WO2020119384A1 - 基于大数据分析的医保异常检测方法、装置、设备和介质 - Google Patents

基于大数据分析的医保异常检测方法、装置、设备和介质 Download PDF

Info

Publication number
WO2020119384A1
WO2020119384A1 PCT/CN2019/118831 CN2019118831W WO2020119384A1 WO 2020119384 A1 WO2020119384 A1 WO 2020119384A1 CN 2019118831 W CN2019118831 W CN 2019118831W WO 2020119384 A1 WO2020119384 A1 WO 2020119384A1
Authority
WO
WIPO (PCT)
Prior art keywords
medical insurance
drug
data
personal medical
target
Prior art date
Application number
PCT/CN2019/118831
Other languages
English (en)
French (fr)
Inventor
李云峰
Original Assignee
平安医疗健康管理股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安医疗健康管理股份有限公司 filed Critical 平安医疗健康管理股份有限公司
Publication of WO2020119384A1 publication Critical patent/WO2020119384A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance

Definitions

  • the present application relates to the field of information technology, and in particular to medical insurance abnormality detection methods, devices, equipment, and media based on big data analysis.
  • the main purpose of the present application is to provide a medical insurance abnormality detection method, device, equipment and medium based on big data analysis, aiming to achieve effective medical insurance abnormality detection based on medical insurance data analysis.
  • the present application provides a medical insurance abnormality detection method based on big data analysis.
  • the medical insurance abnormality detection method based on big data analysis includes the following steps:
  • the present application also provides a medical insurance abnormality detection device based on big data analysis.
  • the medical insurance abnormality detection device based on big data analysis includes:
  • the request receiving module is used to receive a medical insurance abnormality detection request and obtain target drugs and drug consumption information of the target drugs;
  • the data processing module is used to process the drug consumption information according to preset data perspective rules to obtain personal medical insurance data;
  • the abnormality judgment module is used to judge whether there is an abnormality in the personal medical insurance data according to the medication time and dosage in the personal medical insurance data;
  • the output prompt module is used for outputting prompt information of abnormal medical insurance if the personal medical insurance data is abnormal.
  • the present application also provides a medical insurance abnormality detection device based on big data analysis
  • the medical insurance abnormality detection device based on big data analysis includes: a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, wherein:
  • this application also provides a computer storage medium
  • Computer-readable instructions are stored on the computer storage medium, and when the computer-readable instructions are executed by the processor, the steps of the medical insurance abnormality detection method based on big data analysis as described above are implemented.
  • the server receives the medical insurance abnormality detection request and obtains the target drug and the drug consumption information of the target drug; according to the preset data perspective rules Process the drug consumption information to obtain personal medical insurance data; determine whether the personal medical insurance data is abnormal according to the medication time and dosage in the personal medical insurance data; if the personal medical insurance data is abnormal, output a medical insurance abnormality prompt information.
  • the server obtains personal medical insurance data corresponding to each user ID by acquiring the consumption data of the target drug and taking the drug consumption data of the target drug as the dimension of the user ID, and then the server uses the drug of the target drug in the personal medical insurance data Time and dosage of medicines are used to detect abnormalities of medical insurance and achieve effective detection of abnormalities of medical insurance.
  • FIG. 1 is a schematic structural diagram of an apparatus for a hardware operating environment involved in an embodiment of this application;
  • FIG. 2 is a schematic flowchart of a first embodiment of a medical insurance abnormality detection method based on big data analysis
  • FIG. 3 is a schematic flowchart of a third embodiment of a medical insurance abnormality detection method based on big data analysis
  • FIG. 4 is a schematic diagram of functional modules of an embodiment of a medical insurance abnormality detection device based on big data analysis of the present application.
  • FIG. 1 is a server of a hardware operating environment involved in an embodiment of the present application (also called a medical insurance abnormality detection device based on big data analysis, where the medical insurance abnormality detection device based on big data analysis may be composed of separate
  • the structure of the medical insurance abnormality detection device based on big data analysis may also be formed by combining other devices with the medical insurance abnormality detection device based on big data analysis).
  • the server in the embodiment of the present application refers to a computer that manages resources and provides services to users, and is generally divided into a file server, a database server, and an application-readable instruction server.
  • a computer or computer system running the above software is also called a server.
  • the server may include a processor 1001, such as a central processor (Central Processing Unit, CPU), network interface 1004, user interface 1003, memory 1005, communication bus 1002, chipset, disk system, network and other hardware.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 may include a display (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as wireless fidelity WIreless-FIdelity, WIFI interface).
  • the memory 1005 may be a high-speed random access memory (random access memory, RAM), can also be a stable memory (non-volatile memory), such as disk storage.
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • the computer software product is stored in a storage medium (storage medium: also called computer storage medium, computer medium, readable medium, readable storage medium, computer readable storage medium, or directly called medium, etc., such as RAM , Disk, CD), including several instructions to enable a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to perform the method described in each embodiment of this application, as a computer
  • the memory 1005 of the storage medium may include an operating system, a network communication module, a user interface module, and computer-readable instructions.
  • the network interface 1004 is mainly used to connect to the back-end database and perform data communication with the back-end database;
  • the user interface 1003 is mainly used to connect to the client and perform data communication with the client;
  • the processor 1001 can be used to Invoke the computer-readable instructions stored in the memory 1005, and execute the steps in the medical insurance abnormality detection method based on big data analysis provided by the following embodiments of the present application.
  • the embodiments of the present application provide a medical insurance abnormality detection method based on big data analysis.
  • FIG. 2 a first embodiment of a medical insurance abnormality detection method based on big data analysis of the present application.
  • the medical insurance abnormality detection method based on big data analysis is applied to the server shown in FIG. 1, and the method includes:
  • Step S10 Receive a medical insurance abnormality detection request, and acquire target drugs and drug consumption information of the target drugs.
  • the server receives the medical insurance abnormality detection request.
  • the medical insurance abnormality detection request in this embodiment can be triggered in different forms. For example, the user clicks the button of “medical insurance abnormality detection” on the terminal display screen to manually trigger the medical insurance abnormality detection request.
  • the terminal sends the medical insurance abnormality detection request to the server; or the user presets the trigger condition of the medical insurance abnormality detection request. When the preset triggering condition is met, the server automatically triggers the medical insurance abnormality detection request.
  • the server When the server receives the medical insurance monitoring request, the server Obtain the target drug associated with the medical insurance abnormality detection and the drug consumption information of the target drug, where the drug consumption information includes: the drug purchaser identification (also called the patient identification or the user identification, for example, the user's ID number, user medical insurance number , User name, etc.), drug purchase time, drug identification (eg, drug name), drug dosage, drug purchase time, drug use, drug sales terminal information, drug manufacturer, etc.
  • the drug purchaser identification also called the patient identification or the user identification, for example, the user's ID number, user medical insurance number , User name, etc.
  • drug purchase time drug identification (eg, drug name)
  • drug identification eg, drug name
  • drug dosage drug purchase time
  • drug use drug sales terminal information
  • drug manufacturer etc.
  • the medical insurance abnormality detection in this embodiment is for the detection of the use of the specified target medicine.
  • the server selects the preset medical insurance database (where the preset medical insurance database refers to the pre-set The data collection of data, the preset medical insurance database contains the medical insurance information of different users. Taking the medical insurance data of user A as an example, the preset medical insurance database stores the visit time, medical record information, medical institution, and the issued Obtain the medicine consumption information related to the target medicine from the prescription information (the prescription information contains medicine consumption information), etc.
  • step S20 the drug consumption information is processed according to preset data perspective rules to obtain personal medical insurance data.
  • the server performs a pivot analysis on the acquired drug consumption information to obtain personal medical insurance data corresponding to the user identification.
  • a method for implementing the drug consumption information for pivoting is provided, specifically including:
  • Step a Obtain the preset pivot rules and the classification labels in the preset pivot rules, where the classification labels include row labels and column labels, and the row labels are user identifiers;
  • step b the drug consumption information is classified and summarized according to the row label and the column label to obtain personal medical insurance data corresponding to each user ID.
  • the server obtains the preset pivot rules, where the preset pivot rules refer to the preset classification label (also called perspective dimension) rules, and the classification labels in the pivot rules can be set according to specific scenarios.
  • the classification labels in the preset pivot rules include row labels and column labels.
  • the row labels are user identifiers
  • the column labels are time and dose.
  • the server classifies and summarizes the drug consumption information according to the classification labels to obtain each user.
  • Step S30 Determine whether the personal medical insurance data is abnormal according to the medication time and dosage in the personal medical insurance data.
