CN114037540A - Medical insurance fund supervision system and monitoring method thereof - Google Patents
Medical insurance fund supervision system and monitoring method thereof Download PDFInfo
- Publication number
- CN114037540A CN114037540A CN202111306471.1A CN202111306471A CN114037540A CN 114037540 A CN114037540 A CN 114037540A CN 202111306471 A CN202111306471 A CN 202111306471A CN 114037540 A CN114037540 A CN 114037540A
- Authority
- CN
- China
- Prior art keywords
- data
- medical insurance
- neural network
- knowledge
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 238000003062 neural network model Methods 0.000 claims abstract description 57
- 238000007726 management method Methods 0.000 claims abstract description 29
- 238000004140 cleaning Methods 0.000 claims abstract description 28
- 238000012550 audit Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000002708 enhancing effect Effects 0.000 claims abstract description 14
- 239000003814 drug Substances 0.000 claims description 48
- 229940079593 drug Drugs 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 13
- 238000003745 diagnosis Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 13
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000036541 health Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/258—Data format conversion from or to a database
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a medical insurance fund supervision system and a supervision method thereof, wherein the system comprises: the data acquisition module is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system; the scene monitoring module is used for shooting videos or images of patients in various scenes; the data processing module is used for cleaning the data related to the medical insurance reimbursement and enhancing the video or the image; the data supervision module is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image through a neural network model in the model base in combination with the knowledge base and the rule base; and the management module is used for storing the result of the audit judgment of the data supervision module so as to be inquired by the management personnel. The medical insurance fund supervision system can perform post supervision according to medical insurance reimbursement related data and can also monitor patient behaviors through scenes to achieve pre supervision, and supervision modes are more diverse.
Description
Technical Field
The invention relates to the technical field of medical insurance supervision, in particular to a medical insurance fund supervision system and a monitoring method thereof.
Background
At present, with the popularization and deep development of the career of "remote medical care of national medical insurance" and "internet + health medical care", each medical insurance department and medical insurance management institution urgently needs to develop a supervision system with higher intelligent degree to reduce the burden of insufficient manpower, fatigue and untimely mind. Meanwhile, the deepening of the aging problem of the population and the increasing demand of the masses on medical health services all put higher requirements on the health and steady development of medical insurance funds. At present, the existing medical insurance fund supervision system has a single supervision mode, generally takes post supervision as a main part, and cannot meet the increasing requirements of medical insurance supervision at present.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
The invention mainly aims to solve the technical problems that the existing medical insurance fund supervision system is single in supervision mode and cannot meet the increasing requirements of medical insurance supervision at present.
The invention provides a medical insurance fund supervision system in a first aspect, which comprises:
the data acquisition module is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system;
the scene monitoring module is used for capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital resident department and a hospital clinic department of the hospital in real time;
the data processing module is used for cleaning incomplete data, error data and repeated data in the medical insurance reimbursement related data;
the video and image processing module is used for performing definition enhancement on the video or the image;
the data supervision module is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image by combining a neural network model in a model base with a knowledge base and a rule base;
and the management module is used for storing the result of the audit judgment of the data supervision module so as to be inquired by managers.
In an optional implementation manner of the first aspect of the present invention, the data processing module includes:
the data selection unit is used for selecting required data to be processed from the medical insurance reimbursement related data;
the data cleaning unit is used for cleaning incomplete data, error data and repeated data in the data to be processed;
and the data conversion unit is used for carrying out format and type conversion on the cleaned data to be processed and the enhanced video or image to obtain the data to be audited which can be identified by the neural network model.
In an optional implementation manner of the first aspect of the present invention, the data supervision module includes:
the data storage unit is used for storing the data to be audited;
the knowledge base comprises limited qualitative medicine-identifying knowledge, limited age medicine-using knowledge, stepped medicine-using knowledge, medicine conflict knowledge and common medicine knowledge;
the rule base comprises payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules;
and the model base comprises a plurality of neural network models, and the neural network models are used for carrying out audit judgment on the data to be audited by combining the knowledge base and the rule base and outputting the result of the audit judgment.
In an optional implementation manner of the first aspect of the present invention, the management module includes: the system comprises an early warning display unit, an information inquiry unit, a statistical analysis unit, a rule management unit and a model management unit.
In an alternative embodiment of the first aspect of the present invention, the medical insurance reimbursement related data includes information of insurers, historical visit and medication information, drug catalog information and site specific medical institution information.
