximum value of the overlapping part, obtaining the overlapping value by making a difference between the maximum value and the minimum value of the overlapping part, obtaining the maximum value and the minimum value of the screening reference range, obtaining the reference range value by making a difference between the maximum value and the minimum value of the screening reference range, and obtaining the similar overlapping ratio by using the overlapping value and the reference range value as a quotient.
In the embodiment, the fraud coefficient reference range obtained through the historical cases is subjected to coincidence comparison with the screening reference range of the medical insurance reimbursement personnel, so that the similarity condition of the medical insurance reimbursement personnel and the medical insurance reimbursement personnel in the historical cases is conveniently judged, the possibility of fraud of the medical insurance reimbursement personnel is conveniently predicted according to means and condition analysis of the medical insurance reimbursement personnel in the historical cases, and the accuracy of early warning of the medical insurance reimbursement personnel is further improved
The suspicious early warning module specifically comprises:
step one, obtaining the similarity of medical insurance reimbursement staff, setting a similarity preset threshold, judging whether the similarity of the medical insurance reimbursement staff is larger than the similarity preset threshold, and if the similarity of the medical insurance reimbursement staff is larger than or equal to the similarity preset threshold, starting an alarm to remind a manager to carry out repeated auditing on the information of the medical insurance reimbursement staff;
and step two, obtaining repeated auditing results of the information of the medical insurance reimbursement personnel by the management personnel, and obtaining the fraud coefficient of the medical insurance reimbursement personnel and incorporating the fraud coefficient into the case database if the medical insurance reimbursement personnel has medical insurance fraud.
In this embodiment, the alarm is controlled to be turned on by the similarity of the medical insurance reimbursement staff, so that the manager is conveniently reminded to carry out strict auditing on the medical insurance reimbursement staff, so that economic loss caused by medical insurance fraud is avoided, whether the fraud coefficient of the medical insurance reimbursement staff is included in the case database is judged by the auditing result of the medical insurance reimbursement staff, so that the case database is conveniently updated in a supplementing manner according to the real-time fraud cases, further the accuracy of the fraud coefficient reference range is improved, and further the accuracy of the medical insurance fraudster early warning is improved.
Referring to fig. 1-2, the invention provides an intelligent management method for medical insurance anti-fraud, which comprises the following steps:
S1, acquiring fraud cases, establishing a case database, acquiring information values through each fraud history case, acquiring mode values through each fraud history case, acquiring fraud coefficients of each fraud history case through the information values and the mode values of each fraud case, and acquiring fraud coefficient reference ranges through the dispersion conditions of all fraud coefficients by taking the fraud coefficients of each fraud case into the case database;
S2, acquiring a fraud coefficient of a medical insurance reimbursement staff, acquiring a history coefficient of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficient and the history coefficient of the medical insurance reimbursement staff, and acquiring a similar coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
And S3, judging whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judging whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (10)
1. An intelligent management system for medical insurance anti-fraud is characterized by comprising the following modules:
The fraud case analysis module is used for acquiring fraud case establishment case databases, acquiring information values through each fraud history case, wherein the information values comprise fraud amount, position information and participant information, so that the medical insurance fraud personnel can be subjected to data analysis and classification according to the information of the medical insurance fraud personnel, the mode values are respectively acquired through each fraud history case, the mode values comprise on-hook hospitalization, medical bill and medical insurance card of the fraud history case, so that the similarity of medical insurance reimbursement personnel is predicted and compared according to the historical fraud mode of the medical insurance fraud personnel, the fraud coefficient of each fraud history case is obtained through the information value and the mode value of each fraud case, the fraud coefficient is used for judging the fraud probability of the medical insurance reimbursement personnel according to the fraud case, the fraud coefficient of each fraud case is included in the case databases, and the fraud coefficient reference range is obtained through the dispersion condition of all the fraud coefficient;
the fraud similarity analysis module is used for acquiring fraud coefficients of medical insurance reimbursement staff, acquiring history coefficients of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficients and the history coefficients of the medical insurance reimbursement staff, and acquiring a similarity coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
And the suspicious early warning module judges whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judges whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel.
