CN109636648A - Social security violation detection method, device, equipment and computer storage medium - Google Patents
Social security violation detection method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN109636648A CN109636648A CN201811530845.6A CN201811530845A CN109636648A CN 109636648 A CN109636648 A CN 109636648A CN 201811530845 A CN201811530845 A CN 201811530845A CN 109636648 A CN109636648 A CN 109636648A
- Authority
- CN
- China
- Prior art keywords
- social security
- data
- medical
- medical data
- expense
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 91
- 230000002159 abnormal effect Effects 0.000 claims abstract description 44
- 239000003814 drug Substances 0.000 claims description 89
- 238000011282 treatment Methods 0.000 claims description 87
- 229940079593 drug Drugs 0.000 claims description 79
- 201000010099 disease Diseases 0.000 claims description 70
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 70
- 238000003745 diagnosis Methods 0.000 claims description 69
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000009471 action Effects 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 14
- 238000013450 outlier detection Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000011176 pooling Methods 0.000 abstract description 12
- 239000002699 waste material Substances 0.000 abstract description 11
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 21
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 230000001225 therapeutic effect Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 230000003444 anaesthetic effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002483 medication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002640 oxygen therapy Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of social security violation detection method, comprising: obtains the medical data that insured people settles accounts expense of seeing and treating patients by social security card；By the medical data input deviation detection model, determined in the medical data by separate-blas estimation model with the presence or absence of the social security payment project got in return by string at one's own expense；If there is the social security payment project got in return by string at one's own expense in medical data, it is determined that the medical data exception, and the abnormal data in the medical data is extracted, to provide the punishment certificate punished to insured people or medical institutions.The present invention also provides a kind of social security violation detection device, equipment and computer readable storage mediums.The present invention, which is realized, is supervised insured people by the medical data that social security card is settled accounts by the separate-blas estimation model based on machine learning, so as to avoid manpower waste and the waste of outpatient service risk-pooling fund caused by artificial supervision, the supervisory efficiency to outpatient service risk-pooling fund is improved.
Description
Technical field
Social security monitoring technology of the present invention field more particularly to a kind of detection, device, equipment and the computer storage in violation of rules and regulations of social security
Medium.
Background technique
Medical insurance refers generally to basic medical insurance, due to being to compensate for labourer's economic loss caused by disease risks
The social security system established.By employing unit and personal payment, Medical Benefits Fund is established, insurant illness is just
It examines after medical expense occurs, gives certain economic compensation to it by Medical Insurance Organizations.Insured people is in designated medical organization pair
When consulting services are settled accounts, the project at one's own expense such as drug, cannot be exchanged into social security and be paid to diagnosis and treatment item at one's own expense or at one's own expense
The social securities payment project such as expense or drug is to achieve the purpose that defraud of social security expense, if discovery will change social security payment by string at one's own expense
Project, then it is assumed that operated for violation social security, be the unlawful practice that medical insurance is forbidden, great harm can be brought to medical insurance fund.
Currently, for will the operation of social security payment terms purpose violation social security be changed by string at one's own expense, by the supervisor being equipped with
The social security behavior of insurant is monitored, the medical insurance document of settlement is calculated, manages the expenditure of outpatient service risk-pooling fund, but
It is that artificial supervision causes manpower to waste, and there are many China's insurant, cause supervisor inadequate, to allow criminal
Have an opportunity to take advantage of, causes the waste of outpatient service risk-pooling fund.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of social security violation detection, device, equipment and computer storage medium, purports
Solving the technical issues of artificial supervision causes manpower waste and outpatient service risk-pooling fund to waste in the prior art.
To achieve the above object, the present invention provides a kind of social security violation detection method, the social security violation detection method packet
Include following steps:
Obtain the medical data that insured people settles accounts expense of seeing and treating patients by social security card；
By the medical data input deviation detection model, by separate-blas estimation model determine in the medical data whether
In the presence of the social security payment project got in return by string at one's own expense；
If there is the social security payment project got in return by string at one's own expense in medical data, it is determined that the medical data are different
Often, and the abnormal data in the medical data is extracted, to provide the punishment certificate punished to insured people or medical institutions.
Optionally, described by the medical data input deviation detection model, by separate-blas estimation model determine it is described just
It examines in data and includes: with the presence or absence of the social security payment terms purpose step got in return by string at one's own expense
By the medical data input deviation detection model, by the Data Cleaning Model in separate-blas estimation model to medical
Data are cleaned, and are gone to a doctor data with the specification after being cleaned；
Medical data configuration text feature is standardized to described, to obtain term vector, and by double in separate-blas estimation model
Sentence vector matrix is converted by term vector to RNN submodel；
The operation of attention mechanism is carried out based on the sentence vector matrix, to obtain normal data；
The normal data is detected based on the Outlier Detection Algorithm in separate-blas estimation model, according to testing result really
With the presence or absence of the social security payment project got in return by string at one's own expense in the fixed medical data.
Optionally, the Outlier Detection Algorithm based in separate-blas estimation model detects the normal data, root
It determines in the medical data according to testing result with the presence or absence of the social security payment terms purpose step packet got in return by string at one's own expense
It includes:
Based on the medical insurance mark in the normal data to social security payment terms purpose drug information in the normal data or
Diagnosis and treatment item information is classified；
Classification results and preset standard classified catalogue are compared, determine classification results whether with preset standard classify mesh
Record matching；
If classification results and preset standard classified catalogue mismatch, it is determined that exist in the medical data by project at one's own expense
The social security payment project exchanged.
Optionally, the Outlier Detection Algorithm based in separate-blas estimation model detects the normal data, root
It determines in the medical data according to testing result with the presence or absence of the social security payment terms purpose step packet got in return by string at one's own expense
It includes:
Social security payment terms in the normal data are determined based on the related information of the disease and drug or diagnosis and treatment item that prestore
The applicable disease information of purpose drug or diagnosis and treatment item；
It is applicable in the disease information that disease information is applied with insured people by described and compares, determine the applicable disease information
Whether matched with the disease information of insured people application；
If the disease information mismatch for being applicable in disease information and insured people application, it is determined that deposited in the medical data
In the social security payment project got in return by string at one's own expense.
Optionally, if there is the social security payment project got in return by string at one's own expense in the medical data, it is determined that institute
Medical data exception is stated, and extracts the abnormal data in the medical data, to provide to insured people or medical institutions
Include: after the step of punishment certificate penalized
Punishment managing detailed catalogue is generated according to default punishment rule and the abnormal data；
Send notice of punishment to the terminal of insured people or medical institutions according to the punishment managing detailed catalogue and to insured people or
Medical institutions are punished.