The invention provides a supervision method of a medical insurance fund supervision system in a second aspect, which comprises the following steps:
acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system, and cleaning incomplete data, error data and repeated data in the medical insurance reimbursement related data;
or capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital department and a hospital department of the hospital, and enhancing the videos or the images;
selecting a proper neural network model in a model base, and carrying out audit judgment on the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancement by combining a knowledge base and a rule base;
and obtaining and storing the result obtained by the audit judgment of the neural network model for the query of management personnel.
In an optional implementation manner of the second aspect of the present invention, the clearing up incomplete data, error data, and repeated data in the data related to medical insurance reimbursement includes:
selecting required data to be processed from the medical insurance reimbursement related data;
cleaning incomplete data, error data and repeated data in the data to be processed;
and carrying out format and type conversion on the cleaned data to be processed to obtain first data to be audited, wherein the first data to be audited can be identified by the neural network model.
In an alternative embodiment of the second aspect of the present invention, the enhancing the video or the image comprises:
selecting a video to be processed or an image to be processed with definition meeting a preset requirement from the video or the image;
carrying out sharpening enhancement on the video to be processed or the image to be processed;
and carrying out format and type conversion on the video to be processed or the image to be processed after sharpening enhancement to obtain second data to be audited, wherein the second data to be audited can be identified by the neural network model.
In an optional implementation manner of the second aspect of the present invention, before the selecting a suitable neural network model from the model base and combining the knowledge base and the rule base adapted to the neural network model, and performing audit judgment on the medical insurance reimbursement related data obtained after cleaning, or the video or the image obtained after enhancement, includes:
collecting gender-limited medication knowledge, age-limited medication knowledge, step medication knowledge, drug conflict knowledge and common drug knowledge to construct the knowledge base;
and drawing up payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules, and constructing the rule base.
In an optional implementation manner of the second aspect of the present invention, before the selecting an appropriate neural network model in the model library and combining the knowledge base and the rule base adapted to the neural network model, performing audit judgment on the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancing, further includes:
constructing a training data set and a testing data set for judging the abnormal medical insurance reimbursement data or the abnormal medical insurance reimbursement behavior;
setting network parameters in the neural network model;
training the neural network model through the training data set and the test data set until the training error and the test error of the neural network model are within a preset range;
and auditing and judging the cleaned related data of medical insurance reimbursement or the enhanced video or image by using the trained neural network model.
Has the advantages that: the invention provides a medical insurance fund supervision system and a supervision method thereof, wherein the system comprises: the data acquisition module is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system; the scene monitoring module is used for shooting videos or images of patients in various scenes; the data processing module is used for cleaning the data related to the medical insurance reimbursement and enhancing the video or the image; the data supervision module is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image through a neural network model in the model base in combination with the knowledge base and the rule base; and the management module is used for storing the result of the audit judgment of the data supervision module so as to be inquired by the management personnel. The medical insurance fund supervision system can perform post supervision according to medical insurance reimbursement related data and can also monitor patient behaviors through scenes to achieve pre supervision, and supervision modes are more diverse.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a medical insurance fund supervision system of the present invention;
FIG. 2 is a schematic diagram of a data processing module of the medical insurance fund monitoring system according to the present invention;
FIG. 3 is a schematic diagram of a data monitoring module of the medical insurance fund monitoring system according to the present invention;
FIG. 4 is a schematic diagram of the structure of a management module of the medical insurance fund monitoring system according to the present invention;
FIG. 5 is a schematic diagram of a monitoring method of a medical insurance fund supervision system according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a medical insurance fund supervision system and a monitoring method thereof. The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and with reference to fig. 1, a first aspect of the present invention provides a medical insurance fund supervision system, including:
the data acquisition module 10 is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system; the main function of the data acquisition module 10 is to solve the problem of data source in the intelligent medical insurance auditing system, the data mainly comes from the medical insurance SMIS system database, the required data includes medical insurance policy parameter information, insured person historical visit and medication information, medicine catalogue information, fixed point medical service institution information and the like, and the most important data in the data acquisition module 10 is the problem that the database of the data acquisition module keeps consistency with the database data of the hospital HIS system, the pharmacy ERP system and the medical insurance SMIS system;
