CN111275086B

CN111275086B - Medical insurance group fraud abnormal behavior detection method and device and electronic equipment

Info

Publication number: CN111275086B
Application number: CN202010045791.5A
Authority: CN
Inventors: 赵蒙海
Original assignee: Shanghai Jinshida Weining Software Technology Co ltd
Current assignee: Shanghai Jinshida Weining Software Technology Co ltd
Priority date: 2020-01-16
Filing date: 2020-01-16
Publication date: 2023-05-23
Anticipated expiration: 2040-01-16
Also published as: CN111275086A

Abstract

The invention discloses a method and a device for detecting medical insurance group fraud abnormal behavior and electronic equipment, wherein the method comprises the following steps: classifying patient information according to the type of hospital and disease being treated; analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group, wherein the target patient group comprises at least two target patients, the admission time difference between the at least two target patients is smaller than or equal to a first target time threshold, and the discharge time difference between the at least two target patients is smaller than or equal to a second target time threshold; and counting target patient groups of a plurality of disease categories in a plurality of hospitals, determining at least two abnormal patients, wherein the at least two abnormal patients are simultaneously present in more than or equal to N target patient groups as an abnormal patient group, and N is more than or equal to 3. The method of the embodiment can determine the abnormal patient group with regular treatment behaviors, further determine the abnormal behaviors of medical insurance group fraud, and improve the accuracy of positioning to medical insurance fraud patients.

Description

Medical insurance group fraud abnormal behavior detection method and device and electronic equipment

Technical Field

The invention relates to the technical field of medical insurance, in particular to a method and a device for detecting fraudulent abnormal behavior of medical insurance groups and electronic equipment.

Background

Medical insurance fund supervision is a long-term difficult task, is a key measure for guaranteeing the interests of vast participants in China, and occupies an important position in medical insurance supervision system construction all the time. Especially, on the 9 th 11 th 2018, the national medical insurance agency, the national health and wellness agency, the public security department and the national medical supervision agency jointly issue a notification about developing actions specific to the medical security fund against fraud, and the problem of hot spot sensitivity of the work becoming social attention is solved after developing actions specific to the medical security fund against fraud in the whole country.

The "fraud protection" has become a common and multiple situation, and for the current fraud protection behavior, experts describe the fraud protection behavior in terms of 'point multiple aspects, wide chain length, secret behavior supervision difficulty', so that the fraud protection patterns are more abundant and are not victory. The intentional fraud is to use fake cases, on-bed hospitalization and other means to collect the medical insurance fund with the purpose of making a profit from the medical insurance fund, and the property is bad.

At present, the conventional mode adopts a statistical analysis and a single threshold rule supervision mode to supervise patients suffering from various diseases, but the accuracy rate of locating the patients with medical insurance fraud is lower.

Disclosure of Invention

The embodiment of the invention provides a method, a device and electronic equipment for detecting medical insurance group fraud abnormal behaviors, which are used for solving the problems that patients suffering from various diseases are supervised in the prior art, but the accuracy rate of locating medical insurance fraud patients is low.

In order to solve the technical problems, the invention is realized as follows:

in a first aspect, a method for detecting abnormal fraudulent activity of a medical insurance group is provided, the method comprising:

classifying patient information according to the type of hospital and disease being treated;

analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group, wherein the target patient group comprises at least two target patients, the admission time difference between the at least two target patients is smaller than or equal to a first target time threshold, and the discharge time difference between the at least two target patients is smaller than or equal to a second target time threshold;

and counting target patient groups of a plurality of disease categories in a plurality of hospitals, and determining at least two abnormal patients as an abnormal patient group, wherein the at least two abnormal patients are simultaneously present in N target patient groups or more, and N is more than or equal to 3.

In a second aspect, there is provided a device for detecting fraudulent use of a medical insurance group, the device comprising:

the first classification module is used for classifying the patient information according to the hospital and the disease type of the doctor;

the analysis module is used for analyzing at least two patient information of target disease categories of a target hospital to obtain a target patient group, the target patient group comprises at least two target patients, the admission time difference between the at least two target patients is smaller than or equal to a first target time threshold, and the discharge time difference between the at least two target patients is smaller than or equal to a second target time threshold;

the determining module is used for counting target patient groups of a plurality of disease categories in a plurality of hospitals, determining at least two abnormal patients, and taking the at least two abnormal patients as an abnormal patient group, wherein the at least two abnormal patients are simultaneously in N target patient groups or more, and N is more than or equal to 3.

In a third aspect, there is provided an electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program implementing the steps of the method according to the first aspect when executed by the processor.