Optionally, the default punishment rule of the basis and the step of abnormal data generation punishment managing detailed catalogue, include:
Counting insured people or medical institutions according to the abnormal data according to the default punishment rule timing will item at one's own expense
Mesh exchanges into social security payment terms purpose violation number or the violation amount of money, obtains corresponding statistical result；
The violation of the statistical result is determined based on the preset association relationship of violation number or the violation amount of money and discipline rating
Grade；
Preset association relationship based on discipline rating and punishment measure obtains the punishment Action Message of current discipline rating；
The punishment managing detailed catalogue is generated based on the punishment Action Message and the abnormal data.
Optionally, the Outlier Detection Algorithm includes nested abnormal circulation detection algorithm.
In addition, to achieve the above object, the present invention also provides a kind of social security violation detection device, the social security detects in violation of rules and regulations
Device includes:
Module is obtained, the medical data of expense of seeing and treating patients are settled accounts by social security card for obtaining insured people；
Detection module is used for the medical data input deviation detection model, by described in the determination of separate-blas estimation model
With the presence or absence of the social security payment project got in return by string at one's own expense in medical data；
Extraction module, if for there is the social security payment project got in return by string at one's own expense in data of going to a doctor, it is determined that
The medical data exception, and the abnormal data in the medical data is extracted, insured people or medical institutions are carried out with providing
The punishment certificate of punishment.
In addition, to achieve the above object, the present invention also provides a kind of social security violation detection device, the social security detects in violation of rules and regulations
Equipment includes processor, memory and is stored on the memory and can be examined in violation of rules and regulations by the social security that the processor executes
Ranging sequence, wherein realizing when social security violation detection program is executed by the processor such as above-mentioned social security violation detection side
The step of method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Social security detection program in violation of rules and regulations is stored on storage medium, wherein realizing when social security violation detection program is executed by processor
Such as the step of above-mentioned social security violation detection method.
The present invention provides a kind of social security violation detection method, device, equipment and computer readable storage medium, and the present invention is logical
It crosses and obtains the medical data that insured people settles accounts expense of seeing and treating patients by social security card；By the medical data input deviation detection model,
It is determined in the medical data by separate-blas estimation model with the presence or absence of the social security payment project got in return by string at one's own expense；If
There is the social security payment project got in return by string at one's own expense in medical data, it is determined that the medical data exception, and extract
Abnormal data in the medical data, to provide the punishment certificate punished to insured people or medical institutions.By above-mentioned
Mode is realized and is supervised to insured people by the medical data that social security card is settled accounts by separate-blas estimation model, to avoid
The waste of manpower caused by artificial supervision and the waste of outpatient service risk-pooling fund, improve the supervisory efficiency to outpatient service risk-pooling fund.
Detailed description of the invention
Fig. 1 is the hardware structural diagram for the social security violation detection device that various embodiments of the present invention are related to；
Fig. 2 is the flow diagram of social security violation detection method first embodiment of the present invention；
Fig. 3 is the flow diagram of social security violation detection method second embodiment of the present invention；
Fig. 4 is the flow diagram of social security violation detection method 3rd embodiment of the present invention；
Fig. 5 is the flow diagram of social security violation detection method fourth embodiment of the present invention；
Fig. 6 is the flow diagram of the 5th embodiment of social security violation detection method of the present invention；
Fig. 7 is the flow diagram of social security violation detection method sixth embodiment of the present invention；
Fig. 8 is the functional block diagram of social security violation detection device first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present embodiments relate to social security violation detection method be mainly used in social security violation detection device, which disobeys
Rule detection device, which can be PC (personal computer personal computer), portable computer, mobile terminal etc., has display
With the equipment of processing function.
Referring to Fig.1, Fig. 1 is the hardware configuration signal of social security violation detection device involved in the embodiment of the present invention
Figure.In the embodiment of the present invention, social security violation detection device may include (such as the central processing unit Central of processor 1001
Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.Wherein,
Communication bus 1002 is for realizing the connection communication between these components；User interface 1003 may include display screen
(Display), input unit such as keyboard (Keyboard)；Network interface 1004 optionally may include that the wired of standard connects
Mouth, wireless interface (such as WI-FI interface)；Memory 1005 can be high speed RAM memory, be also possible to stable memory
(non-volatile memory), such as magnetic disk storage, memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.It will be understood by those skilled in the art that hardware configuration shown in Fig. 1 is not constituted to limit of the invention
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer readable storage medium may include operation system
System, network communication module and social security detect program in violation of rules and regulations.In Fig. 1, network communication module is mainly used for connecting server, with
Server carries out data communication；And processor 1001 can call the social security stored in memory 1005 detection program in violation of rules and regulations, and
Execute social security violation detection method provided in an embodiment of the present invention.
The present invention further provides a kind of social security violation detection methods.Referring to Fig. 2, Fig. 2 is that social security of the present invention detects in violation of rules and regulations
The method schematic diagram of method first embodiment.
Currently, for will the operation of social security payment terms purpose violation social security be changed by string at one's own expense, by the supervisor being equipped with
The social security behavior of insurant is monitored, the medical insurance document of settlement is calculated, manages the expenditure of outpatient service risk-pooling fund, but
It is that artificial supervision causes manpower to waste, and there are many China's insurant, cause supervisor inadequate, to allow criminal
Have an opportunity to take advantage of, causes the waste of outpatient service risk-pooling fund.
In the present embodiment, which includes:
Step S10 obtains the medical data that insured people settles accounts expense of seeing and treating patients by social security card；
In the present embodiment, insurant is settled accounts in designated medical organization (for example, hospital, pharmacy) using social security card
When, medical data can be sent to by people society core system by the terminal device of designated medical organization, people society core system connects
The medical data that terminal device is sent are received, are detected in violation of rules and regulations with carrying out social security to medical data, wherein medical/purchase medicine detailed data
Including information such as insured people's information, medical/purchase medicine unit information, medicine mark information, diagnosis and treatment item information and medical insurance marks
Data.Wherein, insured people's information can be the information such as insured people's name or medical insurance number；Medical organ information can be therapeutic machine
The identification code information of structure；Diagnosis and treatment item information may include that doctor can be used in radiation expense, Anesthetic Fee, blood transfusion expense or oxygen therapy expense etc.