2. The intelligent medical insurance anti-fraud management system according to claim 1, wherein the fraud case analysis module obtains a fraud case creation case database, specifically:
Acquiring medical insurance fraud cases through a medical insurance bureau network, acquiring medical insurance fraud cases through a court judge document database, and acquiring medical insurance fraud cases through a news website and an academic journal;
and step two, summarizing all acquired medical insurance fraud cases, deleting duplicate medical insurance fraud cases, establishing a case database and incorporating all deleted medical insurance fraud cases into the case database.
3. The intelligent medical insurance anti-fraud management system according to claim 1, wherein the fraud case analysis module obtains information values through each fraud history case respectively, specifically:
The method comprises the steps of firstly, obtaining provinces of the participants in a fraud history case, respectively marking all nationwide provinces with different numbers, obtaining numbers corresponding to the provinces of the participants in the fraud history case, marking the numbers as provinces, obtaining the cities of the participants in the fraud history case, respectively marking all nationwide cities with different numbers, obtaining numbers corresponding to the cities of the participants in the fraud history case, marking the numbers as city numbers, and carrying out weighted summation on the provincial numbers and the city numbers to obtain position information;
Step two, acquiring the age of the underwriting person in the fraud history case, acquiring the underwriting person in the fraud history case, marking the underwriting person in the fraud history case as 5 if the underwriting person in the fraud history case is male, marking the underwriting person in the fraud history case as 10 if the underwriting person in the fraud history case is female, and obtaining underwriting person information through weighted summation of the age and sex of the underwriting person in the fraud history case;
step three, obtaining the fraud amount of the participant in the fraud history case, and obtaining an information value through the fraud amount, the position information and the participant information;
The information value is calculated in the following manner:
wherein Xn is represented as an information value, je is represented as a fraud amount, wx is represented as location information, cx is represented as attendee information, 、AndAre all the weights of the materials,,,。
4. The intelligent medical insurance anti-fraud management system according to claim 1, wherein the fraud case analysis module obtains a mode value through each fraud history case, and specifically:
Judging whether a fraud history case has a hanging hospitalization, if so, marking the hanging hospitalization as 1, and if not, marking the hanging hospitalization as 0;
Step two, acquiring medical notes in fraud history cases, judging whether the medical notes in the fraud history cases are suspicious notes according to the paper quality, the printing quality and the format standardization degree, if the medical notes are suspicious notes, marking the medical notes as 1, and if the medical notes are not suspicious notes, marking the medical notes as 0;
Step three, acquiring identity card information of a participant in a fraud history case and used medical insurance card information, judging whether the identity card information of the participant in the fraud history case is consistent with the used medical insurance card information, if the identity card information is inconsistent with the used medical insurance card information, marking the medical insurance card as 1, and if the identity card information is consistent with the used medical insurance card information, marking the medical insurance card as 0;
Step four, obtaining mode values through hanging hospital, medical bill and medical insurance card of fraud history cases;
The mode value calculation mode specifically includes:
wherein Fs is expressed as a mode value, gc is expressed as a hospital stay, yp is expressed as a medical bill, yb is expressed as a medical insurance card, 、AndAre all the weights of the materials,,,。
5. The intelligent medical insurance anti-fraud management system according to claim 1, wherein the fraud coefficient calculation method in the fraud case analysis module is specifically as follows:
Where Qz is denoted as a fraud coefficient, xn is denoted as an information value, fs is denoted as a mode value, AndAre all the weights of the materials,,。
6. The intelligent medical insurance anti-fraud management system according to claim 1, wherein the fraud coefficient reference range is obtained through the dispersion condition of all fraud coefficients in the fraud case analysis module, and specifically comprises the following steps:
Obtaining all fraud coefficients, summing and averaging all fraud coefficients to obtain fraud average coefficients, obtaining a plurality of fraud coefficient differences by making differences between each fraud coefficient and the fraud average coefficient, and obtaining a plurality of fraud coefficient variances by squaring each fraud coefficient difference;
And secondly, summing all fraud coefficient variances to average to obtain a fraud coefficient variance average, squaring the fraud coefficient variance average to obtain a fraud coefficient standard deviation, setting a range preset threshold value, summing the fraud coefficient standard deviation with the range preset threshold value to obtain a range maximum value, obtaining a range minimum value by summing the fraud coefficient standard deviation with the range preset threshold value, and defining a fraud coefficient reference range between the range minimum value and the range maximum value.
