CN107609980A - Medical data processing method, device, computer equipment and storage medium - Google Patents
Medical data processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN107609980A CN107609980A CN201710801892.9A CN201710801892A CN107609980A CN 107609980 A CN107609980 A CN 107609980A CN 201710801892 A CN201710801892 A CN 201710801892A CN 107609980 A CN107609980 A CN 107609980A
- Authority
- CN
- China
- Prior art keywords
- medical
- medical data
- scene
- feature
- examination
- 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
Abstract
The application is related to a kind of medical data processing method, device, computer equipment and storage medium.The above method, including：Medical data is obtained, the medical data includes diagnosis records and/or medication record；The diagnosis records and/or medication record are analyzed, obtain the medical audit scene of the medical data；Choose examination ＆ verification model corresponding with the medical audit scene；The corresponding feature of model is audited with described from medical data extraction by the examination ＆ verification model, and according to the feature calculation medical data risk score；When the risk score is more than the predetermined threshold value with the medical audit scene matching, then the medical data is labeled as suspicious data.Above-mentioned medical data processing method, device, computer equipment and storage medium, insurance fraud behavior can be effectively prevented, reduce public interest loss.
Description
Technical field
The application is related to field of computer technology, is set more particularly to a kind of medical data processing method, device, computer
Standby and storage medium.
Background technology
Social insurance refers to country to prevent and share the social risks such as old, unemployment, disease and death, realizes society
Can be safe, and force what the most members of society participated in, the non-profit-making social safety system with gained reassignment function.Closely
Occur more and more cases swindled using social security card over year, such as undesirable leases social security and snaps into each hospital's set medicine, so
Classification is resell at a profit etc. afterwards so that public interest is severely damaged.
The content of the invention
The embodiment of the present application provides a kind of medical data processing method, device, computer equipment and storage medium, Ke Yiyou
Effect prevents insurance fraud behavior, reduces public interest loss.
A kind of medical data processing method, including：
Medical data is obtained, the medical data includes diagnosis records and/or medication record；
The diagnosis records and/or medication record are analyzed, obtain the medical audit scene of the medical data；
Choose examination ＆ verification model corresponding with the medical audit scene；
Feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to described
The risk score of medical data described in feature calculation；
When the risk score is more than the predetermined threshold value with the medical audit scene matching, then by the medical data
Labeled as suspicious data.
In one of the embodiments, the medical audit scene includes false scene of being in hospital；
It is described that the corresponding feature of model is audited with described from medical data extraction by the examination ＆ verification model, and according to
The risk score of medical data described in the feature calculation, including：
According to the feature of medical data described in examination ＆ verification model extraction corresponding with the false scene of being in hospital, the feature bag
Include length of stay, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity；
Characteristic vector is established according to the feature of extraction, and calculates the characteristic vector and is wrapped with the corresponding examination ＆ verification model
The similarity of each medical sample set contained, each medical sample set to medical sample by being clustered to obtain；
Medical sample set according to belonging to the similarity determines the medical data；
The sample size included according to the affiliated medical sample set calculates the risk score of the medical data.
In one of the embodiments, the medical audit scene includes decomposing scene of being in hospital, described to decompose scene of being in hospital
Including the first sub-scene；
It is described that the corresponding feature of model is audited with described from medical data extraction by the examination ＆ verification model, and according to
The risk score of medical data described in the feature calculation, including：
According to the feature of medical data described in examination ＆ verification model extraction corresponding with first sub-scene, the feature includes
Adjacent consultation time interval；
Most short adjacent consultation time interval is obtained according to the feature of extraction；
According to the risk score of medical data described in the most short adjacent consultation time interval calculation.
In one of the embodiments, the medical audit scene includes decomposing scene of being in hospital, described to decompose scene of being in hospital
Including the second sub-scene；
It is described that the corresponding feature of model is audited with described from medical data extraction by the examination ＆ verification model, and according to
The risk score of medical data described in the feature calculation, including：
According to the feature of medical data described in examination ＆ verification model extraction corresponding with second sub-scene, the feature includes
Adjacent consultation time interval and adjacent medical diagnosis and treatment item；
Most short adjacent consultation time interval and most long adjacent consultation time interval are obtained according to the feature of extraction, and counted
Calculate the similarity of adjacent medical diagnosis and treatment item；
According to the most short adjacent consultation time interval, most long adjacent consultation time interval and the Similarity Measure
The risk score of the medical data.
In one of the embodiments, the medical audit scene includes decomposing scene of being in hospital, described to decompose scene of being in hospital
Including the 3rd sub-scene；
It is described that the corresponding feature of model is audited with described from medical data extraction by the examination ＆ verification model, and according to
The risk score of medical data described in the feature calculation, including：
According to the feature of medical data described in examination ＆ verification model extraction corresponding with the 3rd sub-scene, the feature includes
Physician office visits, accumulative length of stay, accumulative total cost and secondary equal expense；
The hospital mark and disease mark of the medical data are obtained, Hospital Grade is determined according to the hospital mark；
The medical data set matched with the Hospital Grade and disease mark is obtained, counts the medical data collection respectively
Close the average value and standard deviation in each feature；
It is described each according to being calculated respectively with corresponding average value and standard deviation from each feature that the medical data extracts
The criterion score of individual feature；
The criterion score of each feature is weighted to obtain the risk score of the medical data.
In one of the embodiments, before selection examination ＆ verification model corresponding with the medical audit scene, institute
Stating method also includes：
Obtain data filtering condition corresponding with the medical audit scene of the medical data；
When the medical data is unsatisfactory for the data filtering condition, the selection and the medical audit scene are performed
The step of corresponding examination ＆ verification model.
A kind of medical data processing unit, including：
Acquisition module, for obtaining medical data, the medical data includes diagnosis records and/or medication record；
Analysis module, for analyzing the diagnosis records and/or medication record, obtain the medical audit of the medical data
Scene；
Module is chosen, corresponding with the medical audit scene model is audited for choosing；
Computing module, it is corresponding special with the examination ＆ verification model for being extracted by the examination ＆ verification model from the medical data
Sign, and according to the feature calculation medical data risk score；
Mark module, for when the risk score is more than predetermined threshold value with the medical audit scene matching, then
The medical data is labeled as suspicious data.
In one of the embodiments, the medical audit scene includes false scene of being in hospital；
The computing module, including：
Feature extraction unit, for the medical data according to examination ＆ verification model extraction corresponding with the false scene of being in hospital
Feature, the feature includes length of stay, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity；
First computing unit, for establishing characteristic vector according to the feature of extraction, and calculate the characteristic vector with it is described
The similarity of each medical sample set included in corresponding examination ＆ verification model, each medical sample set pass through to medical
Sample is clustered to obtain；
Gather determining unit, for the medical sample set belonging to determining the medical data according to the similarity；
Second computing unit, the sample size for being included according to the affiliated medical sample set calculate the medical treatment
The risk score of data.
A kind of computer equipment, including memory and processor, computer program, the meter are stored in the memory
When calculation machine programmed instruction is by the computing device so that the processor realizes method as described above.
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
Method as described above is realized during row.
Above-mentioned medical data processing method, device, computer equipment and storage medium, medical data is obtained, according to medical treatment
The medical audit scene of data audits model corresponding to choosing, by auditing model from medical data extraction and the examination ＆ verification model pair
The feature answered, and according to feature calculation medical data risk score, when risk score is more than medical audit scene matching
Predetermined threshold value when, then medical data is labeled as suspicious data, can be according to the medical audit scene of medical data automatically to doctor
Treat data correspondingly to be audited, can effectively and accurately detect suspicious medical data, can effectively prevent insurance fraud row
To reduce public interest loss.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of medical data processing method in one embodiment；
Fig. 2 is the schematic flow sheet for the risk score that medical data is calculated in one embodiment；
Fig. 3 is the schematic flow sheet for the risk score that medical data is calculated in another embodiment；
Fig. 4 is the schematic flow sheet for the risk score that medical data is calculated in another embodiment；
Fig. 5 is the schematic flow sheet for the risk score that medical data is calculated in further embodiment；
Fig. 6 is the block diagram of medical data processing equipment in one embodiment；
Fig. 7 is the block diagram of computing module in one embodiment；
Fig. 8 is the block diagram of one embodiment Computer equipment.
Embodiment
In order that the object, technical solution and advantage of the application are more clearly understood, it is right below in conjunction with drawings and Examples
The application is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the application, not
For limiting the application.
As shown in figure 1, in one embodiment, there is provided a kind of medical data processing method, comprise the following steps：
Step 110, medical data is obtained, medical data includes diagnosis records and/or medication record.