The project of reimbursement is protected, can also include toothwash, be preced with, have a denture made or the project at one's own expense such as artificial tooth；Medical insurance mark refer to doctor or
The medical insurance that relevant staff adds drug or diagnosis and treatment item in medical detailed data/purchase medicine detailed data identifies, can be with
It include: Class A drug, Class B drugs, non-medical insurance drug, Class A diagnosis and treatment item, Class B diagnosis and treatment item or non-medical insurance diagnosis and treatment item,
Whether medical insurance mark applies for the class of the medical insurance clearing reimbursement of medical insurance clearing reimbursement or application for identification of medications or diagnosis and treatment item
Type.
The medical data input deviation detection model is determined the medical number by separate-blas estimation model by step S20
With the presence or absence of the social security payment project got in return by string at one's own expense in；
In the present embodiment, which can use cluster, sequence variation, nearest-neighbors method, multidimensional data
Medical data are analyzed in analysis etc., are able to detect in medical data by separate-blas estimation model with the presence or absence of by project at one's own expense
The social security payment project exchanged specifically carries out standard to the medical data got by separate-blas estimation model first
Change matching, diagnostic message, medicine information, disease information matches are provided into corresponding standardization field to doctor.Medical data
In there are some unnecessary data or nonstandard data that nonstandard field is not only being indicated word itself but also can examined
Under the requirement for considering semantic distance, using the longer more complicated content of text of RNN submodeling analysis in separate-blas estimation model, such as examine
It treats the data medical for first such as data, drug data, disease data to clean, such as carries out word segmentation processing, for example, one
Chinese sentence is all continuous between word, and the minimum unit granularity of data analysis is word, so needing to carry out at participle
Reason, and for the sentence of English text, the minimum unit of English sentence is word, it is separated between word by space, meanwhile,
Need to be labeled part of speech, for example, noun, from word, adjective, numeral-classifier compound etc., the purpose of part-of-speech tagging is to allow sentence
More useful language messages are incorporated in processing below for some text-processing tasks, can not have to part of speech certainly
Mark.Further, stop words can also be removed, stop words is exactly the word for not appointing contribution function to text feature, for example,
Eh, punctuation mark etc., need to get rid of these stop words when carrying out text analyzing, certainly, can for different applications
The word that parameter removes regulation part of speech to be arranged in preset model.After standardization matches completion acquisition normal data, it is based on
Outlier Detection Algorithm is paid project in medical data with the presence or absence of the social security got in return by string at one's own expense.In the present embodiment
In, it include the treatment service item such as the drug project of medication and diagnosis and treatment item in the therapeutic process of insured people in data of going to a doctor, just
It examines one of data drug or a diagnosis and treatment item corresponds to a treatment service item, in general, wrapped in medical data
Include multiple treatment service items.Treatment service item can be divided into project at one's own expense and social security payment project.Wherein, project refers at one's own expense
It is the treatment service item refusing insured people by social security and being submitted an expense account.Social security payment project refers to that social security gives insured people part
The treatment service item of expense reimbursement.The social security payment project got in return by string at one's own expense is referred to based on preset standard, example
Such as three catalogues, social security payment terms therapeutic interest service is classified as in the data uploaded for project at one's own expense, medical institutions' terminal
Project, i.e. medical institutions will change social security payment terms purpose service item by string at one's own expense in medical data.In the present embodiment
In, medical institutions' terminal device operates the item at one's own expense added to drug or diagnosis and treatment item based on medical institutions relevant staff
Target knows or social security payment project label.People society core system receives medical data, is based on above-mentioned standard to medical data
After matching process obtains normal data, the medical data for carrying social security payment project label, including medicine are extracted from normal data
The name information and corresponding information of submitting an expense account of object or diagnosis and treatment item.It may include first in this social security payment project label
The different types of marks such as class drug, Class B drugs, Class A diagnosis and treatment item, Class B diagnosis and treatment item.People society core system is being based on
Extraction social security payment project label to each social security payment project classify, the classification of classification may include Class A drug,
Class B drugs, Class A diagnosis and treatment item, Class B diagnosis and treatment item etc..Then the standard classification lists such as classification results and three catalogues are carried out pair
Than if determining perhaps whether the classification results of diagnosis and treatment item with three catalogues match some drug or diagnosis and treatment item to each drug
Classification results and the classification results of three catalogues mismatch, it is determined that the drug or diagnosis and treatment item are to be got in return by string at one's own expense
Social security pay project, using the name information of drug or diagnosis and treatment item, diagnosis and treatment quantity or amount of money involved as in violation of rules and regulations extremely
Data.Specifically, if in classification results, by toothwash this classification of the items to Class B diagnosis and treatment item, and in the Class B of three catalogues
Toothwash project is not present in diagnosis and treatment item, then the toothwash project in data of going to a doctor is that the social security got in return by string at one's own expense is paid
Project, the related datas such as amount of money involved are abnormal data.Certainly, in the present embodiment, social security paying identification will can also be carried
Drug or be applicable in disease and the insured people of diagnosis and treatment item apply for that the disease information of reimbursement compares, both determine whether
Match, if mismatching, it is determined that corresponding drug or diagnosis and treatment item are that the social security got in return by string at one's own expense is paid project.
Step S30 is paid project if existing in medical data by the social security that string at one's own expense is got in return, it is determined that it is described just
Data exception is examined, and extracts the abnormal data in the medical data, insured people or medical institutions are punished with offer
Punishment certificate.
When there is the social security payment project got in return by string at one's own expense in determining medical data, then above-mentioned classification is tied
Fruit and the unmatched drug of three catalogues perhaps diagnosis and treatment item or to be applicable in the disease information that disease and insured people apply unmatched
Drug or diagnosis and treatment item extract the title of anomaly item and the quantity of anomaly item, medicine as the anomaly item exchanged
The relevant abnormalities data such as object dosage or the amount of money being related to, and punishment certificate is generated according to abnormal data, which includes place
Penalize title, punishment measure, punishment reason, punishment mechanism, the penalty minutes etc. of object.The abnormal data can be used to as ginseng
Guarantor or medical institutions utilize the evidence of social security card violation operation.
The social security violation detection method that the present embodiment proposes obtains insured people by social security card and settles accounts the medical of expense of seeing and treating patients
Data；By the medical data input deviation detection model, determine in the medical data whether deposit by separate-blas estimation model
In the social security payment project got in return by string at one's own expense；It is paid if existing in medical data by the social security that string at one's own expense is got in return
Take project, it is determined that the medical data exception, and extract the abnormal data in the medical data, to provide to insured people or
The punishment certificate that medical institutions are punished.Society is passed through to insured people by separate-blas estimation model by the above-mentioned means, realizing
The medical data for protecting card clearing are supervised, so as to avoid the wave of manpower waste and outpatient service risk-pooling fund caused by artificial supervision
Take, improves the supervisory efficiency to outpatient service risk-pooling fund.