7. The intelligent management system for medical insurance anti-fraud according to claim 1, wherein the fraud similarity analysis module obtains a history coefficient of medical insurance reimbursement personnel, and obtains a screening reference range through the fraud coefficient and the history coefficient of the medical insurance reimbursement personnel, and the screening reference range is specifically as follows:
Acquiring the last medical insurance reimbursement date of medical insurance reimbursement staff, acquiring the current date, obtaining interval time by making a difference between the current date and the last medical insurance reimbursement date of the medical insurance reimbursement staff, setting a time correlation preset threshold value, and obtaining a history coefficient by multiplying the interval time by the time correlation preset threshold value;
Obtaining a fraud coefficient of the medical insurance reimbursement personnel, summing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient to obtain a fraud coefficient maximum value, and obtaining a fraud coefficient minimum value by differencing the fraud coefficient of the medical insurance reimbursement personnel and the historical coefficient, wherein the fraud coefficient minimum value and the fraud coefficient maximum value are defined as a screening reference range.
8. The intelligent management system for medical insurance anti-fraud according to claim 1, wherein the similarity is obtained by screening reference range and fraud coefficient reference range of medical insurance reimbursement personnel in a fraud similarity analysis module, and the method is specifically as follows:
Step one, acquiring a screening reference range of medical insurance reimbursement personnel, acquiring a fraud coefficient reference range, judging whether the fraud coefficient reference range and the screening reference range have overlapping parts, if the fraud coefficient reference range and the screening reference range have no overlapping parts, marking the similar overlapping ratio as 0, and if the fraud coefficient reference range and the screening reference range have overlapping parts, executing step two;
Obtaining the minimum value and the maximum value of the overlapping part, obtaining the overlapping value by making a difference between the maximum value and the minimum value of the overlapping part, obtaining the maximum value and the minimum value of the screening reference range, obtaining the reference range value by making a difference between the maximum value and the minimum value of the screening reference range, and obtaining the similar overlapping ratio by using the overlapping value and the reference range value as a quotient.
9. The intelligent medical insurance fraud prevention management system according to claim 1, wherein the suspicious early warning module is specifically:
step one, obtaining the similarity of medical insurance reimbursement staff, setting a similarity preset threshold, judging whether the similarity of the medical insurance reimbursement staff is larger than the similarity preset threshold, and if the similarity of the medical insurance reimbursement staff is larger than or equal to the similarity preset threshold, starting an alarm to remind a manager to carry out repeated auditing on the information of the medical insurance reimbursement staff;
and step two, obtaining repeated auditing results of the information of the medical insurance reimbursement personnel by the management personnel, and obtaining the fraud coefficient of the medical insurance reimbursement personnel and incorporating the fraud coefficient into the case database if the medical insurance reimbursement personnel has medical insurance fraud.
10. An intelligent management method for medical insurance anti-fraud, applied to an intelligent management system for medical insurance anti-fraud according to any one of claims 1 to 9, comprising the following steps:
S1, acquiring fraud cases, establishing a case database, respectively acquiring information values through each fraud history case, wherein the information values comprise fraud amount, position information and sponsor information, so as to realize the data analysis and classification of medical insurance fraud personnel according to the information of the medical insurance fraud personnel, respectively acquiring mode values through each fraud history case, wherein the mode values comprise on-bed hospitalization, medical bill and medical insurance card of the fraud history cases, so as to realize the prediction and comparison of the similarity of medical insurance reimbursement personnel according to the historical fraud mode of the medical insurance fraud personnel, respectively acquiring fraud coefficients of each fraud history case through the information values and the mode values of each fraud case, wherein the fraud coefficients are used for judging the fraud probability of the medical insurance reimbursement personnel according to the fraud cases, and acquiring fraud coefficient reference ranges through the dispersion of all fraud coefficients;
S2, acquiring a fraud coefficient of a medical insurance reimbursement staff, acquiring a history coefficient of the medical insurance reimbursement staff, acquiring a screening reference range through the fraud coefficient and the history coefficient of the medical insurance reimbursement staff, and acquiring a similar coincidence degree through the screening reference range and the fraud coefficient reference range of the medical insurance reimbursement staff;