Specifically, when the insured people of social insurance needs to carry out medical insurance reimbursement, can be protected by terminal typing medical treatment
Nearly reimbursement information, terminal generate corresponding medical insurance document, and social security card information and this need are may include on medical insurance document
The medical data submitted an expense account, wherein, social security card information may include social security card number, the name of social security card holder, identity card
Number etc., medical data may include visit type, diagnosis and treatment item mark, consultation time, diagnostic result, medicining condition etc., but unlimited
In this.The medical insurance document of generation can be sent to server and carry out document examination ＆ verification by terminal.In one embodiment, server
The medical insurance document of acquisition is buffered in Redis, Redis be one increase income can based on internal memory also can persistence daily record
The speed of Key-Value (key-value) database of type, Redis storages and reading data is all very high, and doctor is read from Redis
Insurance document is treated to be audited.
In one embodiment, when server is audited to the medical insurance document of reading, it can obtain and be protected with the medical treatment
Medical data corresponding to dangerous document, wherein, medical data may include the medical treatment that this needs is submitted an expense account in medical insurance document
Data, and the historical medical data with social security card information matches, medical data may include related to social security card information each
Diagnosis records and/or medication record, wherein, diagnosis records may include visit type, diagnosis and treatment item mark, consultation time, medical
Place, diagnostic result etc., medication record may include drug variety, dosage etc..Visit type refers to the medical treatment of insured people
Type, it may include general out patient service, Priority ward and be in hospital medical etc.；Diagnosis and treatment item refer to various medical technology service accounts and
Using the diagnosis of Medical Instruments, equipment and medical material progress, treatment project, such as Electrocardiography, Ultrasonic Diagnosis etc., diagnosis and treatment
Project label can be the information that title, numbering or letter abbreviations of diagnosis and treatment item etc. can be used for unique mark diagnosis and treatment item.
Step 120, diagnosis records and/or medication record are analyzed, obtains the medical audit scene of medical data.
Specifically, server can analyze the diagnosis records and/or medication record included in medical data, obtain medical data
Medical audit scene, wherein, medical audit scene refers to the insurance fraud scene that medical data may relate to.In one embodiment
In, medical audit scene may include false scene of being in hospital, decompose be in hospital scene and limited medication scene etc., wherein, falseness is lived
Institute's scene is referred to by manufacturing false document and in hospital detailed data in hospital, so as to gain the scene of social security by cheating；Decomposition is in hospital
Scene refer to will once it is normal be in hospital it is medical resolve into Multiple Hospitalization and go to a doctor, so as to gain the scene of social security by cheating；Limited use
Medicine scene refers to having used restriction sex pill in the case where being unsatisfactory for qualifications, can be with so as to gain the scene of social security by cheating
Understand ground, medical audit scene is not limited in above-mentioned three kinds, there can also be other several scenes, such as charges against regulation
Scene etc..
In one embodiment, server can analyze the diagnosis records and/or medication record of medical data, judge medical number
According to diagnosis records and/or medication record whether meet scene condition corresponding to each medical audit scene.Different medical treatment are examined
Nuclear field scape can set different scene conditions, for example, false scene condition corresponding to scene of being in hospital can be wrapped in medical data
Containing hospitalization data, it can include multiple hospitalization data in medical data to decompose scene condition corresponding to scene of being in hospital, limit
Scene condition corresponding to qualitative medication scene can include to limit sex pill usage record etc. in medical data, but be not limited to
This.If medical data meet medical audit scene corresponding to scene condition, can determine that medical data belongs to the medical audit field
Scape, it is possible to understand that ground, when medical data meets scene condition corresponding to multiple medical audit scenes simultaneously, then can determine that medical treatment
Data belong to multiple medical audit scenes met.For example, medical data includes Multiple Hospitalization data, then medical number is can determine that
According to medical audit scene include false be in hospital and scene and decompose scene of being in hospital.
Step 130, examination ＆ verification model corresponding with medical audit scene is chosen.
Specifically, server can choose it is corresponding with the medical audit scene of medical data audit model, and pass through selection
Examination ＆ verification model medical data is audited.The examination ＆ verification model of each medical audit scene can be built in advance, and server can be first
Substantial amounts of medical data is gathered, and, as the input of examination ＆ verification model, will be passed through per a medical data as a medical sample
Study is trained to medical sample, obtains auditing model.Each different examination ＆ verification model, can set different risk score meters
Calculation mode, server can calculate the risk score of medical data by auditing model, so as to judge to whether there is in medical data
Suspicious insurance fraud behavior.
Step 140, by auditing model from medical data extraction feature corresponding with examination ＆ verification model, and according to feature calculation
The risk score of medical data.
Specifically, can be according to examination ＆ verification after server chooses examination ＆ verification model corresponding with the medical audit scene of medical data
The different risk score calculations set in model, it is corresponding with the risk score calculation set from medical data extraction
Feature, feature refers to the parameter value for being used for calculation risk scoring in medical data, the extractable difference of different examination ＆ verification models
Feature, for example, the feature of the examination ＆ verification model extraction of false scene of being in hospital may include the medical data that this needs is submitted an expense account
In length of stay, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity etc., decompose scene of being in hospital
The feature of examination ＆ verification model extraction may include adjacent consultation time interval etc., however it is not limited to this.Server can be according to the feature of extraction
The risk score of medical data is calculated, risk score can be used for the risk for assessing medical data, determine whether wrapped in medical data
Contain suspicious insurance fraud behavior.
Step 150, when risk score is more than the predetermined threshold value with medical audit scene matching, then medical data is marked
For suspicious data.
Specifically, server can be corresponding with the medical audit scene of medical data default by the risk score of medical data
Threshold value is compared, and when risk score is more than the predetermined threshold value with medical audit scene matching, then can determine that in medical data
Comprising suspicious insurance fraud behavior, medical data can be labeled as suspicious data.Different medical audit scenes can correspond to different
Predetermined threshold value, auditing result can be made more accurate.
In one embodiment, when risk score is more than the predetermined threshold value with medical audit scene matching, wind can be calculated
Danger is scored and the difference of the predetermined threshold value, and the suspicious degree of medical data, when difference is bigger, suspicious journey are determined according to difference
Degree can be bigger.Different suspicious degree can be divided in advance, for example, suspicious degree can be divided into slight suspicious, moderate it is suspicious and
Serious suspicious, different suspicious degree can correspond to different difference sections, server can according to the risk score of medical data with
Difference section residing for the difference of predetermined threshold value, the suspicious degree of medical data is determined, and according to suspicious degree in medical data
Marked corresponding to middle addition, for example, slightly suspicious add mark 0, moderate is suspicious to add mark 1, seriously suspicious to add
Mark 2 etc., but not limited to this.
In one embodiment, when the medical audit scene of medical data includes multiple, can calculate respectively each
The risk score of medical audit scene, and the risk score of each medical audit scene is compared with corresponding predetermined threshold value
Compared with.When there are the risk score under multiple medical audit scenes and be more than corresponding predetermined threshold value, server is by medical number
During according to labeled as suspicious data, the information such as corresponding medical audit scene, corresponding suspicious degree mark can be added.
In the present embodiment, medical data is obtained, mould is audited according to corresponding to being chosen the medical audit scene of medical data
Type, feature corresponding with the examination ＆ verification model, and the medical number according to feature calculation are extracted from medical data by auditing model
According to risk score, when risk score is more than the predetermined threshold value of medical audit scene matching, then by medical data labeled as can
Data are doubted, medical data can correspondingly be audited automatically according to the medical audit scene of medical data, can be effectively and accurately
Suspicious medical data is detected, can effectively prevent insurance fraud behavior, reduces public interest loss.
As shown in Fig. 2 in one embodiment, step 140 is extracted with auditing model by auditing model from medical data
Corresponding feature, and according to the risk score of feature calculation medical data, comprise the following steps：
Step 202, include living according to the feature of examination ＆ verification model extraction medical data corresponding with false scene of being in hospital, feature
Institute's number of days, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity.
Specifically, when medical data meets the scene condition of false scene of being in hospital, server can be chosen and is in hospital with falseness
Examination ＆ verification model is audited to medical data corresponding to scene.Server can scene is corresponding to audit model according to being in hospital with falseness
Extract the feature of medical data, the feature of extraction may include length of stay in the medical data that this needss is submitted an expense account, always
Expense, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity etc..
Step 204, characteristic vector is established according to the feature of extraction, and calculates characteristic vector and wrapped with corresponding examination ＆ verification model
The similarity of each medical sample set contained, each medical sample set to medical sample by being clustered to obtain.
Specifically, server can establish characteristic vector according to the feature of extraction according to default form, pass through characteristic vector
Form represent the feature of medical data.In the present embodiment, characteristic vector can be established according to following form：
V=(v1,v2,v3,...,vp)；
Wherein, v1Represent length of stay, v2To vpRepresent the amount of money for all diagnosis and treatment items that same disease is related to.Server
Disease mark is obtained in the medical data that first can be submitted an expense account from this needs, and acquisition is identified according to disease and belongs to the disease mark
All diagnosis and treatment items known, it may be determined that the diagnosis and treatment item and corresponding gold being related in the medical data that this needs is submitted an expense account
Volume, characteristic vector is established according still further to above-mentioned form, if belonging in all diagnosis and treatment items of disease mark, i-th of diagnosis and treatment item does not have
Have and occur in the medical data that this needs is submitted an expense account, then corresponding viCan be 0.