  • the server obtains the medication time and dose in the personal medical insurance data to determine whether the personal healthcare data is abnormal based on the medication time and dosage in the personal medical insurance data, specifically, including:
  • Step S31 Query the preset medicine database to obtain the medicine usage instructions of the target medicine.
  • the server queries the preset medicine database (the preset medicine database refers to the preset settings for storing the information of each medicine (the medicine information includes but is not limited to: medicine indications, medicine instructions, medicine formula, medicine duration, medicine origin, Database of common names, product names, usage and dosage, adverse reactions, contraindications, precautions, etc.), the server obtains the instructions for the use of the target drug.
  • the preset medicine database refers to the preset settings for storing the information of each medicine (the medicine information includes but is not limited to: medicine indications, medicine instructions, medicine formula, medicine duration, medicine origin, Database of common names, product names, usage and dosage, adverse reactions, contraindications, precautions, etc.), the server obtains the instructions for the use of the target drug.
  • Step S32 combining the usage and dosage in the instructions for use of the drug with the medication time in the personal medical insurance data to calculate the theoretical drug dosage of the target drug;
  • the server combines the usage and dosage in the drug instructions with the medication time in the personal medical insurance data to calculate the theoretical dosage of the target drug; for example, the usage in the drug instructions for the dosage of mycophenolate mofetil
  • the dosage includes: the maximum reasonable daily dosage of 2g/person, the medication time in the personal medical insurance data is 255 days, and the server calculates the theoretical dosage of the target drug as 510g based on the medication time and usage.
  • Step S33 comparing the medical dosage in the personal medical insurance data with the theoretical dosage of the target drug; if the medical dosage matches the theoretical dosage, the personal medical insurance data is normal; if the If the dose of medication does not match the theoretical dose, the personal medical insurance data is abnormal.
  • the server compares the dosage in the personal medical insurance data with the theoretical dosage of the target drug to obtain a comparison result, and the server determines whether the personal medical insurance data is abnormal according to the comparison result.
  • the theoretical dosage is matched, that is, the server determines that the difference between the dosage and the theoretical dosage is within the range allowed by the error, the server determines that the personal medical insurance data is normal; if the dosage does not match the theoretical dosage That is, if the server determines that the difference between the dose of medication and the theoretical dose exceeds the allowable range of error, the server determines that the personal medical insurance data is abnormal.
  • computer data analysis is used to determine whether personal medical insurance data is abnormal, and automatic analysis and detection of medical insurance data is implemented.
  • Step S40 if there is an abnormality in the personal medical insurance data, a prompt message for medical insurance abnormality is output.
  • the server When the server determines that the personal medical insurance data is abnormal, the server outputs a medical insurance abnormal prompt message, where the implementation method of the medical insurance abnormal prompt message is not specifically limited, for example, a voice prompts the medical insurance abnormal, so that the user can understand the abnormal situation of the personal data.
  • the server obtains the personal medical insurance data corresponding to each user ID by acquiring the consumption data of the target drug and taking the user identification as the dimension of the drug consumption data of the target drug, and then the server according to the target drug in the personal medical insurance data The medication time and dosage are used to detect abnormal medical insurance and achieve effective detection of abnormal medical insurance.
  • This embodiment is a refinement of step S10 in the first embodiment.
  • the difference between this embodiment and the first embodiment of this application is that the target drug in the first embodiment is a drug, and the target drug in this embodiment is Multiple medicines of the same type.
  • the determination of the abnormality of the medical insurance in this application is based on the dosage of the personal medical insurance data.
  • the server determines that the personal medical insurance data is abnormal, but if the disease A can be cured by using the drug 1, It can be cured by using drug 2, that is, drug 1 and drug 2 have the same or similar efficacy (also called indication information).
  • drug 2 is an alternative drug for drug 1
  • the patient goes to the hospital to prescribe After a reasonable dose of medicine 1, at the same time, the patient went to the second hospital to prescribe a reasonable dose of medicine 2.
  • the result will be output: the test result of normal personal medical insurance data, but this is not the case. Therefore, a second embodiment of the present application is proposed.
  • the medical insurance abnormality detection method based on big data analysis includes:
  • Step S11 Receive the medical insurance abnormality detection request, and obtain the medicine to be tested in the medical insurance abnormality detection request and the indication information of the medicine to be tested.
  • the user enters the drug identifier and triggers the medical insurance abnormality detection request based on the drug identifier.
  • the server receives the medical insurance abnormality detection request triggered by the user based on the drug identifier, the server obtains the drug identifier included in the medical insurance abnormality detection request.
  • the medicine corresponding to the medicine identifier is regarded as the medicine to be tested, and the server obtains indication information of the medicine to be monitored (the indication information refers to the scope and standard of the medicine suitable for use), and the server determines whether there is a Alternative medicines with the same or similar indication information.
  • Step S12 Query a preset medicine database to determine whether there is a substitute medicine matching the indication information, where the substitute medicine refers to a medicine other than the medicine to be tested.
  • the server queries the preset drug database, where the preset drug database refers to a preset database containing a variety of drug information.
  • the drug information includes but is not limited to: drug indications, drug instructions, drug formulations, drug deadlines, drug origin , Common name, product name, usage, adverse reactions, contraindications, precautions, etc.
  • the server compares the indication information of the drug to be monitored with the indication information of each drug in the preset drug database, and the server determines the preset drug Whether there are other drugs in the database that are the same or similar to the indication information of the drug to be monitored. If there are other drugs in the preset drug database that are the same or similar to the indication information of the drug to be monitored, the server regards the drug as the drug to be monitored. Alternative medicine.
  • step S13 if there is no substitute medicine matching the indication information, the medicine to be tested is taken as the target medicine, and the medicine consumption information of the target medicine is obtained.
  • the server uses the medicine to be tested as the target medicine, and obtains the medicine consumption information of the target medicine, and executes step S20 in the first embodiment: Process the drug consumption information according to preset data perspective rules to obtain personal medical insurance data.
  • step S14 if there is a substitute drug matching the indication information, the drug to be tested and the substitute drug are used as the target drug, and the drug consumption information of the target drug is obtained.
  • the target drug and the substitute drug are used as the target drug, and the drug consumption information of the target drug is obtained.
  • the alternative medicine in the embodiment may include one or more. That is, in this embodiment, drugs with the same or similar indication information are considered as target drugs, which effectively avoids the problem of inaccurate test results caused by repeated detection of different drugs with the same indication information, making medical insurance based on big data analysis The data of anomaly detection is more comprehensive and more accurate.
  • a third embodiment of the medical insurance abnormality detection method based on big data analysis of the present application is proposed on the basis of the foregoing embodiment.
  • This embodiment is a step after step S20 in the first embodiment.
  • Medical insurance anomaly detection methods based on big data analysis include:
  • Step S50 Query a preset medical insurance database to obtain a medical record corresponding to the personal medical insurance data.
  • the server queries the preset medical insurance database, wherein the preset medical insurance database in this embodiment is the same as the preset medical insurance database in the first embodiment, and is not described in detail in this embodiment.
  • the server obtains the user ID in the personal medical insurance data and obtains all
  • the medical record corresponding to the user identification (the medical record may be an electronic medical record), the server uses the personal medical insurance data and the medical record with the same user identification as the medical record corresponding to the personal medical insurance data.
  • Step S60 comparing the disease information in the medical record with the indication information of the target drug to determine whether the disease information matches the indication information
  • the server compares the disease information in the medical record with the indication information of the target drug, that is, the server obtains the comparison result by comparing the disease data in the medical record with the indication information of the target drug According to the comparison results, determine whether the target drug is symptomatic.
  • Step S70 if the disease information and the indication information do not match, output a prompt message of abnormal medication
  • the server determines that the target drug is not properly used, and the server outputs a medication abnormality prompt message.
  • step S20 The step of determining whether there is an abnormality in the personal medical insurance data according to the medication time and dosage in the personal medical insurance data.
  • the server before performing the step of determining whether there is an abnormality in the personal medical insurance data according to the medication time and dosage in the personal medical insurance data in the first embodiment, first obtain the medical record corresponding to the personal medical insurance data, and By comparing the disease information in the medical record with the indication information of the target drug, it is determined whether the target drug is used symptomatically. After the server determines that the target drug is used incorrectly, the server can directly output the drug abnormality prompt information. After determining the symptomatic use of the target drug, the server judges the amount of the target drug, which makes the treatment of medical insurance quantity more efficient.