And S3, judging whether to start an alarm to remind a manager according to the similarity of the medical insurance reimbursement personnel, and judging whether to incorporate the fraud coefficient of the medical insurance reimbursement personnel into the case database according to the auditing result of the medical insurance reimbursement personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510075719.XA CN119963343B (en) | 2025-01-17 | 2025-01-17 | Medical insurance anti-fraud intelligent management system and management method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510075719.XA CN119963343B (en) | 2025-01-17 | 2025-01-17 | Medical insurance anti-fraud intelligent management system and management method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119963343A CN119963343A (en) | 2025-05-09 |
| CN119963343B true CN119963343B (en) | 2025-09-26 |
Family
ID=95596911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510075719.XA Active CN119963343B (en) | 2025-01-17 | 2025-01-17 | Medical insurance anti-fraud intelligent management system and management method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119963343B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942455A (en) * | 2014-05-07 | 2014-07-23 | 东南大学 | Operation schedule optimization design method based on remote data |
| CN108596770A (en) * | 2017-12-29 | 2018-09-28 | 山大地纬软件股份有限公司 | Medicare fraud detection device and method based on outlier analysis |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8831677B2 (en) * | 2010-11-17 | 2014-09-09 | Antony-Euclid C. Villa-Real | Customer-controlled instant-response anti-fraud/anti-identity theft devices (with true-personal identity verification), method and systems for secured global applications in personal/business e-banking, e-commerce, e-medical/health insurance checker, e-education/research/invention, e-disaster advisor, e-immigration, e-airport/aircraft security, e-military/e-law enforcement, with or without NFC component and system, with cellular/satellite phone/internet/multi-media functions |
| CN109003191A (en) * | 2018-07-12 | 2018-12-14 | 上海金仕达卫宁软件科技有限公司 | The anti-fraud template automatic generation method of medical treatment and system based on hierarchical clustering |
| CN114004483B (en) * | 2021-10-29 | 2025-08-26 | 深圳平安医疗健康科技服务有限公司 | Application program adjustment method and related device |
| CN114841819A (en) * | 2022-04-22 | 2022-08-02 | 北京鲸鹳科技有限公司 | Method and device for determining claim settlement scheme, electronic equipment and storage medium |
-
2025
- 2025-01-17 CN CN202510075719.XA patent/CN119963343B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942455A (en) * | 2014-05-07 | 2014-07-23 | 东南大学 | Operation schedule optimization design method based on remote data |
| CN108596770A (en) * | 2017-12-29 | 2018-09-28 | 山大地纬软件股份有限公司 | Medicare fraud detection device and method based on outlier analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119963343A (en) | 2025-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110706090A (en) | Credit fraud identification method and device, electronic equipment and storage medium | |
| US20060202012A1 (en) | Secure data processing system, such as a system for detecting fraud and expediting note processing | |
| CN111179089B (en) | Money laundering transaction identification method, device and equipment | |
| CN111062808B (en) | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium | |
| CN112101520A (en) | Risk assessment model training method, business risk assessment method and other equipment | |
| CN110458662A (en) | Anti-fraud risk control method and device | |
| CN112669187A (en) | Identity recognition method and device, electronic equipment and related products | |
| CN115187252A (en) | Method for identifying fraud in network transaction system, server and storage medium | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| CN113159778B (en) | Financial fraud detection method and device | |
| CN117478366A (en) | Method and system for resisting back door attack in federal learning field | |
| CN108125686B (en) | Anti-fraud method and system | |
| CN112749973A (en) | Authority management method and device and computer readable storage medium | |
| CN116579841A (en) | Credit wind control evaluation method and system and electronic equipment | |
| CN119963343B (en) | Medical insurance anti-fraud intelligent management system and management method thereof | |
| CN110223080B (en) | Method and device for determining target account of face-scanning payment platform | |
| CN115114851A (en) | Scorecard modeling method and device based on five-fold cross-validation | |
| CN110795715A (en) | Data entry method, device and system and storage medium | |
| CN113095841B (en) | Transaction identification method, device, electronic device and storage medium | |
| CN113657902A (en) | Financial security management method, system and storage medium based on graph database | |
| CN115375893A (en) | Certificate authenticity identification method and device, computer readable medium and electronic equipment | |
| CN112053244A (en) | Information processing method and device and server | |
| CN113779635B (en) | Medical data verification method, device, equipment and storage medium | |
| Bergmann et al. | Preventing interview falsifications during fieldwork in the Survey of Health, Ageing and Retirement in Europe (SHARE) | |
| JPWO2021130991A1 (en) | Fraud detection systems, fraud detection methods, and programs |
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 | ||
| GR01 | Patent grant |