Medical insurance common outpatient service supervision system and method based on fraud abnormal portrait technology

Abstract

The invention relates to the technical field of medical behavior data monitoring, in particular to a medical insurance common outpatient service supervision system and method based on a fraud abnormal portrait technology, and the system comprises a medical transaction data collection module, a medical behavior analysis module, a risk assessment feedback module and a medical transaction database. According to the medical insurance ordinary outpatient service supervision system and method based on the fraud anomaly portrait technology, a more comprehensive risk assessment system is provided, and by means of an intelligent means, the medical object behavior anomaly risk, the medical institution behavior anomaly risk and the number of abnormal behavior overlapping cycles are comprehensively analyzed, so that the risk assessment efficiency is improved. According to the invention, the method achieves the precise recognition, early warning and prevention of fraud abnormal behaviors in a common medical insurance outpatient service, facilitates the improvement of the use efficiency of medical insurance funds, guarantees the fairness and sustainability of a medical insurance system, protects the benefits of a patient, maintains the fairness and efficiency of a medical system, and also facilitates the improvement of the management level and service quality of a medical institution.

Description

Technical Field

[0001] The present invention relates to the technical field of medical behavior data monitoring, and specifically to a medical insurance general outpatient supervision system and method based on fraud anomaly profiling technology. Background Art

[0002] With the expansion of medical insurance coverage and the increase in demand for general outpatient medical services, medical insurance funds are facing increasing regulatory pressure. There are a large number of complex medical behaviors in general outpatient clinics, which provides opportunities for fraud and abnormal behavior. The current medical insurance supervision system is mainly based on rule matching or simple anomaly detection methods, lacking the ability to deeply characterize and dynamically evaluate behavioral patterns.

[0003] For example, the invention patent with publication number: CN119007956A is a portable intelligent terminal for medical staff, including: a behavior tracking module, a communication module, a medical application module and a data transmission module; wherein: the behavior tracking module is used to collect the behavior data of medical staff in real time through high-precision sensors and algorithms; the communication module is used to realize real-time communication between medical staff and other personnel or equipment; the medical application module has a variety of professional medical applications built in, which is used to provide convenient work support for medical staff; the data transmission module is used to send the behavior data of medical staff collected by the behavior tracking module to the behavior data analysis system, and provide data support for the data analysis of the behavior data analysis system.

[0004] For example, the invention patent with publication number: CN118717066A is a health data information detection system, including an ARM Cortex-M processor reasoning module, a data analysis module, a data storage module, a data transmission module, a high-precision 24-bit ADC chip, an information acquisition module, a prompt module and a display. The reasoning module includes a data acquisition module responsible for collecting raw data from sensors and a data preprocessing module for preprocessing the collected raw data.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present applicant discovered that the above technology has at least the following technical problems: the current medical insurance supervision system often relies on fixed rule review, which makes it difficult to dynamically identify new abnormal behaviors. In addition, simple rule matching can easily lead to false alarms, further increasing the burden of manual verification. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a medical insurance general outpatient supervision system and method based on fraud anomaly profiling technology, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a medical insurance general outpatient supervision system based on fraud anomaly profiling technology, including: a medical transaction data collection module, a medical behavior analysis module and a risk assessment feedback module.

[0008] The medical transaction data collection module is used to obtain medical transaction data, wherein the medical transaction data includes medical institution behavior data and medical subject behavior data.

[0009] The medical behavior analysis module is used to process the abnormal behavior risk assessment value of each medical object based on the medical object behavior data, and to process the abnormal behavior risk assessment value of the medical institution based on the medical institution behavior data, and to issue an initial warning based on the abnormal behavior risk assessment value of the medical institution.

[0010] The risk assessment feedback module is used to obtain medical transaction data of each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index based on the medical institution behavior data and the medical object behavior data. Based on the abnormal medical behavior risk assessment index, risk warnings and feedback are provided for medical behaviors.

[0011] As a further method, the processing obtains the abnormal behavior risk assessment value of each medical object, and the specific process is: the medical object behavior data includes: the frequency of visits of each medical object in each preset monitoring period, the amount of repeated prescriptions of the same medicine for each medical object, the number of times each medical object changes medicine, the number of places where each medical object's medical insurance account is used, and the total number of times each medical object's medical insurance account is used.

[0012] The average frequency of medical visits for each medical subject within the preset monitoring period, the critical amount of drugs for repeated prescriptions of the same drugs for medical subjects with chronic diseases, the critical amount of drugs for repeated prescriptions of the same drugs for medical subjects with acute diseases, the critical number of times of drug changes for medical subjects with chronic diseases, the critical number of times of drug changes for medical subjects with acute diseases, the critical number of locations where the medical subjects' medical insurance accounts are used, and the critical number of total uses of the medical subjects' medical insurance accounts are extracted from the medical transaction database.

[0013] Based on the medical object behavior data, a comprehensive analysis is performed to obtain an abnormal risk assessment value for each medical object behavior. The abnormal risk assessment value for each medical object behavior is used to quantitatively assess the degree of fraud and violation risk of each medical object behavior, and provide a basis for assessing the degree of abnormal risk of medical behavior.

[0014] As a further method, the processing obtains an abnormal risk assessment value for medical institution behavior, and the specific process is: the medical institution behavior data includes: the number of specific drug prescriptions of the medical institution within each preset monitoring period, the total number of drug prescriptions of the medical institution, the proportion of drug costs of the medical institution, the number of modified settlement records of the medical institution, the total number of settlement records of the medical institution and the behavior data of medical staff.

[0015] The medical staff behavior data include: the amount of medicines prescribed by each medical staff at one time and the amount of examination items prescribed by each medical staff at one time during each preset monitoring period.

[0016] The proportion of industry standard drug costs, the average single prescription volume of drugs in the same department, and the average single prescription volume of examination items in the same department within the preset monitoring period are extracted from the medical transaction database.