the scene monitoring module 20 is used for capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital department and a hospital department of the hospital in real time; in the technical scheme, the scene supervision module 20 mainly corresponds to hospitalization, outpatient service and pharmacy, is used for monitoring and capturing behavior images and videos of each scene in real time, and analyzes and judges behavior information according to corresponding scene rules in a medical insurance fund scene supervision rule base, such as inconsistent testimonies, bed hanging hospitalization, imposition hospitalization, frequent hospitalization of patients in the same institution, drug and non-drug identification of pharmacy and the like;
the data processing module 30 is configured to clean incomplete data, error data and repeated data in the medical insurance reimbursement related data; because inconsistent and worthless data may exist in the databases of the hospital HIS system, the pharmacy ERP system and the medical insurance SMIS system, the inconsistent data mainly includes the difference between disease codes, time formats and the like used by each medical unit, and the worthless data refers to data which has no direct or indirect relation with fraudulent behaviors, such as patient's native language, birth place and the like; therefore, the data needs to be preprocessed, including data selection, data cleaning, data conversion, data loading and other processes, so as to improve the quality of the data and ensure the accuracy of the mining result;
a video and image processing module 40 for performing sharpness enhancement on the video or the image; because the scene monitoring module 20 (including the monitoring camera) may have a problem that the video or the image has insufficient definition and cannot effectively identify the features in the video or the image, the definition enhancement in the present technical solution emphasizes or sharpens some features of the image, such as edges, contours, contrast, etc., so as to facilitate display, observation or further analysis and processing.
The data supervision module 50 is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image by combining a neural network model in a model base with a knowledge base and a rule base; the data supervision module 50 is a core module of the technical scheme, and mainly comprises a knowledge base, a rule base and a model base, wherein the knowledge base, the rule base and the model base are mutually linked to achieve real-time and intelligent auditing of medical insurance treatment settlement information, and the knowledge base is mainly used for storing medical field expert knowledge required in the auditing process and assisting the rule base in preprocessing data;
and the management module 60 is used for storing the result of the audit judgment of the data supervision module so as to be inquired by the manager. The management module 60 in the technical scheme provides comprehensive and diversified services such as audit, violation statistics, information inquiry, rule management and the like for a user, wherein the audit service supports audit on medical insurance treatment settlement information, so that the efficiency and the coverage of medical insurance supervision work are effectively improved, meanwhile, medical insurance audit workers can obtain early warning information of suspected violation documents at the first time, perform key audit on the documents, refuse payment of medical insurance funds for the documents with violation problems, and effectively guarantee the safety of the medical insurance funds.
Referring to fig. 2, in an alternative implementation of the first aspect of the present invention, the data processing module includes:
the data selection unit is used for selecting required data to be processed from the medical insurance reimbursement related data; according to the technical scheme, required data are extracted from databases of a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system according to actual audit requirements and are integrated into a database of a data supervision module 50, so that the storage space and the processing range of the database of the data supervision module 50 are reduced, and as data tables in the hospital HIS system, the pharmacy ERP system and the medical insurance SMIS system are very many, but not all data are useful, the data tables selected according to the requirements are as follows: after the basic information table of the ginseng insurance person, the information table of the medical institution, the medicine coding table, the specific information table of the medicine, the visit table, the visit expense detailed table and the like are selected, the required data are synchronized into the database of the supervision module 50;
the data cleaning unit is used for cleaning incomplete data, error data and repeated data in the data to be processed; in the data cleaning unit, incomplete data, error data and repeated data in the data set are mainly processed to improve the data quality, for example, whether fields in the clinic information, diagnosis, medical insurance category, and the like have null values is checked.
And the data conversion unit is used for carrying out format and type conversion on the cleaned data to be processed and the enhanced video or image to obtain the data to be audited which can be identified by the neural network model. The purpose of data conversion in the technical scheme is to ensure that the format or type of data meets the requirement of neural network model discrimination, and the conversion strategy comprises data smoothness, attribute construction, data aggregation, normalization, discretization and the like.
