CN118349586A - Medical insurance catalog and bill item matching method - Google Patents
Medical insurance catalog and bill item matching method Download PDFInfo
- Publication number
- CN118349586A CN118349586A CN202410515840.5A CN202410515840A CN118349586A CN 118349586 A CN118349586 A CN 118349586A CN 202410515840 A CN202410515840 A CN 202410515840A CN 118349586 A CN118349586 A CN 118349586A
- Authority
- CN
- China
- Prior art keywords
- library
- matching
- bill
- medical insurance
- items
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2468—Fuzzy queries
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Technology Law (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for matching medical insurance catalogs and bill items, which comprises the following steps: constructing a general basic library and a special basic library through a natural language processing algorithm based on the national medical insurance catalog and the medical related data; collecting bill item data, and classifying the bill items into a medicine major class, a diagnosis major class and a consumable major class after cleaning the bill items through a general basic library; carrying out data cleaning on bill items in each major category through a special basic library, and carrying out matching on the bill items subjected to data cleaning in a medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog; by combining the validation algorithm rule and the natural language algorithm, the matching accuracy and the matching efficiency are greatly improved, and meanwhile, the labor cost is saved.
Description
Technical Field
The invention relates to a method for matching medical insurance catalogs and bill items, and belongs to the technical field of medical information.
Background
The matching of the medical insurance catalog and the bill items refers to the corresponding of the charging items in the medical insurance fund settlement list and the items in the medical insurance catalog so as to judge whether the charging items belong to the medical insurance reimbursement scope and whether the charging items meet the medical insurance policy requirements;
The medical insurance catalog refers to a list of medicines, diagnosis and treatment projects, materials and the like paid by the medical insurance fund, and is regularly formulated and updated by the national medical insurance bureau and the medical insurance departments in each place according to the development of medical technology and the running condition of the medical insurance fund; the medical insurance settlement list refers to a data list submitted when a medical insurance point medical institution applies for expense settlement to medical insurance departments after carrying out medical services such as hospitalization, outpatient service and the like, and comprises basic information of patients, diagnosis and treatment information, expense information and the like. Generating and reporting a medical insurance settlement list, wherein the medical information system of a medical institution and the medical insurance information system of a medical insurance department are required to carry out data interaction and verification; the matching and auditing of the medical insurance catalog and the bill items means that the medical insurance department automatically or manually matches and audits the charge items in the medical insurance settlement list through a medical insurance information system or a third party platform so as to determine whether the charge items belong to the range of the medical insurance catalog, meet the medical insurance policy requirements, whether the illegal conditions such as superscalar, supersrequency, overscope exist, and whether the processing such as deduction, refund, fine and the like is required.
The matching and auditing of the medical insurance catalog and the bill item are complex, tedious and professional work, a great amount of manpower, material resources and financial resources are required to be input by the medical insurance department, and the matching and auditing of the medical insurance department at present has problems such as non-uniform, opaque and inflexible matching rules, non-simplified auditing flow, non-standardization, non-intellectualization and the like, so that the matching and auditing of the medical insurance catalog and the bill item are low in efficiency, and the ageing of the medical insurance settlement and the satisfaction of patients are influenced;
at present, matching of medical insurance catalogs and bill items is mainly carried out in a manual matching or text similarity matching mode; the manual matching mode depends on the medical foundation of personnel, meanwhile, the manual processing is influenced by factors such as personal emotion and the like, errors can occur, and the manual processing efficiency is low; the text similarity algorithm matching mode is low in matching accuracy according to text similarity because similar characters (such as XXX, XX capsules and the like which are used once) are frequently found in medical knowledge of medicines, diagnosis and treatment, consumable materials and the like.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method for matching medical insurance catalogs and bill items.
The technical scheme of the invention is as follows:
In one aspect, the invention provides a method for matching medical insurance catalogs with bill items, which comprises the following steps:
based on nationwide medical insurance catalogs and medical related data, constructing a medical insurance catalogs library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library and a special name library through a natural language processing algorithm;
Collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill item through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill item into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
And respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog.
As a preferred embodiment of the invention, the general classification steps of the bill items are as follows:
respectively carrying out accurate matching on bill items in a medicine library, a diagnosis and treatment library and a consumable library, and returning a result;
If the accurate matching of the bill items fails, fuzzy matching is carried out through a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened through a TF-IDF algorithm, the fuzzy matching result and the bill items are converted into word vectors, finally the bill items are compared with each fuzzy matching result through a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a classification result.
