WO2020119176A1 - 报销数据的排查方法、识别服务端及存储介质 - Google Patents

报销数据的排查方法、识别服务端及存储介质 Download PDF

Info

Publication number
WO2020119176A1
WO2020119176A1 PCT/CN2019/102432 CN2019102432W WO2020119176A1 WO 2020119176 A1 WO2020119176 A1 WO 2020119176A1 CN 2019102432 W CN2019102432 W CN 2019102432W WO 2020119176 A1 WO2020119176 A1 WO 2020119176A1
Authority
WO
WIPO (PCT)
Prior art keywords
reimbursement
item
standard
name
preset
Prior art date
Application number
PCT/CN2019/102432
Other languages
English (en)
French (fr)
Inventor
陈明东
黄越
胥畅
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 WO2020119176A1 publication Critical patent/WO2020119176A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/279Recognition of textual entities
    • G06F40/289Phrasal analysis, e.g. finite state techniques or chunking
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/103Workflow collaboration or project management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q40/00Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08Insurance

Definitions

  • the present application relates to the field of data identification technology, and in particular, to a method for checking reimbursement data, an identification server, and a storage medium.
  • Medical insurance Social medical insurance
  • medical institutions need to upload the details of medical drugs or services generated by patients to the medical insurance audit system for unified reimbursement processing.
  • the medical items included in the catalog are reimbursed based on the drug catalog, the diagnosis and treatment catalog, the scope of medical service facilities and the payment standard catalog.
  • medical institutions intentionally or unintentionally upload a part of medical items outside the catalog to the audit system for reimbursement.
  • Staff need to check a large amount of reimbursement data to analyze and identify medical items that are not in the catalog. It takes a lot of manpower, and it is easy to cause malicious medical institutions to upload abnormal data and the identification is not comprehensive.
  • the main purpose of the present application is to provide a method for checking reimbursement data, identifying the server and storage media, aiming to solve the technical problem of huge workload due to the huge amount of medical insurance reimbursement data and manual verification of medical expenses.
  • this application provides a method for checking reimbursement data, including the steps of:
  • the preset cleaning model is used to clean the data corresponding to the reimbursement item code to obtain the corresponding standardized field ;
  • the input error flag is set to be associated with the reimbursement item code.
  • this application also provides an identification server, including:
  • a receiving module the receiving module is used to receive reimbursement data sent by a server of a medical institution, wherein the reimbursement data includes a reimbursement item code;
  • a judgment module the judgment module is used to judge whether there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • a storage module configured to store data corresponding to the reimbursement item code in the reimbursement data if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • An identification module where the identification module is used to set an entry error identifier to be associated with the reimbursement item code if there is no standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • Storage modules include:
  • a cleaning unit wherein if the standard item code corresponding to the reimbursement item code exists in the preset standard reimbursement catalog table, the cleaning unit is used to perform data corresponding to the reimbursement item code using a preset cleaning model Cleaning process to get corresponding standardized fields;
  • a searching unit configured to search for the information to be imported corresponding to a preset keyword in the standardized field
  • An import unit configured to store the information to be imported in a form corresponding to the preset keyword to store data corresponding to the reimbursement item code in the reimbursement data.
  • the present application also provides an identification server.
  • the identification server includes: a communication module, a memory, a processor, and a computer stored on the memory and capable of running on the processor.
  • An instruction reading program when the computer-readable instruction program is executed by the processor, implements the steps of the reimbursement data checking method as described above.
  • the present application also provides a storage medium on which a computer-readable instruction program is stored, and when the computer-readable instruction program is executed by the processor, the reimbursement data is checked as described above Method steps.
  • This application proposes a method for checking reimbursement data, identifying the server and storage media, and matching the reimbursement item code with the standard item code of the preset standard reimbursement catalog table, thereby avoiding the diversification of medical project names by various medical institutions, resulting in
  • the comparison accuracy rate is improved;
  • the verification staff can only code the standard items that exist in the preset standard reimbursement catalog table Corresponding to the said reimbursement item code for reimbursement, reducing the workload of verification, and avoiding the situation that medical staff reimburse non-reimbursement items for medical insurance.
  • FIG. 1 is a schematic structural diagram of a hardware operating environment involved in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of a method for checking reimbursement data of an application
  • FIG. 3 is a schematic flowchart of a second embodiment of a method for checking reimbursement data of an application
  • FIG. 4 is a schematic flowchart of a third embodiment of a method for checking reimbursement data of an application
  • FIG. 5 is a schematic flowchart of a fourth embodiment of a method for checking reimbursement data of an application
  • FIG. 6 is a schematic flowchart of a fifth embodiment of a method for checking reimbursement data of the application
  • FIG. 7 is a schematic flowchart of a sixth embodiment of a method for checking reimbursement data of an application
  • FIG. 8 is a schematic flowchart of a seventh embodiment of a method for checking reimbursement data of an application
  • FIG. 9 is a schematic diagram of the functional modules of the monitoring server of the application.
  • FIG. 1 is a schematic diagram of the hardware structure of the monitoring server 100 in various embodiments of the present application.
  • the monitoring server 100 may be a server that is communicatively connected to a terminal for medical expenses reimbursement by an insured person or a medical institution, or It is a monitoring service platform dedicated to data monitoring that is communicatively connected to the server and the terminal for medical expense reimbursement.
  • the monitoring server 100 provided by this application includes components such as a communication module 10, a memory 20, and a processor 30.
  • the processor 30 is respectively connected to the memory 20 and the communication module 10, and the computer readable instruction program is stored on the memory 20, and the computer readable instruction program is simultaneously executed by the processor 30.
  • the communication module 10 can be connected to external communication equipment through a network.
  • the memory 20 can be used to store software programs and various data.
  • the processor 30 is a control center of the monitoring server 100, and uses various interfaces and lines to connect the various parts of the entire monitoring server 100, by running or executing software programs and/or modules stored in the memory 20,
  • the data in the memory 20 executes various functions and processing data of the monitoring server 100, thereby performing overall monitoring on the monitoring server 100.
  • FIG. 1 does not constitute a limitation on the monitoring server 100, and may include more or fewer components than the illustration, or a combination of certain components, or different Parts arrangement.
  • the method includes the following steps:
  • Step S100 Receive the reimbursement data sent by the server of the medical institution, and use the cleaning model to preprocess the reimbursement data, where the reimbursement data includes the reimbursement item code;
  • the medical institution may be a hospital, nursing home, outpatient department, clinic, health center, and first-aid station that performs disease diagnosis and treatment.
  • the medical institution may also be a pharmacy that legally sells medicines.
  • the reimbursement data is a detailed reimbursable bill issued for the medical treatment or medicine purchase of the patient at the medical institution, including the medical institution logo of the medical institution, the name of the reimbursable item consumed, the reimbursement item code, and the actual unit price corresponding to the reimbursement item code. , Actual valuation unit, reimbursement ratio, etc.
  • the reimbursement project is a medical insurance reimbursement project for medical institutions to provide drugs, diagnosis and treatment, and medical service facilities for patients.
  • the application software is installed on the server of the medical institution, so that the server of the medical institution sends reimbursement data to the monitoring server regularly or in real time.
  • the monitoring server can directly obtain the reimbursement data reported by the application software from its own memory; when the monitoring server is a dedicated monitoring service platform, it can send a request to the medical institution server to obtain the reimbursement data, or the medical institution server actively sends the reimbursement data To the monitoring service platform.
  • the medical institution server regularly sends the reimbursement data, or the medical institution staff can send the reimbursement data to the monitoring server in real time after entering the relevant data.
  • the reimbursement data specifically includes the name of the reimbursement project to be reimbursed, the corresponding reimbursement project code, etc., and may also include the dosage form, and/or the applicable population, and/or the origin information.
  • the medical items prepared for reimbursement in the reimbursement data are reimbursement items.
  • the health management departments of various regions have formulated corresponding standard project codes for medical project names to correspond to medical project codes to distinguish each medical project.
  • Step S200 Determine whether there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table
  • the preset standard reimbursement catalogue table is for a person skilled in the art to use a pre-selected set model to study the reimbursement rule files such as the medicine catalogue, the diagnosis and treatment catalogue, the scope of medical service facilities, and the payment standard catalogue used in the insured area where the medical institution is located, so that The reimbursement item names, corresponding reimbursement item codes, and corresponding reimbursement item names that can be reimbursed in the insured area are all included in the preset standard reimbursement catalog table.
  • Step S300 if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table, the data corresponding to the reimbursement item code in the reimbursement data is stored;
  • the standard project code corresponding to the project code stores the data corresponding to the reimbursement item code in the reimbursement data, and waits for the staff to operate the subsequent reimbursement procedure, according to the expenses paid by the reimbursement project and the reimbursement ratio, to the medical institution or the insured person Pay reimbursement costs.