Referring to fig. 3, in an alternative embodiment of the first aspect of the present invention, the data policing module includes:
the data storage unit is used for storing the data to be audited;
the knowledge base comprises limited qualitative medicine-identifying knowledge, limited age medicine-using knowledge, stepped medicine-using knowledge, medicine conflict knowledge and common medicine knowledge; in order to better realize the function and the target of systematically identifying the violation and abuse behaviors in the medical treatment of the insured person and analyze whether the medical care supervisor has the violation problem in the audit medical treatment information in the actual process, the technical scheme considers from multiple angles such as whether the dosage of the medicine is reasonable, whether the medicine accords with the use characteristics of the sex, whether the treatment medicine is suitable for the disease and the like, and constructs a knowledge base by combining the actual problems, wherein the knowledge base comprises the knowledge of restricting sex medication, the knowledge of restricting age medication, the knowledge of step medication, the knowledge of medicine conflict, the knowledge of common medication and the like;
the rule base comprises payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules;
and the model base comprises a plurality of neural network models, and the neural network models are used for carrying out audit judgment on the data to be audited by combining the knowledge base and the rule base and outputting the result of the audit judgment. For the model base, the most important is the construction of the neural network model, the data processed by the rule base is used as a data source, the monitoring and early warning model is constructed by constructing a data file and utilizing the existing neural network algorithm (such as BP neural network), and the construction of the model is divided into a training process and a testing process.
Referring to fig. 4, in an alternative implementation of the first aspect of the present invention, the management module includes: the system comprises an early warning display unit, an information inquiry unit, a statistical analysis unit, a rule management unit and a model management unit.
The medical insurance fund supervision system mainly comprises a data acquisition module 10, a scene monitoring module 20, a data processing module 30, a video and image processing module 40, a data supervision module 50 and a management module 60, wherein the data acquisition module 10 is the basis for the system to realize the identification of medical insurance visit violation, the module is mainly responsible for collecting the medical insurance medicine information, the information of the personnel participating in the insurance, the information of the medical record, the information of the fixed-point medical institution of the medical insurance and the like of the medical insurance data center, the knowledge base of the data supervision module 50 combines the requirements of problem solving, organically stores the expert knowledge in the medical field in the computer, knowledge is an important basis for realizing the automatic and intelligent auditing of the medical insurance document by the system, the accuracy and comprehensiveness of the knowledge determine the reliability of the auditing result, and the knowledge management module provides support for knowledge experts to establish knowledge and manage the knowledge. The management module 60 not only includes the creation of the monitoring model, but also allows the user to save and manage the model according to the prediction error conditions of the neural network model under different data sets or different parameters, and also supports the untimely query requirement of medical insurance management personnel.
In an alternative embodiment of the first aspect of the present invention, the medical insurance reimbursement related data includes information of insurers, historical visit and medication information, drug catalog information and site specific medical institution information.
Referring to fig. 5, a second aspect of the present invention provides a method for supervising a medical insurance fund supervision system, including:
s100, acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system, and cleaning incomplete data, error data and repeated data in the medical insurance reimbursement related data;
or capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital department and a hospital department of the hospital, and enhancing the videos or the images;
s200, selecting a proper neural network model from a model base, and checking and judging the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancing by combining a knowledge base and a rule base;
s300, obtaining and storing the result obtained by the auditing and judging of the neural network model for the query of management personnel.
In an optional implementation manner of the second aspect of the present invention, the clearing up incomplete data, error data, and repeated data in the data related to medical insurance reimbursement includes:
selecting required data to be processed from the medical insurance reimbursement related data;
cleaning incomplete data, error data and repeated data in the data to be processed;
and carrying out format and type conversion on the cleaned data to be processed to obtain first data to be audited, wherein the first data to be audited can be identified by the neural network model.
In an alternative embodiment of the second aspect of the present invention, the enhancing the video or the image comprises:
selecting a video to be processed or an image to be processed with definition meeting a preset requirement from the video or the image;
carrying out sharpening enhancement on the video to be processed or the image to be processed; in an alternative embodiment of the second aspect of the present invention, the purpose of image enhancement is to adopt one or more technical means to improve the visual effect of the image, or convert the image into a form more suitable for human eye observation and machine recognition, and the basic methods of image enhancement used in the technical solution are mainly gray scale transformation, gray scale equalization, pseudo color enhancement, smoothing, sharpening, filtering, and the like.