[0017] Based on the medical institution behavior data, a comprehensive analysis is conducted to obtain an abnormal risk assessment value for the medical institution behavior. The abnormal risk assessment value for the medical institution behavior is used to quantitatively assess the degree of abnormal fraud risk in the medical institution behavior, and to provide a basis for assessing the degree of abnormal risk in medical behavior.

[0018] As a further method, the initial warning is carried out according to the abnormal risk assessment value of the medical institution behavior. The specific warning process is: extracting the first threshold value of the abnormal risk assessment of the medical institution behavior and the second threshold value of the abnormal risk assessment of the medical institution behavior from the medical transaction database, and comparing the abnormal risk assessment value of the medical institution behavior with the first threshold value of the abnormal risk assessment of the medical institution behavior and the second threshold value of the abnormal risk assessment of the medical institution behavior; if the abnormal risk assessment value of the medical institution behavior is higher than or equal to the first threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a high-risk behavior and a warning is issued; if the abnormal risk assessment value of the medical institution behavior is lower than the first threshold value of the abnormal risk assessment of the medical institution behavior and higher than the second threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a low-risk behavior and it is continuously monitored; if the abnormal risk assessment value of the medical institution behavior is lower than or equal to the second threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a risk-free behavior.

[0019] Conduct secondary analysis on low-risk behaviors and issue early warnings based on the analysis results.

[0020] As a further method, the screening obtains the number of overlapping cycles of abnormal behavior. The specific screening process is: obtaining medical transaction data of each historical monitoring period, processing to obtain abnormal behavior risk assessment values ​​of medical institutions in each historical monitoring period and abnormal behavior risk assessment values ​​of each medical subject in each historical monitoring period.

[0021] According to the abnormal behavior risk assessment value of each medical object in each historical monitoring period, the number of abnormal medical objects in each historical monitoring period is processed and obtained.

[0022] The second threshold for risk assessment of abnormal behavior of medical institutions and the critical value for the number of abnormal medical subjects are extracted from the medical transaction database.

[0023] The abnormal risk assessment value of medical institution behavior and the number of abnormal medical subjects in each historical monitoring period are compared with the second threshold of the abnormal risk assessment of medical institution behavior and the critical value of the number of abnormal medical subjects, respectively. If the abnormal risk assessment value of medical institution behavior in a certain monitoring period is higher than the second threshold of the abnormal risk assessment of medical institution behavior and the number of abnormal medical subjects is greater than the critical value of the number of abnormal medical subjects, the monitoring period is marked as an overlapping period.

[0024] Count the number of coincidence cycles.

[0025] As a further method, the processing obtains the number of abnormal medical subjects in each historical monitoring period. The specific process is: comparing the abnormal behavior risk assessment value of each medical subject in each historical monitoring period with the abnormal behavior risk assessment threshold of the medical subject. If the abnormal behavior risk assessment value of a medical subject in a historical monitoring period is greater than or equal to the abnormal behavior risk assessment threshold of the medical subject, the medical subject is marked as an abnormal medical subject.

[0026] Count the number of abnormal medical objects in each historical monitoring period.

[0027] As a further method, the comprehensive analysis obtains the abnormal risk assessment index of medical behavior. The specific analysis process is: based on the number of abnormal behavior overlapping cycles, the abnormal behavior risk assessment value of each medical object and the abnormal behavior risk assessment value of the medical institution, a comprehensive analysis is performed to obtain the abnormal risk assessment index of medical behavior. The abnormal risk assessment index of medical behavior is used to quantitatively assess the degree of fraud and violation risk of medical behavior, and provide a basis for risk warning of medical behavior.

[0028] As a further method, the risk warning and feedback of medical behavior are carried out according to the abnormal medical behavior risk assessment index. The specific analysis process is: the abnormal medical behavior risk assessment index is extracted from the medical transaction database, and the abnormal medical behavior risk assessment index is compared with the abnormal medical behavior risk assessment index. If the abnormal medical behavior risk assessment index is higher than or equal to the abnormal medical behavior risk assessment index, the medical behavior is evaluated as abnormal behavior and a risk warning is issued for it. If the abnormal medical behavior risk assessment index is lower than the abnormal medical behavior risk assessment index, the medical behavior is evaluated as normal behavior and displayed and outputted.

[0029] As a further method, the abnormal behavior risk assessment value of the medical institution is specifically expressed as:

[0030] In the formula, represents the risk assessment value of abnormal behavior of medical institutions, represents the number of times a specific drug is prescribed by a medical institution within the sth preset monitoring period, s represents the number of each preset monitoring period, , t represents the total number of preset monitoring cycles, It represents the total number of drug prescriptions issued by the medical institution during the sth preset monitoring period. represents the proportion of drug expenses of medical institutions in the sth preset monitoring period, Indicates the number of times the medical institution modified its settlement records within the sth preset monitoring period. Indicates the total number of settlement records of the medical institution in the sth preset monitoring period, represents the proportion of industry standard drug costs within the preset monitoring period, n represents the number of each medical staff, , m represents the total number of medical staff, It indicates the amount of medicines prescribed by the nth medical staff in the sth preset monitoring period. It indicates the number of examination items prescribed by the nth medical staff in the sth preset monitoring period. It indicates the average amount of drugs prescribed in a single session in the same department during the preset monitoring period. It indicates the average number of inspection items issued at one time by the same department during the preset monitoring period.

[0031] The second aspect of the present invention provides a medical insurance general outpatient supervision method based on fraud anomaly profiling technology, including: S1. Acquire medical transaction data, wherein the medical transaction data includes medical institution behavior data and medical object behavior data.

[0032] S2. Based on the medical subject behavior data, obtain the medical subject behavior abnormal risk assessment value; based on the medical institution behavior data, obtain the medical institution behavior abnormal risk assessment value; and issue an initial warning based on the medical institution behavior abnormal risk assessment value.