In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method according to the first aspect.

In the embodiment of the invention, the patient information is classified according to the hospital and the disease type of the doctor, so as to obtain a plurality of disease categories of a plurality of hospitals; analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group consisting of at least two target patients, wherein the admission time and discharge time between the at least two target patients are smaller than corresponding time thresholds; and counting target patient groups of a plurality of disease categories of a plurality of hospitals, and determining at least two target patients in the target patient groups with the occurrence of N or more as abnormal patients as abnormal patient groups. At least two patients which are discharged in the same hospital in the same time period are determined as target patient groups, the target patient groups of a plurality of disease categories of a plurality of hospitals are counted, the frequency of occurrence of the same target patient group is determined to be more than N times as abnormal patient groups, N is more than or equal to 3, the abnormal patient groups can be determined to be regular groups of treatment behaviors, further, the medical insurance group fraud abnormal behaviors can be determined, and the accuracy of positioning to medical insurance fraud patients is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

FIG. 1 is a flow diagram of a method of detecting medical insurance group fraud anomalies in accordance with one embodiment of the present invention;

FIG. 2 is a flow chart of a method of detecting abnormal medical insurance group fraud in accordance with another embodiment of the present invention;

FIG. 3 is a schematic diagram of the structure of a device for detecting fraudulent anomalies in a medical insurance population in accordance with one embodiment of the present invention;

fig. 4 is a schematic structural view of an electronic device according to another embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.

FIG. 1 is a flow chart of a method for detecting abnormal medical insurance group fraud, according to an embodiment of the present invention, where the method shown in FIG. 1 may be performed by a device for detecting abnormal medical insurance group fraud, as shown in FIG. 1, and the method includes:

step S102, classifying the patient information according to the hospital and the disease type of the doctor.

It will be appreciated that the classification of patient information by disease type may be classification of patient information by disease name, duration of a disease visit, etc., without limitation. For example, if classified by disease name, appendicitis is classified into one type, diabetes is classified into one type, and cerebral infarction is classified into one type. If the diseases are classified according to the diagnosis time, diabetes and cerebral infarction with the diagnosis time being similar are classified into one type, and appendicitis is classified into one type.

In step S102, patient information is acquired, the patient information including a patient, a hospital in which the patient is at a doctor, and a disease in which the patient gets. Patient information is classified according to the hospital and the disease type of the doctor, so that a plurality of disease types of a plurality of hospitals are obtained, and the patient information of the target disease type of the target hospital can be processed in a targeted manner conveniently. For example, zhang three, liu four, wang five, liu Liu and Xiao seven, wherein Zhang three, liu four and Wang five are treated in the same hospital, liu Liu is treated in another hospital, zhang three, liu four and Wang five are classified into one type and Liu six is classified into the other type according to the treated hospital; and classifying Zhang three, lifour and Wang five according to the disease types to obtain at least one disease type.

Optionally, in some embodiments, the classification of the disease type is related to the length of time the disease is treated.

It can be appreciated that classifying the differences in the treatment time of the disease as less than the predetermined value into one disease category facilitates statistics and determines a time threshold corresponding to the disease category. The time threshold may be a numerical value, or the time threshold may be a section.

For example, zhang three, lifour and Wang five are respectively suffering from diabetes, acute appendicitis and acute cerebral infarction, the treatment time of diabetes is 22 days, the treatment time of acute appendicitis is 5 days, the treatment time of acute cerebral infarction is 20 days, the preset value is 3 days, the diabetes and acute cerebral infarction with the treatment time difference less than 3 are classified into one disease category, the time threshold corresponding to the disease category is determined to be [20, 21 and 22], and the acute appendicitis is classified into the other disease category.

Or, the treatment time period of the diseases 1 to 6 is 9 days, 10 days, 11 days, 12 days, 13 days and 14 days, the preset value is 3 days, the diseases 1 to 3 with the treatment time period difference less than 3 are classified into a disease category, the corresponding time threshold value of the disease category is [9, 10, 11], namely the treatment time period of the diseases of the disease category is [9, 10, 11]; diseases 4 to 6 with a visit duration difference less than 3 are classified into another disease category, and the time threshold corresponding to the disease category is [12, 13, 14], namely the disease visit duration of the disease category is [12, 13, 14].

Optionally, before acquiring the patient information, acquiring initial information, performing code matching processing on abnormal values, null values and disease names on the initial information, removing error and redundant information, acquiring the patient information, and ensuring the quality of the patient information.