In one embodiment, corresponding audit in model of scene of being in hospital with falseness can include multiple medical sample sets
Close, each medical sample set represents a classification, and server construction is corresponding with false scene of being in hospital when auditing model, can be right
The medical sample of input is clustered, and the medical sample with similar features is divided into a classification, is generated corresponding medical
Sample set.Further, when being clustered, the medical sample with identical hospital mark and disease mark can be chosen and carried out
Cluster, it is ensured that obtained each medical sample set has more reference value, and auditing result can be made more accurate.
Step 206, the medical sample set according to belonging to similarity determines medical data.
Specifically, server can calculate the feature of the medical sample included in characteristic vector and each medical sample set
Similarity, and the maximum medical sample set of similarity is therefrom chosen as the medical sample set belonging to medical data.Enter one
Step ground, server can identify according to the hospital mark and disease included in the medical data that this needs is submitted an expense account, obtain tool
All medical sample sets that standby identical hospital mark and disease identify, then calculate characteristic vector and each possess identical hospital and mark
The similarity of the medical sample set of knowledge and disease mark, determines the medical sample set belonging to medical data.
Step 208, the sample size included according to affiliated medical sample set calculates the risk score of medical data.
Specifically, server can obtain the sample size included in the medical sample set belonging to medical data, and obtain
Maximum sample size in all medical sample sets included in examination ＆ verification model corresponding with false scene of being in hospital, and with this
There is the parameters such as the medical sample size summation of identical hospital mark and disease mark in the secondary medical data for needing to be submitted an expense account,
The risk score of medical data is calculated further according to the parameter of acquisition.
In one embodiment, server can calculate the risk score of medical data according to formula (1), and formula (1) can be such as
Shown in lower：
Wherein, risk represents risk score, and N represents the sample number included in the medical sample set belonging to medical data
Amount, NmaxRepresent sample size maximum in all medical sample sets that examination ＆ verification model includes, NregisterRepresent in examination ＆ verification model
There is the sample size summation of identical hospital mark and disease mark, λ is wind in the medical data submitted an expense account with this needs
Dangerous hyper parameter, available for proportion of the expression risk in each determinant, between λ values are 0 to 1, when λ takes 0, then it represents that doctor
The degree of risk for treating data is determined by the size of the medical sample set where it completely, when λ takes 1, then it represents that medical data
Degree of risk accounted for and this doctor for being submitted an expense account of needs as the sample size of the medical sample set belonging to medical data completely
Treating has the sample size summation of identical hospital mark and disease mark ratio in data determines.λ can be according to the experience of reality
Requirement extract sets fixed value, dynamically can be also adjusted according to the parameter of acquisition.
In the present embodiment, when medical data meets the scene condition of false scene of being in hospital, can be in hospital according to falseness
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious falseness in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, when medical data meet decompose be in hospital scene scene condition when, server can choose with
Examination ＆ verification model corresponding to scene of being in hospital is decomposed to audit medical data.Decompose may include the first subfield again under scene of being in hospital
Scape, the second sub-scene and the 3rd sub-scene etc., the first sub-scene, the second sub-scene and the 3rd sub-scene etc. can correspond to repeatedly respectively
Different situations in hospital.
As shown in figure 3, step 140 extracts feature corresponding with examination ＆ verification model, and root by auditing model from medical data
According to the risk score of feature calculation medical data, comprise the following steps：
Step 302, according to the feature of examination ＆ verification model extraction medical data corresponding with the first sub-scene, feature includes adjacent
Consultation time interval.
Specifically, in the present embodiment, server can obtain it is corresponding with the first sub-scene audit model, and examined according to this
Nuclear model is audited to medical data, wherein, the first sub-scene refers to directly once normally being in hospital and resolved into repeatedly
Go to a doctor in hospital, the medical title identical scene that diagnoses the illness of Multiple Hospitalization.Server can be by corresponding with the first sub-scene
The feature of model extraction medical data is audited, wherein, feature may include adjacent consultation time interval.
Step 304, most short adjacent consultation time interval is obtained according to the feature of extraction.
Specifically, server can obtain each consultation time from medical data, and according to consultation time sequencing
Arranged, then the time interval of the adjacent consultation time twice of calculated permutations.Further, server can be from medical data
Obtaining the medical data submitted an expense account with this needs has the consultation time of identical disease mark, successively suitable according to consultation time
After sequence enters first arrangement, the adjacent medical time interval of being in hospital of identical disease mark can be calculated, and is therefrom chosen most short adjacent
Consultation time interval, and according to the risk score of the most short adjacent consultation time interval calculation medical data.
Step 306, according to the risk score of most short adjacent consultation time interval calculation medical data.
Specifically, time interval threshold value can be set with examination ＆ verification model corresponding with the first sub-scene, server can determine whether
Whether the most short consultation time interval of medical data is less than time interval threshold value, if being less than, illustrates that medical data may be deposited
It is in hospital behavior in suspicious decomposition.In one embodiment, server can calculate most short adjacent consultation time interval and time
The difference of interval threshold, the risk score of medical data is determined according to the difference, when most short consultation time interval is less than the time
During interval threshold, the difference of the two is bigger, and the risk score of medical data is higher, when most short consultation time interval is not less than
Between interval threshold when, the difference of the two is bigger, and the risk score of medical data is smaller.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, medical audit scene includes decomposing scene of being in hospital, and decomposing scene of being in hospital includes the second subfield
Scape.As shown in figure 4, step 140 extracts feature corresponding with examination ＆ verification model by auditing model from medical data, and according to feature
The risk score of medical data is calculated, is comprised the following steps：
Step 402, according to the feature of examination ＆ verification model extraction medical data corresponding with the second sub-scene, feature includes adjacent
Consultation time interval and adjacent medical diagnosis and treatment item.
Specifically, server can obtain examination ＆ verification model corresponding with the second sub-scene for decomposing scene in hospital, and according to this
Examination ＆ verification model is audited to medical data, wherein, the second sub-scene refer to it is preceding be once in hospital it is medical on the basis of, forge
The title that diagnoses the illness gone to a doctor in hospital next time, but diagnosis and treatment item is still directed to the medical scene of being in hospital of last time.
Server can by it is corresponding with the second sub-scene examination ＆ verification model extraction medical data feature, wherein, feature may include adjacent
Consultation time interval and adjacent medical diagnosis and treatment item.
Step 404, most short adjacent consultation time interval and most long adjacent consultation time are obtained according to the feature of extraction
Interval, and calculate the similarity of adjacent medical diagnosis and treatment item.
Specifically, server can obtain each consultation time from medical data, and according to consultation time sequencing
Arranged, then the time interval of the adjacent consultation time twice of calculated permutations.Server can be from the adjacent consultation time of calculating
In interval, most short adjacent consultation time interval and most long adjacent consultation time interval are obtained.Server is according to consultation time
After sequencing is to each medical arrange of being in hospital, the diagnosis and treatment item mark included during adjacent being in hospital is gone to a doctor can be obtained,
And calculate the similarity of adjacent medical diagnosis and treatment item, can first calculate it is adjacent be in hospital it is medical in, possess identical diagnosis and treatment item mark
The quantity of knowledge accounts for the ratio of diagnosis and treatment item mark total quantity, and the phase of adjacent medical diagnosis and treatment item is calculated further according to the ratio
Like degree.
In the present embodiment, server can obtain the diagnosis and treatment target identification in the medical data that this needs is submitted an expense account, and
The diagnosis and treatment target identification that last time goes to a doctor in hospital, the similarity of adjacent medical diagnosis and treatment item is calculated, and it is adjacent according to this
The risk score of the Similarity Measure medical data of medical diagnosis and treatment item.
Step 406, according to most short adjacent consultation time interval, most long adjacent consultation time interval and Similarity Measure
The risk score of medical data.
Specifically, server can be according to most short adjacent consultation time interval, most long adjacent consultation time interval and phase
The risk score of the Similarity Measure medical data of the medical diagnosis and treatment item of neighbour.
In one embodiment, server can calculate the risk score of medical data according to formula (2), and formula (2) can be such as
Shown in lower：
Wherein, risk represents risk score, dtmaxRepresent most long adjacent consultation time interval, dtminRepresent most short phase
Adjacent consultation time interval, SregisterThe similarity of adjacent medical diagnosis and treatment item is represented, λ is risk hyper parameter, available for representing
Proportion of the risk in each determinant, between λ values are 0 to 1, when λ takes 0, then it represents that the degree of risk of medical data is complete
Determined entirely by adjacent consultation time interval, when λ takes 1, then it represents that the degree of risk of medical data is completely by adjacent medical
The similarity of diagnosis and treatment item determines that λ can be set according to the experience needs of reality.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, medical audit scene includes decomposing scene of being in hospital, and decomposing scene of being in hospital includes the 3rd subfield
Scape.As shown in figure 5, step 140 extracts feature corresponding with examination ＆ verification model by auditing model from medical data, and according to feature
The risk score of medical data is calculated, is comprised the following steps：
Step 502, according to the feature of examination ＆ verification model extraction medical data corresponding with the 3rd sub-scene, feature includes medical
Number, accumulative length of stay, accumulative total cost and secondary equal expense.