[0033] S3. Obtain medical transaction data for each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index through comprehensive analysis based on the medical institution behavior data and medical subject behavior data. Provide risk warning and feedback for medical behavior based on the abnormal medical behavior risk assessment index.

[0034] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0035] (1) The present invention provides a more comprehensive risk assessment system by providing a medical insurance general outpatient supervision system and method based on fraud abnormality profiling technology. By using intelligent means, through comprehensive analysis of the abnormal behavior risk of medical subjects, the abnormal behavior risk of medical institutions and the number of abnormal behavior overlap cycles, it realizes the accurate identification, early warning and prevention of fraud abnormal behavior in medical insurance general outpatient clinics, which is conducive to improving the efficiency of the use of medical insurance funds, ensuring the fairness and sustainability of the medical insurance system, and also helps to improve the management level and service quality of medical institutions.

[0036] (2) The present invention can significantly improve the medical insurance system's ability to identify fraudulent behavior, protect the rational use of medical insurance funds, and provide medical subjects with safer and more effective medical services by comprehensively analyzing the medical subject's frequency of visits to the doctor, the amount of the same drug repeatedly prescribed to the medical subject, the number of times the medical subject changes drugs, the number of locations where the medical subject's medical insurance account is used, and the total number of times the medical subject's medical insurance account is used.

[0037] (3) The present invention can provide strong support for assessing the risk of fraud by comprehensively analyzing the number of times a medical institution prescribes specific drugs, the proportion of drug costs in the medical institution, the number of times a medical institution modifies settlement records, the amount of drugs prescribed by medical staff at a time, and the amount of examination items prescribed by medical staff at a time. This is conducive to significantly improving the ability to identify and prevent fraud, thereby protecting the interests of patients and maintaining the fairness and efficiency of the medical system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0040] Figure 1 It is a schematic diagram of system module connection of the present invention.

[0041] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] Reference Figure 1As shown, the first aspect of the present invention provides a medical insurance general outpatient supervision system based on fraud anomaly profiling technology, including: a medical transaction data collection module, a medical behavior analysis module and a risk assessment feedback module.

[0045] The medical transaction data collection module is used to obtain medical transaction data, wherein the medical transaction data includes medical institution behavior data and medical subject behavior data.

[0046] It should be added that by connecting to the hospital's information system, the diagnosis and treatment behavior data of medical institutions can be obtained in real time or regularly. The medical insurance general outpatient supervision system is connected to the medical insurance system to obtain medical insurance settlement data, reimbursement records, etc. An EDI interface can be established with medical institutions to transmit data through standard electronic data exchange protocols. It is also possible to develop or use existing APIs to extract data from the databases of medical institutions.

[0047] The medical behavior analysis module is used to process the abnormal behavior risk assessment value of each medical object based on the medical object behavior data, and to process the abnormal behavior risk assessment value of the medical institution based on the medical institution behavior data, and to issue an initial warning based on the abnormal behavior risk assessment value of the medical institution.

[0048] Specifically, the abnormal behavior risk assessment value of each medical object is processed, and the specific process is: the medical object behavior data includes: the frequency of visits of each medical object in each preset monitoring period, the amount of repeated prescriptions of the same medicine for each medical object, the number of times each medical object changes medicine, the number of places where each medical object's medical insurance account is used, and the total number of times each medical object's medical insurance account is used.

[0049] It should be added that the duration of each preset monitoring cycle is the same.

[0050] The average frequency of medical visits for each medical subject within the preset monitoring period, the critical amount of drugs for repeated prescriptions of the same drugs for medical subjects with chronic diseases, the critical amount of drugs for repeated prescriptions of the same drugs for medical subjects with acute diseases, the critical number of times of drug changes for medical subjects with chronic diseases, the critical number of times of drug changes for medical subjects with acute diseases, the critical number of locations where the medical subjects' medical insurance accounts are used, and the critical number of total uses of the medical subjects' medical insurance accounts are extracted from the medical transaction database.

[0051] Based on the medical object behavior data, a comprehensive analysis is performed to obtain an abnormal risk assessment value for each medical object behavior. The abnormal risk assessment value for each medical object behavior is used to quantitatively assess the degree of fraud and violation risk of each medical object behavior, and provide a basis for assessing the degree of abnormal risk of medical behavior.

[0052] In a specific embodiment, the numerical expression of the abnormal behavior risk assessment value of each medical subject is:

[0053] In the formula, represents the risk assessment value of abnormal behavior of the rth medical object, e represents a natural constant, represents the frequency of visits of the rth medical subject in the sth preset monitoring period, s represents the number of each preset monitoring period, , t represents the total number of preset monitoring cycles, r represents the number of each medical object, , h represents the total number of medical objects, represents the amount of the same drug repeatedly prescribed to the rth medical subject during the sth preset monitoring period, represents the number of times the rth medical subject changes his / her medication within the sth preset monitoring period, Indicates the number of locations where the medical insurance account of the rth medical object is used in the sth preset monitoring period, Indicates the total number of times the medical insurance account of the rth medical object is used in the sth preset monitoring period, represents the average frequency of visits of the rth medical subject during the preset monitoring period, Indicates the critical amount of drugs for which chronic disease patients are repeatedly prescribed the same drug. Indicates the critical amount of the same drug that is repeatedly prescribed to an acute disease patient. Indicates the critical number of times that chronic disease medical subjects change their medications. Indicates the critical number of times that the acute disease medical object changes the medicine, Indicates the critical number of locations where medical objects’ medical insurance accounts are used. Indicates the critical total usage times of the medical insurance account of the medical object.

[0054] It is necessary to explain that, for example, Set to 3, when When the chronic disease of the medical object is At that time, the medical object suffers from an acute disease.