Step S104, analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group, wherein the target patient group comprises at least two target patients, the admission time difference between the at least two target patients is smaller than or equal to a first target time threshold, and the discharge time difference between the at least two target patients is smaller than or equal to a second target time threshold.

It should be appreciated that the first target time threshold and the second target time threshold are set according to actual situation requirements.

Taking a disease class A of a hospital A as a target disease class, wherein the disease treatment duration of the target disease class is [12, 13, 14], and combining a floating date of admission and a date of discharge to obtain a plurality of target patient groups admitted in the same time period.

Specifically, if the disease treatment duration of the target disease class is [12, 13, 14], the first target time threshold may be 1 day, the second target time threshold may be 1 day, 100 patient information of the target disease class is analyzed to obtain 15 target patient groups, and the target patient groups include at least two target patients, that is, the number of people in the target patient groups may be 2, 3, 4, 5, or even more.

For example, the first group includes two target patients, the first target patient is admitted for 1 month and 1 day, the discharge time is 1 month and 15 days, the second target patient is admitted for 1 month and 1 day, the discharge time is 1 month and 14 days, the difference in admission time between the two target patients is less than 1 day, and the difference in discharge time between the two target patients is equal to 1 day.

The second group included six target patients, the first target patient was admitted for 2 months 1 day and the discharge time was 2 months 13 days, the second, third target patient was admitted for 2 months 1 day and the discharge time was 2 months 14 days, the fourth target patient was admitted for 2 months 2 days and the discharge time was 2 months 13 days, and the fifth and sixth target patient was admitted for 2 months and 2 months 14 days. The difference in admission time between the six target patients is less than or equal to 1 day, and the difference in discharge time between the six target patients is less than or equal to 1 day.

And so on until the fifteenth target patient group is determined. By analyzing at least two patients in the same disease category, a target patient group is obtained, and the analysis of at least two patients in different disease categories can be avoided, so that the analysis range is reduced, and the analysis efficiency is improved.

And S106, counting target patient groups of a plurality of disease categories in a plurality of hospitals, determining at least two abnormal patients, wherein the at least two abnormal patients are simultaneously present in N target patient groups or more as an abnormal patient group, and N is more than or equal to 3.

For example, there are 5 hospitals, 10 disease categories per hospital, and 15 target patient groups per disease category, then 10 disease categories for 5 hospitals together have 750 target patient groups. If N is 5, if at least two target patients are simultaneously present in 8 target patient groups, the frequency of the at least two target patients entering and exiting in the same time period is indicated to be 8 times, the at least two target patients are determined to be abnormal patients, the abnormal patient group is used as an abnormal patient group, the abnormal patient group can be determined to be a medical insurance fraudulent patient group with regular visit behaviors, and medical insurance group fraudulent abnormal behaviors are determined. Based on the fact that target patients with the frequency of being discharged from the hospital in the same time period being greater than or equal to N times are determined to be medical insurance fraudulent patients, the accidental among the patients is eliminated, and the accuracy of locating the medical insurance fraudulent patients can be improved.

Optionally, in some embodiments, the method shown in fig. 1 further comprises:

and deleting the target abnormal patient when the cost reimbursement proportion of the target abnormal patient meets a first threshold value.

It should be appreciated that the first threshold and the second threshold may be a single value, or the first threshold and the second threshold may be a single interval.

For example, if the first threshold is 80%, if the cost reimbursement proportion of the target abnormal patient is greater than 80%, indicating that the target abnormal patient has a low self-cost proportion and a high reimbursement proportion, the target abnormal patient is determined to be a medical insurance fraudulent patient, and the target abnormal patient is retained.

Or if the first threshold is 60%, if the cost reimbursement proportion of the target abnormal patient is less than 60%, which indicates that the self-cost reimbursement proportion of the target abnormal patient is high, determining the target abnormal patient as a non-medical insurance fraudulent patient, and deleting the target abnormal patient. By eliminating non-medical insurance fraudulent patients with high self-charge proportion and low reimbursement proportion, the accuracy rate of locating the medical insurance fraudulent patients can be improved.

Optionally, in other embodiments, the method shown in fig. 1 further comprises:

and deleting the target abnormal patient when the empty bed rate of the hospital where the target abnormal patient is in the visit meets the second threshold.

It will be appreciated that if the number of beds in a hospital itself is 100, but only 50 patients are held, this means that the empty bed rate is 50%.

For example, if the second threshold is 40%, if the empty rate of the hospital with the target abnormal patient at the visit is lower than 20%, the hospital is determined to be a visit saturated hospital, and the saturated hospital is not possible to get in hospital, that is, the target abnormal patient with the visit saturated hospital is a non-medical insurance fraudulent patient, the target abnormal patient is deleted, and the false positive rate of the detection result is reduced by excluding the non-medical insurance fraudulent patient with the visit saturated hospital.