As a preferred implementation mode of the invention, the specific matching steps of the large medicine bill items and the medical insurance catalogs are as follows:
Data cleaning is carried out on the large-class bill items of the medicines through a special medicine library, wherein the special medicine library comprises a dosage form library, an acid group library, a salt group library, a deletable name library and a trade name library;
accurately matching the large-class medicine bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the large-class medicine bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, a medicine confirmation algorithm trained on a dosage form library, an acid base library, a salt base library and a trade name library is used for confirming a fuzzy matching result, and the confirmed result is used as a medical insurance catalog matching result of the large-class bill item of the medicine;
If the medicine confirmation algorithm cannot confirm, screening keywords of each fuzzy matching result through the TF-IDF algorithm, converting the fuzzy matching result and the medicine large-class bill item into word vectors, and finally comparing the medicine large-class bill item with each fuzzy matching result through the cosine similarity algorithm, wherein the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the medicine large-class bill item.
As a preferred implementation mode of the invention, the specific matching steps of the diagnosis and treatment general bill item and the medical insurance catalog are as follows:
Carrying out data cleaning on the diagnosis and treatment large-class bill items through a diagnosis and treatment special library, wherein the diagnosis and treatment special library comprises a determination library and a chemical method library;
accurately matching the diagnosis and treatment large-class bill items after any data are cleaned in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the diagnosis and treatment large-class bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, diagnosis and treatment confirmation algorithm based on measurement library, chemical method library, bed Fei Ku and deletable name library training is used for confirming the fuzzy matching result, and the confirmation result is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item;
If the diagnosis and treatment confirmation algorithm cannot confirm, the key words of each fuzzy matching result are screened through the TF-IDF algorithm, the fuzzy matching result and the diagnosis and treatment large-class bill item are converted into word vectors, and finally the diagnosis and treatment large-class bill item and each fuzzy matching result are compared through the cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
As a preferred implementation mode of the invention, the specific matching steps of the consumable large-class bill item and the medical insurance catalog are as follows:
performing data cleaning on consumable large-class bill items through a consumable special library, wherein the consumable special library comprises a deletable name library;
accurately matching consumable large-class bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the consumable large-class bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened by a TF-IDF algorithm, the fuzzy matching result and the consumable large-class bill item are converted into word vectors, finally the consumable large-class bill item and each fuzzy matching result are compared by a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
As a preferred embodiment of the invention, bill items which cannot be matched are matched with the medical insurance catalog manually.
As a preferred implementation mode of the invention, a precise matching library is constructed and used for storing bill items which are successfully matched for the first time and corresponding items thereof in the medical insurance catalog, the bill items are precisely matched through the precise matching library before data cleaning, if the bill items are successfully matched, a matching result is returned as the matching result of the bill items and the medical insurance catalog, and if the matching is failed, the data cleaning is carried out.
On the other hand, the invention also provides a medical insurance catalog and bill item matching system, which is characterized by comprising a database construction module, a major matching module and a medical insurance catalog matching module;
the database construction module is used for constructing a medical insurance catalog library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library, a trade name library and a special name library through a natural language processing algorithm based on the nationwide medical insurance catalog and the medical related data;
The major-class matching module is used for collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill items through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill items into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
The medical insurance catalog matching module is used for respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog.
In yet another aspect, the present invention further provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method according to any of the embodiments of the present invention when executing the program.
In yet another aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method according to any of the embodiments of the present invention.
The invention has the following beneficial effects:
1. The invention adopts a mode of combining a machine learning algorithm and an algorithm rule, greatly improves the matching efficiency compared with manual matching, can finish the matching work of a large number of bill items in a short time, reduces the links of manual participation, reduces the labor cost and greatly improves the matching accuracy of colleagues.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flowchart of a base library formation process according to the present invention;
FIG. 3 is a flow chart of general classification of bill items according to the invention;
FIG. 4 is a flow chart of matching of the large-class bill items of the medicines;
FIG. 5 is a flow chart of matching of the diagnosis and treatment general bill items;
FIG. 6 is a flow chart of matching of consumable large-scale bill items according to the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Embodiment one:
referring to fig. 1, a method for matching a medical insurance catalog with a bill item includes the following steps:
referring to fig. 2, based on nationwide medical insurance catalogs and medical related data (specifically: medical insurance catalogs, medical websites, medical books and the like), constructing a medical insurance catalogs library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library and a special name library by combining a natural language processing algorithm with expert analysis;
Collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill item through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill item into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
And respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog.