[0055] It needs to be explained that, for medical subjects suffering from chronic diseases, the more frequently the medical subjects visit the doctor, the larger the amount of repeated prescriptions for the same medicine, the more times the medical subjects change medicines, the more places the medical subjects use their medical insurance accounts, and the more times the medical subjects use their medical insurance accounts in total, the greater the corresponding abnormal behavior risk assessment value of the medical subjects, indicating that the medical subjects' behavior has a higher risk of fraud and violation.

[0056] It needs to be explained that, for medical subjects suffering from acute diseases, the more frequently the medical subjects visit the doctor, the larger the amount of repeated prescriptions for the same medicine, and the more times the medical subjects change medicines, the greater the corresponding abnormal behavior risk assessment value of the medical subjects, indicating that the risk of fraud and violation of regulations in the medical subjects' behavior is higher.

[0057] It is important to explain that patients with chronic diseases may need regular follow-up visits and adjustments to treatment plans, so a high frequency of visits may be normal. However, if the frequency of visits is abnormally higher than the average, it may indicate fraudulent over-diagnosis or falsification of medical records. For chronic diseases, it is common to use the same medication for a long time. However, if the amount of medication is abnormally large, it may indicate fraudulent drug reselling or abuse of medical insurance. Patients with chronic diseases usually do not change medications frequently after their condition stabilizes. If frequent changes occur, it may be a fraud by doctors or patients to obtain more medications. Patients with chronic diseases may visit multiple medical institutions. However, if there are too many places of use, especially in different cities or regions, it may indicate cross-regional fraudulent use of medical insurance funds. Chronic disease patients may use their medical insurance accounts more frequently because they need regular treatment. However, if the total number of uses is abnormally high, further investigation may be needed to determine whether there is fraud. Patients with acute diseases usually visit the doctor when their condition flares up, and the frequency decreases after treatment. If the frequency of visits by patients with acute diseases is abnormally high, it may be necessary to investigate whether there is falsification of medical records or over-diagnosis. Patients with acute diseases usually no longer need the same medication after their condition improves. If the same medication is repeatedly prescribed in unusually large quantities, there may be fraud. Acutely ill patients may need medications adjusted during treatment. However, if the number of changes is unusually high, it may be fraud by the doctor or patient in order to obtain more medication.

[0058] It should be explained that in this embodiment, by comprehensively analyzing the frequency of medical subjects' visits, the amount of repeated prescriptions of the same drugs for medical subjects, the number of times medical subjects change drugs, the number of locations where medical subjects' medical insurance accounts are used, and the total number of times medical subjects' medical insurance accounts are used, the medical insurance system's ability to identify fraudulent behavior can be significantly improved, the rational use of medical insurance funds can be protected, and safer and more effective medical services can be provided to medical subjects.

[0059] It should be added that, by analyzing data from multiple dimensions, this embodiment can more accurately identify abnormal behavior patterns, thereby improving the accuracy of fraud detection. For example, if a medical subject has a high frequency of visits, a high amount of repeated prescriptions, a high number of drug changes, multiple locations where medical insurance accounts are used, and an abnormally high total number of medical insurance account uses, this may indicate the presence of fraud. A comprehensive risk assessment can be provided by taking into account different parameters. A single indicator may not fully reflect the behavior of medical subjects, while multi-parameter analysis can reveal more complex behavior patterns. By monitoring changes in these parameters, an early warning system can be established to detect potential fraud in a timely manner, so that intervention measures can be taken before fraud causes greater losses. Centralized analysis of these parameters can also help regulators optimize resource allocation, allocate more attention and investigation resources to high-risk medical subjects, and improve regulatory efficiency. The data provided by the comprehensive analysis can provide decision support for policymakers and help them formulate more effective medical insurance policies and fraud prevention measures.

[0060] Further, the abnormal risk assessment value of medical institution behavior is obtained by processing, and the specific process is: the medical institution behavior data includes: the number of specific drug prescriptions of the medical institution within each preset monitoring period, the total number of drug prescriptions of the medical institution, the proportion of drug costs of the medical institution, the number of modified settlement records of the medical institution, the total number of settlement records of the medical institution and the behavior data of medical staff.

[0061] The medical staff behavior data include: the amount of medicines prescribed by each medical staff at one time and the amount of examination items prescribed by each medical staff at one time during each preset monitoring period.

[0062] The proportion of industry standard drug costs, the average single prescription volume of drugs in the same department, and the average single prescription volume of examination items in the same department within the preset monitoring period are extracted from the medical transaction database.

[0063] Based on the medical institution behavior data, a comprehensive analysis is conducted to obtain an abnormal risk assessment value for the medical institution behavior. The abnormal risk assessment value for the medical institution behavior is used to quantitatively assess the degree of abnormal fraud risk in the medical institution behavior, and to provide a basis for assessing the degree of abnormal risk in medical behavior.

[0064] In a specific embodiment, the numerical expression of the abnormal behavior risk assessment value of the medical institution is:

[0065] In the formula, represents the risk assessment value of abnormal behavior of medical institutions, Indicates the number of times a specific drug is prescribed by a medical institution during the sth preset monitoring period. It represents the total number of drug prescriptions issued by the medical institution during the sth preset monitoring period. represents the proportion of drug expenses of medical institutions in the sth preset monitoring period, Indicates the number of times the medical institution modified its settlement records within the sth preset monitoring period. Indicates the total number of settlement records of the medical institution in the sth preset monitoring period, represents the proportion of industry standard drug costs within the preset monitoring period, n represents the number of each medical staff, , m represents the total number of medical staff, It indicates the amount of medicines prescribed by the nth medical staff in the sth preset monitoring period. It indicates the number of examination items prescribed by the nth medical staff in the sth preset monitoring period. It indicates the average amount of drugs prescribed in a single session in the same department during the preset monitoring period. It indicates the average number of inspection items issued at one time by the same department during the preset monitoring period.

[0066] What needs to be explained is that the more times a medical institution prescribes specific drugs, the greater the proportion of the medical institution's drug expenses, the more times the medical institution modifies its settlement records, the larger the amount of drugs prescribed by medical staff at a single time, and the more examination items prescribed by medical staff at a single time, the higher the degree of fraud risk in the medical institution's behavior.

[0067] It is important to explain that high rates of specific drug prescriptions may be associated with fraudulent behavior, especially if the drug is expensive or there is no sufficient medical necessity. This may indicate that the medical institution or medical staff is promoting unnecessary drug sales. If the proportion of drug costs in total medical costs is abnormally high, it may indicate that drugs are over-prescribed, which may be a sign of fraud. An abnormally high number of modified settlement records may indicate that the medical institution is trying to cover up fraud, such as falsely reporting expenses or providing medical services that did not occur. If a medical staff prescribes a significantly higher than average amount of drugs in a single session, it may indicate that the person is suspected of over-prescribing drugs, especially when there is no sufficient medical reason. If a medical staff prescribes an abnormally large number of examination items in a single session, it may indicate that he or she is promoting unnecessary examinations, which may be a fraudulent behavior to increase revenue.

[0068] It should be explained that this embodiment can provide strong support for assessing the risk of fraud by comprehensively analyzing the number of specific drug prescriptions of medical institutions, the proportion of drug expenses of medical institutions, the number of times medical institutions modify settlement records, the amount of drugs prescribed by medical staff at a time, and the number of examination items prescribed by medical staff at a time, which is conducive to significantly improving the ability to identify and prevent fraud, thereby protecting the interests of patients and maintaining the fairness and efficiency of the medical system. At the same time, it also helps to improve the management level and service quality of medical institutions.

[0069] Furthermore, an initial warning is made based on the abnormal risk assessment value of the medical institution behavior. The specific warning process is: extracting the first threshold value of the abnormal risk assessment of the medical institution behavior and the second threshold value of the abnormal risk assessment of the medical institution behavior from the medical transaction database, and comparing the abnormal risk assessment value of the medical institution behavior with the first threshold value of the abnormal risk assessment of the medical institution behavior and the second threshold value of the abnormal risk assessment of the medical institution behavior; if the abnormal risk assessment value of the medical institution behavior is higher than or equal to the first threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a high-risk behavior and a warning is issued; if the abnormal risk assessment value of the medical institution behavior is lower than the first threshold value of the abnormal risk assessment of the medical institution behavior and higher than the second threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a low-risk behavior and is continuously monitored; if the abnormal risk assessment value of the medical institution behavior is lower than or equal to the second threshold value of the abnormal risk assessment of the medical institution behavior, the medical institution behavior is assessed as a risk-free behavior.

[0070] For example, for medical institutions that meet the early warning conditions, that is, medical institutions whose behaviors are high-risk behaviors, the monitoring system immediately generates an early warning signal. The early warning signal should contain key information such as the name of the medical institution, the evaluation value, and the trigger time. Then the early warning signal is promptly notified to the regulatory department through SMS, email, system messages, etc. After receiving the early warning, the regulatory department organizes supervisors to conduct a preliminary analysis of the early warning signal. Identify possible risk points and assess the severity and potential impact of the risks. And based on the preliminary analysis results, conduct an in-depth investigation of medical institutions involved in high-risk behaviors. Then, based on the investigation results, formulate targeted risk handling measures. It may include strengthening supervision, rectifying violations, and improving service quality. Finally, the supervisor needs to feedback the risk handling results to the regulatory department. And continue to track and monitor the medical institutions after the treatment to ensure that the risks are effectively controlled.

[0071] Conduct secondary analysis on low-risk behaviors and issue early warnings based on the analysis results.

[0072] Furthermore, the screening obtains the number of overlapping cycles of abnormal behavior, and the specific screening process is: obtaining medical transaction data of each historical monitoring period, processing to obtain abnormal behavior risk assessment values ​​of medical institutions in each historical monitoring period and abnormal behavior risk assessment values ​​of each medical subject in each historical monitoring period.

[0073] According to the abnormal behavior risk assessment value of each medical object in each historical monitoring period, the number of abnormal medical objects in each historical monitoring period is processed and obtained.

[0074] The second threshold for risk assessment of abnormal behavior of medical institutions and the critical value for the number of abnormal medical subjects are extracted from the medical transaction database.

[0075] The abnormal risk assessment value of medical institution behavior and the number of abnormal medical subjects in each historical monitoring period are compared with the second threshold of the abnormal risk assessment of medical institution behavior and the critical value of the number of abnormal medical subjects, respectively. If the abnormal risk assessment value of medical institution behavior in a certain monitoring period is higher than the second threshold of the abnormal risk assessment of medical institution behavior and the number of abnormal medical subjects is greater than the critical value of the number of abnormal medical subjects, the monitoring period is marked as an overlapping period.

[0076] Count the number of coincidence cycles.

[0077] Specifically, the processing obtains the number of abnormal medical objects in each historical monitoring period, and the specific process is: comparing the abnormal behavior risk assessment value of each medical object in each historical monitoring period with the abnormal behavior risk assessment threshold of the medical object; if the abnormal behavior risk assessment value of a medical object in a historical monitoring period is greater than or equal to the abnormal behavior risk assessment threshold of the medical object, the medical object is marked as an abnormal medical object.

[0078] Count the number of abnormal medical objects in each historical monitoring period.

[0079] The risk assessment feedback module is used to obtain medical transaction data of each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index based on the medical institution behavior data and the medical object behavior data. Based on the abnormal medical behavior risk assessment index, risk warnings and feedback are provided for medical behaviors.

[0080] Specifically, a comprehensive analysis is performed to obtain an abnormal risk assessment index for medical behavior. The specific analysis process is as follows: based on the number of overlapping cycles of abnormal behavior, the abnormal risk assessment value of each medical subject's behavior, and the abnormal risk assessment value of the medical institution's behavior, a comprehensive analysis is performed to obtain an abnormal risk assessment index for medical behavior. The abnormal risk assessment index for medical behavior is used to quantitatively assess the degree of risk of fraud and violation of regulations in medical behavior, and to provide a basis for risk warning of medical behavior.