Specifically, server can obtain examination ＆ verification model corresponding with the 3rd sub-scene for decomposing scene in hospital, and according to this
Examination ＆ verification model is audited to medical data, wherein, the 3rd sub-scene refer to by once it is longer be in hospital it is medical resolve into it is more
Individual shorter medical scene of being in hospital.Server can pass through the spy of examination ＆ verification model extraction medical data corresponding with the 3rd sub-scene
Sign, wherein, feature may include physician office visits, accumulative length of stay, accumulative total cost and secondary expense etc., and physician office visits refer to
All medical numbers of being in hospital included in medical data, accumulative length of stay refer to all medical length of stay of being in hospital
Summation, accumulative total cost refer to all medical expense summations of being in hospital, and secondary expense refers to averagely being in hospital what is gone to a doctor every time
Expense, expense summation divided by physician office visits can be obtained to time equal expense.
Step 504, the hospital mark and disease mark of medical data are obtained, Hospital Grade is determined according to hospital mark.
Specifically, server can obtain the hospital mark for the medical data that this needs is submitted an expense account and disease identifies, and according to
Hospital mark determines Hospital Grade, and in one embodiment, Hospital Grade can be divided into three-level, can divide first, second, the third three under every grade again
Deng, but not limited to this.
Step 506, the medical data set matched with Hospital Grade and disease mark is obtained, counts medical data collection respectively
Close the average value and standard deviation in each feature.
Specifically, server can be identified according to Hospital Grade and disease, and tool is obtained from the substantial amounts of medical data of collection
The medical data that standby identical Hospital Grade and disease identify, medical data set is formed, and counted respectively in medical data set
In the average value and standard deviation of physician office visits, accumulative length of stay, accumulative total cost and each feature of secondary expense etc..
Step 508, calculated respectively respectively according to from each feature that medical data extracts with corresponding average value and standard deviation
The criterion score of individual feature.
Specifically, server can be according to physician office visits extracted from the medical data audited, accumulative length of stay, tired
Total cost and secondary expense etc. are counted, with the corresponding average value counted in medical data set and standard deviation, is calculated medical time
The criterion score of each features such as number, accumulative length of stay, accumulative total cost and secondary equal expense.Criterion score, alternatively referred to as z point
Number (z-score), for representing the distance of original value and respective average.Criterion score can be calculated according to formula (3)：
Wherein, z represents criterion score, and x represents the feature from the medical data extraction audited, and μ is represented and the extraction
Feature corresponding to average value, σ represents corresponding with the feature of extraction standard deviation.The criterion score of each feature is calculated, can
Embody each feature of extraction and the dispersion degree of medical data set.
Step 510, the criterion score of each feature is weighted to obtain the risk score of medical data.
Specifically, server can be weighted to obtain the risk of medical data and comment to the criterion score of each feature
Point, weight corresponding to each feature can be preset.In one embodiment, server can calculate medical data according to formula (4)
Risk score：
Wherein, risk represents risk score, zpRepresent the criterion score of feature, wpThe weight of feature is represented, four features
Weight sum can be 1.
In one embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, server can obtain simultaneously
The examination ＆ verification model for decomposing each sub-scene included under scene of being in hospital is taken, calculates medical data respectively in the first sub-scene, second
The risk score of sub-scene and the 3rd sub-scene.Server can be respectively by the first sub-scene, the second sub-scene and the 3rd sub-scene
The corresponding predetermined threshold value of risk score be compared, judge in medical data whether comprising can corresponding to suspicious insurance fraud row
Can to be also weighted to the risk score of the first sub-scene, the second sub-scene and the 3rd sub-scene, obtain decomposition and be in hospital
The risk score of scene, then by decompose be in hospital scene risk score compared with corresponding predetermined threshold value, so as to judge to cure
Whether included in treatment data can corresponding suspicious insurance fraud behavior.
In one embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, server also can be simultaneously
The examination ＆ verification model for decomposing each sub-scene included under scene of being in hospital is obtained, and medical data is audited respectively.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, before step 130 chooses examination ＆ verification model corresponding with medical audit scene, in addition to：
Data filtering condition corresponding with the medical audit scene of medical data is obtained, when medical data is unsatisfactory for data filtering condition
When, perform step 130 and choose examination ＆ verification model corresponding with the medical audit scene.
Specifically, server first can enter before being audited to medical data according to data filtering condition to medical data
Row filtering.In one embodiment, different medical audit scenes can correspond to different data filtering conditions, data filtering condition
Medical data that information solicitation is inaccurate or fraud possibility is especially low etc. can be helped to filter.For example, medical data scene is void
Scene, corresponding data filtering condition may include in hospital for vacation：Disease title is fuzzy, hospital name is fuzzy, includes specific disease
(such as cataract etc.), comprising specific medicine (such as arcotic etc.) etc., but not limited to this.
When medical data meets any data filter condition corresponding with medical audit scene, illustrate that the medical data can
The problem of energy existence information fills in inaccuracy, or the possibility that the medical data is faked are especially low, if existence information is filled in
The problem of inaccurate, then server medical data need to be returned to mobile terminal, filled in by insured people get Xin, if the doctor
It is especially low to treat the possibility of data fabrication, then the medical data can be put into reimbursement pond, waits the reimbursement flow of next step.Work as doctor
When treatment data are unsatisfactory for data filtering condition corresponding with medical audit scene, server can be chosen corresponding with medical audit scene
Examination ＆ verification model medical data is audited.
In the present embodiment, before being audited to medical data, first medical data can be filtered, can effectively improved
The review efficiency of medical data.
As shown in fig. 6, in one embodiment, there is provided a kind of medical data processing unit 600, including acquisition module
610th, analysis module 620, selection module 630, computing module 640 and mark module 650.
Acquisition module 610, for obtaining medical data, medical data includes diagnosis records and/or medication record.
Analysis module 620, for analyzing diagnosis records and/or medication record, obtain the medical audit scene of medical data.
Module 630 is chosen, corresponding with medical audit scene model is audited for choosing.
Computing module 640, for by auditing model from medical data extraction with auditing the corresponding feature of model, and according to
The risk score of feature calculation medical data.
Mark module 650, for when risk score is more than predetermined threshold value with medical audit scene matching, then by medical treatment
Data markers are suspicious data.
In the present embodiment, medical data is obtained, mould is audited according to corresponding to being chosen the medical audit scene of medical data
Type, feature corresponding with the examination ＆ verification model, and the medical number according to feature calculation are extracted from medical data by auditing model
According to risk score, when risk score is more than the predetermined threshold value of medical audit scene matching, then by medical data labeled as can
Data are doubted, medical data can correspondingly be audited automatically according to the medical audit scene of medical data, can be effectively and accurately
Suspicious medical data is detected, can effectively prevent insurance fraud behavior, reduces public interest loss.
In one embodiment, medical audit scene includes false scene of being in hospital.As shown in fig. 7, computing module 640, bag
Include feature extraction unit 642, the first computing unit 644, the set computing unit 648 of determining unit 646 and second.
Feature extraction unit 642, for the spy according to examination ＆ verification model extraction medical data corresponding with false scene of being in hospital
Sign, feature include length of stay, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity.
First computing unit 644, for establishing characteristic vector according to the feature of extraction, and calculate characteristic vector with it is corresponding
The similarity of each medical sample set included in examination ＆ verification model, each medical sample set to medical sample by gathering
Class obtains.
Gather determining unit 646, for the medical sample set belonging to determining medical data according to similarity.
Second computing unit 648, the sample size for being included according to affiliated medical sample set calculate medical data
Risk score.
In the present embodiment, when medical data meets the scene condition of false scene of being in hospital, can be in hospital according to falseness
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious falseness in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, medical audit scene includes decomposing scene of being in hospital, and decomposing scene of being in hospital includes the first subfield
Scape.
Feature extraction unit 642, it is additionally operable to the spy according to examination ＆ verification model extraction medical data corresponding with the first sub-scene
Sign, feature include adjacent consultation time interval.
Computing module 640, in addition to time interval acquiring unit.
Time interval acquiring unit, for obtaining most short adjacent consultation time interval according to the feature of extraction.
Second computing unit 648, it is additionally operable to be commented according to the risk of most short adjacent consultation time interval calculation medical data
Point.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, medical audit scene includes decomposing scene of being in hospital, and decomposing scene of being in hospital includes the second subfield
Scape.
Feature extraction unit 642, it is additionally operable to the spy according to examination ＆ verification model extraction medical data corresponding with the second sub-scene
Sign, feature include adjacent consultation time interval and adjacent medical diagnosis and treatment item.
First computing unit 644, it is additionally operable to obtain most short adjacent consultation time interval and most long according to the feature of extraction
Adjacent consultation time interval, and calculate the similarity of adjacent medical diagnosis and treatment item.
Second computing unit 648, it is additionally operable to according between most short adjacent consultation time interval, most long adjacent consultation time
Every and Similarity Measure medical data risk score.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, medical audit scene includes decomposing scene of being in hospital, and decomposing scene of being in hospital includes the 3rd subfield
Scape.
Feature extraction unit 642, it is additionally operable to the spy according to examination ＆ verification model extraction medical data corresponding with the 3rd sub-scene
Sign, feature include physician office visits, accumulative length of stay, accumulative total cost and secondary equal expense.
Computing module 640, in addition to determining unit and statistic unit.
Determining unit, for obtaining the hospital mark and disease mark of medical data, hospital etc. is determined according to hospital mark
Level.
Statistic unit, for obtaining the medical data set matched with Hospital Grade and disease mark, respectively statistics medical treatment
Average value and standard deviation of the data acquisition system in each feature.
First computing unit 644, it is additionally operable to according to each feature and corresponding average value and mark from medical data extraction
Quasi- difference does not calculate the criterion score of each feature.
Second computing unit 648, it is additionally operable to that the criterion score of each feature is weighted to obtain the doctor
Treat the risk score of data.
In the present embodiment, when medical data meets to decompose the scene condition for scene of being in hospital, can be in hospital according to decomposition
The feature of examination ＆ verification model extraction medical data corresponding to scene, and the risk score of medical data is calculated, so as to accurate judgement
Whether it is in hospital behavior comprising suspicious decomposition in medical data, can effectively prevents insurance fraud behavior, reduces public interest damage
Lose.
In one embodiment, above-mentioned medical data processing unit 600, except including acquisition module 610, analysis module
620th, module 630, computing module 640 and mark module 650, in addition to filtering module are chosen.
Filtering module, for obtaining data filtering condition corresponding with the medical audit scene of medical data, when medical number
During according to being unsatisfactory for the data filtering condition, then by choosing, the selection of module 630 is corresponding with medical audit scene to audit model.
In the present embodiment, before being audited to medical data, first medical data can be filtered, can effectively improved
The review efficiency of medical data.
Above-mentioned medical data processing unit can be implemented as a kind of form of computer program, and computer program can be such as
Run on computer equipment shown in Fig. 8.
Fig. 8 is the block diagram of one embodiment Computer equipment.As shown in figure 8, the computer equipment includes passing through system
Processor, non-volatile memory medium, built-in storage and the network interface of bus connection.Wherein, the computer equipment is non-easy
The property lost storage medium is stored with operating system, database and computer program, and substantial amounts of medical data etc. is stored with database,
The computer program is used to realize a kind of medical data processing side suitable for computer equipment provided in the embodiment of the present application
Method.The processor of the computer equipment is used to provide calculating and control ability, supports the operation of whole computer equipment.The calculating
The built-in storage of machine equipment provides the operation of cache for the operating system in non-volatile memory medium and computer program
Environment.Other computer equipments that the network interface of the computer equipment is used for according to this with outside are communicated by network connection.Meter
It can be server or terminal to calculate machine equipment, wherein, server can use independent server or multiple services
The server cluster of device composition.It will be understood by those skilled in the art that the structure shown in Fig. 8, it is only and application scheme
The block diagram of related part-structure, does not form the restriction for the computer equipment being applied thereon to application scheme, specifically
Ground computer equipment can include, than more or less parts shown in figure, either combining some parts or with difference
Part arrangement.
In one embodiment, there is provided a kind of computer equipment, including memory and processor, store meter in memory
Calculation machine program, when computer program instructions are by the computing device so that processor realizes above-mentioned medical data processing side
Method.
In one embodiment, there is provided a kind of computer-readable recording medium, be stored thereon with computer program, computer
Above-mentioned medical data processing method is realized when program is executed by processor.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can be read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-OnlyMemory, ROM) etc..
Any reference to memory, storage, database or other media may include non-volatile as used herein
And/or volatile memory.Suitable nonvolatile memory may include read-only storage (ROM), programming ROM (PROM),
Electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the application, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, on the premise of the application design is not departed from, various modifications and improvements can be made, these belong to the protection of the application
Scope.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
- A kind of 1. medical data processing method, it is characterised in that including：Medical data is obtained, the medical data includes diagnosis records and/or medication record；The diagnosis records and/or medication record are analyzed, obtain the medical audit scene of the medical data；Choose examination ＆ verification model corresponding with the medical audit scene；Feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to the feature Calculate the risk score of the medical data；When the risk score is more than the predetermined threshold value with the medical audit scene matching, then the medical data is marked For suspicious data.
- 2. according to the method for claim 1, it is characterised in that the medical audit scene includes false scene of being in hospital；It is described that feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to described The risk score of medical data described in feature calculation, including：According to the feature of medical data described in examination ＆ verification model extraction corresponding with the false scene of being in hospital, the feature includes living Institute's number of days, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity；Characteristic vector established according to the feature of extraction, and calculates the characteristic vector and is included with the corresponding examination ＆ verification model The similarity of each medical sample set, each medical sample set to medical sample by being clustered to obtain；Medical sample set according to belonging to the similarity determines the medical data；The sample size included according to the affiliated medical sample set calculates the risk score of the medical data.
- 3. according to the method for claim 1, it is characterised in that the medical audit scene includes decomposing scene of being in hospital, institute Stating decomposition, scene includes the first sub-scene in hospital；It is described that feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to described The risk score of medical data described in feature calculation, including：According to the feature of medical data described in examination ＆ verification model extraction corresponding with first sub-scene, the feature includes adjacent Consultation time interval；Most short adjacent consultation time interval is obtained according to the feature of extraction；According to the risk score of medical data described in the most short adjacent consultation time interval calculation.
- 4. according to the method for claim 1, it is characterised in that the medical audit scene includes decomposing scene of being in hospital, institute Stating decomposition, scene includes the second sub-scene in hospital；It is described that feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to described The risk score of medical data described in feature calculation, including：According to the feature of medical data described in examination ＆ verification model extraction corresponding with second sub-scene, the feature includes adjacent Consultation time interval and adjacent medical diagnosis and treatment item；Most short adjacent consultation time interval and most long adjacent consultation time interval are obtained according to the feature of extraction, and calculate phase The similarity of the medical diagnosis and treatment item of neighbour；According to the most short adjacent consultation time interval, most long adjacent consultation time interval and the Similarity Measure The risk score of medical data.
- 5. according to the method for claim 1, it is characterised in that the medical audit scene includes decomposing scene of being in hospital, institute Stating decomposition, scene includes the 3rd sub-scene in hospital；It is described that feature corresponding with the examination ＆ verification model is extracted from the medical data by the examination ＆ verification model, and according to described The risk score of medical data described in feature calculation, including：According to the feature of medical data described in examination ＆ verification model extraction corresponding with the 3rd sub-scene, the feature includes medical Number, accumulative length of stay, accumulative total cost and secondary equal expense；The hospital mark and disease mark of the medical data are obtained, Hospital Grade is determined according to the hospital mark；The medical data set matched with the Hospital Grade and disease mark is obtained, the medical data is counted respectively and is integrated into The average value and standard deviation of each feature；Each spy is calculated respectively according to from each feature that the medical data extracts with corresponding average value and standard deviation The criterion score of sign；The criterion score of each feature is weighted to obtain the risk score of the medical data.
- 6. method according to any one of claims 1 to 5, it is characterised in that in the selection and the medical audit scene Before corresponding examination ＆ verification model, methods described also includes：Obtain data filtering condition corresponding with the medical audit scene of the medical data；When the medical data is unsatisfactory for the data filtering condition, it is corresponding with the medical audit scene to perform the selection Examination ＆ verification model the step of.
- A kind of 7. medical data processing unit, it is characterised in that including：Acquisition module, for obtaining medical data, the medical data includes diagnosis records and/or medication record；Analysis module, for analyzing the diagnosis records and/or medication record, obtain the medical audit field of the medical data Scape；Module is chosen, corresponding with the medical audit scene model is audited for choosing；Computing module, for extracting feature corresponding with the examination ＆ verification model from the medical data by the examination ＆ verification model, And according to the feature calculation medical data risk score；Mark module, for when the risk score is more than predetermined threshold value with the medical audit scene matching, then by institute State medical data and be labeled as suspicious data.
- 8. device according to claim 7, it is characterised in that the medical audit scene includes false scene of being in hospital；The computing module, including：Feature extraction unit, the spy for the medical data according to examination ＆ verification model extraction corresponding with the false scene of being in hospital Sign, the feature include length of stay, total cost, the diagnosis and treatment item quantity of each classification and diagnosis and treatment item total quantity；First computing unit, for establishing characteristic vector according to the feature of extraction, and calculate the characteristic vector with it is described corresponding Examination ＆ verification model in the similarity of each medical sample set that includes, each medical sample set passes through to sample of going to a doctor Clustered to obtain；Gather determining unit, for the medical sample set belonging to determining the medical data according to the similarity；Second computing unit, the sample size for being included according to the affiliated medical sample set calculate the medical data Risk score.