  • step S300 includes:
  • Step S301 if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table, the preset cleaning model is used to clean the data corresponding to the reimbursement item code to obtain the corresponding standardized field;
  • the preset cleaning model can be a noise channel model (Noisy Channel Model), it can be compared with the preset dictionary first to determine whether the vocabulary itself is a spelling error, and then calculate the most similar candidate vocabulary set by calculating the minimum editing distance, and calculate the prior of each candidate word through the trained language model Probability P(w) and transition probability P(x
  • Noisy Channel Model Noisy Channel Model
  • Step S302 searching for the information to be imported corresponding to the preset keyword in the standardized field
  • the preset keyword is a vocabulary set in advance by a person skilled in the art according to reimbursement needs, for example: bill payment, quantity, time, etc.
  • Step S303 storing the information to be imported in a form corresponding to the preset keyword to store data corresponding to the reimbursement item code in the reimbursement data;
  • Multiple forms are set in advance, corresponding to the preset keywords respectively.
  • multiple preset keywords can also correspond to one form.
  • step S400 if there is no standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table, an entry error flag is set to be associated with the reimbursement item code.
  • the method for checking the reimbursement data allows the verification staff to reimburse only the reimbursement item codes corresponding to the standard item codes in the preset standard reimbursement catalogue table, reducing the amount of verification work and avoiding medical institution staff Medical insurance reimbursement for non-reimbursed items.
  • the reimbursement data includes the reimbursement item name corresponding to the reimbursement item code; after step S400, it includes:
  • Step S500 Determine the reimbursement item name corresponding to the reimbursement item code according to the reimbursement data
  • the reimbursement project name is a text name corresponding to the reimbursement project code.
  • it is a name composed of Chinese or English text, such as glucose, recombinant human coagulation factor VIIa, gallium [67Ga] citrate, etc.
  • Step S600 Calculate the similarity between the name of the reimbursement item and the name of each standard item in the table of the preset standard reimbursement table through a preset rule;
  • those skilled in the art can set the required preset rules according to the actual situation. For example: setting up a disturbing font that includes multiple fields, deleting the part of the reimbursement item name that matches the fields in the disturbing font, and filtering the reimbursed item name.
  • the neural network algorithm is used to calculate the similarity, the reimbursement rules implemented in the insured areas are learned in advance to establish a recognition model.
  • the standard project name is segmented and a word dictionary is established; set the training text, segment the training text and obtain a word vector file, filter the word vector file according to the word dictionary, only keep The word vectors of the words in the word dictionary are stored in the word vector matrix text; the word vector matrix text is input as the recurrent neural network model to train the recognition model, that is, to establish the recognition model.
  • the word dictionary is used to segment the reimbursement project name, and the similarity is calculated through the recognition model, so that the irregular reimbursement project name uploaded by the medical institution corresponds to the similar standard project name.
  • Step S700 Determine whether the similarity between the reimbursement project name and each standard project name is greater than the first preset threshold
  • a person skilled in the art sets a first preset threshold as needed, and compares the similarity between the reimbursement project name and each standard project name and the first preset threshold one by one. If there are one or more similarities and the first preset threshold, the standard item names corresponding to the similarities greater than the first preset threshold are stored, and step S800 is executed; if none of the similarities is greater than the first preset threshold, then Go to step S900.
  • Step S800 if there is at least one similarity between the standard project name and the reimbursement project name that is greater than the first preset threshold, the information to be confirmed is generated and sent to the server of the medical institution.
  • the information to be confirmed includes the similarity to the reimbursement project name that is greater than the first Standard project name with preset threshold;
  • the standard project name corresponding to the similarity greater than the first preset threshold is most likely the standard project name corresponding to the reimbursement project name, generated
  • the information to be confirmed containing the name of the standard project is sent to the server of the medical institution, so that the staff of the medical institution can modify the name of the original reimbursement project or the logo of the original reimbursement project table to a name that complies with the three catalog review rules according to the prompt of the information to be confirmed Or logo.
  • Step S900 if the similarity between the standard project name and each reimbursement project name is less than or equal to the first preset threshold, the information to be modified is generated and sent to the medical institution server.
  • the similarity between the standard project name and each reimbursement project name is less than or equal to the first preset threshold, it is proved that the similarity is calculated according to the preset rules, and a standard project name that is most similar to the reimbursement project name is not obtained, and the information to be modified is generated And sent to the server of the medical institution, so that the staff of the medical institution can modify or make explanations without the prompt of the relevant name.
  • the difference between the information to be modified and the information to be confirmed is that the information to be modified does not contain the standard project name whose similarity to the reimbursement project name is greater than the first preset threshold, that is, the medical institution staff can modify or do it themselves without the prompt of the relevant name Explanation.
  • the reimbursement data includes the charge category corresponding to the name of the reimbursement item; step S600 includes:
  • Step S610 Determine the charge category corresponding to the reimbursement item name according to the reimbursement data
  • the charge categories include: Western medicine fee, Chinese patent medicine, Chinese herbal medicine, laboratory fee, surgery fee, treatment fee, inspection fee, nursing fee, material fee, etc. Those skilled in the art can also set it according to the medical insurance reimbursement rules of the participating regions.
  • Step S620 classify the reimbursement item names according to a preset category system and a charge category.
  • the preset category system includes a target category corresponding to the charge category, and the target category includes a drug charge category, a diagnosis and treatment item charge category, and a medical facility material charge category;
  • the preset category system is set by technical personnel in the field according to the medical insurance reimbursement rules of the participating regions.
  • the preset category system includes three target categories: drug charges, diagnosis and treatment items, and medical facility materials charges, which correspond to the current basic medical insurance drug catalog, diagnosis and treatment item catalog, and medical service facility standards.
  • Western medicine fees, Chinese patent medicines and Chinese herbal medicines correspond to drug charges; laboratory fees, surgery fees, treatment fees, inspection fees, and nursing fees correspond to the charges for medical treatment items; material fees correspond to the charges for medical facility materials.
  • Step S630 Associate and store the target class and the corresponding reimbursement project name, and determine the target class type associated with the reimbursement project name;
  • the corresponding target category and the reimbursement project name are associated and stored in the memory for later steps to be called.
  • Step S640 if the target category associated with the reimbursement item name is the drug charging category, then the similarity between the reimbursement item name and each standard item name in the preset standard reimbursement catalog table is calculated according to the preset drug classification rules;
  • Step S650 if the target category associated with the reimbursement item name is the charge category of the medical treatment item, the similarity between the reimbursement item name and each standard item name in the preset standard reimbursement catalog table is calculated according to the preset diagnosis item classification rules;
  • Step S660 if the target category associated with the reimbursement project name is the medical facility material charging category, then the similarity between the reimbursement project name and each standard project name in the preset standard reimbursement catalog table is calculated according to the preset medical facility material classification rules.
  • step 640 includes:
  • Step 641 If the target category associated with the reimbursement project name is the drug charge category, then extract the first category of keywords for the reimbursement project name according to the preset first category keyword group;
  • the preset first type of keyword group includes basic organic substances, basic inorganic substances, basic Chinese herbal medicines, etc., for example: basic inorganic substances such as sodium chloride and ethylene glycol; basic organic substances such as glucose and lysine; codonopsis and wolfberry Such as basic Chinese herbal medicine.
  • Step 642 According to the extracted first-type keywords, determine a standard project name that contains the same first-type keywords as the reimbursement project name;
  • Step 643 Calculate the similarity between the reimbursement project name and each standard project name containing the same first-type keywords.
  • the name of the reimbursement project is "polyethylene glycol”
  • extract the keywords for "polyethylene glycol” according to the preset first type keyword group
  • extract ethylene glycol and determine that there are many standard project names containing ethylene glycol .
  • the similarity between the reimbursement project name and each standard project name containing the same first-type keyword can be calculated to improve the accuracy.
  • step S650 includes:
  • Step S651 if the target category associated with the reimbursement item name is the charge category of the diagnosis and treatment item, perform keyword extraction on the reimbursement item name according to the preset second-type keyword group;
  • the second type of keyword group may include action sites, diagnosis and treatment methods, diseases, etc., for example: action sites such as cornea, kidney, and intestine; surgery, measurement, data, repair, amputation, restoration, and other treatment methods; tumors, stones, Fistula and other diseases.