As a preferred implementation of this embodiment, referring to fig. 3, the general classification steps of the ticket item are:
respectively carrying out accurate matching on bill items in a medicine library, a diagnosis and treatment library and a consumable library, and returning a result;
If the accurate matching of the bill item fails, fuzzy matching is carried out through a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened through a TF-IDF algorithm, the fuzzy matching result and the bill item are converted into Word vectors (Word 2 Vec), and finally the bill item and each fuzzy matching result are compared through a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a classification result.
As a preferred implementation manner of this embodiment, referring to fig. 4, the specific matching steps of the large medicine bill item and the medical insurance catalog are as follows:
The method comprises the steps of carrying out data cleaning on a large-scale medicine bill item through a special medicine library to obtain corresponding medicine trade names in the large-scale medicine bill item, wherein the special medicine library comprises a dosage form library, an acid base library, a salt base library, a deletable name library and a trade name library;
accurately matching the large-class medicine bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the large-class medicine bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, a medicine confirmation algorithm trained on a dosage form library, an acid base library, a salt base library and a trade name library is used for confirming a fuzzy matching result, and the confirmed result is used as a medical insurance catalog matching result of the large-class bill item of the medicine;
the medicine confirmation algorithm is obtained after big data training and professional medical staff evaluation;
If the medicine confirmation algorithm cannot confirm, screening keywords of each fuzzy matching result through the TF-IDF algorithm, converting the fuzzy matching result and the medicine large-class bill item into word vectors, and finally comparing the medicine large-class bill item with each fuzzy matching result through the cosine similarity algorithm, wherein the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the medicine large-class bill item.
As a preferred implementation manner of this embodiment, referring to fig. 5, the specific matching steps of the diagnosis and treatment general bill item and the medical insurance catalog are as follows:
Carrying out data cleaning on the diagnosis and treatment large-class bill items through a diagnosis and treatment special library, wherein the diagnosis and treatment special library comprises a measurement library, a chemical method library, a bed Fei Ku and a deletable name library;
accurately matching the diagnosis and treatment large-class bill items after any data are cleaned in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the diagnosis and treatment large-class bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, a diagnosis and treatment confirmation algorithm based on measurement library and chemical law library training is used for confirming a fuzzy matching result, and the confirmation result is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item;
the diagnosis and treatment confirmation algorithm is obtained after big data training and professional medical staff evaluation;
If the diagnosis and treatment confirmation algorithm cannot confirm, the key words of each fuzzy matching result are screened through the TF-IDF algorithm, the fuzzy matching result and the diagnosis and treatment large-class bill item are converted into word vectors, and finally the diagnosis and treatment large-class bill item and each fuzzy matching result are compared through the cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
As a preferred implementation manner of this embodiment, referring to fig. 6, the specific matching steps of the consumable large-class bill item and the medical insurance catalog are as follows:
performing data cleaning on consumable large-class bill items through a consumable special library, wherein the consumable special library comprises a deletable name library;
accurately matching consumable large-class bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the consumable large-class bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened by a TF-IDF algorithm, the fuzzy matching result and the consumable large-class bill item are converted into word vectors, finally the consumable large-class bill item and each fuzzy matching result are compared by a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
As a preferred implementation of the embodiment, bill items which cannot be matched are manually matched with the medical insurance catalog.
As a preferred implementation manner of the embodiment, an accurate matching library is constructed and used for storing bill items which are successfully matched for the first time and corresponding items thereof in the medical insurance catalog, the bill items are accurately matched through the accurate matching library before data cleaning, if the bill items are successfully matched, a matching result is returned as a matching result of the bill items and the medical insurance catalog, and if the matching is failed, the data cleaning is performed.
Embodiment two:
a medical insurance catalog and bill item matching system comprises a database construction module, a major class matching module and a medical insurance catalog matching module;
The database construction module is used for constructing a medical insurance catalog library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library and a special name library based on nationwide medical insurance catalog and medical related data through a natural language processing algorithm;
The major-class matching module is used for collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill items through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill items into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
The medical insurance catalog matching module is used for respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog;
The present embodiment is used to implement the functions in the first embodiment, and will not be described herein.