- 9. a kind of computer equipment, including memory and processor, computer program is stored in the memory, its feature exists In when the computer program instructions are by the computing device so that the processor is realized as claim 1 to 6 is any Described method.
- 10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the computer program The method as described in claim 1 to 6 is any is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710801892.9A CN107609980A (en) | 2017-09-07 | 2017-09-07 | Medical data processing method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710801892.9A CN107609980A (en) | 2017-09-07 | 2017-09-07 | Medical data processing method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107609980A true CN107609980A (en) | 2018-01-19 |
Family
ID=61062522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710801892.9A Pending CN107609980A (en) | 2017-09-07 | 2017-09-07 | Medical data processing method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609980A (en) |
Cited By (77)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| CN108962342A (en) * | 2018-06-14 | 2018-12-07 | 四川久远银海软件股份有限公司 | A kind of homogeneity crowd screening technique and device |
| CN109003193A (en) * | 2018-09-10 | 2018-12-14 | 平安科技（深圳）有限公司 | Insurance risk prediction technique, device, computer equipment and storage medium |
| CN109036506A (en) * | 2018-07-25 | 2018-12-18 | 平安科技（深圳）有限公司 | Monitoring and managing method, electronic device and the readable storage medium storing program for executing of internet medical treatment interrogation |
| CN109118376A (en) * | 2018-08-14 | 2019-01-01 | 平安医疗健康管理股份有限公司 | Medical insurance premium calculation principle method, apparatus, computer equipment and storage medium |
| CN109119137A (en) * | 2018-08-24 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of method for detecting abnormality, device, server and storage medium |
| CN109242709A (en) * | 2018-10-27 | 2019-01-18 | 平安科技（深圳）有限公司 | The method and apparatus for estimating medical expense |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN109346189A (en) * | 2018-10-31 | 2019-02-15 | 平安医疗健康管理股份有限公司 | Medical data detection method and relevant apparatus based on big data |
| CN109360622A (en) * | 2018-10-22 | 2019-02-19 | 平安医疗健康管理股份有限公司 | Prescriptions of traditional Chinese medicine drug expenditure risk control method and device based on data processing |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109377059A (en) * | 2018-10-27 | 2019-02-22 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109493242A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Unit joining insurance's recognition methods and Related product |
| CN109493243A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | A kind of disease score value method of calibration neural network based and calculate equipment |
| CN109492135A (en) * | 2018-10-27 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of data checking method and device based on data processing |
| CN109493238A (en) * | 2018-10-27 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Method and relevant device are handled in supplement medical insurance based on data analysis |
| CN109493108A (en) * | 2018-09-26 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Curative activity information processing method, device, computer equipment and medium |
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
| CN109509550A (en) * | 2018-10-27 | 2019-03-22 | 平安医疗健康管理股份有限公司 | Diagnosis information processing method, device, equipment and medium based on data analysis |
| CN109522387A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Lumbar vertebra protrusion quality certification method, equipment and server based on data processing |
| CN109524065A (en) * | 2018-11-07 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Medical data querying method, medical data platform and relevant apparatus |
| CN109523404A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Unlawful practice detection method, device and terminal based on data analysis |
| CN109523394A (en) * | 2018-10-23 | 2019-03-26 | 平安科技（深圳）有限公司 | A kind of risk checking method based on data processing, device and storage medium |
| CN109545316A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Purchase the processing method and Related product of medicine data |
| CN109544362A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109544358A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Medical insurance method of charging out and relevant device based on data analysis |
| CN109544373A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Medical insurance unlawful practice detection method and relevant apparatus based on artificial intelligence |
| CN109545312A (en) * | 2018-10-23 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of pharmacy's advice of settlement risk checking method and device |
| CN109545317A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
| CN109544385A (en) * | 2018-11-07 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of diagnosis and treatment authenticity detection method and system based on reimbursement data |
| CN109544356A (en) * | 2018-10-23 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of risk checking method based on data processing, device and storage medium |
| CN109545382A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | A kind of identical case recognition methods and calculating equipment based on big data |
| CN109545298A (en) * | 2018-10-30 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of disease score value calculation method and calculating equipment based on data analysis |
| CN109559806A (en) * | 2018-10-30 | 2019-04-02 | 平安医疗健康管理股份有限公司 | The determination method and Related product of abnormal behavior of being hospitalized |
| CN109584086A (en) * | 2018-10-30 | 2019-04-05 | 平安医疗健康管理股份有限公司 | Be hospitalized rational method and Related product are predicted based on prediction model |
| CN109598628A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Recognition methods, device, equipment and the readable storage medium storing program for executing of medical insurance fraud |
| CN109615204A (en) * | 2018-11-30 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data |
| CN109615203A (en) * | 2018-11-30 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Processing method, device, equipment and the readable storage medium storing program for executing of tracheopathy reimbursement process |
| CN109614609A (en) * | 2018-11-06 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method for establishing model and device |
| CN109636641A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis |
| CN109636645A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN109636647A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine |
| CN109636613A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data abnormality recognition method, device, terminal and storage medium |
| CN109636623A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data method for detecting abnormality, device, equipment and storage medium |
| CN109636646A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Extremely medical recognition methods, device, terminal and computer readable storage medium |
| CN109636649A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Monitoring method, monitoring service end and the storage medium of medical expense exception |
| CN109636652A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Purchase monitoring method, monitoring service end and the storage medium of medicine abnormal behavior |
| CN109636643A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine |
| CN109636653A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Monitoring method, monitoring service end and the storage medium of medical expense exception |
| CN109658260A (en) * | 2018-12-10 | 2019-04-19 | 泰康保险集团股份有限公司 | Method and device, medium and electronic equipment are determined based on the fraud of block chain |
| CN109658266A (en) * | 2018-12-13 | 2019-04-19 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN109754325A (en) * | 2018-11-30 | 2019-05-14 | 平安科技（深圳）有限公司 | Nephrosis submits an expense account access method, device, equipment and readable storage medium storing program for executing |
| CN109785174A (en) * | 2019-02-01 | 2019-05-21 | 泰康保险集团股份有限公司 | The method and apparatus for identifying high risk of fraud |
| CN109785148A (en) * | 2018-11-30 | 2019-05-21 | 平安科技（深圳）有限公司 | Processing method, device, equipment and the readable storage medium storing program for executing of hepatopathy reimbursement process |
| CN109785966A (en) * | 2018-12-14 | 2019-05-21 | 平安科技（深圳）有限公司 | Medical record checking method, device, equipment and storage medium based on machine learning |
| CN110245703A (en) * | 2019-06-13 | 2019-09-17 | 泰康保险集团股份有限公司 | Medical information processing method, device, medium and electronic equipment |
| WO2020010712A1 (en) * | 2018-07-13 | 2020-01-16 | 平安科技（深圳）有限公司 | Electronic device, user insurance fraud risk pre-warning method, and storage medium |
| CN110693486A (en) * | 2019-09-27 | 2020-01-17 | 武汉中旗生物医疗电子有限公司 | Electrocardiogram abnormity labeling method and device |
| CN110782360A (en) * | 2019-10-24 | 2020-02-11 | 泰康保险集团股份有限公司 | Settlement data processing method and device, storage medium and electronic equipment |
| WO2020034874A1 (en) * | 2018-08-14 | 2020-02-20 | 平安医疗健康管理股份有限公司 | Medical document examining method and apparatus, computer device, and storage medium |
| WO2020082788A1 (en) * | 2018-10-27 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Medical data processing method, apparatus and device, and storage medium |
| WO2020082790A1 (en) * | 2018-10-22 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Data-processing-based drug use monitoring method and apparatus for traditional chinese medicine prescription |
| CN111179096A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Medical data auditing method and device, electronic equipment and computer readable medium |
| WO2020107909A1 (en) * | 2018-11-30 | 2020-06-04 | 平安医疗健康管理股份有限公司 | Method, apparatus and device for determining abnormal treatment expense, and computer storage medium |
| CN111241084A (en) * | 2020-01-14 | 2020-06-05 | 平安医疗健康管理股份有限公司 | Medical information cleaning method, device, computer equipment and storage medium |
| WO2020119403A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Hospitalization data abnormity detection method, apparatus and device, and readable storage medium |
| WO2020119176A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Reimbursement data checking method, identification server, and storage medium |
| CN111445343A (en) * | 2020-03-23 | 2020-07-24 | 平安医疗健康管理股份有限公司 | Risk medical data identification method and device, computer equipment and storage medium |
| CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
| CN112036750A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Abnormity identification method, device, equipment and storage medium suitable for medical wind control |
| CN112148898A (en) * | 2020-09-18 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for media content auditing |
| CN112308722A (en) * | 2019-07-28 | 2021-02-02 | 四川谦泰仁投资管理有限公司 | Aquaculture insurance declaration request verification system based on infrared camera shooting |
| CN112837781A (en) * | 2021-02-05 | 2021-05-25 | 南通市第二人民医院 | Pharmacy management system and method based on hospital prescription information |
| CN113223729A (en) * | 2021-05-26 | 2021-08-06 | 广州天鹏计算机科技有限公司 | Data processing method of medical data |
| CN117116504A (en) * | 2023-07-24 | 2023-11-24 | 北京同仁堂互联网医院管理有限公司 | Management method, device, equipment and readable medium for traditional Chinese medicine medication safety |
| EP4073819A4 (en) * | 2019-12-03 | 2024-01-03 | Moelnlycke Health Care Ab | A method for determining a risk score for a patient |
| CN112016302B (en) * | 2020-08-03 | 2024-04-30 | 青岛国新健康产业科技有限公司 | Identification method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101421734A (en) * | 2006-03-17 | 2009-04-29 | 英吉尼克斯股份有限公司 | System and method for identifying and analyzing patterns or aberrations in healthcare claims |
| CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
| CN104134157A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Suspicious behavior audit system and method in medical insurance reimbursement process |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN105279382A (en) * | 2015-11-10 | 2016-01-27 | 成都数联易康科技有限公司 | Medical insurance abnormal data on-line intelligent detection method |
-
2017
- 2017-09-07 CN CN201710801892.9A patent/CN107609980A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101421734A (en) * | 2006-03-17 | 2009-04-29 | 英吉尼克斯股份有限公司 | System and method for identifying and analyzing patterns or aberrations in healthcare claims |
| CN102013084A (en) * | 2010-12-14 | 2011-04-13 | 江苏大学 | System and method for detecting fraudulent transactions in medical insurance outpatient services |
| CN104134157A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Suspicious behavior audit system and method in medical insurance reimbursement process |
| CN104408547A (en) * | 2014-10-30 | 2015-03-11 | 浙江网新恒天软件有限公司 | Data-mining-based detection method for medical insurance fraud behavior |
| CN105279382A (en) * | 2015-11-10 | 2016-01-27 | 成都数联易康科技有限公司 | Medical insurance abnormal data on-line intelligent detection method |
Cited By (97)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492196B (en) * | 2018-03-08 | 2020-11-10 | 平安医疗健康管理股份有限公司 | Wind control method for deducing medical insurance violation behavior through data analysis |
| CN108492196A (en) * | 2018-03-08 | 2018-09-04 | 平安医疗健康管理股份有限公司 | The air control method of medical insurance unlawful practice is inferred by data analysis |
| CN108962342A (en) * | 2018-06-14 | 2018-12-07 | 四川久远银海软件股份有限公司 | A kind of homogeneity crowd screening technique and device |
| WO2020010712A1 (en) * | 2018-07-13 | 2020-01-16 | 平安科技（深圳）有限公司 | Electronic device, user insurance fraud risk pre-warning method, and storage medium |
| CN109036506A (en) * | 2018-07-25 | 2018-12-18 | 平安科技（深圳）有限公司 | Monitoring and managing method, electronic device and the readable storage medium storing program for executing of internet medical treatment interrogation |
| CN109118376A (en) * | 2018-08-14 | 2019-01-01 | 平安医疗健康管理股份有限公司 | Medical insurance premium calculation principle method, apparatus, computer equipment and storage medium |
| WO2020034874A1 (en) * | 2018-08-14 | 2020-02-20 | 平安医疗健康管理股份有限公司 | Medical document examining method and apparatus, computer device, and storage medium |
| CN109119137A (en) * | 2018-08-24 | 2019-01-01 | 腾讯科技（深圳）有限公司 | A kind of method for detecting abnormality, device, server and storage medium |
| CN109003193A (en) * | 2018-09-10 | 2018-12-14 | 平安科技（深圳）有限公司 | Insurance risk prediction technique, device, computer equipment and storage medium |
| CN109377388A (en) * | 2018-09-13 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Medical insurance is insured method, apparatus, computer equipment and storage medium |
| CN109377388B (en) * | 2018-09-13 | 2023-08-18 | 深圳平安医疗健康科技服务有限公司 | Medical insurance application method, medical insurance application device, computer equipment and storage medium |
| CN109493108A (en) * | 2018-09-26 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Curative activity information processing method, device, computer equipment and medium |
| CN109493108B (en) * | 2018-09-26 | 2024-02-06 | 深圳平安医疗健康科技服务有限公司 | Medical activity information processing method, device, computer equipment and medium |
| CN109636613A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data abnormality recognition method, device, terminal and storage medium |
| WO2020078058A1 (en) * | 2018-10-19 | 2020-04-23 | 平安医疗健康管理股份有限公司 | Medical data abnormality identification method and device, terminal, and storage medium |
| CN109636623A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data method for detecting abnormality, device, equipment and storage medium |
| WO2020082790A1 (en) * | 2018-10-22 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Data-processing-based drug use monitoring method and apparatus for traditional chinese medicine prescription |
| CN109360622A (en) * | 2018-10-22 | 2019-02-19 | 平安医疗健康管理股份有限公司 | Prescriptions of traditional Chinese medicine drug expenditure risk control method and device based on data processing |
| CN109545312B (en) * | 2018-10-23 | 2023-08-08 | 平安医疗健康管理股份有限公司 | Drug store statement risk detection method and device |
| CN109544356B (en) * | 2018-10-23 | 2023-10-20 | 平安医疗健康管理股份有限公司 | Risk detection method, device and storage medium based on data processing |
| CN109523394B (en) * | 2018-10-23 | 2023-06-23 | 平安科技（深圳）有限公司 | Risk detection method, device and storage medium based on data processing |
| CN109545312A (en) * | 2018-10-23 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of pharmacy's advice of settlement risk checking method and device |
| CN109523394A (en) * | 2018-10-23 | 2019-03-26 | 平安科技（深圳）有限公司 | A kind of risk checking method based on data processing, device and storage medium |
| CN109544356A (en) * | 2018-10-23 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of risk checking method based on data processing, device and storage medium |
| CN109492885A (en) * | 2018-10-25 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method device, terminal and readable medium |
| CN109492885B (en) * | 2018-10-25 | 2024-02-09 | 平安医疗健康管理股份有限公司 | Medical insurance risk project analysis method and device, terminal and readable medium |
| WO2020082788A1 (en) * | 2018-10-27 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Medical data processing method, apparatus and device, and storage medium |
| CN109492135B (en) * | 2018-10-27 | 2024-03-19 | 平安科技（深圳）有限公司 | Data auditing method and device based on data processing |
| CN109242709B (en) * | 2018-10-27 | 2024-02-13 | 平安科技（深圳）有限公司 | Method and device for estimating medical cost |
| CN109492135A (en) * | 2018-10-27 | 2019-03-19 | 平安科技（深圳）有限公司 | A kind of data checking method and device based on data processing |
| CN109377059A (en) * | 2018-10-27 | 2019-02-22 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109493238A (en) * | 2018-10-27 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Method and relevant device are handled in supplement medical insurance based on data analysis |
| WO2020082796A1 (en) * | 2018-10-27 | 2020-04-30 | 平安医疗健康管理股份有限公司 | Method, device and apparatus for processing medical visit information based on data analysis, and medium |
| CN109509550A (en) * | 2018-10-27 | 2019-03-22 | 平安医疗健康管理股份有限公司 | Diagnosis information processing method, device, equipment and medium based on data analysis |
| CN109523404A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Unlawful practice detection method, device and terminal based on data analysis |
| CN109544358A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | Medical insurance method of charging out and relevant device based on data analysis |
| CN109242709A (en) * | 2018-10-27 | 2019-01-18 | 平安科技（深圳）有限公司 | The method and apparatus for estimating medical expense |
| CN109522387A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Lumbar vertebra protrusion quality certification method, equipment and server based on data processing |
| CN109544362A (en) * | 2018-10-27 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of data processing method and equipment based on risk management and control |
| CN109584086A (en) * | 2018-10-30 | 2019-04-05 | 平安医疗健康管理股份有限公司 | Be hospitalized rational method and Related product are predicted based on prediction model |
| CN109545382A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | A kind of identical case recognition methods and calculating equipment based on big data |
| CN109493242A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | Unit joining insurance's recognition methods and Related product |
| CN109544373A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Medical insurance unlawful practice detection method and relevant apparatus based on artificial intelligence |
| CN109493243A (en) * | 2018-10-30 | 2019-03-19 | 平安医疗健康管理股份有限公司 | A kind of disease score value method of calibration neural network based and calculate equipment |
| WO2020087971A1 (en) * | 2018-10-30 | 2020-05-07 | 平安医疗健康管理股份有限公司 | Prediction model-based hospitalization rationality prediction method and related products |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN109559806A (en) * | 2018-10-30 | 2019-04-02 | 平安医疗健康管理股份有限公司 | The determination method and Related product of abnormal behavior of being hospitalized |