  • action sites such as cornea, kidney, and intestine
  • tumors, stones, Fistula and other diseases for example: action sites such as cornea, kidney, and intestine; surgery, measurement, data, repair, amputation, restoration, and other treatment methods; tumors, stones, Fistula and other diseases.
  • Step S652 Calculate the similarity between the reimbursed item name and the standard item name with the same second type keyword according to the extracted second type keyword and the preset weight corresponding to the extracted second type keyword.
  • the preset weight corresponding to the action site is greater than the disease, diagnosis and treatment.
  • the reimbursement data uploaded by the medical institution contains "femoral artery exploration”.
  • the second type of keywords are extracted from “femoral artery” and "exploration”.
  • the preset weight corresponding to the femoral artery is 90%. Set the weight to 50%, then calculate the familiarity between "femoral artery exploration” and each standard project name containing "femoral artery", and then multiply it by the corresponding preset weight; calculate “femoral artery exploration” and each containing “exploration technique” "The recognition degree of the standard project name is multiplied by the corresponding preset weight, and the two are added together to obtain the recognition degree of "femoral artery exploration” and each standard project name. Because the naming of diagnosis and treatment items usually adopts the combination of action parts and diagnosis and treatment methods, the introduction of the concept of weight makes the accuracy of the calculated acquaintance higher.
  • step S660 includes:
  • Step S661 determining the origin information corresponding to the reimbursement project name according to the reimbursement data
  • Step S662 According to the origin information, confirm the preset origin directory corresponding to the reimbursement project name, the preset origin directory includes the standard project name with the same origin information;
  • the origin information includes domestic and import.
  • the preset origin directory is a directory that is divided in advance according to the origin information corresponding to the standard project name.
  • Step S663 Calculate the similarity between the reimbursement project name and the name of each standard project in the preset origin catalog.
  • step S300 includes:
  • Step S310 if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table, determine the number of standard item codes corresponding to the reimbursement item code;
  • Step S320 if the number of standard item codes corresponding to the reimbursement item code is 1, storing data corresponding to the reimbursement item code in the reimbursement data;
  • the reimbursement item code only corresponds to the standard item code unique to the preset standard reimbursement catalogue table, so that further expense reimbursement can be carried out.
  • step S330 if the number of standard item codes corresponding to the reimbursement item code is multiple, the information to be confirmed is generated and sent to the medical institution server.
  • step S301 is executed after step S330.
  • this application also provides an identification server, including:
  • the receiving module 10 the receiving module 10 is used to receive the reimbursement data sent by the server of the medical institution, wherein the reimbursement data includes the reimbursement item code;
  • the judgment module 20 is used to judge whether there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • the storage module 30 is used to store data corresponding to the reimbursement item code in the reimbursement data if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • the identification module 40 which is used to set the entry error identification to be associated with the reimbursement item code if there is no standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table;
  • Storage modules include:
  • the cleaning unit is used to clean the data corresponding to the reimbursement item code by using the preset cleaning model if the standard item code corresponding to the reimbursement item code exists in the preset standard reimbursement catalog table, so as to obtain the corresponding standardization Field
  • Search unit the search unit is used to search for the information to be imported corresponding to the preset keyword in the standardized field;
  • the importing unit is used to store the information to be imported in a form corresponding to a preset keyword to store the data corresponding to the reimbursement item code in the reimbursement data.
  • the reimbursement data includes the reimbursement item name corresponding to the reimbursement item code; it is to identify that the server includes a confirmation module 50, which is used to determine the reimbursement item name corresponding to the reimbursement item code according to the reimbursement data; Module 60, the calculation module 60 is used to calculate the similarity between the reimbursement project name and each standard project name in the preset standard reimbursement catalog table through the preset rules; the judgment module 20 is also used to judge the similarity between the reimbursement project name and each standard project name Whether it is greater than the first preset threshold; the identification server also includes a sending module 70, which is used to generate information to be confirmed if there is at least one similarity between the standard project name and the reimbursed project name that is greater than the first preset threshold And sent to the server of the medical institution, the information to be confirmed includes the standard project name whose similarity to the reimbursement project name is greater than the first preset threshold; the sending module 70 is also used if the similarity between the standard project name and each reimbursement project name is less than or equal to The first preset threshold generates information to be
  • the preset category system includes the target corresponding to the charge category Category, the target category includes medicine charging category, medical treatment project charging category and medical facility material charging category; storage module 30 is also used to associate the target category with the corresponding reimbursement project name and determine the target category type associated with the reimbursement project name ; If the target category associated with the reimbursement project name is the drug charge category, the similarity between the reimbursement project name and each standard project name in the preset standard reimbursement catalog table is calculated according to the preset drug classification rules; the calculation module 60 is also used to reimburse the project The target category of name association is the charge category of diagnosis and treatment items, the similarity between the name of the reimbursement item and the name of each standard item in the preset standard reimbursement catalogue table is calculated according to the preset diagnosis and treatment item classification rules; the calculation module 60 is also used to associate the name of the reimbursement item The target category is the medical facility material charging category, then the similarity between the reimbursement item name and the name of each standard item in the preset standard reimbursement catalog table is calculated according to the preset medical facility material classification rules.
  • the recognition server further includes an extraction module 80, which is used to perform the reimbursement project name according to the preset first-type keyword group if the target category associated with the reimbursement project name is the drug charging category The first type of keyword extraction; the confirmation module 50 is also used to determine the standard project name containing the same first type of keyword as the reimbursement project name based on the extracted first type keyword; the calculation module 60 is also used to calculate the reimbursement project name and The similarity of each standard item name containing the same first type keywords.
  • the extraction module 80 is further configured to perform second-type keyword extraction on the reimbursement item name according to a preset second-type keyword group if the target category associated with the reimbursement item name is the charge category of the medical treatment item;
  • the module 60 is also used to calculate the similarity between the reimbursed item name and the standard item name with the same second type keyword according to the extracted second type keyword and the preset weight corresponding to the extracted second type keyword.
  • the confirmation module 50 is also used to determine the origin information corresponding to the reimbursement project name according to the reimbursement data if the target category associated with the reimbursement project name is the medical facility material charging category; the confirmation module 50 is also used to The origin information corresponding to the reimbursement project name confirms the standard project name corresponding to the origin information; the calculation module 60 is also used to calculate the similarity between the reimbursement project name and each standard project name corresponding to the origin information.
  • the determination module 20 is further used to determine the number of standard item codes corresponding to the reimbursement item code if there is a standard item code corresponding to the reimbursement item code in the preset standard reimbursement catalog table; the storage module 30 also If the number of standard item codes corresponding to the reimbursement item code is 1, the data corresponding to the reimbursement item code in the reimbursement data is stored; the sending module 70 is also used if the number of standard item codes corresponding to the reimbursement item code is multiple , The information to be confirmed is generated and sent to the server of the medical institution.
  • the recognition server 100 includes a communication module 10, a memory 20, and a processor 30.
  • the processor 30 is respectively connected to the memory 20 and the communication module 10.
  • the memory 20 stores a computer
  • the instruction reading program when the computer readable instruction program is executed by the processor 20, implements the steps of the above reimbursement data checking method.
  • the present application also proposes a storage medium on which computer-readable instruction programs are stored.
  • the computer-readable storage medium may be a non-volatile readable storage medium.
  • the methods in the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware, but in many cases the former is better Implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or part that contributes to the existing technology, and the computer software product is stored in a storage medium (such as ROM/RAM as described above) , Magnetic disk, optical disk), including several instructions to make a terminal device (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to perform the method described in each embodiment of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Computational Linguistics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Finance (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Accounting & Taxation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Technology Law (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本申请公开了一种报销数据的排查方法、识别服务端及存储介质,该方法包括步骤:接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;若预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则存储所述报销数据中与所述报销项目编码相对应的数据;若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联。本申请基于神经网络能方便快速找到录入报销数据中的错误。