For example, the process of the graph enhancement of the technical scheme comprises the following steps: 1. the contrast ratio is raised, and a linear function is adopted to transform the gray value of the image; gamma correction, which adopts a nonlinear function (exponential function) to transform the gray value of the image; 3. and (3) histogram equalization, namely converting the histogram of the original image into an image with the probability density of 1 through an integral probability density function, thereby achieving the effect of improving the contrast. The essence of histogram equalization is also a broadening of certain regions, but it results in a transformation of the entire image to bright regions. When the original image is given, the corresponding histogram equalization effect is correspondingly determined; histogram specification for some of the problems of histogram equalization, the histogram of the original image is converted into the form of a specified histogram. Determining a histogram of a general target image needs to refer to a histogram of an original image and obtain the histogram by utilizing a multi-Gaussian function; 5. the homomorphic filter, the gray-scale image f (x, y) of the image can be considered to be composed of two parts, an incident light component and a reflected light component: the f (x, y) ═ i (x, y) r (x, y), the incident light is uniform, the variation along with the space position is small, the incident light occupies a low-frequency component band, the reflected light reflects light with different intensity due to different object properties and structural characteristics, and the variation along with the space position is severe. Occupying high frequency components, the image enhancement method of the present invention is designed based on the principle that an image is formed by combining an illumination spectrum and a reflection spectrum.
And carrying out format and type conversion on the video to be processed or the image to be processed after sharpening enhancement to obtain second data to be audited, wherein the second data to be audited can be identified by the neural network model.
In an optional implementation manner of the second aspect of the present invention, before the selecting a suitable neural network model from the model base and combining the knowledge base and the rule base adapted to the neural network model, and performing audit judgment on the medical insurance reimbursement related data obtained after cleaning, or the video or the image obtained after enhancement, includes:
collecting gender-limited medication knowledge, age-limited medication knowledge, step medication knowledge, drug conflict knowledge and common drug knowledge to construct the knowledge base;
and drawing up payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules, and constructing the rule base.
In an optional implementation manner of the second aspect of the present invention, before the selecting an appropriate neural network model in the model library and combining the knowledge base and the rule base adapted to the neural network model, performing audit judgment on the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancing, further includes:
constructing a training data set and a testing data set for judging the abnormal medical insurance reimbursement data or the abnormal medical insurance reimbursement behavior; and reading corresponding clinic settlement data from the database as a training data set and a test set data set of the model according to conditions such as data volume, data interval and the like set by a user. In the step, the diagnosis settlement data is converted into an N-dimensional input vector through the processing of a rule engine according to the model construction requirement;
setting network parameters in the neural network model; after the structure of the neural network model is determined, some parameters in the training process are required to be set, wherein the parameters mainly comprise training iteration times, network learning rate and training times. The larger the value of the iteration parameter is, the more the training takes, wherein, the network learning rate parameter is used for controlling the learning rate and determining how long distance each iteration jump is, and if the value is small, the process of changing the network weight needs to be long; if the value is too large, the optimal point can be directly skipped and missed, and the training iteration times are set by the training time parameter;
training the neural network model through the training data set and the test data set until the training error and the test error of the neural network model are within a preset range; if the training error and the testing error are within the allowable range, the neural network model is stored, and if the training error and the testing error are not within the allowable range, the parameters are modified and the construction of the neural network model is repeated until the errors meet the requirements;
and auditing and judging the cleaned related data of medical insurance reimbursement or the enhanced video or image by using the trained neural network model.
In summary, the present invention provides a medical insurance fund monitoring system and a monitoring method thereof, wherein the system comprises: the data acquisition module is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system; the scene monitoring module is used for shooting videos or images of patients in various scenes; the data processing module is used for cleaning the data related to the medical insurance reimbursement and enhancing the video or the image; the data supervision module is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image through a neural network model in the model base in combination with the knowledge base and the rule base; and the management module is used for storing the result of the audit judgment of the data supervision module so as to be inquired by the management personnel. The medical insurance fund supervision system can perform post supervision according to medical insurance reimbursement related data and can also monitor patient behaviors through scenes to achieve pre supervision, and supervision modes are more diverse.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A medical insurance fund supervision system, comprising:
the data acquisition module is used for acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system;
the scene monitoring module is used for capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital resident department and a hospital clinic department of the hospital in real time;
the data processing module is used for cleaning incomplete data, error data and repeated data in the medical insurance reimbursement related data;
the video and image processing module is used for performing definition enhancement on the video or the image;
the data supervision module is used for auditing and judging the cleaned medical insurance reimbursement related data and the enhanced video or image by combining a neural network model in a model base with a knowledge base and a rule base;
and the management module is used for storing the result of the audit judgment of the data supervision module so as to be inquired by managers.