Embodiment III:
The present embodiment proposes an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing a method according to any of the embodiments of the invention when executing said program.
Embodiment four:
The present embodiment proposes a computer readable storage medium on which a computer program is stored, which when executed by a processor implements a method according to any of the embodiments of the invention.
In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relation of association objects, and indicates that there may be three kinds of relations, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.
Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in the embodiments disclosed herein can be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In several embodiments provided by the present application, any of the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (hereinafter referred to as ROM), a random access Memory (Random Access Memory hereinafter referred to as RAM), a magnetic disk, or an optical disk, etc., which can store program codes.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. The method for matching the medical insurance catalog with the bill items is characterized by comprising the following steps of:
based on nationwide medical insurance catalogs and medical related data, constructing a medical insurance catalogs library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library and a special name library through a natural language processing algorithm;
Collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill item through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill item into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
And respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog.
2. The method for matching a medical insurance directory to a bill item according to claim 1, wherein the step of classifying the bill item into a major class is as follows:
respectively carrying out accurate matching on bill items in a medicine library, a diagnosis and treatment library and a consumable library, and returning a result;
If the accurate matching of the bill items fails, fuzzy matching is carried out through a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened through a TF-IDF algorithm, the fuzzy matching result and the bill items are converted into word vectors, finally the bill items are compared with each fuzzy matching result through a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a classification result.
3. The method for matching medical insurance catalogs and bill items according to claim 1, wherein the specific matching steps of the medical insurance catalogs and the bill items of the medicine major class are as follows:
Data cleaning is carried out on the large-class bill items of the medicines through a special medicine library, wherein the special medicine library comprises a dosage form library, an acid group library, a salt group library, a deletable name library and a trade name library;
accurately matching the large-class medicine bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the large-class medicine bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, a medicine confirmation algorithm trained on a dosage form library, an acid base library, a salt base library and a trade name library is used for confirming a fuzzy matching result, and the confirmed result is used as a medical insurance catalog matching result of the large-class bill item of the medicine;
If the medicine confirmation algorithm cannot confirm, screening keywords of each fuzzy matching result through the TF-IDF algorithm, converting the fuzzy matching result and the medicine large-class bill item into word vectors, and finally comparing the medicine large-class bill item with each fuzzy matching result through the cosine similarity algorithm, wherein the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the medicine large-class bill item.
4. The method for matching medical insurance catalogs and bill items according to claim 1, wherein the specific matching steps of the medical insurance catalogs and the bill items of the diagnosis and treatment major category are as follows:
Carrying out data cleaning on the diagnosis and treatment large-class bill items through a diagnosis and treatment special library, wherein the diagnosis and treatment special library comprises a measurement library, a chemical method library, a bed Fei Ku and a deletable name library;
accurately matching the diagnosis and treatment large-class bill items after any data are cleaned in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the diagnosis and treatment large-class bill items;
if the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, diagnosis and treatment confirmation algorithm based on measurement library and chemical law library training is used for confirming the fuzzy matching result, and the confirmation result is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item;
If the diagnosis and treatment confirmation algorithm cannot confirm, the key words of each fuzzy matching result are screened through the TF-IDF algorithm, the fuzzy matching result and the diagnosis and treatment large-class bill item are converted into word vectors, and finally the diagnosis and treatment large-class bill item and each fuzzy matching result are compared through the cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
5. The method for matching medical insurance catalogs and bill items according to claim 1, wherein the specific matching steps of the consumable major bill items and the medical insurance catalogs are as follows:
Performing data cleaning on consumable large-class bill items through a consumable special library, wherein the consumable special library comprises a deletable name library;
accurately matching consumable large-class bill items after any data cleaning in a medical insurance catalog library, and returning a matching result as a medical insurance catalog matching result of the consumable large-class bill items;
If the accurate matching fails, fuzzy matching is carried out by using a fuzzy matching algorithm of an elastic search engine, keywords of each fuzzy matching result are screened by a TF-IDF algorithm, the fuzzy matching result and the consumable large-class bill item are converted into word vectors, finally the consumable large-class bill item and each fuzzy matching result are compared by a cosine similarity algorithm, and the fuzzy matching result with the highest similarity is used as a medical insurance catalog matching result of the diagnosis and treatment large-class bill item.