Description

报销数据的排查方法、识别服务端及存储介质
本申请要求于2018年12月13日提交中国专利局、申请号为201811531035.2、发明名称为“报销数据的排查方法、识别服务端及存储介质”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
本申请涉及数据识别技术领域,尤其涉及报销数据的排查方法、识别服务端及存储介质。
背景技术
居民参加社会医疗保险(下文称为医保)以保障基本生活。现有的社会医疗保险运行规则中,医疗机构需要将患者产生的医疗药品或服务明细上传至医保审核系统,进行统一报销处理。现有技术中,以药品目录、诊疗目录、医疗服务设施范围和支付标准目录为标准,对于目录中包含的医疗项目进行报销。在医疗机构上传报销数据过程中,医疗机构有意或无意地将一部分目录外医疗项目上传至审核系统进行报销,工作人员需要对大量的报销数据进行排查,以分析识别不在目录内的医疗项目,这样需要消耗大量人力,而且容易导致恶意医疗机构上传异样数据识别不全面。
发明内容
本申请的主要目的在于提供一种报销数据的排查方法、识别服务端及存储介质,旨在解决由于医保报销数据巨大,人工核查医疗费用异常的工作量大的技术问题。
为实现上述目的,本申请提供一种报销数据的排查方法,包括步骤:
接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;
判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
在所述标准化字段中查找与预设关键字相对应的待导入信息;
将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据;
若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联。
此外,为实现上述目的,本申请还提供一种识别服务端,包括:
接收模块,所述接收模块用于接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;
判断模块,所述判断模块用于判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
存储模块,所述存储模块用于若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则存储所述报销数据中与所述报销项目编码相对应的数据;
标识模块,所述标识模块用于若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联;
存储模块包括:
清洗单元,所述清洗单元用于若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
查找单元,所述查找单元用于在所述标准化字段中查找与预设关键字相对应的待导入信息;
导入单元,所述导入单元用于将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据。
此外,为实现上述目的,本申请还提供一种识别服务端,所述识别服务端包括:通信模块、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程序,所述计算机可读指令程序被所述处理器执行时实现如上所述的报销数据的排查方法的步骤。
此外,为实现上述目的,本申请还提供一种存储介质,所述存储介质上存储有计算机可读指令程序,所述计算机可读指令程序被处理器执行时实现如上所述的报销数据的排查方法的步骤。
本申请提出的一种报销数据的排查方法、识别服务端及存储介质,通过报销项目编码与预设标准报销目录表的标准项目编码匹配,从而避免各医疗机构针对医疗项目名称制定多样化,导致比对失败率高、计算量大的情况,提高比对正确率;通过本申请提供的报销数据的排查方法,使得进行核查的工作人员可仅对在预设标准报销目录表中存在标准项目编码对应的所述报销项目编码进行报销,减小核对工作量,避免医疗机构工作人员将非报销项目进行医保报销的情况。
附图说明
图1是本申请实施例方案涉及的硬件运行环境的结构示意图;
图2为本申请报销数据的排查方法第一实施例的流程示意图;
图3为本申请报销数据的排查方法第二实施例的流程示意图;
图4为本申请报销数据的排查方法第三实施例的流程示意图;
图5为本申请报销数据的排查方法第四实施例的流程示意图;
图6为本申请报销数据的排查方法第五实施例的流程示意图;
图7为本申请报销数据的排查方法第六实施例的流程示意图;
图8为本申请报销数据的排查方法第七实施例的流程示意图;
图9为本申请监控服务端的功能模块示意图。
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。
请参照图1,图1为本申请各个实施例中的监控服务端100的硬件结构示意图,监控服务端100可以是与参保人或医疗机构办理医疗费用报销的终端通信连接的服务器,也可以是与服务器以及办理医疗费用报销的终端通信连接的专用于数据监控的监控服务平台。本申请所提供的监控服务端100包括通信模块10、存储器20及处理器30等部件。其中,处理器30分别与存储器20和通信模块10连接,存储器20上存储有计算机可读指令程序,计算机可读指令程序同时被处理器30执行。
通信模块10,可通过网络与外部通讯设备连接。存储器20,可用于存储软件程序以及各种数据。处理器30,是监控服务端100的控制中心,利用各种接口和线路连接整个监控服务端100的各个部分,通过运行或执行存储在存储器20内的软件程序和/或模块,以及调用存储在存储器20内的数据,执行监控服务端100的各种功能和处理数据,从而对监控服务端100进行整体监控。本领域技术人员可以理解,图1中示出的监控服务端100结构并不构成对监控服务端100的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
基于上述硬件结构,提出本申请方法各个实施例。参照图2,在本申请报销数据的排查方法的第一实施例中,包括步骤:
步骤S100,接收医疗机构服务器发送的报销数据,并利用清洗模型对报销数据进行预处理,其中,报销数据包括报销项目编码;
具体地,医疗机构可以是进行疾病诊断、治疗的医院、疗养院、门诊部、诊所、卫生所以及急救站,医疗机构还可以是合法出售药品的药房。报销数据具体为针对就诊病患在医疗机构就诊或购药出具的可报销详单,具体包括就诊医疗机构的医疗机构标识、消费的可报销项目名称、报销项目编码、报销项目编码对应的实际单价、实际计价单位、报销比例等。报销项目为医疗机构为针对患者提供的药品、诊疗、医疗服务设施等可进行医保报销的项目。在医疗机构服务器上安装有应用软件,以使得医疗机构服务器定时或实时向监控服务端发送报销数据。监控服务端可以直接从自身存储器中获取应用软件上报的报销数据;当监控服务端是专用的监控服务平台时,可以向医疗机构服务器发送请求以获取报销数据,或由医疗机构服务器主动发送报销数据给监控服务平台。医疗机构服务器定时发送报销数据,也可以是医疗机构工作人员输入相关数据后,实时发送报销数据到监控服务端。报销数据具体包括预备进行报销的报销项目名称、对应的报销项目编码等,还可以包括剂型、和/或适用人群、和/或产地信息等。在本申请中,报销数据中预备进行报销医疗项目为报销项目。各地区卫生管理部门针对医疗项目名称制定了相应的标准项目编码与医疗项目编码对应,以区分各个医疗项目。
步骤S200,判断预设标准报销目录表中是否存在与报销项目编码对应的标准项目编码;
预设标准报销目录表为本领域技术人员使用预选设置好的模型,对医疗机构所在参保地区使用的药品目录、诊疗目录、医疗服务设施范围和支付标准目录等报销规则文件进行学习,以使得参保地区内可进行报销的报销项名称目、对应的报销项目编码、对应报销项目名称等全部收录于预设标准报销目录表中。
步骤S300,若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,则存储报销数据中与报销项目编码相对应的数据;
将预设标准报销目录表中的标准项目编码与报销项目编码进行一一比对,直至比对到与报销项目编码一致的标准项目编码,此时可认为预设标准报销目录表中存在与报销项目编码对应的标准项目编码,存储报销数据中与报销项目编码相对应的数据,以待工作人员操作后续的报销程序工作,根据该报销项目支付的费用和报销比例,向医疗机构或参保人支付报销费用。
具体地,步骤S300包括:
步骤S301,若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,则利用预设清洗模型对与报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
由于与报销项目编码相对应的数据为医务工作人员手动敲入或手动导出上传,不可避免的会出现拼写错误、漏输入、错输入等问题,通过预设清洗模型进行清洗,可减少该情况。预设清洗模型可以为噪声信道模型(Noisy Channel Model),具体可先与预设词典进行比对,以判断词汇本身是否为拼写错误,再通过计算最小编辑距离计算最相似的候选词汇集,通过训练完毕的语言模型计算各个候选词的先验概率P(w)和转移概率P(x|w),通过先验概率P(w)和转移概率P(x|w)的积,选取最相似的候选词,将该候选词替换拼写错误词汇,完成清洗处理。
步骤S302,在标准化字段中查找与预设关键字相对应的待导入信息;
预设关键词为本领域技术人员根据报销需求预先设置词汇,例如:支付账单、数量、时间等。
步骤S303,将待导入信息存储于与预设关键字对应的表单中,以存储报销数据中与报销项目编码相对应的数据;
预先设置多个表单,分别与预设关键字对应,当然也可以多个预设关键字对应一个表单。调取或将报销数据发往对应审核部门时,将多个表单发送即可,有利于文件处理规范化、提高工作效率。
步骤S400,若预设标准报销目录表中不存在与报销项目编码对应的标准项目编码,则设置录入错误标识与报销项目编码关联。
将预设标准报销目录表中的标准项目编码与报销项目编码进行一一比对,直至报销项目编码与所有标准项目编码比对完毕,未得到与报销项目编码一致的标准项目编码,此时可认为预设标准报销目录表中不存在与报销项目编码对应的标准项目编码,设置录入错误标识与报销项目编码关联,以使得工作人员可直接对设置有录入错误标识的报销项目编码不进行报销审核工作,减少工作量,医疗机构录入人员也可根据错误标识进行改正。通过报销项目编码与预设标准报销目录表的标准项目编码匹配,从而避免各医疗机构针对医疗项目名称制定多样化,导致比对失败率高、计算量大的情况,提高比对正确率;通过本申请提供的报销数据的排查方法,使得进行核查的工作人员可仅对在预设标准报销目录表中存在标准项目编码对应的报销项目编码进行报销,减小核对工作量,避免医疗机构工作人员将非报销项目进行医保报销的情况。
参照图3,在本申请报销数据的排查方法的第二实施例中,报销数据包括与报销项目编码对应的报销项目名称;步骤S400之后,包括:
步骤S500,根据报销数据确定报销项目编码对应的报销项目名称;
报销项目名称为与报销项目编码对应的文字名,在本实施例中,为中文或英文文字组成的名称,例如:葡萄糖、重组人凝血因子Ⅶa、镓[67Ga]枸橼酸盐等。
步骤S600,通过预设规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;
在本实施例中,本领域技术人员可根据实际情况,设定所需的预设规则。例如:设置包括多个字段的干扰字库,将报销项目名称中与干扰字库内的字段匹配的部分删除,对报销项目名称进行过滤。将报销项目名称与各个标准项目名称通过神经网络算法、或者余弦相识度算法等相似度算法计算相似度。当采用神经网络算法计算相似度时,预先对参保地区实行的报销规则进行学习,建立识别模型。在考虑词本身、语义距离的要求下,对标准项目名称进行分词,并建立词词典;设置训练文本,对训练文本进行分词并得到词向量文件,根据词词典对词向量文件进行筛选,仅保留词词典中存在词的词向量,并存入词向量矩阵文本中;将词向量矩阵文本作为循环神经网络模型输入,进行识别模型的训练,即建立识别模型。计算相似度时,使用词词典将报销项目名称进行分词,通过识别模型计算相似度,从而将医疗机构上传的不规则报销项目名称与相似的标准项目名称对应。
步骤S700,判断报销项目名称与各个标准项目名称的相似度是否大于第一预设阈值;
本领域技术人员根据需要设置第一预设阈值,将报销项目名称与各个标准项目名称的相似度与第一预设阈值一一进行比较。若存在一个或多个相似度与第一预设阈值,则将大于第一预设阈值的相似度对应的标准项目名称存储,执行步骤S800;若没有一个相似度大于第一预设阈值,则执行步骤S900。
步骤S800,若存在至少一项标准项目名称与报销项目名称的相似度大于第一预设阈值,则生成待确认信息并发送至医疗机构服务器,待确认信息包括与报销项目名称相似度大于第一预设阈值的标准项目名称;
若存在至少一项标准项目名称与报销项目名称的相似度大于第一预设阈值,证明大于第一预设阈值的相似度对应的标准项目名称最可能是报销项目名称对应的标准项目名称,生成包含该标准项目名称的待确认信息并发送至医疗机构服务器,以使得医疗机构工作人员可根据待确认信息的提示,将原报销项目名称或原报销项目表标识修改为符合三目录审核规则的名称或标识。
步骤S900,若标准项目名称与各个报销项目名称的相似度小于或等于第一预设阈值,则生成待修改信息并发送至医疗机构服务器。
若标准项目名称与各个报销项目名称的相似度小于或等于第一预设阈值,证明根据预设规则计算得到相似度,得不到一个与报销项目名称最为相似的标准项目名称,生成待修改信息并发送至医疗机构服务器,以使得医疗机构工作人员在无相关名称提示下,自行修改或做出解释说明。待修改信息与待确认信息不同之处在于,待修改信息不包含与报销项目名称相似度大于第一预设阈值的标准项目名称,即医疗机构工作人员在无相关名称提示下,自行修改或做出解释说明。
参照图4,在本申请报销数据的排查方法的第三实施例中,报销数据包括与报销项目名称对应的收费类别;步骤S600包括:
步骤S610,根据报销数据确定报销项目名称对应的收费类别;
具体地,在本实施例中,收费类别包括:西药费、中成药、中草药、化验费、手术费、治疗费、检查费、护理费、材料费等。本领域技术人员,也可根据参保地区医保报销规则自行设定。
步骤S620,根据预设类别体系、收费类别对报销项目名称进行分类,预设类别体系包括与收费类别相对应的目标类,目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;
预设类别体系为本领域技术人员根据参保地区医保报销规则进行设定。在本实施例中,预设类别体系包括药品收费类、诊疗项目收费类和医疗设施材料收费类三个目标类,与现行基本医疗保险药品目录、诊疗项目目录、医疗服务设施标准对应,其中,西药费、中成药和中草药对应药品收费类;化验费、手术费、治疗费、检查费、护理费对应诊疗项目收费类;材料费对应医疗设施材料收费类。
步骤S630,将目标类和对应的报销项目名称进行关联存储,并判断与报销项目名称关联的目标类类型;
根据报销项目名称对应的收费类别与预设类别体系的各个目标类对应,将对应的目标类和报销项目名称关联,并存储在存储器中,以待后续步骤调用。
步骤S640,若报销项目名称关联的目标类为药品收费类,则根据预设药品分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;
步骤S650,若报销项目名称关联的目标类为诊疗项目收费类,则根据预设诊疗项目分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;
步骤S660,若报销项目名称关联的目标类为医疗设施材料收费类,则根据预设医疗设施材料分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度。
由于《基本医疗保险药品目录》、《诊疗项目目录》、《医疗设施材料目录》内限定了不同性质的医疗收费项目,所以各目标类关联的标准项目名称的命名具有一定的规则性。将报销项目名称先区分至各个目标类,再进行相似度计算,减小计算的工作量;采用不同的目标类对应的计算规则,使得计算得到的相似度准确性高。
参照图5,在本申请报销数据的排查方法的第四实施例中,步骤640包括:
步骤641,若报销项目名称关联的目标类为药品收费类,则根据预设第一类关键词组对报销项目名称进行第一类关键词提取;
具体地,预设第一类关键词组包括基础有机物、基础无机物、基础中草药等,例如:氯化钠、乙二醇等基础无机物等;葡萄糖、赖氨酸等基础有机物等;党参、枸杞等基础中草药。
步骤642,根据提取的第一类关键词,确定与报销项目名称含有相同第一类关键词的标准项目名称;
步骤643,计算报销项目名称与各含有相同第一类关键词的标准项目名称的相似度。
例如:报销项目名称为“聚乙二醇”,根据预设第一类关键词组对“聚乙二醇”提取关键字,提取得到乙二醇,确定含有乙二醇的标准项目名称有多种。再通过神经网络算法计算“聚乙二醇”与上述多种标准项目名称的相似度。若报销项目名称中同时提取到多个第一关键字,则根据各个第一关键字的权重计算报销项目名称与多个第一关键字对应的标准项目名称的相似度。通过设置第一关键字,从而可计算报销项目名称与各含有相同第一类关键词的标准项目名称的相似度,提高正确性。
参照图6,在本申请报销数据的排查方法的第五实施例中,步骤S650包括:
步骤S651,若报销项目名称关联的目标类为诊疗项目收费类,根据预设第二类关键词组对报销项目名称进行关键词提取;
具体地,第二类关键词组可以包括作用部位、诊疗手段、病症等,例如:角膜、肾、肠等作用部位;手术、测定、资料、修补、切断、整复等诊疗手段;肿瘤、结石、瘘等病症。
步骤S652,根据提取的第二类关键词和提取的第二类关键词对应的预设权重计算报销项目名称与具有相同第二类关键词的标准项目名称的相似度。
优选地,作用部位对应的预设权重大于病症、诊疗手段。例如:医疗机构上传的报销数据中含有“股动脉探查术”,提取第二类关键词包括“股动脉”和“探查术”,股动脉对应的预设权重为90%,探查术对应的预设权重为50%,则计算“股动脉探查术”与各个含有“股动脉”的标准项目名称的相识度,再乘以对应预设权重;计算“股动脉探查术”与各个含有“探查术”的标准项目名称的相识度,再乘以对应预设权重,两者相加得到“股动脉探查术”与各个标准项目名称的相识度。由于诊疗项目的命名通常采用作用部位、诊疗手段相结合的方式命名,通过引入权重概念,使得计算的相识度准确率更高。
参照图7,在本申请报销数据的排查方法的第六实施例中,报销数据还包括与报销项目名称对应的产地信息;步骤S660,包括:
步骤S661,根据报销数据确定报销项目名称对应的产地信息;
步骤S662,根据产地信息,确认与报销项目名称相对应的预设产地目录,预设产地目录包括具有相同产地信息的标准项目名称;
具体地,产地信息包括国产和进口。预设产地目录为预先根据标准项目名称对应的产地信息进行划分的目录。
步骤S663,计算报销项目名称与预设产地目录中各个标准项目名称的相似度。
将报销项目名称与预设产地目录中各个标准项目名称通过神经网络算法、或者余弦相识度算法等相似度算法计算相似度。例如:产地信息为“国产”的人工肘关节,根据产地信息,确认人工肘关节相对应的预设产地目录,在该预设产地目录中设置有多个产地信息为国产的标准项目名称;将人工肘关节与预设产地目录中各个标准项目名称计算相似度,得到与“人工肘关节(国产)”相似度为0.9。
参照图8,在本申请报销数据的排查方法的第七实施例中,步骤S300包括:
步骤S310,若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,判断与报销项目编码对应的标准项目编码数量;
计算与报销项目编码对应的标准项目编码的数量,并进行判断。
步骤S320,若与报销项目编码对应的标准项目编码数量为1,则存储报销数据中与报销项目编码相对应的数据;
若与报销项目编码对应的标准项目编码数量为1,证明报销项目编码仅对应预设标准报销目录表唯一的标准项目编码,从而可进行进一步费用报销。
步骤S330,若与报销项目编码对应的标准项目编码数量为多个,则生成待确认信息并发送至医疗机构服务器。
若与报销项目编码对应的标准项目编码数量为多个,证明报销项目编码对应预设标准报销目录表种多个的标准项目编码,即有可能是医疗机构工作人员录入错误或标识位数录入错误等。生成待确认息中包含与报销项目编码对应的标准项目编码并发送至医疗机构服务器,以使医疗机构工作人员作出进一步修改。进一步地,步骤S330后执行步骤S301。
参见图9,本申请还提供一种识别服务端,包括:
接收模块10,接收模块10用于接收医疗机构服务器发送的报销数据,其中,报销数据包括报销项目编码;
判断模块20,判断模块20用于判断预设标准报销目录表中是否存在与报销项目编码对应的标准项目编码;
存储模块30,存储模块30用于若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,则存储报销数据中与报销项目编码相对应的数据;
标识模块40,标识模块40用于若预设标准报销目录表中不存在与报销项目编码对应的标准项目编码,则设置录入错误标识与报销项目编码关联;
存储模块包括:
清洗单元,清洗单元用于若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,则利用预设清洗模型对与报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
查找单元,查找单元用于在标准化字段中查找与预设关键字相对应的待导入信息;
导入单元,导入单元用于将待导入信息存储于与预设关键字对应的表单中,以存储报销数据中与报销项目编码相对应的数据。
进一步地,在一实施例中,报销数据包括与报销项目编码对应的报销项目名称;是识别服务端包括确认模块50,确认模块50用于根据报销数据确定报销项目编码对应的报销项目名称;计算模块60,计算模块60用于通过预设规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;判断模块20还用于判断报销项目名称与各个标准项目名称的相似度是否大于第一预设阈值;是识别服务端还包括发送模块70,发送模块70用于若存在至少一项标准项目名称与报销项目名称的相似度大于第一预设阈值,则生成待确认信息并发送至医疗机构服务器,待确认信息包括与报销项目名称相似度大于第一预设阈值的标准项目名称;发送模块70还用于若标准项目名称与各个报销项目名称的相似度均小于或等于第一预设阈值,则生成待修改信息并发送至医疗机构服务器。
进一步地,在一实施例中,报销数据包括与报销项目名称对应的收费类别;通过预设规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度的步骤,包括:确认模块50还用于根据报销数据确定报销项目名称对应的收费类别;确认模块50还用于根据预设类别体系、收费类别对报销项目名称进行分类,预设类别体系包括与收费类别相对应的目标类,目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;存储模块30还用于将目标类和对应的报销项目名称进行关联存储,并判断与报销项目名称关联的目标类类型;若报销项目名称关联的目标类为药品收费类,则根据预设药品分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;计算模块60还用于若报销项目名称关联的目标类为诊疗项目收费类,则根据预设诊疗项目分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度;计算模块60还用于若报销项目名称关联的目标类为医疗设施材料收费类,则根据预设医疗设施材料分类规则计算报销项目名称与预设标准报销目录表中各个标准项目名称的相似度。
进一步地,在一实施例中,识别服务端还包括提取模块80,提取模块80用于若报销项目名称关联的目标类为药品收费类,则根据预设第一类关键词组对报销项目名称进行第一类关键词提取;确认模块50还用于根据提取的第一类关键词,确定与报销项目名称含有相同第一类关键词的标准项目名称;计算模块60还用于计算报销项目名称与各含有相同第一类关键词的标准项目名称的相似度。
进一步地,在一实施例中,提取模块80还用于若报销项目名称关联的目标类为诊疗项目收费类,根据预设第二类关键词组对报销项目名称进行第二类关键词提取;计算模块60还用于根据提取的第二类关键词和提取的第二类关键词对应的预设权重计算报销项目名称与具有相同第二类关键词的标准项目名称的相似度。
进一步地,在一实施例中,确认模块50还用于若报销项目名称关联的目标类为医疗设施材料收费类,则根据报销数据确定报销项目名称对应的产地信息;确认模块50还用于根据报销项目名称对应的产地信息,确认产地信息对应的标准项目名称;计算模块60还用于计算报销项目名称与产地信息对应的各标准项目名称的相似度。
进一步地,在一实施例中,判断模块20还用于若预设标准报销目录表中存在与报销项目编码对应的标准项目编码,判断与报销项目编码对应的标准项目编码数量;存储模块30还用于若与报销项目编码对应的标准项目编码数量为1,则存储报销数据中与报销项目编码相对应的数据;发送模块70还用于若与报销项目编码对应的标准项目编码数量为多个,则生成待确认信息并发送至医疗机构服务器。
请再次结合图1,在一实施例中,识别服务端100包括通信模块10、存储器20及处理器30,其中,处理器30分别与存储器20和通信模块10连接,存储器20上存储有计算机可读指令程序,计算机可读指令程序被处理器20执行时实现如上的报销数据的排查方法的步骤。
本申请还提出一种存储介质,其上存储有计算机可读指令程序,计算机可读指令程序被处理器执行时实现如上述报销数据的排查方法的步骤。计算机可读存储介质可以为非易失性可读存储介质。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在如上所述的一个存储介质(如ROM/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。

Claims (20)

  1. 一种报销数据的排查方法,其特征在于,包括步骤:
    接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;
    判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
    若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
    在所述标准化字段中查找与预设关键字相对应的待导入信息;
    将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据;
    若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联。
  2. 如权利要求1所述的报销数据的排查方法,其特征在于,所述报销数据包括与所述报销项目编码对应的报销项目名称;所述若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联的步骤之后,包括:
    根据所述报销数据确定所述报销项目编码对应的报销项目名称;
    通过预设规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    判断所述报销项目名称与各个所述标准项目名称的相似度是否大于第一预设阈值;
    若存在至少一项所述标准项目名称与所述报销项目名称的相似度大于所述第一预设阈值,则生成待确认信息并发送至所述医疗机构服务器,所述待确认信息包括与所述报销项目名称相似度大于所述第一预设阈值的标准项目名称;
    若所述标准项目名称与各个所述报销项目名称的相似度均小于或等于所述第一预设阈值,则生成待修改信息并发送至所述医疗机构服务器。
  3. 如权利要求2所述的报销数据的排查方法,其特征在于,所述报销数据包括与所述报销项目名称对应的收费类别;所述通过预设规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度的步骤,包括:
    根据所述报销数据确定所述报销项目名称对应的所述收费类别;
    根据预设类别体系、所述收费类别对所述报销项目名称进行分类,所述预设类别体系包括与所述收费类别相对应的目标类,所述目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;
    将所述目标类和对应的所述报销项目名称进行关联存储,并判断与所述报销项目名称关联的目标类类型;
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设药品分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,则根据预设诊疗项目分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类,则根据预设医疗设施材料分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度。
  4. 如权利要求3所述的报销数据的排查方法,其特征在于,所述若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设药品分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度的步骤包括:
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设第一类关键词组对所述报销项目名称进行第一类关键词提取;
    根据提取的第一类关键词,确定与所述报销项目名称含有相同所述第一类关键词的标准项目名称;
    计算所述报销项目名称与各所述含有相同第一类关键词的标准项目名称的相似度。
  5. 如权利要求3所述的报销数据的排查方法,其特征在于,所述若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,则根据预设诊疗项目分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度的步骤包括:
    若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,根据预设第二类关键词组对所述报销项目名称进行第二类关键词提取;
    根据提取的第二类关键词和所述提取的第二类关键词对应的预设权重计算所述报销项目名称与所述具有相同第二类关键词的标准项目名称的相似度。
  6. 如权利要求3所述的报销数据的排查方法,其特征在于,所述报销数据还包括与所述报销项目名称对应的产地信息;所述若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类对应,则根据预设医疗设施材料分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度的步骤,包括:
    若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类,则根据所述报销数据确定所述报销项目名称对应的产地信息;
    根据所述报销项目名称对应的产地信息,确认所述产地信息对应的标准项目名称;
    计算所述报销项目名称与所述产地信息对应的各所述标准项目名称的相似度。
  7. 如权利要求2所述的报销数据的排查方法,其特征在于,所述接收医疗机构服务器发送的报销数据的步骤之后,还包括:
    若预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,判断与所述报销项目编码对应的所述标准项目编码数量;
    若与所述报销项目编码对应的所述标准项目编码数量为1,则存储所述报销数据中与所述报销项目编码相对应的数据;
    若与所述报销项目编码对应的所述标准项目编码数量为多个,则生成待确认信息并发送至所述医疗机构服务器。
  8. 一种识别服务端,其特征在于,包括:
    接收模块,所述接收模块用于接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;
    判断模块,所述判断模块用于判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
    存储模块,所述存储模块用于若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则存储所述报销数据中与所述报销项目编码相对应的数据;
    标识模块,所述标识模块用于若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联;
    存储模块包括:
    清洗单元,所述清洗单元用于若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
    查找单元,所述查找单元用于在所述标准化字段中查找与预设关键字相对应的待导入信息;
    导入单元,所述导入单元用于将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据。
  9. 如权利要求8所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目编码对应的报销项目名称;所述识别服务端还包括:
    确认模块,所述确认模块用于根据所述报销数据确定所述报销项目编码对应的报销项目名称;
    计算模块,所述计算模块用于通过预设规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    所述判断模块还用于判断所述报销项目名称与各个所述标准项目名称的相似度是否大于第一预设阈值;
    所述是识别服务端还包括发送模块,所述发送模块用于若存在至少一项所述标准项目名称与所述报销项目名称的相似度大于所述第一预设阈值,则生成待确认信息并发送至所述医疗机构服务器,所述待确认信息包括与所述报销项目名称相似度大于所述第一预设阈值的标准项目名称;
    若所述标准项目名称与各个所述报销项目名称的相似度均小于或等于所述第一预设阈值,则生成待修改信息并发送至所述医疗机构服务器。
  10. 如权利要求8所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目名称对应的收费类别;所述确认模块还用于根据所述报销数据确定所述报销项目名称对应的所述收费类别;
    根据预设类别体系、所述收费类别对所述报销项目名称进行分类,所述预设类别体系包括与所述收费类别相对应的目标类,所述目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;
    所述存储模块还用于将所述目标类和对应的所述报销项目名称进行关联存储,并判断与所述报销项目名称关联的目标类类型;
    所述计算模块还用于若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设药品分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,则根据预设诊疗项目分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类,则根据预设医疗设施材料分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度。
  11. 如权利要求10所述的识别服务端,其特征在于,所述识别服务端还包括:
    提取模块,所述提取模块用于若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设第一类关键词组对所述报销项目名称进行第一类关键词提取;
    所述确认模块还用于根据提取的第一类关键词,确定与所述报销项目名称含有相同所述第一类关键词的标准项目名称;
    所述计算模块还用于计算所述报销项目名称与各所述含有相同第一类关键词的标准项目名称的相似度。
  12. 如权利要求10所述的识别服务端,其特征在于,所述提取模块还用于若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,根据预设第二类关键词组对所述报销项目名称进行第二类关键词提取;
    所述计算模块还用于根据提取的第二类关键词和所述提取的第二类关键词对应的预设权重计算所述报销项目名称与所述具有相同第二类关键词的标准项目名称的相似度。
  13. 一种识别服务端,其特征在于,所述识别服务端包括:通信模块、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程序,所述计算机可读指令程序被所述处理器执行时实现如下步骤:
    接收医疗机构服务器发送的报销数据,其中,所述报销数据包括报销项目编码;
    判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
    若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
    在所述标准化字段中查找与预设关键字相对应的待导入信息;
    将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据;
    若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联。
  14. 如权利要求13所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目编码对应的报销项目名称;所述计算机可读指令程序被所述处理器执行时实现如下步骤:
    根据所述报销数据确定所述报销项目编码对应的报销项目名称;
    通过预设规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    判断所述报销项目名称与各个所述标准项目名称的相似度是否大于第一预设阈值;
    若存在至少一项所述标准项目名称与所述报销项目名称的相似度大于所述第一预设阈值,则生成待确认信息并发送至所述医疗机构服务器,所述待确认信息包括与所述报销项目名称相似度大于所述第一预设阈值的标准项目名称;
    若所述标准项目名称与各个所述报销项目名称的相似度均小于或等于所述第一预设阈值,则生成待修改信息并发送至所述医疗机构服务器。
  15. 如权利要求14所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目名称对应的收费类别;所述计算机可读指令程序被所述处理器执行时实现如下步骤:
    根据所述报销数据确定所述报销项目名称对应的所述收费类别;
    根据预设类别体系、所述收费类别对所述报销项目名称进行分类,所述预设类别体系包括与所述收费类别相对应的目标类,所述目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;
    将所述目标类和对应的所述报销项目名称进行关联存储,并判断与所述报销项目名称关联的目标类类型;
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设药品分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,则根据预设诊疗项目分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类,则根据预设医疗设施材料分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度。
  16. 如权利要求14所述的识别服务端,其特征在于,所述计算机可读指令程序被所述处理器执行时实现如下步骤:
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设第一类关键词组对所述报销项目名称进行第一类关键词提取;
    根据提取的第一类关键词,确定与所述报销项目名称含有相同所述第一类关键词的标准项目名称;
    计算所述报销项目名称与各所述含有相同第一类关键词的标准项目名称的相似度。
  17. 一种存储介质,其特征在于,所述存储介质上存储有计算机可读指令程序,所述计算机可读指令程序被处理器执行时实现如下所述的报销数据的排查方法的步骤:
    接收医疗机构服务器发送的报销数据,并利用清洗模型对所述报销数据进行预处理,其中,所述报销数据包括报销项目编码和与所述报销项目编码对应的报销项目名称;
    判断预设标准报销目录表中是否存在与所述报销项目编码对应的标准项目编码;
    若所述预设标准报销目录表中存在与所述报销项目编码对应的标准项目编码,则利用预设清洗模型对与所述报销项目编码相对应的数据进行清洗处理,以得到对应的标准化字段;
    在所述标准化字段中查找与预设关键字相对应的待导入信息;
    将所述待导入信息存储于与所述预设关键字对应的表单中,以存储所述报销数据中与所述报销项目编码相对应的数据;
    若预设标准报销目录表中不存在与所述报销项目编码对应的标准项目编码,则设置录入错误标识与所述报销项目编码关联。
  18. 如权利要求17所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目编码对应的报销项目名称;所述计算机可读指令程序被处理器执行时实现如下所述的报销数据的排查方法的步骤:
    根据所述报销数据确定所述报销项目编码对应的报销项目名称;
    通过预设规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    判断所述报销项目名称与各个所述标准项目名称的相似度是否大于第一预设阈值;
    若存在至少一项所述标准项目名称与所述报销项目名称的相似度大于所述第一预设阈值,则生成待确认信息并发送至所述医疗机构服务器,所述待确认信息包括与所述报销项目名称相似度大于所述第一预设阈值的标准项目名称;
    若所述标准项目名称与各个所述报销项目名称的相似度均小于或等于所述第一预设阈值,则生成待修改信息并发送至所述医疗机构服务器。
  19. 如权利要求18所述的识别服务端,其特征在于,所述报销数据包括与所述报销项目名称对应的收费类别;所述计算机可读指令程序被处理器执行时实现如下所述的报销数据的排查方法的步骤:
    根据所述报销数据确定所述报销项目名称对应的所述收费类别;
    根据预设类别体系、所述收费类别对所述报销项目名称进行分类,所述预设类别体系包括与所述收费类别相对应的目标类,所述目标类包括药品收费类、诊疗项目收费类和医疗设施材料收费类;
    将所述目标类和对应的所述报销项目名称进行关联存储,并判断与所述报销项目名称关联的目标类类型;
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设药品分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述诊疗项目收费类,则根据预设诊疗项目分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度;
    若所述报销项目名称关联的所述目标类为所述医疗设施材料收费类,则根据预设医疗设施材料分类规则计算所述报销项目名称与所述预设标准报销目录表中各个标准项目名称的相似度。
  20. 如权利要求18所述的识别服务端,其特征在于,所述计算机可读指令程序被处理器执行时实现如下所述的报销数据的排查方法的步骤:
    若所述报销项目名称关联的所述目标类为所述药品收费类,则根据预设第一类关键词组对所述报销项目名称进行第一类关键词提取;
    根据提取的第一类关键词,确定与所述报销项目名称含有相同所述第一类关键词的标准项目名称;
    计算所述报销项目名称与各所述含有相同第一类关键词的标准项目名称的相似度。
PCT/CN2019/102432 2018-12-13 2019-08-26 报销数据的排查方法、识别服务端及存储介质 WO2020119176A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811531035.2 2018-12-13
CN201811531035.2A CN109670173B (zh) 2018-12-13 2018-12-13 报销数据的排查方法、识别服务端及存储介质