Based on the above embodiment, the second embodiment of social security violation detection method of the present invention is proposed, reference is schemed, and 3, this implementation
In example, step S20 includes:
The medical data input deviation detection model is passed through the data cleansing mould in separate-blas estimation model by step S40
Type cleans medical data, is gone to a doctor data with the specification after being cleaned；
Based on the above embodiment, in the present embodiment, in the present embodiment, the separate-blas estimation model can use cluster,
Sequence variation, nearest-neighbors method, multidimensional data analysis etc. analyze medical data, are able to detect by separate-blas estimation model
The social security payment project whether got in return by string at one's own expense in drug in medical data specifically passes through deviation first and examines
Model to be surveyed to clean the medical data got, cleaning, which refers to, carries out word segmentation processing to the text data in medical data,
There are some unnecessary data or nonstandard data in medical data, not only indicate word itself again it is contemplated that semanteme away from
From requirement under, using the longer more complicated content of text of RNN submodeling analysis in separate-blas estimation model, for data of going to a doctor
Word segmentation processing is carried out, is all continuous between word for example, a Chinese sentence, and the minimum unit granularity of data analysis is
Word, so need to carry out word segmentation processing, and for the sentence of English text, the minimum unit of English sentence is word, word
Separated between language by space, meanwhile, need to be labeled part of speech, for example, noun, from word, adjective, numeral-classifier compound etc., word
Property mark purpose be in order to allow sentence to incorporate more useful language messages in processing below, certainly, for some
Text-processing task can not have to part-of-speech tagging.
Further, stop words can also be removed, stop words is exactly the word for not appointing contribution function to text feature, than
Such as, eh, punctuation mark etc., need to get rid of these stop words when carrying out text analyzing, certainly, different answered
With the word that parameter removal regulation part of speech can be arranged in separate-blas estimation model.
Step S50 standardizes medical data configuration text feature to described, to obtain term vector, and passes through separate-blas estimation mould
Term vector is converted sentence vector matrix by two-way RNN submodel in type；
In the present embodiment, after carrying out cleaning operation to medical data, to the medical data configuration text feature after cleaning,
Text is indicated with the sequence of a vector, word word vector is indicated, is calculated by forward direction and reverse calculating splicing obtains
Complete term vector obtains the sequence of term vector, the use of two-way RNN model is then a sentence by term vector coding (conversion)
Vector matrix, distich subvector matrix carry out attention mechanism, obtain final normal data.
Step S60 carries out the operation of attention mechanism based on the sentence vector matrix, to obtain normal data；
In the present embodiment, distich subvector matrix carries out attention mechanism, by the sentence vector matrix pressure of above-mentioned steps
Being condensed to a vector indicates that the feedforward neural network for being sent into standard is predicted, a matrix is inputted, and exports a vector, from
A context vector is extracted in input content, the context vector of the mechanism is that the parameter learning of model is taken as to obtain.This
So that attention mechanism becomes a pure squeeze operation, any pond step can be replaced.Content of text is compressed into one
After a vector, final normal data is obtained, for example, a kind of class label, a real number value etc..
Step S70 detects the normal data based on the Outlier Detection Algorithm in separate-blas estimation model, according to inspection
It surveys result to determine in the medical data with the presence or absence of the social security payment project got in return by string at one's own expense, wherein described different
Normal detection algorithm includes nested abnormal circulation detection algorithm.
The abnormality detection of the present embodiment is calculated whether there is in the determining medical data of the detection referred to based on to normal data
The social security payment project got in return by string at one's own expense, Outlier Detection Algorithm include nested abnormal circulation detection algorithm.Nesting is followed
Ring Outlier Detection Algorithm refers to detecting normal data based on nested cycle detection algorithm and default detected rule, determines
With the presence or absence of the social security payment terms purpose preset algorithm got in return by string at one's own expense in the medical data.Based on above-mentioned implementation
Example, in the present embodiment, preset rules include being matched and by comparing to social security project label with three catalogues by drug
Or medical project is applicable in disease and compares with the disease that insured people applies the methods of to match and determines whether there is by one's own expense
The social security payment terms purpose rule that string is got in return.Relative to the Outlier Detection Algorithm based on index, nested abnormal circulation inspection
Method of determining and calculating avoids the building of index structure, it is intended to minimize the number of I/O.It the cushion space dimidiation of memory,
Data acquisition system is divided into several logical blocks.By selecting logical block to be packed into the sequence of each buffer area meticulously, I/O efficiency can
Improve.
In the present embodiment, by the medical data input deviation detection model, pass through the data in separate-blas estimation model
Washing moulding cleans medical data, is gone to a doctor data with the specification after being cleaned；Medical data configuration is standardized to described
Text feature, to obtain term vector, and by the two-way RNN submodel in separate-blas estimation model by term vector be converted into sentence to
Moment matrix；The operation of attention mechanism is carried out based on the sentence vector matrix, to obtain normal data；Based on separate-blas estimation model
In Outlier Detection Algorithm the normal data is detected, determine whether there is in the medical data according to testing result
The social security payment project got in return by string at one's own expense.By the above-mentioned means, realizing first through separate-blas estimation model just
It examines data and is converted into normal data, to be conducive to the detection of abnormal data, and then improve the correctness of anomaly data detection.
Based on the above embodiment, the 3rd embodiment for proposing social security violation detection method of the present invention, referring to Fig. 4, this implementation
In example, step S70 includes:
Step S80 is identified based on the medical insurance in the normal data to social security payment terms purpose medicine in the normal data
Object information or diagnosis and treatment item information are classified；
It based on the above embodiment, in the present embodiment, include the medicine of medication in the therapeutic process of insured people in data of going to a doctor
Items mesh and diagnosis and treatment item etc. treat service item, and one of medical data drug or a diagnosis and treatment item correspond to one and control
Service item is treated, includes multiple treatment service items in data of going to a doctor in general.Treatment service item can be divided into project at one's own expense
With social security payment project.Wherein, project refers to refusing the treatment service item that insured people is submitted an expense account by social security at one's own expense.Social security
Payment project refers to that social security gives the treatment service item of insured people part expense reimbursement.The society got in return by string at one's own expense
Payment project is protected to refer to being based on preset standard, such as three catalogues, it will in the data uploaded for project at one's own expense, medical institutions' terminal
It is classified as social security payment terms therapeutic interest service item, i.e. medical institutions will change social security by string at one's own expense in medical data
Payment terms purpose service item.In the present embodiment, medical institutions' terminal device is operated based on medical institutions relevant staff
The project label at one's own expense or social security payment project label added to drug or diagnosis and treatment item.People society core system receives medical
Data are extracted from normal data after being based on above-mentioned standard matching process acquisition normal data to medical data and carry social security
The medical data of payment project label, name information and corresponding information of submitting an expense account including drug or diagnosis and treatment item.