6. The method for matching a medical insurance directory with a bill item according to claim 1, wherein the bill item which cannot be matched is manually matched with the medical insurance directory.
7. The method for matching the medical insurance catalog with the bill items according to claim 1, wherein a precise matching library is constructed and used for storing the bill items which are successfully matched for the first time and the corresponding items in the medical insurance catalog, the bill items are precisely matched through the precise matching library before data cleaning, if the matching is successful, a matching result is returned as the matching result of the bill items and the medical insurance catalog, and if the matching is failed, the data cleaning is performed.
8. The medical insurance catalog and bill item matching system is characterized by comprising a database construction module, a major type matching module and a medical insurance catalog matching module;
the database construction module is used for constructing a medical insurance catalog library, a medicine library, a diagnosis and treatment library, a consumable library, a medicine special library, a diagnosis and treatment special library, a consumable special library, a special symbol library, a trade name library and a special name library through a natural language processing algorithm based on the nationwide medical insurance catalog and the medical related data;
The major-class matching module is used for collecting bill item data, cleaning the bill item data through a special symbol library and a special name library, respectively matching the bill items through a medicine library, a diagnosis and treatment library and a consumable library, and classifying the bill items into a medicine major class, a diagnosis and treatment major class and a consumable major class according to a matching result;
The medical insurance catalog matching module is used for respectively carrying out data cleaning on bill items in the corresponding major categories through the medicine special library, the diagnosis and treatment special library and the consumable special library, and then carrying out matching on the bill items subjected to data cleaning in the medical insurance catalog library to obtain a matching result of the corresponding bill items and the medical insurance catalog.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410515840.5A CN118349586A (en) | 2024-04-26 | 2024-04-26 | Medical insurance catalog and bill item matching method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410515840.5A CN118349586A (en) | 2024-04-26 | 2024-04-26 | Medical insurance catalog and bill item matching method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118349586A true CN118349586A (en) | 2024-07-16 |
Family
ID=91817267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410515840.5A Pending CN118349586A (en) | 2024-04-26 | 2024-04-26 | Medical insurance catalog and bill item matching method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118349586A (en) |
-
2024
- 2024-04-26 CN CN202410515840.5A patent/CN118349586A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9792324B2 (en) | Method and system for uniquely identifying a person to the exclusion of all others | |
| Gagolewski | Bibliometric impact assessment with R and the CITAN package | |
| US6772160B2 (en) | Techniques for facilitating information acquisition and storage | |
| KR100996131B1 (en) | Listing Management System and Methods | |
| US6741986B2 (en) | Method and system for performing information extraction and quality control for a knowledgebase | |
| Cheatham et al. | Conference v2. 0: An uncertain version of the oaei conference benchmark | |
| CN115115257B (en) | Enterprise risk early warning method and system based on relational graph | |
| Nikiforova | Open Data Quality Evaluation: A comparative analysis of open data in Latvia | |
| CN113657605B (en) | Document processor based on artificial intelligence AI | |
| CN117520503A (en) | Financial customer service dialogue generation method, device, equipment and medium based on LLM model | |
| US20200051172A1 (en) | Method and system for creating a legal casefile | |
| CN113610504A (en) | Data processing method and device, computer equipment and storage medium | |
| Klosterman | Data Science Projects with Python: A case study approach to successful data science projects using Python, pandas, and scikit-learn | |
| Owda et al. | Financial discussion boards irregularities detection system (fdbs-ids) using information extraction | |
| US11941064B1 (en) | Machine learning comparison of receipts and invoices | |
| Potin et al. | Foppa: A database of french open public procurement award notices | |
| US7831442B1 (en) | System and method for minimizing edits for medical insurance claims processing | |
| CN113077362A (en) | Method and device for processing regulation and regulation files | |
| CN118349586A (en) | Medical insurance catalog and bill item matching method | |
| CN116739602A (en) | Suspicious electronic bill prediction method based on multi-model fusion | |
| Gabor-Toth et al. | Linking Deutsche Bundesbank Company Data | |
| US20050216394A1 (en) | Computer-based system and method for confirming failed trades of securities | |
| JP2009134375A (en) | Financing examination support system and its method | |
| Sadula | Integrating Big Data Analytics with US SEC Financial Statement Datasets and the Critical Examination of the Altman Z’-Score Model | |
| Goldberg et al. | The FinCEN AI system: finding financial crimes in a large database of cash transactions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |