CN109616185A - The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations - Google Patents
The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations Download PDFInfo
- Publication number
- CN109616185A CN109616185A CN201811526943.2A CN201811526943A CN109616185A CN 109616185 A CN109616185 A CN 109616185A CN 201811526943 A CN201811526943 A CN 201811526943A CN 109616185 A CN109616185 A CN 109616185A
- Authority
- CN
- China
- Prior art keywords
- medical institutions
- diagnosis
- inspection
- threshold value
- frequency threshold
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 210
- 238000001514 detection method Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003745 diagnosis Methods 0.000 claims abstract description 150
- 230000006399 behavior Effects 0.000 claims abstract description 61
- 230000007246 mechanism Effects 0.000 claims description 51
- 239000013598 vector Substances 0.000 claims description 39
- 230000015654 memory Effects 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006835 compression Effects 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 5
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 abstract description 8
- 238000004422 calculation algorithm Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 239000003814 drug Substances 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000001225 therapeutic effect Effects 0.000 description 4
- 230000002457 bidirectional effect Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012797 qualification Methods 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
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000010297 mechanical methods and process Methods 0.000 description 1
- 230000005226 mechanical processes and functions Effects 0.000 description 1
- 230000001404 mediated effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses methods and relevant device that inspection item behavior is issued in a kind of detection in violation of rules and regulations, method includes: the diagnosis and treatment data for obtaining medical institutions and uploading, and Forecasting recognition is carried out using diagnosis and treatment data as the input of preset data identification model, to obtain diagnosis and treatment data label;The inspection number of each user within a preset time is obtained from diagnosis and treatment data label;The inspection number of any user within a preset time is judged whether there is more than frequency threshold value;When being more than frequency threshold value there are the inspection number of any user within a preset time, determine that medical institutions issue inspection item behavior in the presence of violation.The present invention is using the preset data identification model based on machine learning algorithm as prediction model, to obtain diagnosis and treatment data label;User is obtained according to diagnosis and treatment data label and checks number in medical institutions, then compared with the frequency threshold value set, to detect that medical institutions with the presence or absence of the behavior for issuing inspection item in violation of rules and regulations, reduce the waste of medical insurance risk-pooling fund, intelligent decision-making.
Description
Technical field
The present invention relates to electronic information fields, more particularly to detection issues the method for inspection item behavior in violation of rules and regulations and correlation is set
It is standby.
Background technique
Medical insurance refers to social medical insurance, is state and society according to certain laws and regulations, for the labor into scope of insurance coverage
The social security system moving basic medical demand guarantee when person provides illness and establishing.The funds of basic medical insurance is by risk-pooling fund
It is constituted with personal account.In user after designated medical organization completes treatment, designated medical organization can be to mechanism, locals society
Apply risk-pooling fund to pay expenses for medicine.Although medical insurance system gives everybody with convenience, but still have criminal using country and
The medibank policy that society is given checks that the means of inspection project carry out arbitrage by opening in user's treatment more, causes
The waste of medical insurance risk-pooling fund.
Summary of the invention
The main purpose of the present invention is to provide a kind of detections to issue the method and relevant device of inspection item behavior in violation of rules and regulations,
Aim to solve the problem that current medical institutions check that inspection project carries out arbitrage by opening more, the technology for causing medical insurance risk-pooling fund to waste is asked
Topic.
To achieve the above object, the present invention provides a kind of method that detection issues inspection item behavior in violation of rules and regulations, comprising steps of
The diagnosis and treatment data that medical institutions upload are obtained, and using the diagnosis and treatment data as the input of preset data identification model
Forecasting recognition is carried out, to obtain diagnosis and treatment data label;
The inspection number of each user within a preset time is obtained from the diagnosis and treatment data label;
Inspection number of any user in the preset time is judged whether there is more than frequency threshold value;
When the inspection number that there are any users in the preset time is more than frequency threshold value, the therapeutic machine is determined
Structure issues inspection item behavior in the presence of violation.
Optionally, the inspection number of any user in the preset time that judge whether there is is more than frequency threshold value
The step of before, further includes:
According to the diagnosis and treatment data label, it is always secondary to obtain inspection item of the medical institutions in the preset time
Number;
By the inspection item total degree multiplied by preset ratio, frequency threshold value is obtained.
Optionally, described when the inspection number that there are any users in the preset time is more than frequency threshold value, really
There is the step of issuing inspection item behavior in violation of rules and regulations in the fixed medical institutions
When the inspection number that there are any users in the preset time is more than frequency threshold value, the therapeutic machine is obtained
The history of structure checks number;
Number is checked according to the history of the medical institutions, assesses whether the medical institutions meet default check item contents
Number exemption condition;
When the medical institutions, which do not meet default inspection item number, exempts condition, determines that the medical institutions exist and disobey
Rule issue inspection item behavior;
After whether the assessment medical institutions meet the step of default inspection item number exempts condition, also wrap
It includes:
When the medical institutions, which meet default inspection item number, exempts condition, determining the medical institutions, there is no disobey
Rule issue inspection item behavior.
Optionally, the inspection number of any user in the preset time that judge whether there is is more than frequency threshold value
The step of before, further includes:
Obtain the mechanism grade of the medical institutions;
According to the mechanism grade of the medical institutions, the corresponding frequency threshold value of the mechanism grade is obtained, wherein mechanism etc.
The frequency threshold value of the low medical institutions of grade is less than the frequency threshold value of the high medical institutions of mechanism grade.
Optionally, the mechanism grade according to the medical institutions obtains the corresponding frequency threshold value of the mechanism grade
The step of include:
According to the mechanism grade of the medical institutions, the corresponding frequency threshold value range of the mechanism grade is determined;
According to the diagnosis and treatment data label, it is always secondary to obtain inspection item of the medical institutions in the preset time
Number;
The calculated result obtained after the inspection item total degree is multiplied by preset ratio is not in the frequency threshold value range
When interior, using the calculated result as the frequency threshold value;
The calculated result obtained after the inspection item total degree is multiplied by preset ratio is within the scope of the frequency threshold value
When, using the median of the frequency threshold value range as the frequency threshold value.
Optionally, the inspection number of any user in the preset time that judge whether there is is more than frequency threshold value
The step of after, further includes:
When inspection number of each user in the preset time is less than frequency threshold value, according to the diagnosis and treatment number
According to label, each user is obtained in the preset time in the inspection number of each department of the medical institutions;
The corresponding history of each department for obtaining the medical institutions checks number, and is examined according to the corresponding history of each department
It looks into number and determines the corresponding inspection frequency threshold value of each department;
Judge in preset time whether each user in the inspection number of each department of the medical institutions is more than correspondence
The inspection frequency threshold value of department;
When any user in any department of the medical institutions checks that number is more than corresponding department in preset time
When checking frequency threshold value, determine that the medical institutions issue inspection item behavior in the presence of violation.
Optionally, described to carry out Forecasting recognition for the diagnosis and treatment data as the input of preset data identification model, to obtain
Diagnosis and treatment data label the step of include:
According to the default noise entity dictionary in preset data identification model, the noise text in the diagnosis and treatment data is screened out
Data, to obtain standard diagnosis and treatment data;
The standard diagnosis and treatment data are segmented, obtain multiple diagnosis and treatment text participles, and each diagnosis and treatment text is segmented
Be converted to corresponding term vector;
The sequence of all term vectors is obtained, and according to the sequence of each term vector, by preset data identification model
Bidirectional circulating neural network RNN model encodes all term vectors, forms text matrix;
By the text matrix compression be diagnosis and treatment text vector after, pass through the prediction in the preset data identification model
Network is predicted, the corresponding diagnosis and treatment data label of the diagnosis and treatment text vector is obtained.
In addition, to achieve the above object, the present invention also provides a kind of detection systems, comprising:
Module is obtained, for obtaining the diagnosis and treatment data of medical institutions' upload, and using the diagnosis and treatment data as preset data
The input of identification model carries out Forecasting recognition, to obtain diagnosis and treatment data label;
The acquisition module is also used to obtain the inspection of each user within a preset time from the diagnosis and treatment data label
Number;
Judgment module, for judging whether there is inspection number of any user in the preset time more than number threshold
Value;
Determining module, for when the inspection number that there are any users in the preset time be more than frequency threshold value when,
Determine that the medical institutions issue inspection item behavior in the presence of violation.
In addition, to achieve the above object, the present invention also provides a kind of detection device, the detection device includes: communication mould
Block, memory, processor and it is stored in the computer program that can be run on the memory and on the processor, the meter
The step of detection as described above issues the method for inspection item behavior in violation of rules and regulations is realized when calculation machine program is executed by the processor.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
It is stored with computer program on storage medium, detection as described above is realized when the computer program is executed by processor in violation of rules and regulations
The step of issuing the method for inspection item behavior.
The diagnosis and treatment data that the present invention is uploaded by obtaining medical institutions, and identified the diagnosis and treatment data as preset data
The input of model carries out Forecasting recognition, to obtain diagnosis and treatment data label;Each user is obtained from the diagnosis and treatment data label to exist
Inspection number in preset time;Inspection number of any user in the preset time is judged whether there is more than number threshold
Value;When the inspection number that there are any users in the preset time is more than frequency threshold value, determine that the medical institutions deposit
Inspection item behavior is being issued in violation of rules and regulations.To which prediction mould will be used as based on the preset data identification model of machine learning algorithm
Type, on the basis of obtaining diagnosis and treatment data label, by the user that will be obtained according to diagnosis and treatment data label medical institutions inspection
Number is looked into, is compared with frequency threshold value, determines that medical institutions, can with the presence or absence of the behavior for checking inspection project is issued in violation of rules and regulations
It was found that medical institutions carry out the behavior of arbitrage to user's Duo Kai inspection item, reduce the waste of medical insurance risk-pooling fund, decision ten
Divide intelligence.
Detailed description of the invention
Fig. 1 is the structural schematic diagram for the hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram for one embodiment of method that inspection item behavior is issued in present invention detection in violation of rules and regulations;
Fig. 3 is the flow diagram for another embodiment of method that inspection item behavior is issued in present invention detection in violation of rules and regulations;
Fig. 4 is the refinement stream that step S10 in the another embodiment of method of inspection item behavior is issued in present invention detection in violation of rules and regulations
Journey schematic diagram;
Fig. 5 is the modular structure schematic diagram that detection system of the present invention unifies embodiment.
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.
Fig. 1 is please referred to, Fig. 1 is the hardware structural diagram of detection device 100 provided by the present invention, the detection device
100 can be server, computer, at least one of the equipment for being exclusively used in medical institutions' abnormality detection, including communication module
10, the components such as memory 20 and processor 30.Wherein, the processor 30 respectively with the memory 20 and the communication module
10 connect, and are stored with computer program on the memory 20, the computer program is executed by processor 30 simultaneously.
Communication module 10 can be connect by network with external equipment.Communication module 10 can receive external communications equipment hair
Request out, can also broadcast transmission information acquisition device event, instruction and information to the external communications equipment.The outside
Communication apparatus can be other detection devices or medical institutions' terminal.It should be noted that medical institutions' terminal is medical institutions
Staff be used to upload the terminals of diagnosis and treatment data, can be the settlement terminal for calculating medical expense, can be and issue medicine
Prescription and/or the terminal for checking inspection project, can also be paying service terminal of independently registering.
Memory 20 can be used for storing software program and various data.Memory 20 can mainly include storing program area
The storage data area and, wherein storing program area can application program needed for storage program area, at least one function (for example connect
Receive the diagnosis and treatment data that medical institutions upload) etc.;Storage data area, which can be stored, uses created data according to detection device 100
Or information etc..In addition, memory 20 may include high-speed random access memory, it can also include nonvolatile memory, example
Such as at least one disk memory, flush memory device or other volatile solid-state parts.
Processor 30 is the control centre of detection device 100, utilizes various interfaces and the entire detection device of connection
100 various pieces, by running or executing the software program and/or module that are stored in memory 20, and calling storage
Data in memory 20 execute the various functions and processing data of detection device 100, to carry out to detection device 100
Integral monitoring.Processor 30 may include one or more processing units;Optionally, processor 30 can integrate application processor and tune
Demodulation processor processed, wherein the main processing operation system of application processor, user interface and application program etc., modulatedemodulate is mediated
Reason device mainly handles wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 30.
Although Fig. 1 is not shown, above-mentioned detection device 100 can also include circuit control module, be used for and modules
Electrical connection, guarantees the normal work of other modules.Above-mentioned detection device 100 can also include display module, for showing in violation of rules and regulations
The detection process and testing result of behavior.
It will be understood by those skilled in the art that the structure of detection device 100 shown in Fig. 1 is not constituted to detection device
100 restriction may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
Based on above-mentioned hardware configuration, each embodiment of the method for the present invention is proposed.
Referring to Fig. 2, in an embodiment of the method that present invention detection issues inspection item behavior in violation of rules and regulations, the detection is disobeyed
Rule issue inspection item behavior method comprising steps of
Step S10 obtains the diagnosis and treatment data that medical institutions upload, and identifies mould for the diagnosis and treatment data as preset data
The input of type carries out Forecasting recognition, to obtain diagnosis and treatment data label;
The present embodiment is applied to the third-party institution detected to diagnosis and treatment data, and the third-party institution for example can be
Social medical insurance management board.
Medical institutions can be used terminal and upload diagnosis and treatment data to detection device, such as can be when patient is in medical institutions
It is medical or checked when being settled accounts, patient's diagnosis and treatment data with insured qualification are uploaded by the settlement terminal of medical institutions
To the server of the third-party institution.Above-mentioned diagnosis and treatment data be have the patient of insured qualification medical institutions carry out outpatient service and/or
The medical data generated when in hospital, cost detail during may include the medical diagnosis on disease data of patient, treatment issue inspection inspection
The prescription that the doctor of the inventory and medical institutions of testing project and/or drug issues.
After obtaining diagnosis and treatment data, detection device can be by the preset data identification model in memory by diagnosis and treatment data
Identification is matched in corresponding standardization field, and to obtain diagnosis and treatment data label, each diagnosis and treatment data label can be a reality
Numerical value, a vector or a kind of class label etc., as long as can identify that diagnosis and treatment data are corresponding by the diagnosis and treatment data label
Content.Wherein preset data identification model is constructed based on machine learning, has been related to neural network, at natural language
The technologies such as reason and attention mechanism.
Step S20 obtains the inspection number of each user within a preset time from the diagnosis and treatment data label;
Can have by the diagnosis and treatment data label that diagnosis and treatment data and preset data identification model Forecasting recognition obtain it is multiple, often
A diagnosis and treatment data label can indicate part or all of the diagnosis and treatment data content of medical institutions in one dimension.It can be from examining
It treats selection medical institutions in data label and issues whole diagnosis and treatment data labels on this dimension of inspection item, and examined according to these
It treats data label and obtains each user within a preset time in the inspection number of medical institutions.Wherein preset time can be one
Week, one month, a season or 1 year.Certain preset time can also be set according to the detection time of the third-party institution
It sets.
Step S30 judges whether there is inspection number of any user in the preset time more than frequency threshold value;
Since medical institutions realize arbitrage often through to user Duo Kai inspection item, then a user checks that number is got over
It is more, medical institutions are just represented in the presence of higher a possibility that issuing inspection item behavior in violation of rules and regulations.Therefore frequency threshold value can be set, led to
It crosses and is compared the inspection number of the frequency threshold value each user medical with medical institutions, confirmation medical institutions are with the presence or absence of separated
Rule issue the behavior that inspection item carries out arbitrage.
Wherein frequency threshold value can be configured according to actual needs, such as according to province where medical institutions and/or city
Permanent resident population's quantity in city is determined, and can be determined according to the mechanism grade of medical institutions, can also be according to therapeutic machine
The popularity or history of structure check that number is determined.
For example, the setting process of the frequency threshold value may comprise steps of:
According to the diagnosis and treatment data label, it is always secondary to obtain inspection item of the medical institutions in the preset time
Number;
Wherein the inspection item total degree of medical institutions is all inspections that all departments of user are done in preset time
Look into number be added after obtain as a result, represent inspection item quantity situation of the medical institutions in certain section of preset time.At this
It is all diagnosis and treatment data labels acquirement that basis issues this dimension of inspection item in embodiment, or can also be by all users
Inspection number within a preset time is added to obtain.
By the inspection item total degree multiplied by preset ratio, frequency threshold value is obtained.
It should be noted that preset ratio is that the third-party institution is configured according to actual needs, general all medical treatment
The corresponding preset ratio of mechanism is all the same, such as preset ratio is 80%, when inspection item total degree is equal to 400, number threshold
Value is equal to 400*80%=320.Whether the inspection number that single user is measured by the inspection item total degree of acquisition is exceeded,
Discovery certain user can be protruded during the inspection process, the excessive unlawful practice of number is checked caused by medical institutions.
Step S40 determines institute when the inspection number that there are any users in the preset time is more than frequency threshold value
It states medical institutions and issues inspection item behavior in the presence of violation.
As long as any one the inspection number of user within a preset time is more than frequency threshold value, that is, think that medical institutions utilize
The information of the user opens inspection item more and has carried out arbitrage behavior, and the medical institutions that inspection item is issued in confirmation issue in the presence of violation
Inspection item behavior.When the judging result of step S30 is that the inspection number of all users within a preset time is less than number
When threshold value, determining the medical institutions, there is no the behaviors for issuing inspection item in violation of rules and regulations.
The diagnosis and treatment data that the present embodiment is uploaded by obtaining medical institutions, and know the diagnosis and treatment data as preset data
The input of other model carries out Forecasting recognition, to obtain diagnosis and treatment data label;Each user is obtained from the diagnosis and treatment data label
Inspection number within a preset time;Inspection number of any user in the preset time is judged whether there is more than number
Threshold value;When the inspection number that there are any users in the preset time is more than frequency threshold value, the medical institutions are determined
In the presence of issuing inspection item behavior in violation of rules and regulations.To which prediction mould will be used as based on the preset data identification model of machine learning algorithm
Type, on the basis of obtaining diagnosis and treatment data label, by the user that will be obtained according to diagnosis and treatment data label medical institutions inspection
Number is looked into, is compared with frequency threshold value, determines that medical institutions, can with the presence or absence of the behavior for checking inspection project is issued in violation of rules and regulations
It was found that medical institutions carry out the behavior of arbitrage to user's Duo Kai inspection item, reduce the waste of medical insurance risk-pooling fund, decision intelligence
Energyization.
Optionally, it can use following anomalous identification algorithm when being detected using frequency threshold value to be detected, comprising:
Using all diagnosis and treatment data labels relevant to inspection item is issued obtained by preset data identification model as data space
It is divided, data space is divided into side length equal to d/ (2*k1/2) unit.Each unit there are two layer around it, first
The thickness of layer is a unit, and the thickness of the second layer is int [2*k1/2-1].The algorithm one by one counts abnormal point to unit,
Rather than it is counted one by one object.The unit given for one, its accumulative three counting: the number of object in unit
(cell_count), in unit and first layer in the number (cell_+_1_layer_count) of object, unit and two levels
Object number (cell_+_2_layers_count).All objects if cell_+_1_layer_count > M, in unit
It is not abnormal;If cell_+_2_layers_count≤M, all objects in unit are all abnormal;Otherwise, in unit
Certain some data may be abnormal.The detection for carrying out abnormal point numerical to each of data space element is changed to by the algorithm
The detection that abnormal point numerical is carried out to each unit, improves the efficiency of anomalous identification.
Further, in other embodiments, the step S40 includes:
Step S41 obtains institute when the inspection number that there are any users in the preset time is more than frequency threshold value
The history for stating medical institutions checks number;And number is checked according to the history of the medical institutions, assessing the medical institutions is
It is no to meet default inspection item number exemption condition;If it is not, thening follow the steps S42;If so, thening follow the steps S43;
The history of the medical institutions wherein obtained checks that number can be the inspection number of medical institutions over the years.Default inspection
Look into project number exempt condition can be set according to actual needs, such as nearly 5 years medical institutions inspection item number not
More than the first preset limit value, or over the years, the monthly inspection item number of medical institutions is no more than second preset limit value etc.
Deng as long as the history that can embody medical institutions checks number and checks that number wants much less compared to other medical institutions, or even only
When being the sum of the inspection number of several users of other medical institutions, it is believed that the medical institutions meet default inspection item number and exempt
Condition.
Step S42 determines that the medical institutions issue inspection item behavior in the presence of violation;
If medical institutions do not meet exemption condition, that is, think that the medical institutions are not under specific position or specific condition
Medical institutions, and it has been more than frequency threshold value that the medical institutions have the inspection number of any user within a preset time, therefore
The medical institutions issue inspection item behavior in the presence of violation.
Step S43, determining the medical institutions, there is no issue inspection item behavior in violation of rules and regulations.
Since medical institutions meet exemption condition, it can be considered that the medical institutions are under specific position or specific condition
Medical institutions, it may be possible to certain patient needs because of the state of an illness so the case where there is amount of testing more than frequency threshold value.Wherein
Frequency threshold value is to be determined according to the inspection total degree of medical institutions within a preset time multiplied by preset ratio, due to medical treatment itself
The whole of mechanism checks that radix is smaller, once therefore certain patient need repeated detection because of the state of an illness, be easy for leading to the patient's
Amount of testing is greater than frequency threshold value.
The diagnosis report of the patient can also further be obtained, it is determined whether can exclude to issue inspection item behavior in violation of rules and regulations
Suspicion, if according to the diagnosis report of the patient determination do not need to issue so multiple checks for this patient, then it is assumed that should
Medical institutions issue inspection item behavior in the presence of violation.Conversely, then excluding the behavior that medical institutions issue inspection item in violation of rules and regulations.It is logical
It crosses and presets inspection item number exemption condition, the medical institutions for excluding special circumstances is helped to check that number is few, causes throughout the year
The case where some patientss need multiple checks to be more than frequency threshold value because of the state of an illness prevents because special circumstances cause to detect
The situation of inaccuracy.
Further, referring to Fig. 3, in another embodiment, before the step S30, further includes:
Step S21 obtains the mechanism grade of the medical institutions;
The mechanism grade of above-mentioned medical institutions can be country according to hospital's function, facility, technical force etc. pair
The index of hospital's aptitude assessment, such as medical institutions in CONTINENTAL AREA OF CHINA are divided into three-level ten etc. by evaluation.
In the present embodiment, the acquisition methods of the mechanism grade of medical institutions can be the title or word for obtaining medical institutions
Number, it is searched from presetting database according to title or font size and obtains the mechanism grade of the medical institutions, wherein in presetting database
It is stored with all medical institutions' title/font sizes and corresponding mechanism grade.Alternatively, can also website from medical institutions and Jie
Learn the mechanism level condition of medical institutions in the place of continuing.
Step S22 obtains the corresponding frequency threshold value of the mechanism grade according to the mechanism grade of the medical institutions,
The frequency threshold value of the low medical institutions of middle mechanism grade is less than the frequency threshold value of the high medical institutions of mechanism grade.
Corresponding frequency threshold value can be set previously according to all mechanism grades, then in the mechanism etc. of confirmation medical institutions
After grade, the frequency threshold value of the medical institutions can be obtained.Exactly because it is understood that general hospital's function, facility and
Forward medical institutions, technical force, there are larger great disparities for the medical institutions low compared to mechanism grade in strength, so that
User can more be ready the high medical institutions of selection mechanism grade, therefore medical institutions in actual mechanical process during medical treatment
Mechanism higher grade, corresponding frequency threshold value is bigger.The technical solution of the present embodiment is conducive to the doctor to different institutions grade
It treats mechanism and carries out different frequency threshold value restrictions, increase the hommization setting of detection device, also more close to the practical feelings of detection
Condition.
Optionally, can also on this basis, province carries out the further setting of frequency threshold value in conjunction with where medical institutions,
I.e. for the medical institutions of the same grade in different province areas, the frequency threshold value of inspection item is different.Such as it is big in permanent resident population
The frequency threshold value of the medical institutions of province is bound to be greater than the few province of permanent resident population.It further, can also will be more famous
The frequency threshold value for issuing inspection item of hospital improves.The further protection of this programme is conducive to for various areas and grade
Medical institutions carry out inspection item frequency threshold value classifying rationally.
Above-mentioned steps S22 may comprise steps of:
Step S221 determines the corresponding frequency threshold value model of the mechanism grade according to the mechanism grade of the medical institutions
It encloses;
This programme be using in mechanism grade and preset time inspection item total degree combine carry out frequency threshold value into
One step determines.Each corresponding pre-set frequency threshold value range of different mechanism grades, which can
To be the historical data determination for having collected the corresponding all medical institutions of the mechanism grade.
Step S222 obtains inspection of the medical institutions in the preset time according to the diagnosis and treatment data label
Project total degree;And judge inspection item total degree multiplied by the calculated result obtained after preset ratio whether in the frequency threshold value
In range;If it is not, thening follow the steps S223;If so, thening follow the steps S224;
Actually this programme is using inspection item total degree in preset time as the first preferential ginseng for determining frequency threshold value
Factor is examined, using the frequency threshold value range determined by historical data as the second preferential reference factor.It can be when first will be default
The inspection item total degree of Jian Nei medical institutions is multiplied with preset ratio, then by the product being calculated and frequency threshold value range
It is compared, with determined number threshold value.
Step S223, using the calculated result as the frequency threshold value;
Step S224, using the median of the frequency threshold value range as the frequency threshold value.
If calculated result not within the scope of frequency threshold value, utilizes the first preferential reference factor determined number threshold value, i.e.,
Using calculated result as frequency threshold value.If calculated result is within the scope of frequency threshold value, right in conjunction with the second preferential reference factor
Calculated result is modified, and is using the median of frequency threshold value range as frequency threshold value.By frequency threshold value is arranged two
A reference factor keeps the setting of frequency threshold value more accurate suitable.
Optionally, continuing with reference to Fig. 2, in another embodiment, after the step S30, further includes:
Step S50, when inspection number of each user in the preset time is less than frequency threshold value, according to institute
Diagnosis and treatment data label is stated, obtains in the preset time each user in the inspection number of each department of the medical institutions;
The present embodiment is to check the further comparison carried out after number in the whole of medical institutions comparing each user
Operation.It can be according to diagnosis and treatment data label, acquisition issues each user in inspection item dimension in the inspection of different department
Number.
Step S60, the corresponding history of each department for obtaining the medical institutions check number, and corresponding according to each department
History check number determine the corresponding inspection frequency threshold value of each department;
Wherein the history of each department of medical institutions checks that number can be directly according to the diagnosis and treatment number of medical institutions over the years
Obtained according to label, can also the report statement data according to disclosed in medical institutions obtained.Each department is corresponding to be checked time
The setting of number threshold value can be set according to actual needs, such as can be the history over the years inspection number for choosing nearly N,
Middle N is the integer greater than 1, and history over the years is taken to check the average value of number as inspection frequency threshold value.Alternatively, can also take out at random
It takes the history in some department N number of time to check number, history is checked into inspection number threshold of the maximum value of number as the department
Value.Optionally, the average value or maximum value that obtained history can also be checked number are multiplied by the result obtained after preset ratio
As inspection frequency threshold value.
Step S70, judge each user in preset time each department of the medical institutions inspection number whether
More than the inspection frequency threshold value of corresponding department;
Step S80, when in preset time any user any department of the medical institutions inspection number be more than pair
When answering the inspection frequency threshold value of department, determine that the medical institutions issue inspection item behavior in the presence of violation.
After the inspection frequency threshold value of each department has been determined, the processor of detection device can be by each user each
The inspection number of department is compared one by one, simply by the presence of a user any one department inspection number be more than the department
Inspection frequency threshold value, then it is assumed that medical institutions in the presence of issuing the behavior of inspection item, and the section where unlawful practice in violation of rules and regulations
Room is when the inspection number of user within a preset time is more than to check frequency threshold value in inspection number one by one comparison process
Department.
This programme is under the premise of integrally checking number comparison, by the inspection frequency threshold value of each department of setting and each
User is compared in the inspection number of the department, confirms that each department of medical institutions issues inspection item with the presence or absence of violation
Behavior.The unlawful practice of medical institutions can be found in time, reduced the waste of medical risk-pooling fund, detected wide coverage,
Help is quickly found out unlawful practice and position occurs.
Further, referring to fig. 4, in another embodiment, the step S10 includes:
Step S11 obtains the diagnosis and treatment data that medical institutions upload;
It is obtained in the present embodiment in the realization process and previous embodiment for the diagnosis and treatment data that medical institutions upload unanimously, herein
Without repeating.
Step S12 is screened out in the diagnosis and treatment data according to the default noise entity dictionary in preset data identification model
Noise text data, to obtain standard diagnosis and treatment data;
Default noise entity dictionary be it is pre- first pass through training and obtain, wherein be stored with noise text data, for example including
Label symbol, annotation text and JS (JavaScript) code.It is examined according to noise entity dictionary iteration diagnosis and treatment data with eliminating
The noise text data in data is treated, i.e., the standard diagnosis and treatment data of exportable noiseless text data are realized to diagnosis and treatment data
Received text fields match.
Step S13 segments the standard diagnosis and treatment data, obtains multiple diagnosis and treatment texts participle, and by each diagnosis and treatment
Text participle is converted to corresponding term vector;
Standard diagnosis and treatment data are the diagnosis and treatment texts removed after making an uproar, can be by diagnosis and treatment text dividing at several diagnosis and treatment by participle
Text participle, all diagnosis and treatment text participles constitute diagnosis and treatment text participle set.The side that standard diagnosis and treatment data are segmented
Method can be executed with reference to existing participle tool and segmentation methods, herein without repeating.
After by standard diagnosis and treatment data participle, diagnosis and treatment text can also be segmented and carry out the classification of word variant.Word variant is sorted out
Refer to that all differences by diagnosis and treatment text participle change into standardized format.Such as can use preset standard semanteme dictionary,
By regular expression or manual compiling dictionary field, by the word being not present in standard semantic dictionary or word from all diagnosis and treatment
It is found out in text participle and is deleted or corrected.Word variant classification help is carried out more by segmenting to all diagnosis and treatment texts
The good semanteme for quickly identifying diagnosis and treatment data, realizes text standardization.
In the present embodiment, diagnosis and treatment text can be segmented into vectorization, obtain each diagnosis and treatment text segment corresponding word to
It measures (Word embedding).The term vector is the vector that diagnosis and treatment text participle is mapped to real number, can either indicate word sheet
Body, and semantic distance can be considered.
Step S14 obtains the sequence of all term vectors, and according to the sequence of each term vector, is identified by preset data
Bidirectional circulating neural network RNN model in model encodes all term vectors, forms text matrix;
The sequence of term vector can be analogous to and put in order, and be to utilize two-way RNN (Recurrent in this programme
Neural Network, Recognition with Recurrent Neural Network) model is reference with the sequence of sentence in diagnosis and treatment text, after splitting conversion
Term vector recompiles combination and forms text matrix.Every a line of this text matrix indicates each word institute's table within a context
The meaning reached, is equivalent to term vector.
Above-mentioned two-way RNN model is the neural network of processing sequence data, can establish power between neuron between layers
Connection can be according to script diagnosis and treatment after the forward direction for carrying out every a line term vector by two-way RNN model calculates and inversely calculates
The sequence order that text segments corresponding term vector splices and combines term vector, to obtain complete text matrix, or cry sentence to
Moment matrix.
Step S15, by the text matrix compression be diagnosis and treatment text vector after, pass through the preset data identification model
In prediction network predicted, obtain the corresponding diagnosis and treatment data label of the diagnosis and treatment text vector.
Can first by text matrix compression at diagnosis and treatment text vector, then by diagnosis and treatment text vector be sent into prediction network in into
Row prediction, so that study obtains diagnosis and treatment data label.It should be noted that diagnosis and treatment data label, which can be model, understands diagnosis and treatment text
The volume of data obtained after this, these data can be divided into each diagnosis and treatment data label in the form of data generation time, also
It can be ranked up in conjunction with information such as user and sufferers.
Wherein, prediction network can be using standard Architecture of Feed-forward Neural Network and Recursive Neural Network Structure etc..This programme
Simple forecast process be that will standardize field to be input to LTSM (Long Short-Term Memory, length memory network)
In, to export continuous label characteristics, these continuous label characteristics are run by feedforward neural network;Simultaneously by diagnosis and treatment text
Vector is also sent to feedforward neural network, with extracted vector feature, then vector characteristics cascades up to be formed with label characteristics
Vector-label characteristics;Vector-label binding characteristic is finally combined to the diagnosis and treatment data label for being used to predict output.
This programme passes through nerve net according to the sequence of term vector after diagnosis and treatment data segment dyad by noise remove
Network is encoded and is predicted to obtain diagnosis and treatment data label, how is given by preset data identification model progress Forecasting recognition
The process of diagnosis and treatment data label is obtained, is also helped the prescription provided including doctor, the inspection inspection item issued and/or drug
The contents such as inventory diagnosis and treatment Data Matching into corresponding standardization field, reflect word in diagnosis and treatment data in the text
Meaning.
The present invention also proposes that a kind of detection system, the detection system can be server, and computer is exclusively used in therapeutic machine
At least one of the equipment of structure abnormality detection;Referring to Fig. 5, in one embodiment, the detection system includes:
Module 10 is obtained, for obtaining the diagnosis and treatment data of medical institutions' upload, and using the diagnosis and treatment data as present count
Forecasting recognition is carried out according to the input of identification model, to obtain diagnosis and treatment data label;
The acquisition module 10 is also used to obtain the inspection of each user within a preset time from the diagnosis and treatment data label
Look into number;
Judgment module 20, for judging whether there is inspection number of any user in the preset time more than number
Threshold value;
Determining module 30, for being more than frequency threshold value when the inspection number that there are any users in the preset time
When, determine that the medical institutions issue inspection item behavior in the presence of violation.
Optionally, in another embodiment, the detection system further includes computing module;Wherein,
The acquisition module is also used to obtain the medical institutions when described default according to the diagnosis and treatment data label
Interior inspection item total degree;
The computing module, for the inspection item total degree multiplied by preset ratio, to be obtained frequency threshold value.
Optionally, in another embodiment, the determining module includes;
First acquisition unit, for being more than frequency threshold value when the inspection number that there are any users in the preset time
When, the history for obtaining the medical institutions checks number;
Assessment unit assesses whether the medical institutions meet for checking number according to the history of the medical institutions
Default inspection item number exempts condition;
First determination unit, for determining when the medical institutions do not meet default inspection item number and exempt condition
The medical institutions issue inspection item behavior in the presence of violation;And it is exempted when the medical institutions meet default inspection item number
When condition, determining the medical institutions, there is no issue inspection item behavior in violation of rules and regulations.
Optionally, in another embodiment, the acquisition module is also used to obtain the mechanism grade of the medical institutions;
And according to the mechanism grade of the medical institutions, the corresponding frequency threshold value of the mechanism grade is obtained, wherein mechanism grade is low
The frequency threshold value of medical institutions is less than the frequency threshold value of the high medical institutions of mechanism grade.
Optionally, in another embodiment, the acquisition module includes:
Second determination unit determines the mechanism grade corresponding time for the mechanism grade according to the medical institutions
Number threshold range;
Second acquisition unit, for obtaining the medical institutions in the preset time according to the diagnosis and treatment data label
Interior inspection item total degree;
Execution unit, the calculated result for obtaining after the inspection item total degree is multiplied by preset ratio is not described
When within the scope of frequency threshold value, using the calculated result as the frequency threshold value;And when the inspection item total degree is multiplied by pre-
If the calculated result obtained after ratio is within the scope of the frequency threshold value, using the median of the frequency threshold value range as institute
State frequency threshold value.
Optionally, in another embodiment,
The acquisition module is also used to be less than number threshold when inspection number of each user in the preset time
When value, according to the diagnosis and treatment data label, each user in the preset time is obtained in each department of the medical institutions
Check number;
The acquisition module, the corresponding history of each department for being also used to obtain the medical institutions check number, and according to
The corresponding history of each department checks that number determines the corresponding inspection frequency threshold value of each department;
The judgment module is also used to judge that each user is in the inspection of each department of the medical institutions in preset time
Look into number whether be more than corresponding department inspection frequency threshold value;
The determining module is also used in the preset time any user in the inspection of any department of the medical institutions
When number is more than the inspection frequency threshold value of corresponding department, determine that the medical institutions issue inspection item behavior in the presence of violation.
Optionally, in another embodiment, the acquisition module includes:
Unit is screened out, for screening out the diagnosis and treatment number according to the default noise entity dictionary in preset data identification model
Noise text data in, to obtain standard diagnosis and treatment data;
Converting unit is segmented, for segmenting to the standard diagnosis and treatment data, obtains multiple diagnosis and treatment text participles, and will
Each diagnosis and treatment text participle is converted to corresponding term vector;
Coding unit passes through preset data for obtaining the sequence of all term vectors, and according to the sequence of each term vector
Bidirectional circulating neural network RNN model in identification model encodes all term vectors, forms text matrix;
Predicting unit, for by the text matrix compression be diagnosis and treatment text vector after, known by the preset data
Prediction network in other model is predicted, the corresponding diagnosis and treatment data label of the diagnosis and treatment text vector is obtained.
The present invention also proposes a kind of computer readable storage medium, is stored thereon with computer program.The computer can
Read storage medium can be the memory 20 in the detection device 100 of Fig. 1, be also possible to as ROM (Read-Only Memory,
Read-only memory)/RAM (Random Access Memory, random access memory), magnetic disk, at least one of CD, institute
State computer readable storage medium include some instructions use so that one with processor terminal device (can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
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 alternative embodiments of the invention, are 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 method that detection issues inspection item behavior in violation of rules and regulations, which is characterized in that comprising steps of
The diagnosis and treatment data that medical institutions upload are obtained, and are carried out the diagnosis and treatment data as the input of preset data identification model
Forecasting recognition, to obtain diagnosis and treatment data label;
The inspection number of each user within a preset time is obtained from the diagnosis and treatment data label;
Inspection number of any user in the preset time is judged whether there is more than frequency threshold value;
When the inspection number that there are any users in the preset time is more than frequency threshold value, determine that the medical institutions deposit
Inspection item behavior is being issued in violation of rules and regulations.
2. the method that detection as described in claim 1 issues inspection item behavior in violation of rules and regulations, which is characterized in that described to judge whether
There are any users before the step of inspection number in the preset time is more than frequency threshold value, further includes:
According to the diagnosis and treatment data label, inspection item total degree of the medical institutions in the preset time is obtained;
By the inspection item total degree multiplied by preset ratio, frequency threshold value is obtained.
3. the method that detection as claimed in claim 2 issues inspection item behavior in violation of rules and regulations, which is characterized in that described to appoint when existing
When inspection number of one user in the preset time is more than frequency threshold value, determine that the medical institutions issue inspection in the presence of violation
The step of looking into project behavior include:
When the inspection number that there are any users in the preset time is more than frequency threshold value, the medical institutions are obtained
History checks number;
According to the history of the medical institutions check number, assess the medical institutions whether meet default inspection item number slit
Exempt from condition;
When the medical institutions, which do not meet default inspection item number, exempts condition, determine that the medical institutions open in the presence of violation
Has inspection item behavior;
Whether the assessment medical institutions meet after the step of default inspection item number exempts condition, further includes:
When the medical institutions, which meet default inspection item number, exempts condition, determining the medical institutions, there is no open in violation of rules and regulations
Has inspection item behavior.
4. the method that detection as described in claim 1 issues inspection item behavior in violation of rules and regulations, which is characterized in that described to judge whether
There are any users before the step of inspection number in the preset time is more than frequency threshold value, further includes:
Obtain the mechanism grade of the medical institutions;
According to the mechanism grade of the medical institutions, the corresponding frequency threshold value of the mechanism grade is obtained, wherein mechanism grade is low
The frequency threshold values of medical institutions be less than the frequency threshold values of the high medical institutions of mechanism grade.
5. the method that detection as claimed in claim 4 issues inspection item behavior in violation of rules and regulations, which is characterized in that described according to
The mechanism grade of medical institutions, the step of obtaining the mechanism grade corresponding frequency threshold value include:
According to the mechanism grade of the medical institutions, the corresponding frequency threshold value range of the mechanism grade is determined;
According to the diagnosis and treatment data label, inspection item total degree of the medical institutions in the preset time is obtained;
When the calculated result obtained after the inspection item total degree is multiplied by preset ratio is not within the scope of the frequency threshold value,
Using the calculated result as the frequency threshold value;
It, will when the calculated result obtained after the inspection item total degree is multiplied by preset ratio is within the scope of the frequency threshold value
The median of the frequency threshold value range is as the frequency threshold value.
6. the method that detection as described in claim 1 issues inspection item behavior in violation of rules and regulations, which is characterized in that described to judge whether
There are any users after the step of inspection number in the preset time is more than frequency threshold value, further includes:
When inspection number of each user in the preset time is less than frequency threshold value, according to the diagnosis and treatment data mark
Label obtain in the preset time each user in the inspection number of each department of the medical institutions;
The corresponding history of each department for obtaining the medical institutions checks number, and according to the corresponding history inspection time of each department
Number determines the corresponding inspection frequency threshold value of each department;
Judge in preset time whether each user in the inspection number of each department of the medical institutions is more than corresponding department
Inspection frequency threshold value;
When any user in any department of the medical institutions checks that number is more than the inspection of corresponding department in preset time
When frequency threshold value, determine that the medical institutions issue inspection item behavior in the presence of violation.
7. the method that detection as claimed in any one of claims 1 to 6 issues inspection item behavior in violation of rules and regulations, which is characterized in that described
Forecasting recognition is carried out using the diagnosis and treatment data as the input of preset data identification model, the step of to obtain diagnosis and treatment data label
Include:
According to the default noise entity dictionary in preset data identification model, the noise textual data in the diagnosis and treatment data is screened out
According to obtain standard diagnosis and treatment data;
The standard diagnosis and treatment data are segmented, obtain multiple diagnosis and treatment text participles, and each diagnosis and treatment text is segmented and is converted
For corresponding term vector;
The sequence of all term vectors is obtained, and according to the sequence of each term vector, by two-way in preset data identification model
Recognition with Recurrent Neural Network RNN model encodes all term vectors, forms text matrix;
By the text matrix compression be diagnosis and treatment text vector after, pass through the prediction network in the preset data identification model
It is predicted, obtains the corresponding diagnosis and treatment data label of the diagnosis and treatment text vector.
8. a kind of detection system characterized by comprising
Module is obtained, is identified for obtaining the diagnosis and treatment data of medical institutions' upload, and using the diagnosis and treatment data as preset data
The input of model carries out Forecasting recognition, to obtain diagnosis and treatment data label;
The acquisition module is also used to obtain each user inspection within a preset time time from the diagnosis and treatment data label
Number;
Judgment module, for judging whether there is inspection number of any user in the preset time more than frequency threshold value;
Determining module, for determining when the inspection number that there are any users in the preset time is more than frequency threshold value
The medical institutions issue inspection item behavior in the presence of violation.