2. The medical insurance fund supervision system according to claim 1, wherein the data processing module comprises:
the data selection unit is used for selecting required data to be processed from the medical insurance reimbursement related data;
the data cleaning unit is used for cleaning incomplete data, error data and repeated data in the data to be processed;
and the data conversion unit is used for carrying out format and type conversion on the cleaned data to be processed and the enhanced video or image to obtain the data to be audited which can be identified by the neural network model.
3. The medical insurance fund supervision system according to claim 2, wherein the data supervision module comprises:
the data storage unit is used for storing the data to be audited;
the knowledge base comprises limited qualitative medicine-identifying knowledge, limited age medicine-using knowledge, stepped medicine-using knowledge, medicine conflict knowledge and common medicine knowledge;
the rule base comprises payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules;
and the model base comprises a plurality of neural network models, and the neural network models are used for carrying out audit judgment on the data to be audited by combining the knowledge base and the rule base and outputting the result of the audit judgment.
4. The medical insurance fund supervision system according to claim 1, wherein the management module comprises: the system comprises an early warning display unit, an information inquiry unit, a statistical analysis unit, a rule management unit and a model management unit.
5. The medical insurance fund supervision system according to claim 1, wherein the medical insurance reimbursement related data comprises insurer information, historical visit and medication information, drug catalog information and point-of-care medical facility information.
6. A supervision method of a medical insurance fund supervision system is characterized by comprising the following steps:
acquiring medical insurance reimbursement related data from a hospital HIS system, a pharmacy ERP system and a medical insurance SMIS system, and cleaning incomplete data, error data and repeated data in the medical insurance reimbursement related data;
or capturing videos or images of the scenes of medicine purchase, patient visit and patient hospitalization of the patient from a pharmacy department, a hospital department and a hospital department of the hospital, and enhancing the videos or the images;
selecting a proper neural network model in a model base, and carrying out audit judgment on the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancement by combining a knowledge base and a rule base;
and obtaining and storing the result obtained by the audit judgment of the neural network model for the query of management personnel.
7. The method of claim 6, wherein the clearing the incomplete data, the error data and the repeated data in the data related to the reimbursement of the medical insurance comprises:
selecting required data to be processed from the medical insurance reimbursement related data;
cleaning incomplete data, error data and repeated data in the data to be processed;
and carrying out format and type conversion on the cleaned data to be processed to obtain first data to be audited, wherein the first data to be audited can be identified by the neural network model.
8. The method of claim 6, wherein said enhancing the video or the image comprises:
selecting a video to be processed or an image to be processed with definition meeting a preset requirement from the video or the image;
carrying out sharpening enhancement on the video to be processed or the image to be processed;
and carrying out format and type conversion on the video to be processed or the image to be processed after sharpening enhancement to obtain second data to be audited, wherein the second data to be audited can be identified by the neural network model.
9. The method as claimed in claim 6, wherein the selecting a proper neural network model from the model library and the checking and determining the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancing by combining the knowledge base and the rule base adapted to the neural network model comprises:
collecting gender-limited medication knowledge, age-limited medication knowledge, step medication knowledge, drug conflict knowledge and common drug knowledge to construct the knowledge base;
and drawing up payment policy examination rules, diagnosis and treatment rationality rules, clinical normative examination rules and medical behavior abnormity monitoring rules, and constructing the rule base.