[0081] In a specific embodiment, the numerical expression of the abnormal medical behavior risk assessment index is:

[0082] In the formula, represents the risk assessment index of abnormal medical behavior, represents the risk assessment value of abnormal behavior of the rth medical object, represents the risk assessment value of abnormal behavior of medical institutions, Indicates the number of abnormal behavior coincidence cycles, Indicates the total number of preset monitoring cycles. Indicates the abnormal risk correction factor of medical behavior corresponding to the preset abnormal behavior overlap period, represents the medical behavior abnormal risk correction factor corresponding to the preset medical object behavior abnormal risk assessment value, It represents the medical behavior abnormal risk correction factor corresponding to the preset medical institution behavior abnormal risk assessment value.

[0083] It needs to be explained that when the number of overlapping cycles of abnormal behavior increases, the abnormal risk assessment value of the medical subject behavior increases, and the abnormal risk assessment value of the medical institution behavior increases, the corresponding abnormal medical behavior risk assessment index increases, indicating that the degree of fraud and violation risk in the medical behavior is higher.

[0084] It should be explained that in this embodiment Indicates the abnormal risk correction factor of medical behavior corresponding to the preset abnormal behavior overlap period, represents the medical behavior abnormal risk correction factor corresponding to the preset medical object behavior abnormal risk assessment value, The abnormal medical behavior risk correction factor corresponding to the preset abnormal medical behavior risk assessment value of the medical institution is represented, and the numerical value of the influence of the number of abnormal behavior overlap cycles, the abnormal medical object behavior risk assessment value and the abnormal medical behavior risk assessment value unit value on the abnormal medical behavior risk is respectively represented. When used, it can be directly obtained from the medical transaction database, and its corresponding relationship can be a pre-set mapping relationship. For example, the number of abnormal behavior overlap cycles, the abnormal medical object behavior risk assessment value and the abnormal medical institution behavior risk assessment value are respectively formed with the abnormal medical behavior risk correction factors corresponding to the number of abnormal behavior overlap cycles, the abnormal medical object behavior risk assessment value and the abnormal medical institution behavior risk assessment value preset in the medical transaction database to form a mapping set, and the real-time number of abnormal behavior overlap cycles, the abnormal medical object behavior risk assessment value and the abnormal medical institution behavior risk assessment value are input into the mapping set to obtain the corresponding abnormal medical behavior risk correction factor, wherein the mapping relationship can be one-to-one or a many-to-one relationship. The above correction factors are all extracted from the medical transaction database, and the value range is between 0 and 1.

[0085] It is important to explain that a high risk assessment value for one medical object may be superimposed on the assessment values ​​of other medical objects, thereby increasing the risk assessment value of the entire medical institution. An abnormally high risk assessment value of a medical institution may prompt the institution to take measures to improve management and supervision, which in turn affects the individual behavior and risk assessment values ​​of medical objects. The relationship between these three parameters is not static, but changes dynamically over time and changes in the environment.

[0086] It should be explained that this embodiment can provide a more comprehensive risk assessment system by comprehensively analyzing the abnormal behavior risk of medical subjects, the abnormal behavior risk of medical institutions, and the number of abnormal behavior overlap cycles. Not only single behaviors are taken into account, but also the frequency and scope of the behavior. It can provide a basis for formulating targeted intervention measures. For example, for high-risk individuals, additional training or supervision can be carried out; for high-risk institutions, internal audits and compliance inspections can be strengthened. By assessing risks, medical institutions can allocate resources more effectively to areas with the highest risks, thereby improving regulatory efficiency and cost-effectiveness. Effective fraud detection and risk management can enhance patients' trust in medical institutions and improve the quality of medical services.

[0087] Furthermore, risk warnings and feedback are given to medical behaviors based on the abnormal medical behavior risk assessment index. The specific analysis process is as follows: abnormal medical behavior risk assessment indicators are extracted from the medical transaction database, and the abnormal medical behavior risk assessment index is compared with the abnormal medical behavior risk assessment index. If the abnormal medical behavior risk assessment index is higher than or equal to the abnormal medical behavior risk assessment index, the medical behavior is evaluated as abnormal behavior and a risk warning is given. If the abnormal medical behavior risk assessment index is lower than the abnormal medical behavior risk assessment index, the medical behavior is evaluated as normal behavior and displayed and outputted.

[0088] For example, if a medical behavior is both a low-risk behavior and an abnormal behavior, the monitoring system will issue an early warning signal to notify relevant personnel for further review. The early warning may include email notifications, system pop-ups, text messages, etc. According to the review results, take corresponding intervention measures, such as reminding doctors, adjusting treatment plans, and strengthening monitoring. Relevant personnel will record the risk assessment results, early warnings, review process, and intervention measures. The monitoring system generates reports regularly, and relevant personnel are also required to summarize the abnormal behavior, early warning effects, and improvement suggestions.

[0089] In a specific embodiment, the medical transaction database is used to store relevant parameters in the process of accurately identifying and warning abnormal fraud behaviors in medical insurance general outpatient clinics, including the average frequency of visits of each medical object within a preset monitoring period, the critical drug quantity for repeated prescriptions of the same drug for chronic disease medical objects, the critical drug quantity for repeated prescriptions of the same drug for acute disease medical objects, the critical number of drug changes for chronic disease medical objects, the critical number of drug changes for acute disease medical objects, the critical number of locations where medical object medical insurance accounts are used, and the critical number of total use of medical object medical insurance accounts, as well as the data extracted from the medical transaction database in the above embodiment, can use APIs or Web services to obtain data from different medical information system interfaces. For example, the electronic health record system is a standard system for storing and managing patient medical information in medical institutions. Data can be extracted from these systems, including medical records, diagnoses, treatment plans, drug prescriptions, laboratory test results, etc. The medical insurance system records all transaction data settled through medical insurance, including medical expenses, drug expenses, examination expenses, etc. These data are very important for analyzing medical behavior and cost patterns. The drug management system records the purchase, storage, distribution and use of drugs. Relevant data on drug transactions can be obtained through this system.