9. a kind of detection device, which is characterized in that the detection device includes: communication module, memory, processor and is stored in
On the memory and the computer program that can run on the processor, the computer program are executed by the processor
The step of detection of the Shi Shixian as described in any one of claims 1 to 7 issues the method for inspection item behavior in violation of rules and regulations.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes that the detection as described in any one of claims 1 to 7 is issued in violation of rules and regulations when the computer program is executed by processor
The step of method of inspection item behavior.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526943.2A CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811526943.2A CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109616185A true CN109616185A (en) | 2019-04-12 |
Family
ID=66007676
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811526943.2A Pending CN109616185A (en) | 2018-12-13 | 2018-12-13 | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109616185A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110672864A (en) * | 2019-06-26 | 2020-01-10 | 金寓润泽(北京)科技有限责任公司 | Clinical medical body fluid detection quality control method, device and system |
CN110727711A (en) * | 2019-10-14 | 2020-01-24 | 平安医疗健康管理股份有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
WO2021068601A1 (en) * | 2019-10-12 | 2021-04-15 | 平安国际智慧城市科技股份有限公司 | Medical record detection method and apparatus, device and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1704961A (en) * | 2004-05-26 | 2005-12-07 | 冲博子 | Analysis method for diagnosis and treatment behavior and administration |
CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
CN103514576A (en) * | 2013-09-06 | 2014-01-15 | 深圳民太安信息技术有限公司 | Screening method for illegal cashing of social security treatment |
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 |
CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
CN107123072A (en) * | 2017-05-11 | 2017-09-01 | 杭州逸曜信息技术有限公司 | Medical expense restriction rule generation method |
CN107451400A (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 act monitoring method and system |
CN108022635A (en) * | 2017-11-01 | 2018-05-11 | 平安科技(深圳)有限公司 | Violation document methods of marking, violation document scoring apparatus and computer-readable recording medium |
CN108648810A (en) * | 2018-05-11 | 2018-10-12 | 平安医疗健康管理股份有限公司 | Data processing method, device and the computer readable storage medium of medicine audit |
CN108960463A (en) * | 2018-06-28 | 2018-12-07 | 厦门安盟网络股份有限公司 | Reserving method, medium, terminal device and the system of medical examination project |
-
2018
- 2018-12-13 CN CN201811526943.2A patent/CN109616185A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1704961A (en) * | 2004-05-26 | 2005-12-07 | 冲博子 | Analysis method for diagnosis and treatment behavior and administration |
CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
CN103514576A (en) * | 2013-09-06 | 2014-01-15 | 深圳民太安信息技术有限公司 | Screening method for illegal cashing of social security treatment |
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 |
CN105159948A (en) * | 2015-08-12 | 2015-12-16 | 成都数联易康科技有限公司 | Medical insurance fraud detection method based on multiple features |
CN107123072A (en) * | 2017-05-11 | 2017-09-01 | 杭州逸曜信息技术有限公司 | Medical expense restriction rule generation method |
CN107451400A (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 act monitoring method and system |
CN108022635A (en) * | 2017-11-01 | 2018-05-11 | 平安科技(深圳)有限公司 | Violation document methods of marking, violation document scoring apparatus and computer-readable recording medium |
CN108648810A (en) * | 2018-05-11 | 2018-10-12 | 平安医疗健康管理股份有限公司 | Data processing method, device and the computer readable storage medium of medicine audit |
CN108960463A (en) * | 2018-06-28 | 2018-12-07 | 厦门安盟网络股份有限公司 | Reserving method, medium, terminal device and the system of medical examination project |
Non-Patent Citations (1)
Title |
---|
朱明, 中国科学技术大学出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110672864A (en) * | 2019-06-26 | 2020-01-10 | 金寓润泽(北京)科技有限责任公司 | Clinical medical body fluid detection quality control method, device and system |
CN110672864B (en) * | 2019-06-26 | 2023-05-02 | 北京华视诺维医疗科技有限公司 | Quality control method, equipment and system for clinical medical body fluid detection |
WO2021068601A1 (en) * | 2019-10-12 | 2021-04-15 | 平安国际智慧城市科技股份有限公司 | Medical record detection method and apparatus, device and storage medium |
CN110727711A (en) * | 2019-10-14 | 2020-01-24 | 平安医疗健康管理股份有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
CN110727711B (en) * | 2019-10-14 | 2023-10-27 | 深圳平安医疗健康科技服务有限公司 | Method and device for detecting abnormal data in fund database and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20050137912A1 (en) | Systems and methods for automated classification of health insurance claims to predict claim outcome | |
CN110910976A (en) | Medical record detection method, device, equipment and storage medium | |
US20120173289A1 (en) | System and method for detecting and identifying patterns in insurance claims | |
CN109616185A (en) | The method and relevant device of inspection item behavior are issued in detection in violation of rules and regulations | |
Schneider | Locked out by big data: how big data algorithms and machine learning may undermine housing justice | |
CN112686022A (en) | Method and device for detecting illegal corpus, computer equipment and storage medium | |
CN110472011B (en) | Litigation cost prediction method and device and terminal equipment | |
Aires et al. | Norm conflict identification in contracts | |
CN109685670A (en) | Social security violation detection method, device, equipment and computer readable storage medium | |
CN114265967A (en) | Sensitive data security level marking method and device | |
Chatterjee et al. | Classifying facts and opinions in Twitter messages: a deep learning-based approach | |
Pandey et al. | Analyses and detection of health insurance fraud using data mining and predictive modeling techniques | |
Ohata et al. | A text classification methodology to assist a large technical support system | |
Tehler et al. | Designing societal safety: A study of the Swedish crisis management system | |
Prentzas et al. | Assessment of life insurance applications: an approach integrating neuro‐symbolic rule‐based with case‐based reasoning | |
Dimri et al. | A multi-input multi-label claims channeling system using insurance-based language models | |
Lai et al. | BTextCAN: Consumer fraud detection via group perception | |
CN117312514A (en) | Consultation reply method, consultation reply device and computer readable storage medium | |
CN112464670A (en) | Recognition method, recognition model training method, device, equipment and storage medium | |
US20200111054A1 (en) | Automated claims auditing | |
Ullah et al. | A smart secured framework for detecting and averting online recruitment fraud using ensemble machine learning techniques | |
CN114492446B (en) | Legal document processing method and device, electronic equipment and storage medium | |
Li et al. | A deep learning approach of financial distress recognition combining text | |
CN112712270B (en) | Information processing method, device, equipment and storage medium | |
Samadi et al. | Multichannel convolutional neural networks for detecting COVID-19 fake news |
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: 20190412 |