It should be understood that a positive result refers to illegal medical treatment, false medical treatment, etc. False positive rate means the percentage of false positive results to screening results.

Optionally, in still other embodiments, the method shown in fig. 1 further comprises:

and deleting the diseases obtained by the target abnormal patients from the disease list, wherein the diseases in the disease list are diseases which need frequent and regular treatment.

For example, a target abnormal patient suffering from uremia is dialyzed in a hospital at intervals, and based on the condition that uremia itself is a disease requiring frequent and regular treatment, the target abnormal patient is a non-medical insurance fraudulent patient, and the target abnormal patient is deleted.

Or, the target abnormal patient with diabetes should be checked at least once every year, based on the fact that diabetes is a disease requiring frequent and regular treatment, the target abnormal patient is described as a non-medical insurance fraudulent patient, the target abnormal patient is deleted, and the accuracy rate of locating the medical insurance fraudulent patient can be improved by eliminating the non-medical insurance fraudulent patient with the disease requiring frequent and regular treatment.

Optionally, in some embodiments, the behavior features of the target abnormal patient group are classified by combining the business analysis features (such as the discharge and admission in a short time, the number of hospitalization days of related diseases exceeds the corresponding normal hospitalization threshold value), so as to obtain a continuous discharge group and a regular discharge group, which group the target abnormal patient group belongs to can be accurately determined, the practical value is reflected, and the method has the characteristics of accuracy and landing.

It will be understood that a continuous admission group refers to a condition where at least two patients are admitted multiple times on the same day or are hospitalized for a long period of time, a period of hospitalization exceeding the normal hospitalization threshold for the relevant disease, indicating that there is a dismantling hospitalization problem, and a regular admission group refers to a condition where at least two patients are admitted multiple times, either simultaneously or regularly, indicating that there is a hanging hospitalization problem.

Optionally, in some embodiments, the method shown in fig. 1 further comprises:

classifying the target abnormal patient group according to hospitals where the target abnormal patients in the target abnormal patient group visit and the frequency of the visit;

and displaying the target abnormal patient group according to the category of the target abnormal patient group.

In some embodiments, the target abnormal patient group is classified according to the hospitals where the target abnormal patients visit and the frequency of the visits, so that the category of the target abnormal patient group is obtained, and the target abnormal patient group is displayed according to the category, so that the staff can quickly find the required patient information. For example, patients who are at the same hospital and have between 4 and 6 visits per month are classified into one category.

FIG. 2 is a flow chart of another method for detecting abnormal medical insurance group fraud, as shown in FIG. 2, the method includes:

step S202, obtaining patient information, wherein the patient information comprises patients, the treated hospitals and diseases obtained by the patients, and classifying the patient information according to the treated hospitals and the disease types to obtain different disease types of different hospitals.

Step S204, analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group, wherein the target patient group comprises at least two target patients, and the target patients meet the conditions of similar admission time and similar discharge time in the same hospital.

Step S206, counting target patient groups of different disease types of different hospitals, if a plurality of target patient groups are more than or equal to N target patient groups, wherein N is more than or equal to 3, and the occurrence frequency of the target patient groups is more than or equal to N, the target patient groups are used as abnormal patient groups and are connected to form a social network, and the social network is also called an abnormal patient group.

Step S208, analyzing the abnormal patient group according to the characteristics of cost, hospital, disease law and the like, eliminating abnormal patients corresponding to some interference diseases, obtaining a target abnormal patient group, classifying the target abnormal patient group, obtaining a continuous discharge group and a regular discharge group, and listing the continuous discharge group and the regular discharge group in a corresponding abnormal patient list and displaying, thereby further reducing the false positive rate, accurately positioning medical insurance fraudulent patients and giving medical insurance supervision multi-dimensional support.

Fig. 3 is a schematic structural diagram of a device for detecting abnormal fraudulent activity of a medical insurance group according to an embodiment of the present invention, and as shown in fig. 3, the device 30 includes:

a first classification module 31 for classifying patient information according to the type of hospital and disease being treated;

an analysis module 32, configured to analyze at least two patient information of a target disease category of a target hospital to obtain a target patient group, where the target patient group includes at least two target patients, a time difference of admission between the at least two target patients is less than or equal to a first target time threshold, and a time difference of discharge between the at least two target patients is less than or equal to a second target time threshold;

a determining module 33, configured to count target patient groups of a plurality of disease categories in a plurality of hospitals, determine at least two abnormal patients, as an abnormal patient population, where the at least two abnormal patients are present in greater than or equal to N target patient groups at the same time.