[0090] Reference Figure 2 As shown, the second aspect of the present invention provides a medical insurance general outpatient supervision method based on fraud anomaly profiling technology, including: S1. Acquire medical transaction data, the medical transaction data including medical institution behavior data and medical object behavior data.

[0091] S2. Based on the medical subject behavior data, obtain the medical subject behavior abnormal risk assessment value; based on the medical institution behavior data, obtain the medical institution behavior abnormal risk assessment value; and issue an initial warning based on the medical institution behavior abnormal risk assessment value.

[0092] S3. Obtain medical transaction data for each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index through comprehensive analysis based on the medical institution behavior data and medical subject behavior data. Provide risk warning and feedback for medical behavior based on the abnormal medical behavior risk assessment index.

[0093] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. The medical insurance general outpatient supervision system based on fraud anomaly profiling technology is characterized by: include: Medical transaction data collection module, medical behavior analysis module and risk assessment feedback module; A medical transaction data acquisition module, used to acquire medical transaction data, wherein the medical transaction data includes medical institution behavior data and medical subject behavior data; The medical behavior analysis module is used to obtain the abnormal behavior risk assessment value of each medical object based on the medical object behavior data, and to obtain the abnormal behavior risk assessment value of the medical institution based on the medical institution behavior data, and to issue an initial warning based on the abnormal behavior risk assessment value of the medical institution; The risk assessment feedback module is used to obtain medical transaction data of each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index based on the medical institution behavior data and the medical object behavior data. Based on the abnormal medical behavior risk assessment index, risk warnings and feedback are provided for medical behaviors.

2. According to claim 1, the medical insurance general outpatient supervision system based on fraud abnormality profiling technology is characterized by: The processing obtains the risk assessment value of abnormal behavior of each medical object, and the specific process is: The medical subject behavior data includes: the frequency of visits of each medical subject within each preset monitoring period, the amount of the same drug repeatedly prescribed to each medical subject, the number of times each medical subject changed drugs, the number of locations where each medical subject's medical insurance account was used, and the total number of times each medical subject's medical insurance account was used; Extract from the medical transaction database the average frequency of visits of each medical subject within a preset monitoring period, the critical drug quantity for repeated prescriptions of the same drug for medical subjects with chronic diseases, the critical drug quantity for repeated prescriptions of the same drug for medical subjects with acute diseases, the critical number of drug changes for medical subjects with chronic diseases, the critical number of drug changes for medical subjects with acute diseases, the critical number of locations where medical subjects' medical insurance accounts are used, and the critical number of total usages of medical subjects' medical insurance accounts; Based on the medical object behavior data, a comprehensive analysis is performed to obtain an abnormal risk assessment value for each medical object behavior, which is used to quantitatively assess the degree of fraud and violation risk of each medical object behavior, and to provide a basis for assessing the degree of abnormal risk of medical behavior; The numerical expression of the abnormal behavior risk assessment value of each medical object is: In the formula, represents the risk assessment value of abnormal behavior of the rth medical object, e represents a natural constant, represents the frequency of visits of the rth medical subject in the sth preset monitoring period, s represents the number of each preset monitoring period, , t represents the total number of preset monitoring cycles, r represents the number of each medical object, , h represents the total number of medical objects, represents the amount of the same drug repeatedly prescribed to the rth medical subject during the sth preset monitoring period, represents the number of times the rth medical subject changes his / her medication within the sth preset monitoring period, Indicates the number of locations where the medical insurance account of the rth medical object is used in the sth preset monitoring period, Indicates the total number of times the medical insurance account of the rth medical object is used in the sth preset monitoring period, represents the average frequency of visits of the rth medical subject during the preset monitoring period, Indicates the critical amount of drugs for which chronic disease patients are repeatedly prescribed the same drug. Indicates the critical amount of the same drug that is repeatedly prescribed to an acute disease patient. Indicates the critical number of times that chronic disease medical subjects change their medications. Indicates the critical number of times that the acute disease medical object changes the medicine, Indicates the critical number of locations where medical objects’ medical insurance accounts are used. Indicates the critical total usage times of the medical insurance account of the medical object.

3. According to claim 1, the medical insurance general outpatient supervision system based on fraud abnormality profiling technology is characterized by: The processing obtains the risk assessment value of abnormal behavior of the medical institution, and the specific process is: The medical institution behavior data include: the number of specific drug prescriptions of the medical institution, the total number of drug prescriptions of the medical institution, the proportion of drug expenses of the medical institution, the number of modified settlement records of the medical institution, the total number of settlement records of the medical institution and the behavior data of medical staff within each preset monitoring period; The medical staff behavior data include: the amount of medicines prescribed by each medical staff at a time and the amount of examination items prescribed by each medical staff at a time during each preset monitoring period; Extract from the medical transaction database the industry standard drug cost ratio within the preset monitoring period, the average amount of drugs prescribed per time in the same department, and the average number of examination items prescribed per time in the same department; Based on the medical institution behavior data, a comprehensive analysis is conducted to obtain an abnormal risk assessment value for the medical institution behavior. The abnormal risk assessment value for the medical institution behavior is used to quantitatively assess the degree of abnormal fraud risk in the medical institution behavior, and to provide a basis for assessing the degree of abnormal risk in medical behavior.

4. The medical insurance general outpatient supervision system based on fraud abnormality profiling technology according to claim 3 is characterized by: The initial warning is carried out according to the risk assessment value of abnormal behavior of medical institutions. The specific warning process is as follows: Extracting a first threshold value and a second threshold value of the risk assessment of abnormal behavior of a medical institution from a medical transaction database, comparing the risk assessment value of abnormal behavior of a medical institution with the first threshold value and the second threshold value of the risk assessment of abnormal behavior of a medical institution; if the risk assessment value of abnormal behavior of a medical institution is higher than or equal to the first threshold value, the behavior of the medical institution is assessed as a high-risk behavior and an early warning is issued; if the risk assessment value of abnormal behavior of a medical institution is lower than the first threshold value and higher than the second threshold value, the behavior of the medical institution is assessed as a low-risk behavior and is continuously monitored; if the risk assessment value of abnormal behavior of a medical institution is lower than or equal to the second threshold value, the behavior of the medical institution is assessed as a risk-free behavior; Conduct secondary analysis on low-risk behaviors and issue early warnings based on the analysis results.

5. According to claim 1, the medical insurance general outpatient supervision system based on fraud abnormality profiling technology is characterized by: The screening obtains the number of abnormal behavior overlap cycles, and the specific screening process is: Obtaining medical transaction data of each historical monitoring period, and processing to obtain the abnormal behavior risk assessment value of the medical institution in each historical monitoring period and the abnormal behavior risk assessment value of each medical subject in each historical monitoring period; According to the risk assessment value of abnormal behavior of each medical object in each historical monitoring period, the number of abnormal medical objects in each historical monitoring period is obtained; Extracting from the medical transaction database the second threshold for the risk assessment of abnormal medical institution behavior and the critical value for the number of abnormal medical subjects; The abnormal risk assessment value of medical institution behavior and the number of abnormal medical subjects in each historical monitoring period are compared with the second threshold of abnormal risk assessment of medical institution behavior and the critical value of the number of abnormal medical subjects, respectively. If the abnormal risk assessment value of medical institution behavior in a certain monitoring period is higher than the second threshold of abnormal risk assessment of medical institution behavior and the number of abnormal medical subjects is greater than the critical value of the number of abnormal medical subjects, the monitoring period is marked as a coincidence period; Count the number of coincidence cycles.

6. The medical insurance general outpatient supervision system based on fraud abnormality profiling technology according to claim 5 is characterized by: The processing obtains the number of abnormal medical objects in each historical monitoring period, and the specific process is: Compare the abnormal behavior risk assessment value of each medical object in each historical monitoring period with the abnormal behavior risk assessment threshold of the medical object; if the abnormal behavior risk assessment value of a medical object in a historical monitoring period is greater than or equal to the abnormal behavior risk assessment threshold of the medical object, mark the medical object as an abnormal medical object; Count the number of abnormal medical objects in each historical monitoring period.

7. The medical insurance general outpatient supervision system based on fraud abnormality profiling technology according to claim 5 is characterized by: The comprehensive analysis obtains the risk assessment index of abnormal medical behavior, and the specific analysis process is as follows: Based on the number of abnormal behavior overlapping cycles, the abnormal behavior risk assessment value of each medical subject and the abnormal behavior risk assessment value of the medical institution, a comprehensive analysis is conducted to obtain the medical behavior abnormal risk assessment index, which is used to quantitatively assess the degree of fraud and violation risks in medical behavior, and provide a basis for risk warning of medical behavior.

8. The medical insurance general outpatient supervision system based on fraud abnormality profiling technology according to claim 7 is characterized by: The specific analysis process of providing risk warning and feedback for medical behavior based on the abnormal risk assessment index of medical behavior is as follows: The abnormal medical behavior risk assessment index is extracted from the medical transaction database, and the abnormal medical behavior risk assessment index is compared with the abnormal medical behavior risk assessment index. If the abnormal medical behavior risk assessment index is higher than or equal to the abnormal medical behavior risk assessment index, the medical behavior is assessed as abnormal behavior and a risk warning is issued. If the abnormal medical behavior risk assessment index is lower than the abnormal medical behavior risk assessment index, the medical behavior is assessed as normal behavior and displayed and output.

9. The medical insurance general outpatient supervision system based on fraud abnormality profiling technology according to claim 3 is characterized by: The specific numerical expression of the abnormal behavior risk assessment value of the medical institution is: In the formula, represents the risk assessment value of abnormal behavior of medical institutions, represents the number of times a specific drug is prescribed by a medical institution within the sth preset monitoring period, s represents the number of each preset monitoring period, , t represents the total number of preset monitoring cycles, It represents the total number of drug prescriptions issued by the medical institution during the sth preset monitoring period. represents the proportion of drug expenses of medical institutions in the sth preset monitoring period, Indicates the number of times the medical institution modified its settlement records within the sth preset monitoring period. Indicates the total number of settlement records of the medical institution in the sth preset monitoring period, represents the proportion of industry standard drug costs within the preset monitoring period, n represents the number of each medical staff, , m represents the total number of medical staff, It indicates the amount of medicines prescribed by the nth medical staff in the sth preset monitoring period. It indicates the number of examination items prescribed by the nth medical staff in the sth preset monitoring period. It indicates the average amount of drugs prescribed in a single session in the same department during the preset monitoring period. It indicates the average number of inspection items issued at one time by the same department during the preset monitoring period.

10. A method for applying the medical insurance general outpatient supervision system based on fraud abnormality profiling technology as described in any one of claims 1 to 9, characterized in that: include: S1. Acquire medical transaction data, wherein the medical transaction data includes medical institution behavior data and medical subject behavior data; S2. Based on the medical subject behavior data, the abnormal behavior risk assessment value of the medical subject is obtained, and based on the medical institution behavior data, the abnormal behavior risk assessment value of the medical institution is obtained, and the initial warning is issued based on the abnormal behavior risk assessment value of the medical institution; S3. Obtain medical transaction data for each historical monitoring period, screen out the number of overlapping periods of abnormal behavior, and obtain the abnormal medical behavior risk assessment index through comprehensive analysis based on the medical institution behavior data and medical subject behavior data. Provide risk warning and feedback for medical behavior based on the abnormal medical behavior risk assessment index.

Images