10. The method of claim 6, wherein the selecting a proper neural network model from the model library and the checking and determining the medical insurance reimbursement related data obtained after cleaning or the video or the image obtained after enhancing in combination with the knowledge base and the rule base adapted to the neural network model further comprises:
constructing a training data set and a testing data set for judging the abnormal medical insurance reimbursement data or the abnormal medical insurance reimbursement behavior;
setting network parameters in the neural network model;
training the neural network model through the training data set and the test data set until the training error and the test error of the neural network model are within a preset range;
and auditing and judging the cleaned related data of medical insurance reimbursement or the enhanced video or image by using the trained neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111306471.1A CN114037540A (en) | 2021-11-05 | 2021-11-05 | Medical insurance fund supervision system and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111306471.1A CN114037540A (en) | 2021-11-05 | 2021-11-05 | Medical insurance fund supervision system and monitoring method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114037540A true CN114037540A (en) | 2022-02-11 |
Family
ID=80142969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111306471.1A Pending CN114037540A (en) | 2021-11-05 | 2021-11-05 | Medical insurance fund supervision system and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114037540A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080997A (en) * | 2022-06-02 | 2022-09-20 | 武汉金豆医疗数据科技有限公司 | Mobile checking method and device for medical insurance fund, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921710A (en) * | 2018-06-08 | 2018-11-30 | 东莞迪赛软件技术有限公司 | The method and system of medical insurance abnormality detection |
| CN109598630A (en) * | 2018-12-04 | 2019-04-09 | 平安医疗健康管理股份有限公司 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN110827019A (en) * | 2019-11-07 | 2020-02-21 | 南京远致数据技术有限公司 | Block chain-based mobile medical insurance payment method, storage medium and computer equipment |
| CN113360671A (en) * | 2021-06-16 | 2021-09-07 | 浙江工业大学 | Medical insurance medical document auditing method and system based on knowledge graph |
-
2021
- 2021-11-05 CN CN202111306471.1A patent/CN114037540A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921710A (en) * | 2018-06-08 | 2018-11-30 | 东莞迪赛软件技术有限公司 | The method and system of medical insurance abnormality detection |
| CN109598630A (en) * | 2018-12-04 | 2019-04-09 | 平安医疗健康管理股份有限公司 | The monitoring and managing method and relevant device of fixed point medical institution based on living things feature recognition |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN110827019A (en) * | 2019-11-07 | 2020-02-21 | 南京远致数据技术有限公司 | Block chain-based mobile medical insurance payment method, storage medium and computer equipment |
| CN113360671A (en) * | 2021-06-16 | 2021-09-07 | 浙江工业大学 | Medical insurance medical document auditing method and system based on knowledge graph |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080997A (en) * | 2022-06-02 | 2022-09-20 | 武汉金豆医疗数据科技有限公司 | Mobile checking method and device for medical insurance fund, computer equipment and storage medium |
| CN115080997B (en) * | 2022-06-02 | 2024-01-09 | 武汉金豆医疗数据科技有限公司 | Mobile checking method and device for medical insurance fund, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200294667A1 (en) | System and method for machine based medical diagnostic code identification, accumulation, analysis and automatic claim process adjudication | |
| Milovic et al. | Prediction and decision making in health care using data mining | |
| US7725330B2 (en) | Systems and methods for automated extraction and processing of billing information in patient records | |
| CN105069308B (en) | Medical Devices intelligent monitor system | |
| US11488717B2 (en) | Method and system for analysis of spine anatomy and spine disease | |
| US20030149597A1 (en) | System for supporting clinical decision-making | |
| US20050144042A1 (en) | Associated systems and methods for managing biological data and providing data interpretation tools | |
| CN110136837B (en) | Medical data processing platform | |
| WO2002073362A2 (en) | Methods and systems for identifying attributable errors in financial processes | |
| CN110852894A (en) | Insurance underwriting method and device, computer storage medium and electronic equipment | |
| CN103370629B (en) | Clinical quality analytics system | |
| US20210103991A1 (en) | Method and System for Medical Malpractice Insurance Underwriting Using Value-Based Care Data | |
| CN112150298A (en) | Data processing method, system, device and readable medium | |
| CN111584021A (en) | Medical record information verification method and device, electronic equipment and storage medium | |
| CN111223534A (en) | Fine management system for industry and finance integration | |
| US20110257993A1 (en) | Automated association of rating diagnostic codes for insurance and disability determinations | |
| CN111639743A (en) | Intelligent hospital information acquisition method and system with user as core | |
| CN115185936A (en) | Medical clinical data quality analysis system based on big data | |
| CN114037540A (en) | Medical insurance fund supervision system and monitoring method thereof | |
| CN111179096A (en) | Medical data auditing method and device, electronic equipment and computer readable medium | |
| CN112992366A (en) | ICD (identity control document) code artificial intelligence audit quality control mode and system based on medical insurance disease payment system | |
| Tsmots et al. | Information-Analytical Support to Medical Industry. | |
| CN115409380A (en) | Hospital medical insurance performance evaluation method and device, electronic equipment and storage medium thereof | |
| CN114550930A (en) | Disease prediction method, device, equipment and storage medium | |
| CN112967789A (en) | Resource consumption calculation and determination method for special disease species of oral cavity |
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 |