Publications (1)

Publication Number Publication Date
WO2020119176A1 true WO2020119176A1 (zh) 2020-06-18

Family

ID=66145174

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/102432 WO2020119176A1 (zh) 2018-12-13 2019-08-26 报销数据的排查方法、识别服务端及存储介质

Country Status (2)

Country Link
CN (1) CN109670173B (zh)
WO (1) WO2020119176A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112035618A (zh) * 2020-08-31 2020-12-04 平安医疗健康管理股份有限公司 医疗费用分析方法、装置、计算机设备及存储介质
CN112035616A (zh) * 2020-08-31 2020-12-04 平安医疗健康管理股份有限公司 基于bert模型和规则的医保数据对码方法、装置及设备
CN113239811A (zh) * 2021-05-17 2021-08-10 上海中通吉网络技术有限公司 确定报销单中导入的电子发票对应的费用类型的方法
CN113468205A (zh) * 2021-06-29 2021-10-01 杭州每刻科技有限公司 一种自定义费用校验方法和系统
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
CN116759099A (zh) * 2023-08-21 2023-09-15 潍坊医学院 一种医保基金审核系统数据处理方法、装置及设备

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109670173B (zh) * 2018-12-13 2023-02-03 平安医疗健康管理股份有限公司 报销数据的排查方法、识别服务端及存储介质
CN110517050A (zh) * 2019-08-12 2019-11-29 太平洋医疗健康管理有限公司 一种医保反欺诈串换编码挖掘系统及方法
CN111079424A (zh) * 2019-11-15 2020-04-28 泰康保险集团股份有限公司 一种信息审核方法和装置
CN111311422A (zh) * 2020-01-22 2020-06-19 泰康保险集团股份有限公司 理赔数据处理方法、装置、设备及存储介质
CN111950985B (zh) * 2020-08-18 2024-05-07 山东泰和建设管理有限公司 成本控制方法、装置、计算机设备及存储介质
CN112668641B (zh) * 2020-12-28 2024-05-10 平安科技(深圳)有限公司 外部医用材料目录的匹配方法、装置、设备及存储介质
CN113723071B (zh) * 2021-08-31 2023-05-09 重庆富民银行股份有限公司 电子档案校验方法、系统、存储介质及设备
CN115587896B (zh) * 2022-10-13 2023-08-11 星宠王国(北京)科技有限公司 一种犬只医保数据处理方法、装置及设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104134092A (zh) * 2014-08-08 2014-11-05 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
CN104182824A (zh) * 2014-08-08 2014-12-03 平安养老保险股份有限公司 一种识别医保报销违规行为的规则校验系统及校验方法
CN107451401A (zh) * 2017-07-11 2017-12-08 武汉金豆医疗数据科技有限公司 一种医保智能审核方法和系统
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
CN107895593A (zh) * 2017-10-27 2018-04-10 深圳市健康易信息科技有限公司 数据处理方法及相关产品
CN109670173A (zh) * 2018-12-13 2019-04-23 平安医疗健康管理股份有限公司 报销数据的排查方法、识别服务端及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6360423B2 (ja) * 2014-10-31 2018-07-18 株式会社ヴィンテージ 診療報酬加算確認サーバ、診療報酬加算確認方法及び診療報酬加算確認サーバ用プログラム
CN107273709A (zh) * 2017-07-31 2017-10-20 惠州市格农科技有限公司 基于计算机的医院病人资料处理方法
CN108182972B (zh) * 2017-12-15 2021-07-20 中电科软件信息服务有限公司 基于分词网络的中文疾病诊断的智能编码方法及系统
CN108564991A (zh) * 2018-04-13 2018-09-21 重庆医科大学附属儿童医院 基于icd的数据化编码病历错误识别系统及其识别方法
CN108830352A (zh) * 2018-06-16 2018-11-16 深圳市前海安测信息技术有限公司 医保接口对码方法及计算机装置、可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104134092A (zh) * 2014-08-08 2014-11-05 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
CN104182824A (zh) * 2014-08-08 2014-12-03 平安养老保险股份有限公司 一种识别医保报销违规行为的规则校验系统及校验方法
CN107451401A (zh) * 2017-07-11 2017-12-08 武汉金豆医疗数据科技有限公司 一种医保智能审核方法和系统
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
CN107895593A (zh) * 2017-10-27 2018-04-10 深圳市健康易信息科技有限公司 数据处理方法及相关产品
CN109670173A (zh) * 2018-12-13 2019-04-23 平安医疗健康管理股份有限公司 报销数据的排查方法、识别服务端及存储介质

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112035618A (zh) * 2020-08-31 2020-12-04 平安医疗健康管理股份有限公司 医疗费用分析方法、装置、计算机设备及存储介质
CN112035616A (zh) * 2020-08-31 2020-12-04 平安医疗健康管理股份有限公司 基于bert模型和规则的医保数据对码方法、装置及设备
CN113239811A (zh) * 2021-05-17 2021-08-10 上海中通吉网络技术有限公司 确定报销单中导入的电子发票对应的费用类型的方法
CN113468205A (zh) * 2021-06-29 2021-10-01 杭州每刻科技有限公司 一种自定义费用校验方法和系统
CN113468205B (zh) * 2021-06-29 2023-09-12 杭州每刻科技有限公司 一种自定义费用校验方法和系统
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
CN116759099A (zh) * 2023-08-21 2023-09-15 潍坊医学院 一种医保基金审核系统数据处理方法、装置及设备

Also Published As

Publication number Publication date
CN109670173B (zh) 2023-02-03
CN109670173A (zh) 2019-04-23

Similar Documents

Publication Publication Date Title
WO2020119176A1 (zh) 报销数据的排查方法、识别服务端及存储介质
WO2020213843A1 (ko) 사용자 맞춤형 의료정보 제공 시스템 및 이의 구동방법
WO2020078053A1 (zh) 医疗数据异常检测方法、装置、设备及存储介质
WO2020119131A1 (zh) 用药方案异常的识别方法、装置、终端及可读存储介质
US7725479B2 (en) Unique person registry
WO2020119403A1 (zh) 住院数据异常检测方法、装置、设备及可读存储介质
WO2020119116A1 (zh) 基于数据分析的医保审核方法、装置、设备和存储介质
WO2020034526A1 (zh) 保险录音的质检方法、装置、设备和计算机存储介质
WO2020119401A1 (zh) 医师违规执业的监控方法、监控服务端及存储介质
WO2020107909A1 (zh) 异常就诊费用的判断方法、装置、设备及计算机存储介质
WO2022145782A2 (ko) 빅데이터 및 클라우드 시스템 기반 인공지능 응급의료 의사결정 및 응급환자 이송 시스템과 그 방법
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
WO2020087981A1 (zh) 风控审核模型生成方法、装置、设备及可读存储介质
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
WO2016165201A1 (zh) 基于网络医院的自助缴费方法和系统
WO2016190496A1 (ko) 의료용 메타 데이터베이스 관리 방법 및 그 장치
WO2019100595A1 (zh) 保险理赔案件互斥信息的确定方法及装置
WO2021051558A1 (zh) 基于知识图谱的问答方法、装置和存储介质
WO2016165177A1 (zh) 基于面部识别的网络医院自助缴费方法和系统
WO2020119175A1 (zh) 医疗费用异常的监控方法、监控服务端及存储介质
WO2020108111A1 (zh) 医保欺诈行为的识别方法、装置、设备及可读存储介质
WO2020062658A1 (zh) 合同生成方法、装置、设备及存储介质
WO2022035018A1 (ko) 클리닉 매니저 서비스 플랫폼 및 이를 제공하는 시스템
WO2021251558A1 (ko) 임상시험 검색을 위한 데이터 분류 장치, 시스템 및 방법
WO2020119118A1 (zh) 异常数据的处理方法、装置、设备及计算机可读存储介质

Legal Events

Date Code Title Description
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 1205A DATED 15.10.2021)

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

Ref document number: 19896391

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19896391

Country of ref document: EP

Kind code of ref document: A1