It may include the differences such as Class A drug, Class B drugs, Class A diagnosis and treatment item, Class B diagnosis and treatment item in this social security payment project label
The mark of type.People society core system divides each social security payment project in the social security payment project label based on extraction
Class, the classification of classification may include Class A drug, Class B drugs, Class A diagnosis and treatment item, Class B diagnosis and treatment item etc..
Step S90 compares classification results and preset standard classified catalogue, determines whether classification results are marked with pre-
Quasi- classified catalogue matching；
Preset standard classified catalogue in the present embodiment is social security loan standard catalogue, including allowable drug or is examined
Social security type belonging to the name information for the treatment of project and each name information, specifically, preset standard classified catalogue can be
Three catalogues of each department.Then the standard classification lists such as classification results and three catalogues are compared, determine each drug or examined
Whether the classification results for the treatment of project match with three catalogues.During the classification results of drug or diagnosis and treatment item are matched,
For certain drug, the name information that whether there is the drug in three catalogues is judged, if the name information is not present in three catalogues
The classification results and three catalogues for then determining the drug mismatch；If there are the name informations of the drug in three catalogues, it is determined that should
Whether whether the corresponding grade of name information is consistent with the class information of classification results, i.e., be all first-class or the second grade, if inconsistent,
The classification results and three catalogues for then determining the drug mismatch.If class information is consistent.
Step S100, if classification results and preset standard classified catalogue mismatch, it is determined that exist in the medical data
The social security payment project got in return by string at one's own expense.
If some drug or diagnosis and treatment item classification results and the classification results of three catalogues mismatch, it is determined that the drug or
Person's diagnosis and treatment item is the social security payment project got in return by string at one's own expense, that is, can determine in medical data and exist by project at one's own expense
The social security payment project exchanged.Using the name information of drug or diagnosis and treatment item, diagnosis and treatment quantity or amount of money involved as
Violation abnormal data.Specifically, if in classification results, by toothwash this classification of the items to Class B diagnosis and treatment item, and in three mesh
Toothwash project is not present in the Class B diagnosis and treatment item of record, then the toothwash project in data of going to a doctor is to be got in return by string at one's own expense
Social security payment project, the related datas such as amount of money involved are abnormal data.
In the present embodiment, based on the medical insurance mark in the normal data to social security payment project in the normal data
Drug information or diagnosis and treatment item information classify；Classification results and preset standard classified catalogue are compared, determines and divides
Whether class result matches with preset standard classified catalogue；If classification results and preset standard classified catalogue mismatch, it is determined that institute
State the social security payment project for existing in medical data and being got in return by string at one's own expense.By the above-mentioned means, realize based on drug or
The classification results of diagnosis and treatment item information and the matching result of preset standard classified catalogue determine in medical data with the presence or absence of by certainly
The social security payment project that expense string is got in return.
Based on the above embodiment, the fourth embodiment for proposing social security violation detection method of the present invention, referring to Fig. 5, this implementation
In example, step S70 includes:
Step S110 determines society in the normal data based on the related information of the disease and drug or diagnosis and treatment item that prestore
Protect the applicable disease information of payment terms purpose drug or diagnosis and treatment item；
Based on the above embodiment, in the present embodiment, it is applicable in disease information and refers to that drug or diagnosis and treatment item play treatment
The disease information of effect.In the present embodiment, it by the information of each drug or diagnosis and treatment item and drug or can examine in advance
The disease information that treatment project plays therapeutic effect is associated, and generates the related information of disease and drug or diagnosis and treatment item, and
Related information is stored in predeterminated position.During carrying out abnormality detection, the related information according to above-mentioned predeterminated position is true
Surely each drug or diagnosis and treatment item correspond to associated disease information in medical data, using associated disease information as drug or
The applicable disease information of diagnosis and treatment item.
Step S120 is applicable in described the disease information that disease information is applied with insured people and compares, determines described suitable
Whether matched with disease information with the disease information that insured people applies；
In the present embodiment, the identity informations such as the insured account number of insured people can be extracted from medical data, based on insured
The identity information of people extracts the disease information of insured people's application.The disease information of insured people's application refers to the society of insured people's application
Protect reimbursement disease information.After determining the applicable disease information of each drug or diagnosis and treatment item, by applicable disease information and ginseng
The disease information of guarantor's application compares, and determines whether the two matches, so that it is determined that being applicable in whether disease belongs to insured people Shen
Disease please.
Step S130, if it is described be applicable in disease information and insured people application disease information mismatch, it is determined that it is described just
Examine the social security payment project for existing in data and being got in return by string at one's own expense.
If being applicable in the disease information that disease information is applied with insured people and mismatching, illustrate the drug or diagnosis and treatment item
Be applicable in the disease that disease is not insured people application, the drug or diagnosis and treatment item are not belonging to social security payment project, but by from
The social security payment project that expense string is got in return.
In the present embodiment, the normal data is determined based on the related information of the disease and drug or diagnosis and treatment item that prestore
The applicable disease information of middle social security payment terms purpose drug or diagnosis and treatment item；The applicable disease information and insured people are applied
Whether disease information compares, determine and described be applicable in disease information and match with the disease information that insured people applies；If described suitable
It is mismatched with the disease information of disease information and insured people application, it is determined that exist in the medical data and exchanged by project at one's own expense
Obtained social security payment project.By the above-mentioned means, realize applicable disease information based on drug or diagnosis and treatment item with it is insured
The matching result of the disease information of people's application, which determines, pays in medical data with the presence or absence of the social security got in return by string at one's own expense
Project.
Based on the above embodiment, the 5th embodiment for proposing social security violation detection method of the present invention, referring to Fig. 6, this implementation
In example, include: after step S30
Step S140 generates punishment managing detailed catalogue according to default punishment rule and the abnormal data；
In the present embodiment, if detecting, there are abnormal datas in medical data, search default punishment in the database
Rule, and rule of punishing is then according to this and abnormal data generates punishment managing detailed catalogue, which is set by technical staff,
Punishment managing detailed catalogue includes abnormal data information, and the information such as punishment Action Message based on abnormal data can also include punishment
Title, punishment reason, punishment mechanism, penalty minutes of object etc..