| CN109545298A (en) * | 2018-10-30 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of disease score value calculation method and calculating equipment based on data analysis |
| CN109545317A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
| CN109545316A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Purchase the processing method and Related product of medicine data |
| CN109346189A (en) * | 2018-10-31 | 2019-02-15 | 平安医疗健康管理股份有限公司 | Medical data detection method and relevant apparatus based on big data |
| CN109614609B (en) * | 2018-11-06 | 2023-05-05 | 创新先进技术有限公司 | Model building method and device |
| CN109614609A (en) * | 2018-11-06 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method for establishing model and device |
| CN109544385A (en) * | 2018-11-07 | 2019-03-29 | 平安医疗健康管理股份有限公司 | A kind of diagnosis and treatment authenticity detection method and system based on reimbursement data |
| CN109524065A (en) * | 2018-11-07 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Medical data querying method, medical data platform and relevant apparatus |
| CN109544385B (en) * | 2018-11-07 | 2023-06-02 | 平安医疗健康管理股份有限公司 | Diagnosis and treatment authenticity detection method and system based on reimbursement data |
| CN111179096A (en) * | 2018-11-09 | 2020-05-19 | 天津幸福生命科技有限公司 | Medical data auditing method and device, electronic equipment and computer readable medium |
| CN109598628A (en) * | 2018-11-30 | 2019-04-09 | 平安医疗健康管理股份有限公司 | Recognition methods, device, equipment and the readable storage medium storing program for executing of medical insurance fraud |
| CN109615204B (en) * | 2018-11-30 | 2023-02-03 | 平安医疗健康管理股份有限公司 | Quality evaluation method, device and equipment of medical data and readable storage medium |
| CN109785148A (en) * | 2018-11-30 | 2019-05-21 | 平安科技（深圳）有限公司 | Processing method, device, equipment and the readable storage medium storing program for executing of hepatopathy reimbursement process |
| CN109754325A (en) * | 2018-11-30 | 2019-05-14 | 平安科技（深圳）有限公司 | Nephrosis submits an expense account access method, device, equipment and readable storage medium storing program for executing |
| WO2020107909A1 (en) * | 2018-11-30 | 2020-06-04 | 平安医疗健康管理股份有限公司 | Method, apparatus and device for determining abnormal treatment expense, and computer storage medium |
| CN109785148B (en) * | 2018-11-30 | 2023-10-24 | 平安科技（深圳）有限公司 | Method, device, equipment and readable storage medium for processing liver disease reimbursement flow |
| CN109615203A (en) * | 2018-11-30 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Processing method, device, equipment and the readable storage medium storing program for executing of tracheopathy reimbursement process |
| CN109615204A (en) * | 2018-11-30 | 2019-04-12 | 平安医疗健康管理股份有限公司 | Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data |
| CN109658260A (en) * | 2018-12-10 | 2019-04-19 | 泰康保险集团股份有限公司 | Method and device, medium and electronic equipment are determined based on the fraud of block chain |
| CN109636643A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine |
| CN109636641A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance method for detecting abnormality, device, equipment and medium based on big data analysis |
| WO2020119403A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Hospitalization data abnormity detection method, apparatus and device, and readable storage medium |
| WO2020119176A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Reimbursement data checking method, identification server, and storage medium |
| CN109636647A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the computer readable storage medium of abnormal purchase medicine |
| CN109636649A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Monitoring method, monitoring service end and the storage medium of medical expense exception |
| CN109636652A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Purchase monitoring method, monitoring service end and the storage medium of medicine abnormal behavior |
| CN109636653A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Monitoring method, monitoring service end and the storage medium of medical expense exception |
| CN109658266A (en) * | 2018-12-13 | 2019-04-19 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN109636646A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Extremely medical recognition methods, device, terminal and computer readable storage medium |
| CN109636645A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical insurance monitoring and managing method, unit and computer readable storage medium |
| CN109785966A (en) * | 2018-12-14 | 2019-05-21 | 平安科技（深圳）有限公司 | Medical record checking method, device, equipment and storage medium based on machine learning |
| CN109785174A (en) * | 2019-02-01 | 2019-05-21 | 泰康保险集团股份有限公司 | The method and apparatus for identifying high risk of fraud |
| CN110245703A (en) * | 2019-06-13 | 2019-09-17 | 泰康保险集团股份有限公司 | Medical information processing method, device, medium and electronic equipment |
| CN112308722A (en) * | 2019-07-28 | 2021-02-02 | 四川谦泰仁投资管理有限公司 | Aquaculture insurance declaration request verification system based on infrared camera shooting |
| CN110693486B (en) * | 2019-09-27 | 2022-06-14 | 武汉中旗生物医疗电子有限公司 | Electrocardiogram abnormity labeling method and device |
| CN110693486A (en) * | 2019-09-27 | 2020-01-17 | 武汉中旗生物医疗电子有限公司 | Electrocardiogram abnormity labeling method and device |
| CN110782360A (en) * | 2019-10-24 | 2020-02-11 | 泰康保险集团股份有限公司 | Settlement data processing method and device, storage medium and electronic equipment |
| EP4073819A4 (en) * | 2019-12-03 | 2024-01-03 | Moelnlycke Health Care Ab | A method for determining a risk score for a patient |
| CN111241084A (en) * | 2020-01-14 | 2020-06-05 | 平安医疗健康管理股份有限公司 | Medical information cleaning method, device, computer equipment and storage medium |
| CN111445343A (en) * | 2020-03-23 | 2020-07-24 | 平安医疗健康管理股份有限公司 | Risk medical data identification method and device, computer equipment and storage medium |
| CN112016302B (en) * | 2020-08-03 | 2024-04-30 | 青岛国新健康产业科技有限公司 | Identification method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
| CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
| CN112036750A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Abnormity identification method, device, equipment and storage medium suitable for medical wind control |
| CN112148898A (en) * | 2020-09-18 | 2020-12-29 | 京东数字科技控股股份有限公司 | Data processing method and device for media content auditing |
| CN112148898B (en) * | 2020-09-18 | 2024-04-05 | 京东科技控股股份有限公司 | Data processing method and device for auditing media content |
| CN112837781B (en) * | 2021-02-05 | 2021-11-23 | 南通市第二人民医院 | Pharmacy management system and method based on hospital prescription information |
| CN112837781A (en) * | 2021-02-05 | 2021-05-25 | 南通市第二人民医院 | Pharmacy management system and method based on hospital prescription information |
| CN113223729A (en) * | 2021-05-26 | 2021-08-06 | 广州天鹏计算机科技有限公司 | Data processing method of medical data |
| CN117116504A (en) * | 2023-07-24 | 2023-11-24 | 北京同仁堂互联网医院管理有限公司 | Management method, device, equipment and readable medium for traditional Chinese medicine medication safety |
| CN117116504B (en) * | 2023-07-24 | 2024-04-19 | 北京同仁堂互联网医院管理有限公司 | Management method, device, equipment and readable medium for traditional Chinese medicine medication safety |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609980A (en) | Medical data processing method, device, computer equipment and storage medium | |
| Qaiser et al. | Her 2 challenge contest: a detailed assessment of automated her 2 scoring algorithms in whole slide images of breast cancer tissues | |
| CN107133437B (en) | The method and device that monitoring drug uses | |
| CN103559208B (en) | The ranking fraud detection method of application program and ranking fraud detection system | |
| CN109636623A (en) | Medical data method for detecting abnormality, device, equipment and storage medium | |
| CN107657536A (en) | The recognition methods of social security fraud and device | |
| CN109545317A (en) | The method and Related product of behavior in hospital are determined based on prediction model in hospital | |
| CN106997493A (en) | Lottery user attrition prediction method and its system based on multi-dimensional data | |
| CN109522400A (en) | Core protects method, apparatus, computer equipment and storage medium | |
| Jesus et al. | A morphometric approach to track opium poppy domestication | |
| CN110729054B (en) | Abnormal diagnosis behavior detection method and device, computer equipment and storage medium | |
| CN109615280A (en) | Employee's data processing method, device, computer equipment and storage medium | |
| CN109119137A (en) | A kind of method for detecting abnormality, device, server and storage medium | |
| DE10143712A1 (en) | Process, computer system and computer program product for data evaluation | |
| CN108197795A (en) | The account recognition methods of malice group, device, terminal and storage medium | |
| CN104166952A (en) | Analysis system and analysis method | |
| Bochaton et al. | Human impacts reduce morphological diversity in an insular species of lizard | |
| Kashyap et al. | Management and monitoring patterns and future scope | |
| CN115148370A (en) | Method and system for generating DIP disease category catalog | |
| CN108197885A (en) | The Work attendance method and device of employee | |
| Duman et al. | Heath care fraud detection methods and new approaches | |
| CN103559210B (en) | The ranking fraud detection method and ranking fraud detection system of application program | |
| US20070219820A1 (en) | Anomaly tracking system and method for detecting fraud and errors in the healthcare field | |
| Cox et al. | Techniques for preserving statistical confidentiality | |
| CN110010231A (en) | A kind of data processing system 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 |
Application publication date: 20180119 |
|
| RJ01 | Rejection of invention patent application after publication |