  • Step S80 if the personal medical insurance data is normal, add a reimbursable label to the personal medical insurance data;
  • the server adds a reimbursable label to the personal medical insurance data, that is, after determining that the personal medical insurance data is normal in this embodiment, the server adds the reimbursable label to the personal medical insurance data Reduce the reimbursement process. specifically:
  • Step S90 When receiving the medical insurance reimbursement request, obtain the user identification in the medical insurance reimbursement request;
  • the server When the server receives the medical insurance reimbursement request, in this embodiment, when the medical insurance reimbursement request is received, it can be triggered in different forms. For example, the user clicks the button of "Medical Insurance Reimbursement" on the terminal display screen to manually trigger the medical insurance reimbursement request Then, the terminal sends the medical insurance reimbursement request to the server; or is triggered by other means, after the server receives the medical insurance reimbursement request, the server obtains the user identification in the medical insurance reimbursement request.
  • Step S100 query a preset medical insurance database, obtain personal medical insurance data corresponding to the user identification, and determine whether there is a reimbursable label in the personal medical insurance data;
  • the server queries the preset medical insurance database (where the preset medical insurance database in this embodiment is the same as the preset medical insurance database in the first embodiment, which is not repeated in this embodiment), and the server obtains personal medical insurance data corresponding to the user ID And determine whether there is a reimbursable label in the personal medical insurance data.
  • Step S110 if there is a reimbursable label in the personal medical insurance data, multiply the drug cost in the personal medical insurance data and the preset reimbursement ratio of the target drug to obtain the reimbursement amount of the target drug, and Reimburse according to the stated reimbursement amount.
  • the server reimburses the drug cost in the personal medical insurance data and the preset reimbursement of the target drug Multiply the ratio to obtain the reimbursement amount of the target drug, and reimburse the reimbursement amount according to the reimbursement amount.
  • the preset reimbursement ratio refers to the pre-set reimbursement ratio for each type of medicine. For example, the preset reimbursement ratio is set to 80%.
  • Step S120 if there is no reimbursable label in the personal medical insurance data, obtain the medical insurance reimbursement review material corresponding to the user ID; determine the reasonable reimbursement amount of the target drug according to the medical insurance reimbursement audit material, and press Reasonable reimbursement amount for reimbursement.
  • the server needs to perform normal medical insurance reimbursement, the server obtains medical insurance reimbursement audit materials corresponding to the user ID, and the server determines whether the medical insurance reimbursement audit materials meet the preset audit standards (The preset audit standard can be set according to the specific scenario), if the server determines that the medical insurance reimbursement audit material does not meet the preset audit standard, the medical insurance reimbursement request is rejected, and the server determines that the medical insurance reimbursement audit material meets the preset audit standard, that is, due to personal medical insurance data There is an anomaly in the server, the server determines that the user has excess reimbursement, the server needs to determine a reasonable amount of reimbursement, specifically:
  • the server After the server determines that the medical insurance reimbursement audit materials meet the preset audit standards, the server obtains the medical record information in the medical insurance reimbursement audit materials, combines the usage and usage in the drug use instructions with the medication time in the personal medical insurance data, and calculates Obtain the theoretical drug dosage of the target drug; where the server determines the theoretical drug dosage of the target drug can be combined with the first embodiment, which will not be repeated in this embodiment.
  • the server uses the theoretical drug dosage as The reasonable dosage of the target drug, the server obtains the drug cost corresponding to the theoretical drug amount, the server multiplies the drug cost and the target drug's preset reimbursement ratio to obtain the target drug's reimbursement amount, and press The reimbursement amount is reimbursed.
  • the medical insurance reimbursement process is determined according to the medical insurance abnormality detection detection result, which makes the medical insurance reimbursement faster.
  • an embodiment of the present application also provides a medical insurance abnormality detection device based on big data analysis.
  • the medical insurance abnormality detection device based on big data analysis includes:
  • the request receiving module 10 is used to receive a medical insurance abnormality detection request and obtain target drugs and drug consumption information of the target drugs;
  • the data processing module 20 is configured to process the medicine consumption information according to preset data perspective rules to obtain personal medical insurance data;
  • the abnormality determination module 30 is configured to determine whether there is an abnormality in the personal medical insurance data according to the medication time and dosage in the personal medical insurance data;
  • the output prompt module 40 is configured to output prompt information of abnormal medical insurance if the personal medical insurance data is abnormal.
  • the request receiving module 10 includes:
  • a request receiving unit configured to receive a medical insurance abnormality detection request, and obtain the drug to be tested in the medical insurance abnormality detection request, and indication information of the drug to be tested;
  • the query unit is used to query a preset drug database to determine whether there is a substitute drug matching the indication information, wherein the substitute drug refers to a drug other than the drug to be tested;
  • the first obtaining unit is configured to use the drug to be tested as a target drug and obtain drug consumption information of the target drug if there is no substitute drug matching the indication information;
  • the second obtaining unit is configured to use the drug to be tested and the substitute drug as target drugs if there are substitute drugs matching the indication information, and obtain drug consumption information of the target drugs.
  • the data processing module 20 includes:
  • An obtaining unit configured to obtain preset pivot rules and classification tags in the preset pivot rules, wherein the classification tags include row tags and column tags, and the row tags are user identifiers;
  • a sorting and summarizing unit is used for sorting and summarizing the medicine consumption information according to the row label and the column label to obtain personal medical insurance data corresponding to each user ID.
  • the medical insurance abnormality detection device based on big data analysis includes:
  • the medical record query module is used to query a preset medical insurance database to obtain medical records corresponding to the personal medical insurance data;
  • the comparison judgment module is used to compare the disease information in the medical record with the indication information of the target drug to determine whether the disease information matches the indication information;
  • the abnormality prompt module is used for outputting abnormality prompt information of medication if the disease information does not match the indication information;
  • the abnormality determination module executes the step of determining whether the personal medical insurance data is abnormal according to the medication time and dosage in the personal medical insurance data.
  • the abnormality determination module 30 includes:
  • the query obtaining unit is used to query a preset drug database to obtain the drug use instructions of the target drug
  • the theoretical calculation unit is used to combine the usage and dosage in the instructions for use of the drug with the medication time in the personal medical insurance data to calculate the theoretical dose of the target drug;
  • a comparison unit used to compare the dosage of medicine in the personal medical insurance data with the theoretical dosage of the target medicine
  • the first determination unit is configured to: if the medication dose matches the theoretical medication dose, the personal medical insurance data is normal;
  • the second determination unit is used to make the personal medical insurance data abnormal if the medication dose does not match the theoretical medication dose.
  • the medical insurance abnormality detection device based on big data analysis includes:
  • a label adding module which is used to add a reimbursable label to the personal medical insurance data if the personal medical insurance data is normal;
  • the reimbursement receiving module is used to obtain the user identification in the medical insurance reimbursement request when receiving the medical insurance reimbursement request;
  • the label judgment module is used to query a preset medical insurance database, obtain personal medical insurance data corresponding to the user identification, and determine whether there is a reimbursable label in the personal medical insurance data;
  • the first reimbursement module is used to multiply the drug cost in the personal medical insurance data and the preset reimbursement ratio of the target drug if the reimbursable label exists in the personal medical insurance data to obtain the target drug’s Reimbursement amount, and reimbursement according to said reimbursement amount;
  • a material acquisition module used to obtain medical insurance reimbursement review materials corresponding to the user identification if there is no reimbursable label in the personal medical insurance data
  • the second reimbursement module is used to determine a reasonable reimbursement amount of the target drug based on the medical insurance reimbursement review materials, and reimbursement according to the reasonable reimbursement amount.
  • the second reimbursement module includes:
  • the medication determination unit is used to obtain the medical record information in the medical insurance reimbursement review materials, combine the usage and dosage in the drug use instructions with the medication time in the personal medical insurance data, and calculate the theoretical medication dosage of the target drug ;
  • the quota determination unit is used to obtain the drug cost corresponding to the theoretical drug amount, multiply the drug cost and the target reimbursement ratio of the target drug to obtain the reimbursement amount of the target drug, and according to the reimbursement The amount is reimbursed.
  • embodiments of the present application also provide a computer storage medium.
  • Computer-readable instructions are stored on the computer storage medium, and when the computer-readable instructions are executed by the processor, the operations in the medical insurance abnormality detection method based on big data analysis provided by the foregoing embodiments are implemented.
  • the storage medium may be a non-volatile storage medium.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

一种基于大数据分析的医保异常检测方法，包括以下步骤：接收医保异常检测请求，获取目标药品及目标药品的药品消费信息（S10）；按预设数据透视规则处理药品消费信息，得到个人医保数据（S20）；根据个人医保数据中的用药时间和用药剂量，判断个人医保数据是否存在异常（S30）；若个人医保数据存在异常，则输出医保异常提示信息（S40）。还公开了一种基于大数据分析的医保异常检测装置、设备和介质。基于大数据分析，有效地实现了医保异常的检测。

Description

基于大数据分析的医保异常检测方法、装置、设备和介质
本申请要求于2018年12月13日提交中国专利局、申请号为201811529378.5、发明名称为“基于大数据分析的医保异常检测方法、装置、设备和介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及信息技术领域，尤其涉及基于大数据分析的医保异常检测方法、装置、设备和介质。
背景技术
随着社会医疗服务的普及，越来越多的人使用医保享受一系列相关的医疗服务。
虽然社会医保制度日渐完善，但是近年来却出现了许多医保诈骗事件，严重损害了公众利益。例如，医疗诈骗者为病患，病患在患病期间去不同的医疗机构进行重复看诊得到多于合理剂量的药品，并将多于的药品进行倒卖赚取差价，这样的异常行为破坏了医保使用规范，针对上述现象如何有效地进行医保异常检测成为了当前亟待解决的技术问题。
发明内容
本申请的主要目的在于提供一种基于大数据分析的医保异常检测方法、装置、设备和介质，旨在实现基于医保数据分析有效地医保异常检测。
为实现上述目的，本申请提供基于大数据分析的医保异常检测方法，所述基于大数据分析的医保异常检测方法包括以下步骤：
接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
若所述个人医保数据存在异常，则输出医保异常提示信息。
此外，为实现上述目的，本申请还提供一种基于大数据分析的医保异常检测装置，所述基于大数据分析的医保异常检测装置包括：
请求接收模块，用于接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
数据处理模块，用于按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
异常判断模块，用于根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
输出提示模块，用于若所述个人医保数据存在异常，则输出医保异常提示信息。
此外，为实现上述目的，本申请还提供一种基于大数据分析的医保异常检测设备；
所述基于大数据分析的医保异常检测设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，其中：
所述计算机可读指令被所述处理器执行时实现如上所述的基于大数据分析的医保异常检测方法的步骤。
此外，为实现上述目的，本申请还提供计算机存储介质；
所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现如上述的基于大数据分析的医保异常检测方法的步骤。
本申请实施例提出的一种基于大数据分析的医保异常检测方法、装置、设备和介质，服务器接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；按预设数据透视规则处理所述药品消费信息，得到个人医保数据；根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；若所述个人医保数据存在异常，则输出医保异常提示信息。本申请中服务器通过获取目标药品的消费数据，并将目标药品的药品消费数据以用户标识为维度进行数据透视，得到各用户标识对应的个人医保数据，然后服务器根据个人医保数据中目标药品的用药时间和用药剂量，进行医保异常的检测，实现了医保异常有效检测。
附图说明
图1为本申请实施例方案涉及的硬件运行环境的装置结构示意图；
图2为本申请基于大数据分析的医保异常检测方法第一实施例的流程示意图；
图3为本申请基于大数据分析的医保异常检测方法第三实施例的流程示意图
图4为本申请基于大数据分析的医保异常检测装置一实施例的功能模块示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的硬件运行环境的服务器（又叫基于大数据分析的医保异常检测设备，其中，基于大数据分析的医保异常检测设备可以是由单独的基于大数据分析的医保异常检测装置构成，也可以是由其他装置与基于大数据分析的医保异常检测装置组合形成）结构示意图。
本申请实施例服务器指一个管理资源并为用户提供服务的计算机，通常分为文件服务器、数据库服务器和应用可读指令服务器。运行以上软件的计算机或计算机系统也被称为服务器。相对于普通PC(personal computer)个人计算机来说，服务器在稳定性、安全性、性能等方面都要求较高；如图1所示，该服务器可以包括：处理器1001，例如中央处理器（Central Processing Unit，CPU），网络接口1004，用户接口1003，存储器1005，通信总线1002、芯片组、磁盘系统、网络等硬件等。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如无线保真WIreless-FIdelity，WIFI接口）。存储器1005可以是高速随机存取存储器（random access memory，RAM），也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
如图1所示，该计算机软件产品存储在一个存储介质（存储介质：又叫计算机存储介质、计算机介质、可读介质、可读存储介质、计算机可读存储介质或者直接叫介质等，如RAM、磁碟、光盘）中，包括若干指令用以使得一台终端设备（可以是手机，计算机，服务器，空调器，或者网络设备等）执行本申请各个实施例所述的方法，作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及计算机可读指令。
在图1所示的服务器中，网络接口1004主要用于连接后台数据库，与后台数据库进行数据通信；用户接口1003主要用于连接客户端，与客户端进行数据通信；而处理器1001可以用于调用存储器1005中存储的计算机可读指令，并执行本申请以下实施例提供的基于大数据分析的医保异常检测方法中的步骤。
本申请实施例提供一种基于大数据分析的医保异常检测方法。
参照图2，本申请基于大数据分析的医保异常检测方法的第一实施例，所述基于大数据分析的医保异常检测方法应用于如图1所示的服务器，该方法包括：
步骤S10，接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息。
服务器接收医保异常检测请求，本实施例中的医保异常检测请求，可以通过不同的形式触发，例如，用户在终端显示屏上点击“医保异常检测”的按键，手动触发医保异常检测请求，然后，终端将医保异常检测请求发送至服务器；或者用户预设了医保异常检测请求的触发条件，在满足预设的触发条件时，服务器自动触发医保异常检测请求，在服务器接收到医保监测请求时，服务器获取医保异常检测关联的目标药品，及所述目标药品的药品消费信息，其中，药品消费信息包括：药品购买者标识（又叫患者标识或者用户标识，例如，用户的身份证号码、用户医保编号、用户姓名等）、药品的购买时间、药品标识（如，药品名称）、药品剂量、药品购买时间、药品用途、药品销售终端信息和药品厂家等。
即，本实施例中的医保异常检测是针对指定目标药品的使用检测，在服务器接收医保异常检测请求时，服务器从预设医保数据库（其中，预设医保数据库是指预先设置的用于存放医保数据的数据集合，预设医保数据库中包含有不同用户的医保信息，以用户A的医保数据为例，预设医保数据库中保存有用户A的看诊时间、病历信息、看诊机构、开具的处方信息（处方信息中包含有药品消费信息）等等）中获取目标药品相关的药品消费信息。
步骤S20，按预设数据透视规则处理所述药品消费信息，得到个人医保数据。
服务器将获取的药品消费信息进行数据透视分析，得到用户标识对应的个人医保数据，本实施例中给出了一种药品消费信息进行数据透视的实现方式，具体地包括：
步骤a，获取预设数据透视规则及所述预设数据透视规则中分类标签，其中，所述分类标签包括行标签和列标签，所述行标签为用户标识；
步骤b，将所述药品消费信息按所述行标签和所述列标签进行分类汇总，得到各所述用户标识对应的个人医保数据。
即，服务器获取预设的数据透视规则，其中，预设数据透视规则是指预先设置的分类标签（又叫透视维度）规则，数据透视规则中的分类标签可以根据具体的场景设置，本实施例预设数据透视规则中分类标签包括行标签和列标签，例如，本实施例中行标签为用户标识，列标签为时间和剂量，服务器将药品消费信息按分类标签进行分类汇总，得到各所述用户标识对应的个人医保数据，如下表1所示：
用户标识 入院时间 出院时间 用药时间 用药剂量
李xx 1-Jan-16 12-Sep-16 255.00 1210.00
吴xx 5-Jan-16 22-Sep-16 261.00 1170.00
高xx 5-Jan-16 20-Sep-16 259.00 995.00
王x 1-Jan-16 27-Sep-16 270.00 880.00
黄xx 8-Jan-16 28-Sep-16 264.00 720.00
赵x 19-Jan-16 29-Sep-16 254.00 590.00
钱xx 5-Jan-16 20-Sep-16 259.00 423.00
孙x 6-Jan-16 6-Sep-16 244.00 350.00
表1
步骤S30，根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常。
服务器获取个人医保数据中的用药时间和用药剂量，以根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常，具体地，包括：
步骤S31，查询预设药品数据库，获取所述目标药品的药品使用说明。
即，服务器查询预设药品数据库（预设药品数据库是指预设设置的用于保存各个药品信息（药品信息包括但不仅限于：药品适应症，药品使用说明、药品配方、药品期限、药品产地、通用名称、商品名称、用法用量、不良反应、禁忌症、注意事项等）的数据库，服务器获取所述目标药品的药品使用说明。
步骤S32，将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
服务器将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；例如，吗替麦考酚酚酯用量药品使用说明中的用法用量包括：每日最大合理用量2g/人，个人医保数据中的用药时间为255天，服务器根据用药时间和用法用量，计算得到目标药品的理论用药量为510g。
步骤S33，将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对；若所述用药剂量与所述理论用药量匹配，则所述个人医保数据正常；若所述用药剂量与所述理论用药量不匹配，则所述个人医保数据异常。
然后，服务器将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对，得到比对结果，服务器根据比对结果确定个人医保数据是否异常，若所述用药剂量与所述理论用药量匹配，即，服务器确定用药剂量与所述理论用药量的差值在误差允许的范围，则服务器判定所述个人医保数据正常；若所述用药剂量与所述理论用药量不匹配，即，服务器确定用药剂量与所述理论用药量的差值超出误差允许范围，则服务器判定所述个人医保数据异常。本实施例中通过计算机数据分析，判断个人医保数据是否存在异常，实现了医保数据自动分析检测。
步骤S40，若所述个人医保数据存在异常，则输出医保异常提示信息。
在服务器确定个人医保数据存在异常，则服务器输出医保异常提示信息，其中，医保异常提示信息的实现方式不作具体限定，例如，语音提示医保异常，以使用户了解个人数据异常的情况。在本实施例中服务器通过获取目标药品的消费数据，并将目标药品的药品消费数据以用户标识为维度进行数据透视，得到各用户标识对应的个人医保数据，然后服务器根据个人医保数据中目标药品的用药时间和用药剂量，进行医保异常的检测，实现了医保异常有效检测。
进一步的，在本申请第一实施例的基础上，提出了本申请基于大数据分析的医保异常检测方法的第二实施例。
本实施例是第一实施例中步骤S10的细化，本实施例与本申请第一实施例的区别在于，第一实施例中的目标药品是一种药品，本实施例中的目标药品是相同类型的多种药品。
即，本申请中医保异常判断是根据个人医保数据的使用剂量进行的，在使用剂量超过理论用药剂量时，服务器确定该个人医保数据异常，但是，如果疾病A既可以通过使用药品1治愈，又可以通过使用药品2治愈，即，药品1和药品2具有相同或者相近的功效（又叫适应症信息），药品2是药品1的可替代药品时，在出现这样的场景：患者去甲医院开具了合理剂量的药品1，以此同时，患者去乙医院开具了合理剂量的药品2，按照第一实施例中的方法，得到就会输出：个人医保数据正常的检测结果，然而事实并非如此，因此提出了本申请的第二实施例。
在本实施例中所述基于大数据分析的医保异常检测方法包括：
步骤S11，接收医保异常检测请求，获取所述医保异常检测请求中的待检测药品，及所述待检测药品的适应症信息。
用户输入药品标识并基于所述药品标识触发医保异常检测请求，服务器接收到用户基于所述药品标识触发的医保异常检测请求时，服务器获取所述医保异常检测请求中包含的药品标识，服务器将所述药品标识对应的药品作为待检测药品，服务器获取所述待监测药品的适应症信息（适应症信息是指药物适合运用的范围、标准），以时服务器根据所述适应症信息判定是否存在与所述适应症信息相同或者相近的可替代药品。
步骤S12，查询预设药品数据库，判断是否存在与所述适应症信息匹配的替代药品，其中，所述替代药品是指除所述待检测药品之外的药品。
服务器查询预设药品数据库，其中，预设药品数据库是指预先设置的包含有多种药品信息的数据库，药品信息包括但不仅限于：药品适应症，药品使用说明、药品配方、药品期限、药品产地、通用名称、商品名称、用法用量、不良反应、禁忌症、注意事项等，服务器将待监测药品的适应症信息与预设药品数据库中各个药品的适应症信息进行比对，服务器确定预设药品数据库中是否存在与待监测药品的适应症信息相同或者相近的其他药品，若预设药品数据库中存在与待监测药品的适应症信息相同或者相近的其他药品，服务器将该药品作为待监测药品的替代药品。
步骤S13，若不存在与所述适应症信息匹配的替代药品，则将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息。
若不存在所述适应症信息对应的替代药品，则服务器将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息，并执行第一实施例中步骤S20: 按预设数据透视规则处理所述药品消费信息，得到个人医保数据。
步骤S14，若存在与所述适应症信息匹配的替代药品，则将所述待检测药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息。
若预设药品数据库中存在所述适应症信息对应的替代药品，则将所述目标药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息，需要补充说明的是，本实施例中的替代药品可以包含一个或者多个。即，本实施例中将适应症信息相同或者相近的药品作为目标药品进行综合考虑，有效地避免了相同适应症信息的不同药品重复检测导致检测结果不准确的问题，使得基于大数据分析的医保异常检测的数据更加全面，准确性更高。
进一步的，参照图3，在上述实施例的基础上提出了本申请基于大数据分析的医保异常检测方法的第三实施例，本实施例是第一实施例中步骤S20之后的步骤，所述基于大数据分析的医保异常检测方法包括：
步骤S50，查询预设医保数据库，获取所述个人医保数据对应的病历。
服务器查询预设医保数据库，其中，本实施例中的预设医保数据库第一实施例中的预设医保数据库相同，本实施例中不作赘述，服务器获取个人医保数据中的用户标识，并获取所述用户标识对应的病历（病历可以是电子病历），服务器将用户标识相同的个人医保数据与病历，作为个人医保数据对应的病历。
步骤S60，将所述病历中的病症信息与所述目标药品的适应症信息进行比对，以判断所述病症信息与所述适应症信息是否匹配；
服务器将所述病历中的病症信息与所述目标药品的适应症信息进行比对，即，服务器通过将病历中的病症数据与所述目标药品的适应症信息进行比对，得到比对结果并根据比对结果判断目标药品是否对症。
步骤S70，若所述病症信息与所述适应症信息不匹配，则输出用药异常提示信息；
若所述病症信息与所述适应症信息不匹配，服务器确定目标药品使用不对症，则服务器输出用药异常提示信息。
此外，需要补充说明的是，若所述病症信息与所述适应症信息匹配，服务器确定目标药品使用对症，服务器进一步地判断所述目标药品的使用剂量是否合理，具体地，服务器执行步骤S20：根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤。
在本实施例中在执行第一实施例中根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤之前，首先获取了个人医保数据对应的病历，并通过将所述病历中的病症信息与所述目标药品的适应症信息进行比对，判断目标药品使用是否对症，在服务器确定目标药品使用不对症之后，服务器可以直接输出用药异常提示信息，在服务器确定目标药品使用对症之后，服务器进行目标药品的用量的判断，使得医保数量的处理效率更高。
进一步的，在上述实施例的基础上提出了本申请基于大数据分析的医保异常检测方法的第四实施例。
步骤S80，若所述个人医保数据正常，则将所述个人医保数据添加可报销标签；
若所述个人医保数据正常，则服务器将所述个人医保数据添加可报销标签，即，本实施例中在确定个人医保数据正常之后，服务器将所述个人医保数据添加可报销标签，以对应的缩减报销流程。具体地：
步骤S90，在接收到医保报销请求时，获取所述医保报销请求中的用户标识；
服务器在接收到医保报销请求时，本实施例中的在接收到医保报销请求时，可以通过不同的形式触发，例如，用户在终端显示屏上点击“医保报销”的按键，手动触发医保报销请求，然后，终端将医保报销请求发送至服务器；或者通过其他形式触发，在服务器在接收到医保报销请求时之后，服务器获取所述医保报销请求中的用户标识。
步骤S100，查询预设医保数据库，获取所述用户标识对应的个人医保数据，并判断所述个人医保数据中是否存在可报销标签；
服务器查询预设医保数据库（其中，本实施例中的预设医保数据库与第一实施例中的预设医保数据库相同，本实施例中不作赘述），服务器获取所述用户标识对应的个人医保数据，并判断所述个人医保数据中是否存在可报销标签。
步骤S110，若所述个人医保数据中存在可报销标签，则将所述个人医保数据中的药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销。
若所述个人医保数据中存在可报销标签，即，服务器更改医保报销的审核流程，对该医保数据进行免审，服务器将所述个人医保数据中的药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销，其中，预设报销比例是指预先设置的各个种类药品对应的报销比例，例如，预设报销比例设置为80%。
步骤S120，若所述个人医保数据中不存在可报销标签，则获取所述用户标识对应的医保报销审核材料；根据所述医保报销审核材料确定所述目标药品的合理报销额度，并按所述合理报销额度进行报销。
若所述个人医保数据中不存在可报销标签，则服务器需要进行正常的医保报销，服务器获取所述用户标识对应的医保报销审核材料，服务器判断所述医保报销审核材料是否符合预设审核标准（预设审核标准可以根据具体场景设置），若服务器确定医保报销审核材料不符合预设审核标准，则驳回医保报销请求，在服务器确定医保报销审核材料符合预设审核标准，即，由于个人医保数据中存在异常，服务器判定用户存在超额报销的情况，服务器需要确定合理报销额度，具体地：
在服务器确定医保报销审核材料符合预设审核标准之后，服务器获取所述医保报销审核材料中的病历信息，将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；其中，服务器确定目标药品的理论用药量可以结合第一实施例，本实施例中不作赘述，在得到目标药品的理论用药量之后，服务器将理论用药量作为目标药品的合理使用剂量，服务器获取所述理论用药量对应的药品费用，服务器将所述药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销。在本实施例中根据医保异常检测检测结果，确定医保报销流程，使得医保报销更加快速。
此外，参照图4，本申请实施例还提出一种基于大数据分析的医保异常检测装置，所述基于大数据分析的医保异常检测装置包括：
请求接收模块10，用于接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
数据处理模块20，用于按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
异常判断模块30，用于根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
输出提示模块40，用于若所述个人医保数据存在异常，则输出医保异常提示信息。
可选地，所述请求接收模块10，包括：
请求接收单元，用于接收医保异常检测请求，获取所述医保异常检测请求中的待检测药品，及所述待检测药品的适应症信息；
查询单元，用于查询预设药品数据库，判断是否存在与所述适应症信息匹配的替代药品，其中，所述替代药品是指除所述待检测药品之外的药品；
第一获取单元，用于若不存在与所述适应症信息匹配的替代药品，则将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息；
第二获取单元，用于若存在与所述适应症信息匹配的替代药品，则将所述待检测药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息。
可选地，所述数据处理模块20，包括：
获取单元，用于获取预设数据透视规则及所述预设数据透视规则中分类标签，其中，所述分类标签包括行标签和列标签，所述行标签为用户标识；
分类汇总单元，用于将所述药品消费信息按所述行标签和所述列标签进行分类汇总，得到各所述用户标识对应的个人医保数据。
可选地，所述基于大数据分析的医保异常检测装置，包括：
病历查询模块，用于查询预设医保数据库，获取所述个人医保数据对应的病历；
比对判断模块，用于将所述病历中的病症信息与所述目标药品的适应症信息进行比对，以判断所述病症信息与所述适应症信息是否匹配；
异常提示模块，用于若所述病症信息与所述适应症信息不匹配，则输出用药异常提示信息；
若所述病症信息与所述适应症信息匹配，则通过所述异常判断模块，执行根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤。
可选地，所述异常判断模块30，包括：
查询获取单元，用于查询预设药品数据库，获取所述目标药品的药品使用说明；
理论计算单元，用于将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
比对单元，用于将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对；
第一判定单元，用于若所述用药剂量与所述理论用药量匹配，则所述个人医保数据正常；
第二判定单元，用于若所述用药剂量与所述理论用药量不匹配，则所述个人医保数据异常。
可选地，所述基于大数据分析的医保异常检测装置，包括：
标签添加模块，用于若所述个人医保数据正常，则将所述个人医保数据添加可报销标签；
报销接收模块，用于在接收到医保报销请求时，获取所述医保报销请求中的用户标识；
标签判断模块，用于查询预设医保数据库，获取所述用户标识对应的个人医保数据，并判断所述个人医保数据中是否存在可报销标签；
第一报销模块，用于若所述个人医保数据中存在可报销标签，则将所述个人医保数据中的药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销；
材料获取模块，用于若所述个人医保数据中不存在可报销标签，则获取所述用户标识对应的医保报销审核材料；
第二报销模块，用于根据所述医保报销审核材料确定所述目标药品的合理报销额度，并按所述合理报销额度进行报销。
可选地，所述第二报销模块，包括：
用药确定单元，用于获取所述医保报销审核材料中的病历信息，将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
额度确定单元，用于获取所述理论用药量对应的药品费用，将所述药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销。
其中，基于大数据分析的医保异常检测装置的各个功能模块实现的步骤可参照本申请基于大数据分析的医保异常检测方法的各个实施例，此处不再赘述。
此外，本申请实施例还提出一种计算机存储介质。
所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现上述实施例提供的基于大数据分析的医保异常检测方法中的操作。所述存储介质可以是非易失性存储介质。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于大数据分析的医保异常检测方法，其特征在于，所述基于大数据分析的医保异常检测方法包括以下步骤：
    接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
    按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
    根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
    若所述个人医保数据存在异常，则输出医保异常提示信息。
  2. 如权利要求1所述的基于大数据分析的医保异常检测方法，其特征在于，所述接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息的步骤，包括：
    接收医保异常检测请求，获取所述医保异常检测请求中的待检测药品，及所述待检测药品的适应症信息；
    查询预设药品数据库，判断是否存在与所述适应症信息匹配的替代药品，其中，所述替代药品是指除所述待检测药品之外的药品；
    若不存在与所述适应症信息匹配的替代药品，则将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息；
    若存在与所述适应症信息匹配的替代药品，则将所述待检测药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息。
  3. 如权利要求1所述的基于大数据分析的医保异常检测方法，其特征在于，所述按预设数据透视规则处理所述药品消费信息，得到个人医保数据的步骤，包括：
    获取预设数据透视规则及所述预设数据透视规则中分类标签，其中，所述分类标签包括行标签和列标签，所述行标签为用户标识；
    将所述药品消费信息按所述行标签和所述列标签进行分类汇总，得到各所述用户标识对应的个人医保数据。
  4. 如权利要求1所述的基于大数据分析的医保异常检测方法，其特征在于，所述按预设数据透视规则处理所述药品消费信息，得到个人医保数据的步骤之后，包括：
    查询预设医保数据库，获取所述个人医保数据对应的病历；
    将所述病历中的病症信息与所述目标药品的适应症信息进行比对，以判断所述病症信息与所述适应症信息是否匹配；
    若所述病症信息与所述适应症信息不匹配，则输出用药异常提示信息；
    若所述病症信息与所述适应症信息匹配，则执行根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤。
  5. 如权利要求1所述的基于大数据分析的医保异常检测方法，其特征在于，所述根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤，包括：
    查询预设药品数据库，获取所述目标药品的药品使用说明；
    将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
    将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对；
    若所述用药剂量与所述理论用药量匹配，则所述个人医保数据正常；
    若所述用药剂量与所述理论用药量不匹配，则所述个人医保数据异常。
  6. 如权利要求1所述的基于大数据分析的医保异常检测方法，其特征在于，所述根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤之后，包括：
    若所述个人医保数据正常，则将所述个人医保数据添加可报销标签；
    在接收到医保报销请求时，获取所述医保报销请求中的用户标识；
    查询预设医保数据库，获取所述用户标识对应的个人医保数据，并判断所述个人医保数据中是否存在可报销标签；
    若所述个人医保数据中存在可报销标签，则将所述个人医保数据中的药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销；
    若所述个人医保数据中不存在可报销标签，则获取所述用户标识对应的医保报销审核材料；
    根据所述医保报销审核材料确定所述目标药品的合理报销额度，并按所述合理报销额度进行报销。
  7. 如权利要求6所述的基于大数据分析的医保异常检测方法，其特征在于，所述根据所述医保报销审核材料确定所述目标药品的合理报销额度，并按所述合理报销额度进行报销的步骤，包括：
    获取所述医保报销审核材料中的病历信息，将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
    获取所述理论用药量对应的药品费用，将所述药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销。
  8. 一种基于大数据分析的医保异常检测装置，其特征在于，所述基于大数据分析的医保异常检测装置包括：
    请求接收模块，用于接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
    数据处理模块，用于按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
    异常判断模块，用于根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
    输出提示模块，用于若所述个人医保数据存在异常，则输出医保异常提示信息。
  9. 如权利要求8所述的基于大数据分析的医保异常检测装置，其特征在于，所述请求接收模块，包括：
    请求接收单元，用于接收医保异常检测请求，获取所述医保异常检测请求中的待检测药品，及所述待检测药品的适应症信息；
    查询单元，用于查询预设药品数据库，判断是否存在与所述适应症信息匹配的替代药品，其中，所述替代药品是指除所述待检测药品之外的药品；
    第一获取单元，用于若不存在与所述适应症信息匹配的替代药品，则将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息；
    第二获取单元，用于若存在与所述适应症信息匹配的替代药品，则将所述待检测药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息。
  10. 如权利要求8所述的基于大数据分析的医保异常检测装置，其特征在于，所述数据处理模块，包括：
    获取单元，用于获取预设数据透视规则及所述预设数据透视规则中分类标签，其中，所述分类标签包括行标签和列标签，所述行标签为用户标识；
    分类汇总单元，用于将所述药品消费信息按所述行标签和所述列标签进行分类汇总，得到各所述用户标识对应的个人医保数据。
  11. 如权利要求8所述的基于大数据分析的医保异常检测装置，其特征在于，所述基于大数据分析的医保异常检测装置，包括：
    病历查询模块，用于查询预设医保数据库，获取所述个人医保数据对应的病历；
    比对判断模块，用于将所述病历中的病症信息与所述目标药品的适应症信息进行比对，以判断所述病症信息与所述适应症信息是否匹配；
    异常提示模块，用于若所述病症信息与所述适应症信息不匹配，则输出用药异常提示信息；
    若所述病症信息与所述适应症信息匹配，则通过所述异常判断模块，执行根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤。
  12. 如权利要求8所述的基于大数据分析的医保异常检测装置，其特征在于，所述异常判断模块，包括：
    查询获取单元，用于查询预设药品数据库，获取所述目标药品的药品使用说明；
    理论计算单元，用于将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
    比对单元，用于将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对；
    第一判定单元，用于若所述用药剂量与所述理论用药量匹配，则所述个人医保数据正常；
    第二判定单元，用于若所述用药剂量与所述理论用药量不匹配，则所述个人医保数据异常。
  13. 如权利要求8所述的基于大数据分析的医保异常检测装置，其特征在于，所述基于大数据分析的医保异常检测装置，包括：
    标签添加模块，用于若所述个人医保数据正常，则将所述个人医保数据添加可报销标签；
    报销接收模块，用于在接收到医保报销请求时，获取所述医保报销请求中的用户标识；
    标签判断模块，用于查询预设医保数据库，获取所述用户标识对应的个人医保数据，并判断所述个人医保数据中是否存在可报销标签；
    第一报销模块，用于若所述个人医保数据中存在可报销标签，则将所述个人医保数据中的药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销；
    材料获取模块，用于若所述个人医保数据中不存在可报销标签，则获取所述用户标识对应的医保报销审核材料；
    第二报销模块，用于根据所述医保报销审核材料确定所述目标药品的合理报销额度，并按所述合理报销额度进行报销。
  14. 如权利要求13所述的基于大数据分析的医保异常检测装置，其特征在于，所述第二报销模块，包括：
    用药确定单元，用于获取所述医保报销审核材料中的病历信息，将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
    额度确定单元，用于获取所述理论用药量对应的药品费用，将所述药品费用与所述目标药品的预设报销比例进行乘积运算，得到所述目标药品的报销额度，并按所述报销额度进行报销。
  15. 一种基于大数据分析的医保异常检测设备，其特征在于，所述基于大数据分析的医保异常检测设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令，其中：
    所述计算机可读指令被所述处理器执行时实现以下步骤：
    接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
    按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
    根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
    若所述个人医保数据存在异常，则输出医保异常提示信息。
  16. 如权利要求15所述的基于大数据分析的医保异常检测设备，其特征在于，所述接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息的步骤，包括：
    接收医保异常检测请求，获取所述医保异常检测请求中的待检测药品，及所述待检测药品的适应症信息；
    查询预设药品数据库，判断是否存在与所述适应症信息匹配的替代药品，其中，所述替代药品是指除所述待检测药品之外的药品；
    若不存在与所述适应症信息匹配的替代药品，则将所述待检测药品作为目标药品，并获取所述目标药品的药品消费信息；
    若存在与所述适应症信息匹配的替代药品，则将所述待检测药品和所述替代药品作为目标药品，并获取所述目标药品的药品消费信息。
  17. 如权利要求15所述的基于大数据分析的医保异常检测设备，其特征在于，所述按预设数据透视规则处理所述药品消费信息，得到个人医保数据的步骤，包括：
    获取预设数据透视规则及所述预设数据透视规则中分类标签，其中，所述分类标签包括行标签和列标签，所述行标签为用户标识；
    将所述药品消费信息按所述行标签和所述列标签进行分类汇总，得到各所述用户标识对应的个人医保数据。
  18. 如权利要求15所述的基于大数据分析的医保异常检测设备，其特征在于，所述按预设数据透视规则处理所述药品消费信息，得到个人医保数据的步骤之后，包括：
    查询预设医保数据库，获取所述个人医保数据对应的病历；
    将所述病历中的病症信息与所述目标药品的适应症信息进行比对，以判断所述病症信息与所述适应症信息是否匹配；
    若所述病症信息与所述适应症信息不匹配，则输出用药异常提示信息；
    若所述病症信息与所述适应症信息匹配，则执行根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤。
  19. 如权利要求15所述的基于大数据分析的医保异常检测设备，其特征在于，所述根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常的步骤，包括：
    查询预设药品数据库，获取所述目标药品的药品使用说明；
    将所述药品使用说明中的用法用量与所述个人医保数据中的用药时间结合，计算得到所述目标药品的理论用药量；
    将所述个人医保数据中的用药剂量与所述目标药品的理论用药量进行比对；
    若所述用药剂量与所述理论用药量匹配，则所述个人医保数据正常；
    若所述用药剂量与所述理论用药量不匹配，则所述个人医保数据异常。
  20. 一种计算机存储介质，其特征在于，所述计算机存储介质上存储有计算机可读指令，所述计算机可读指令被处理器执行时实现下的步骤：
    接收医保异常检测请求，获取目标药品及所述目标药品的药品消费信息；
    按预设数据透视规则处理所述药品消费信息，得到个人医保数据；
    根据所述个人医保数据中的用药时间和用药剂量，判断所述个人医保数据是否存在异常；
    若所述个人医保数据存在异常，则输出医保异常提示信息。
PCT/CN2019/118831 2018-12-13 2019-11-15 基于大数据分析的医保异常检测方法、装置、设备和介质 WO2020119384A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811529378.5A CN109636641A (zh) 2018-12-13 2018-12-13 基于大数据分析的医保异常检测方法、装置、设备和介质
CN201811529378.5 2018-12-13

Publications (1)

Publication Number Publication Date
WO2020119384A1 true WO2020119384A1 (zh) 2020-06-18

Family

ID=66073873

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/118831 WO2020119384A1 (zh) 2018-12-13 2019-11-15 基于大数据分析的医保异常检测方法、装置、设备和介质

Country Status (2)

Country Link
CN (1) CN109636641A (zh)
WO (1) WO2020119384A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636641A (zh) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 基于大数据分析的医保异常检测方法、装置、设备和介质
CN111192643A (zh) * 2019-12-02 2020-05-22 泰康保险集团股份有限公司 病历数据处理方法及相关设备
CN111259089B (zh) * 2020-01-14 2023-03-21 平安医疗健康管理股份有限公司 医保数据处理方法、装置、计算机设备和存储介质
CN111242793B (zh) * 2020-01-16 2024-02-06 上海金仕达卫宁软件科技有限公司 医保数据异常的检测方法和装置
CN111402070A (zh) * 2020-03-23 2020-07-10 平安医疗健康管理股份有限公司 医疗信息识别方法、装置、计算机设备及存储介质
CN113284614A (zh) * 2021-06-07 2021-08-20 平安国际智慧城市科技股份有限公司 异常就诊的识别方法、装置、电子设备及存储介质
CN113626488A (zh) * 2021-08-04 2021-11-09 挂号网（杭州）科技有限公司 数据处理方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989218A (zh) * 2015-01-28 2016-10-05 中兴通讯股份有限公司 一种信息化处理方法和装置
CN107133438A (zh) * 2017-03-03 2017-09-05 平安医疗健康管理股份有限公司 医疗行为监控方法及装置
CN108766509A (zh) * 2018-05-16 2018-11-06 中国联合网络通信集团有限公司 基于区块链技术的鉴真方法、装置、终端及存储介质
CN109636641A (zh) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 基于大数据分析的医保异常检测方法、装置、设备和介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102012974A (zh) * 2010-12-15 2011-04-13 中国人民解放军第四军医大学 临床安全合理用药决策支持系统
CN104134157B (zh) * 2014-08-08 2018-04-13 平安养老保险股份有限公司 一种医疗保险报销过程中可疑行为审核系统及审核方法
CN104134092B (zh) * 2014-08-08 2017-12-01 平安养老保险股份有限公司 一种医保报销行为监控系统及监控方法
CN104537764B (zh) * 2014-12-31 2017-06-27 浙江大学 一种医保卡异常使用的检测方法和检测系统
CN104933324A (zh) * 2015-07-10 2015-09-23 庞健 处方用药识别方法及系统
CN106530166B (zh) * 2016-08-31 2019-12-13 中国人民解放军总医院第一附属医院 医院医保费用防拒付辅助管理信息系统及防拒付方法
CN107133437B (zh) * 2017-03-03 2018-09-14 平安医疗健康管理股份有限公司 监控药品使用的方法及装置
CN107609980A (zh) * 2017-09-07 2018-01-19 平安医疗健康管理股份有限公司 医疗数据处理方法、装置、计算机设备及存储介质
CN108921710A (zh) * 2018-06-08 2018-11-30 东莞迪赛软件技术有限公司 医保异常检测的方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989218A (zh) * 2015-01-28 2016-10-05 中兴通讯股份有限公司 一种信息化处理方法和装置
CN107133438A (zh) * 2017-03-03 2017-09-05 平安医疗健康管理股份有限公司 医疗行为监控方法及装置
CN108766509A (zh) * 2018-05-16 2018-11-06 中国联合网络通信集团有限公司 基于区块链技术的鉴真方法、装置、终端及存储介质
CN109636641A (zh) * 2018-12-13 2019-04-16 平安医疗健康管理股份有限公司 基于大数据分析的医保异常检测方法、装置、设备和介质

Also Published As

Publication number Publication date
CN109636641A (zh) 2019-04-16

Similar Documents

Publication Publication Date Title
WO2020119384A1 (zh) 基于大数据分析的医保异常检测方法、装置、设备和介质
WO2020119116A1 (zh) 基于数据分析的医保审核方法、装置、设备和存储介质
WO2020078058A1 (zh) 医疗数据异常识别方法、装置、终端及存储介质
WO2020119385A1 (zh) 基于数据分析的处方生成监测方法、装置、设备和介质
WO2020087981A1 (zh) 风控审核模型生成方法、装置、设备及可读存储介质
WO2018205373A1 (zh) 人伤理赔定损费用测算方法、装置、服务器和介质
WO2020006852A1 (zh) 差旅费自助核销处理方法、装置、设备和计算机存储介质
WO2020119176A1 (zh) 报销数据的排查方法、识别服务端及存储介质
WO2019174090A1 (zh) 截屏文件分享的控制方法、装置、设备和计算机存储介质
WO2020108111A1 (zh) 医保欺诈行为的识别方法、装置、设备及可读存储介质
WO2020119403A1 (zh) 住院数据异常检测方法、装置、设备及可读存储介质
WO2020119115A1 (zh) 数据审核方法、装置、设备及存储介质
WO2020224250A1 (zh) 智能合约的触发方法、装置、设备及存储介质
WO2020015064A1 (zh) 系统故障处理方法、装置、设备及存储介质
WO2020119402A1 (zh) 无关用药的识别方法、装置、终端及计算机可读存储介质
WO2020119131A1 (zh) 用药方案异常的识别方法、装置、终端及可读存储介质
WO2020147385A1 (zh) 数据录入方法、装置、终端及计算机可读存储介质
WO2020107591A1 (zh) 重复投保限制方法、装置、设备及可读存储介质
WO2020062641A1 (zh) 识别用户角色的方法、用户设备、存储介质及装置
WO2020226456A1 (ko) 처방 정보를 통한 의료 정보 제공 방법 및 장치
WO2019024485A1 (zh) 数据共享方法、装置及计算机可读存储介质
WO2021027143A1 (zh) 信息推送方法、装置、设备及计算机可读存储介质
WO2020119369A1 (zh) 智能it运维故障定位方法、装置、设备及可读存储介质
WO2020073494A1 (zh) 网页后门检测方法、设备、存储介质及装置
WO2021003956A1 (zh) 产品信息的管理方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19895749

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 15/10/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19895749

Country of ref document: EP

Kind code of ref document: A1