Step S150 sends notice of punishment to the terminal of insured people or medical institutions and right according to the punishment managing detailed catalogue
Insured people or medical institutions punish.
In the present embodiment, insured people or medical institutions can be sent to using punishment managing detailed catalogue as notice of punishment information
Terminal device, i.e., the terminal device of each medical institutions.Notice of punishment is sent to mobile terminal by people society core system, and certainly
It is dynamic that insured people or medical institutions are punished, wherein the number of insured people's preset time period violation operation can also to be counted, really
Determine the degree of punitive measures, for example, warning, fine etc., alternatively, in the pre- behavior for detecting that insured people or medical institutions have violation
When, related prompt can be carried out, pre- behavior refers to behavioural analysis prediction insured people's purchase next time according to the purchase drug of insured people
It buys drug and is up to violation operation, reminding method can be short message telephone notice or wechat message notifying etc..
In the present embodiment, punishment managing detailed catalogue is generated according to default punishment rule and the abnormal data；According to described
Punishment managing detailed catalogue sends notice of punishment and punishes to the terminal of insured people or medical institutions and to insured people or medical institutions.
Medical institutions are punished based on violation data by the above-mentioned means, realizing, pipe is carried out with the violation operation to medical institutions
Control, reduces the generation of violations of rules and regulations.
Based on sixth embodiment, the 7th embodiment of social security violation detection method of the present invention is proposed, referring to Fig. 8, this implementation
In example, step S140 includes:
Step S160 counts insured people or medical institutions according to the abnormal data according to the default punishment rule timing
Social security payment terms purpose violation number or the violation amount of money will be changed by string at one's own expense, and obtain corresponding statistical result；
In the present embodiment, people society core system can go to a doctor data according to the history for obtaining insured people or medical institutions,
And society will be changed by string at one's own expense according to what the history of insured people or medical institutions went to a doctor the insured people of data statistics or medical institutions
Payment terms purpose history violation number or the violation amount of money are protected, the violation amount of money of the present embodiment, which can be, changes string at one's own expense into society
It protects payment terms purpose social security payment terms purpose and counts the amount of money.
Step S170 determines that the statistics is tied based on the preset association relationship of violation number or the violation amount of money and discipline rating
The discipline rating of fruit；
Different violation number or the violation amount of money correspond to different punishment levels in punishment rule, so, it is first determined
Insured people or medical institutions' history violation number number or violation amount of money range corresponding in punishment rule, with according to should
Numbers range determines the discipline rating of insured people or medical institutions.
Step S180, the punishment that the preset association relationship based on discipline rating and punishment measure obtains current discipline rating are arranged
Apply information；
In the present embodiment, when history violation number is in different numbers ranges, corresponding discipline rating is different, according to
Punishment rule determines the numbers range where history violation number, and the corresponding punishment measure of determined number range, for example, at this
The first estate, the second grade, tertiary gradient etc. can be divided by penalizing grade, and the first estate, which corresponds to punishment measure and can be warning, to be mentioned
Show, the corresponding punishment measure of the second grade, which can be, carries out certain amount of money fine, and the corresponding punishment measure of the tertiary gradient can be
Medical insurance card etc. is nullified, of course, it is possible to according to numbers range pair different where the history violation number of insured people or medical institutions
Insured people or medical institutions carry out the fine of the different amount of money.
Step S190 generates the punishment managing detailed catalogue based on the punishment Action Message and the abnormal data.
After determining current punishment Action Message, using abnormal data as the punishment certificate of punishment Action Message, based on punishment
Action Message and abnormal data information generate punishment managing detailed catalogue.Wherein, punishing in managing detailed catalogue includes to insured people or medical treatment
The specific punishment Action Message of mechanism, such as deducted amount, punishment managing detailed catalogue further includes being exchanged as social security payment terms purpose
The name information of drug or diagnosis and treatment item, the quantity of drug or diagnosis and treatment item or amount of money involved information can also include
The information such as relevant punishment regulations or the method for determination for punishing Action Message.
In the present embodiment, insured people or medical treatment are counted according to the abnormal data according to the default punishment rule timing
Mechanism will change social security payment terms purpose violation number or the violation amount of money by string at one's own expense, obtain corresponding statistical result；Base
The discipline rating of the statistical result is determined in the preset association relationship of violation number or the violation amount of money and discipline rating；Based on separated
Rule grade and the preset association relationship for punishing measure obtain the punishment Action Message of current discipline rating；Based on the punishment measure
Information and the abnormal data generate the punishment managing detailed catalogue.It is hit by the above-mentioned means, realizing according to insured people or medical treatment
The history violation number in drum Europe carries out different punishment measures to insured people or medical institutions, to be punished automatically, improves
To the supervisory efficiency of outpatient service risk-pooling fund.
In addition, the embodiment of the present invention also provides a kind of social security violation detection device.
It is the functional block diagram of social security violation detection device first embodiment of the present invention referring to Fig. 8, Fig. 8.
Social security violation detection device of the present invention is virtual bench, is stored in the storage of the detection device of social security violation shown in Fig. 1
In device 1005, the institute for detecting program in violation of rules and regulations for realizing social security is functional: obtaining insured people and settles accounts medical expenditure by social security card
Medical data；By the medical data input deviation detection model, determined in the medical data by separate-blas estimation model
Drug in repel each other drug with the presence or absence of first, wherein described first repels each other drug refers to cannot simultaneous drug；If medicine
Repel each other drug in product there are first, it is determined that the medical data exception, and the abnormal data in the medical data is extracted, with
The punishment certificate punished to insured people or medical institutions is provided.
Specifically, in the present embodiment, the social security violation detection device includes:
Module 10 is obtained, the medical data of expense of seeing and treating patients are settled accounts by social security card for obtaining insured people；
Detection module 10, for determining institute by separate-blas estimation model for the medical data input deviation detection model
It states in medical data with the presence or absence of the social security payment project got in return by string at one's own expense；
Extraction module 30, if for there is the social security payment project got in return by string at one's own expense in data of going to a doctor, really
The fixed medical data exception, and extract the abnormal data in the medical data, with provide to insured people or medical institutions into
The punishment certificate of row punishment.
Further, the detection module is also used to:
By the medical data input deviation detection model, by the Data Cleaning Model in separate-blas estimation model to medical
Data are cleaned, and are gone to a doctor data with the specification after being cleaned；
Medical data configuration text feature is standardized to described, to obtain term vector, and by double in separate-blas estimation model
Sentence vector matrix is converted by term vector to RNN submodel；
The operation of attention mechanism is carried out based on the sentence vector matrix, to obtain normal data；
The normal data is detected based on the Outlier Detection Algorithm in separate-blas estimation model, according to testing result really
With the presence or absence of the social security payment project got in return by string at one's own expense in the fixed medical data.