Optionally, as one embodiment, the classification of the disease type is related to the duration of the visit to the disease.

Optionally, as an embodiment, the apparatus 30 further includes:

the first deleting module is used for deleting the target abnormal patient under the condition that the cost reimbursement proportion of the target abnormal patient meets a first threshold value.

Optionally, as an embodiment, the apparatus 30 further includes:

and the second deleting module is used for deleting the target abnormal patient under the condition that the empty bed rate of the hospital where the target abnormal patient is in a doctor meets a second threshold.

Optionally, as an embodiment, the apparatus 30 further includes:

and the third deleting module is used for deleting the diseases obtained by the target abnormal patients from the disease list, wherein the diseases in the disease list are diseases which need to be frequently and regularly treated.

Optionally, as an embodiment, the apparatus 30 further includes:

the second classification module is used for classifying the target abnormal patient group according to the hospitals where the target abnormal patients in the target abnormal patient group visit and the frequency of the visits;

and the display module is used for displaying the target abnormal patient group according to the category of the target abnormal patient group.

The mobile terminal provided by the embodiment of the present invention can implement each process implemented in the method embodiment of fig. 1, and in order to avoid repetition, a description is omitted here.

An electronic device according to an embodiment of the present application will be described in detail below in conjunction with fig. 4. Referring to fig. 4, at the hardware level, the electronic device includes a processor, optionally including an internal bus, a network interface, a memory. The memory may include a memory, such as a high-speed Random access memory (Random-AccessMemory, RAM), and may further include a non-volatile memory (non-volatile memory), such as at least 1 disk memory, etc. Of course, the electronic device may also include hardware required for other services.

The processor, network interface, and memory may be interconnected by an internal bus, which may be an industry standard architecture (Industry Standard Architecture, ISA) bus, a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 4, but not only one bus or type of bus.

And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.

The processor reads the corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to form the detection device for the medical insurance group fraud abnormal behavior on the logic level. The processor is used for executing the programs stored in the memory and is specifically used for executing the following operations:

and counting target patient groups of a plurality of disease categories in a plurality of hospitals, determining at least two abnormal patients as abnormal patient groups, wherein the at least two abnormal patients are simultaneously in greater than or equal to N target patient groups.

The method executed by the device for detecting abnormal medical insurance group fraud behavior disclosed in the embodiment shown in fig. 1 of the present application may be applied to a processor or implemented by the processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.

Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flow is not limited to each logic unit, but may be hardware or a logic device.

The embodiment of the invention provides a computer readable storage medium, which classifies patient information according to the type of hospital and disease in a doctor; analyzing at least two patient information of a target disease category of a target hospital to obtain a target patient group, wherein the target patient group comprises at least two target patients, the admission time difference between the at least two target patients is smaller than or equal to a first target time threshold, and the discharge time difference between the at least two target patients is smaller than or equal to a second target time threshold; and counting target patient groups of a plurality of disease categories in a plurality of hospitals, determining at least two abnormal patients as abnormal patient groups, wherein the at least two abnormal patients are simultaneously in greater than or equal to N target patient groups.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. According to the definitions herein, the computer-readable medium does not include a transitory computer-readable medium (transmission medium), such as a modulated data signal and carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

The foregoing is merely exemplary of the present invention and is not intended to limit the present invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are to be included in the scope of the claims of the present invention.

Claims

1. A method for detecting abnormal fraudulent activity of a medical insurance population, the method comprising: :

2. The method of claim 1, wherein the classification of the disease type is related to a duration of a visit to the disease.

3. The method of claim 1 or 2, wherein the method further comprises:

and deleting the target abnormal patient under the condition that the cost reimbursement proportion of the target abnormal patient meets a first threshold value.

4. A method as claimed in claim 3, wherein the method further comprises:

and deleting the target abnormal patient when the empty bed rate of the hospital where the target abnormal patient is in the visit meets a second threshold.

5. The method of claim 4, wherein the method further comprises:

and deleting the diseases obtained by the target abnormal patients from a disease list, wherein the diseases in the disease list are diseases which need frequent and regular treatment.

6. The method of claim 5, wherein the method further comprises:

7. A device for detecting abnormal fraud in a medical insurance group, the device comprising: :

8. The apparatus of claim 7, wherein the classification of the disease type is related to a duration of a visit to the disease.

9. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor performs the steps of the method according to any one of claims 1 to 6.

10. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1 to 6.