Further, the detection module is also used to:
Based on the medical insurance mark in the normal data to social security payment terms purpose drug information in the normal data or
Diagnosis and treatment item information is classified；
Classification results and preset standard classified catalogue are compared, determine classification results whether with preset standard classify mesh
Record matching；
If classification results and preset standard classified catalogue mismatch, it is determined that exist in the medical data by project at one's own expense
The social security payment project exchanged.
Further, the detection module is also used to:
Social security payment terms in the normal data are determined based on the related information of the disease and drug or diagnosis and treatment item that prestore
The applicable disease information of purpose drug or diagnosis and treatment item；
It is applicable in the disease information that disease information is applied with insured people by described and compares, determine the applicable disease information
Whether matched with the disease information of insured people application；
If the disease information mismatch for being applicable in disease information and insured people application, it is determined that deposited in the medical data
In the social security payment project got in return by string at one's own expense.
Further, the social security violation detection device further include:
Generation module, for generating punishment managing detailed catalogue according to default punishment rule and the abnormal data；
Module is punished, for sending notice of punishment to insured people or the terminal of medical institutions according to the punishment managing detailed catalogue
And insured people or medical institutions are punished.
Further, the generation module is also used to:
Counting insured people or medical institutions according to the abnormal data according to the default punishment rule timing will item at one's own expense
Mesh exchanges into social security payment terms purpose violation number or the violation amount of money, obtains corresponding statistical result；
The violation of the statistical result is determined based on the preset association relationship of violation number or the violation amount of money and discipline rating
Grade；
Preset association relationship based on discipline rating and punishment measure obtains the punishment Action Message of current discipline rating；
The punishment managing detailed catalogue is generated based on the punishment Action Message and the abnormal data.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium.
Social security detection program in violation of rules and regulations is stored on computer readable storage medium of the present invention, wherein the social security detects in violation of rules and regulations
When program is executed by processor, realize such as the step of above-mentioned social security violation detection method.
Wherein, social security violation detection program, which is performed realized method, can refer to social security violation detection method of the present invention
Each embodiment, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of social security violation detection method, which is characterized in that the social security violation detection method includes:
Obtain the medical data that insured people settles accounts expense of seeing and treating patients by social security card；
By the medical data input deviation detection model, being determined in the medical data by separate-blas estimation model whether there is
The social security payment project got in return by string at one's own expense；
If there is the social security payment project got in return by string at one's own expense in medical data, it is determined that the medical data exception,
And the abnormal data in the medical data is extracted, to provide the punishment certificate punished to insured people or medical institutions.
2. social security violation detection method as described in claim 1, which is characterized in that described by the medical data input deviation
Detection model is determined in the medical data by separate-blas estimation model and is paid with the presence or absence of the social security got in return by string at one's own expense
The step of expense project includes:
By the medical data input deviation detection model, by the Data Cleaning Model in separate-blas estimation model to medical data
It is cleaned, is gone to a doctor data with the specification after being cleaned；
Medical data configuration text feature is standardized to described, to obtain term vector, and passes through the two-way RNN in separate-blas estimation model
Term vector is converted sentence vector matrix by submodel；
The operation of attention mechanism is carried out based on the sentence vector matrix, to obtain normal data；
The normal data is detected based on the Outlier Detection Algorithm in separate-blas estimation model, determines institute according to testing result
It states in medical data with the presence or absence of the social security payment project got in return by string at one's own expense.
3. social security violation detection method as claimed in claim 2, which is characterized in that described based on different in separate-blas estimation model
Normal detection algorithm detects the normal data, is determined in the medical data according to testing result with the presence or absence of by one's own expense
The social security payment terms purpose step that string is got in return includes:
It is identified based on the medical insurance in the normal data to social security payment terms purpose drug information or diagnosis and treatment in the normal data
Project information is classified；
Classification results and preset standard classified catalogue are compared, determine classification results whether with preset standard classified catalogue
Match；
If classification results and preset standard classified catalogue mismatch, it is determined that exist in the medical data and exchanged by project at one's own expense
Obtained social security payment project.
4. social security violation detection method as claimed in claim 2, which is characterized in that described based on different in separate-blas estimation model
Normal detection algorithm detects the normal data, is determined in the medical data according to testing result with the presence or absence of by one's own expense
The social security payment terms purpose step that string is got in return includes:
Social security payment terms purpose in the normal data is determined based on the related information of the disease and drug or diagnosis and treatment item that prestore
The applicable disease information of drug or diagnosis and treatment item；
It is applicable in the disease information that disease information is applied with insured people by described and compares, determine the applicable disease information and ginseng
Whether the disease information of guarantor's application matches；
If it is described be applicable in disease information and insured people application disease information mismatch, it is determined that in the medical data exist by
The social security payment project that string is got in return at one's own expense.
5. social security violation detection method as described in claim 1, which is characterized in that if existing in the medical data by one's own expense
The social security payment project that string is got in return, it is determined that the medical data exception, and extract the exception in the medical data
Include: after the step of data, the punishment certificate punished with offer to insured people or medical institutions
Punishment managing detailed catalogue is generated according to default punishment rule and the abnormal data；
Notice of punishment is sent to the terminal of insured people or medical institutions and to insured people or medical treatment according to the punishment managing detailed catalogue
Mechanism is punished.
6. social security violation detection method as claimed in claim 5, which is characterized in that the default punishment of the basis is regular and described
Abnormal data generate punishment managing detailed catalogue the step of include:
Counting insured people or medical institutions according to the abnormal data according to the default punishment rule timing will string at one's own expense
It changes social security payment terms purpose violation number or the violation amount of money into, obtains corresponding statistical result；
The discipline rating of the statistical result is determined based on the preset association relationship of violation number or the violation amount of money and discipline rating；
Preset association relationship based on discipline rating and punishment measure obtains the punishment Action Message of current discipline rating；
The punishment managing detailed catalogue is generated based on the punishment Action Message and the abnormal data.
7. social security violation detection method as claimed in claim 2, which is characterized in that the Outlier Detection Algorithm is followed including nesting
Ring Outlier Detection Algorithm.
8. a kind of social security violation detection device, which is characterized in that the social security violation detection device includes:
Module is obtained, the medical data of expense of seeing and treating patients are settled accounts by social security card for obtaining insured people；
Detection module, for being determined the medical data input deviation detection model by separate-blas estimation model described medical
With the presence or absence of the social security payment project got in return by string at one's own expense in data；
Extraction module, if for there is the social security payment project got in return by string at one's own expense in data of going to a doctor, it is determined that described
Medical data exception, and the abnormal data in the medical data is extracted, insured people or medical institutions are punished with providing
Punishment certificate.
9. a kind of social security violation detection device, which is characterized in that the social security violation detection device include processor, memory,
And be stored on the memory and program can be detected by the social security that the processor executes in violation of rules and regulations, wherein the social security is in violation of rules and regulations
When detection program is executed by the processor, realizing the social security violation detection method as described in any one of claims 1 to 7
Step.
10. a kind of computer readable storage medium, which is characterized in that be stored with social security on the computer readable storage medium and disobey
Rule detection program, wherein realizing such as any one of claims 1 to 7 when social security violation detection program is executed by processor
The step of described social security violation detection method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811530845.6A CN109636648A (en) | 2018-12-13 | 2018-12-13 | Social security violation detection method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811530845.6A CN109636648A (en) | 2018-12-13 | 2018-12-13 | Social security violation detection method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636648A true CN109636648A (en) | 2019-04-16 |
Family
ID=66073821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811530845.6A Pending CN109636648A (en) | 2018-12-13 | 2018-12-13 | Social security violation detection method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636648A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517050A (en) * | 2019-08-12 | 2019-11-29 | 太平洋医疗健康管理有限公司 | A kind of medical insurance, which instead cheats to exchange, encodes digging system and method |
| CN111429289A (en) * | 2020-03-23 | 2020-07-17 | 平安医疗健康管理股份有限公司 | Single disease identification method and device, computer equipment and storage medium |
| CN112582054A (en) * | 2020-12-11 | 2021-03-30 | 北京软通智慧城市科技有限公司 | Medical insurance data supervision method and device, electronic equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| CN105141842A (en) * | 2015-08-31 | 2015-12-09 | 广州市幸福网络技术有限公司 | Tamper-proof license camera system and method |
| CN106447500A (en) * | 2016-11-09 | 2017-02-22 | 北京好运到信息科技有限公司 | Method for scoring according to matching degree of diseases and drugs and system of scoring method |
| CN206021351U (en) * | 2016-07-01 | 2017-03-15 | 中国人民解放军总医院第一附属医院 | Army's ground medical insurance is required to report his or her problems within a prescribed time and in a prescribed place and runs hospitalization cost settlement system |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN108154443A (en) * | 2017-07-18 | 2018-06-12 | 邹鑫洋 | A kind of medical treatment medical insurance data processing equipment and method |
-
2018
- 2018-12-13 CN CN201811530845.6A patent/CN109636648A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| CN105141842A (en) * | 2015-08-31 | 2015-12-09 | 广州市幸福网络技术有限公司 | Tamper-proof license camera system and method |
| CN206021351U (en) * | 2016-07-01 | 2017-03-15 | 中国人民解放军总医院第一附属医院 | Army's ground medical insurance is required to report his or her problems within a prescribed time and in a prescribed place and runs hospitalization cost settlement system |
| CN106447500A (en) * | 2016-11-09 | 2017-02-22 | 北京好运到信息科技有限公司 | Method for scoring according to matching degree of diseases and drugs and system of scoring method |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN108154443A (en) * | 2017-07-18 | 2018-06-12 | 邹鑫洋 | A kind of medical treatment medical insurance data processing equipment and method |
Non-Patent Citations (1)
| Title |
|---|
| 周如意: "基于BP神经网络和关联规则的智能医疗保险稽核系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517050A (en) * | 2019-08-12 | 2019-11-29 | 太平洋医疗健康管理有限公司 | A kind of medical insurance, which instead cheats to exchange, encodes digging system and method |
| CN111429289A (en) * | 2020-03-23 | 2020-07-17 | 平安医疗健康管理股份有限公司 | Single disease identification method and device, computer equipment and storage medium |
| CN111429289B (en) * | 2020-03-23 | 2023-03-24 | 平安医疗健康管理股份有限公司 | Single disease identification method and device, computer equipment and storage medium |
| CN112582054A (en) * | 2020-12-11 | 2021-03-30 | 北京软通智慧城市科技有限公司 | Medical insurance data supervision method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11900473B2 (en) | Method of personalizing, individualizing, and automating the management of healthcare fraud-waste-abuse to unique individual healthcare providers | |
| US20200242626A1 (en) | Fraud lead detection system for efficiently processing database-stored data and automatically generating natural language explanatory information of system results for display in interactive user interfaces | |
| CN111145844B (en) | Comprehensive medical supervision platform | |
| Aral et al. | A prescription fraud detection model | |
| CN109685670A (en) | Social security violation detection method, device, equipment and computer readable storage medium | |
| CN107785058A (en) | Anti- fraud recognition methods, storage medium and the server for carrying safety brain | |
| CN109635044A (en) | Hospitalization data method for detecting abnormality, device, equipment and readable storage medium storing program for executing | |
| CN102013084A (en) | System and method for detecting fraudulent transactions in medical insurance outpatient services | |
| CN109636648A (en) | Social security violation detection method, device, equipment and computer storage medium | |
| CN109615547A (en) | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine | |
| CN109671476A (en) | Recognition methods, device, terminal and the computer readable storage medium of unrelated medication | |
| CN109409619A (en) | Prediction technique, device, medium and the electronic equipment of public sentiment trend | |
| CN109636650A (en) | Recognition methods, device, terminal and the readable storage medium storing program for executing of therapeutic regimen exception | |
| CN109636645A (en) | Medical insurance monitoring and managing method, unit and computer readable storage medium | |
| US11361381B1 (en) | Data integration and prediction for fraud, waste and abuse | |
| Evans | Economic regulation of next-generation sequencing | |
| Iyengar et al. | Computer-aided auditing of prescription drug claims | |
| US10776890B1 (en) | Generation from data threats and predictive application of the data models | |
| Gao et al. | Predicting opioid use disorder and associated risk factors in a Medicaid managed care population. | |
| CN109215756A (en) | A kind of medicine assisting in diagnosis and treatment system | |
| CN109615538A (en) | Social security violation detection method, device, equipment and computer storage medium | |
| CN109377059A (en) | A kind of data processing method and equipment based on risk management and control | |
| CN109598633A (en) | Social security violation detection method, device, equipment and computer storage medium | |
| CN109615546A (en) | Extremely medical recognition methods, device, terminal and computer readable storage medium | |
| CN109636646A (en) | Extremely medical recognition methods, device, terminal and computer readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |