CN107145587A - A kind of anti-fake system of medical insurance excavated based on big data - Google Patents
A kind of anti-fake system of medical insurance excavated based on big data Download PDFInfo
- Publication number
- CN107145587A CN107145587A CN201710329362.9A CN201710329362A CN107145587A CN 107145587 A CN107145587 A CN 107145587A CN 201710329362 A CN201710329362 A CN 201710329362A CN 107145587 A CN107145587 A CN 107145587A
- Authority
- CN
- China
- Prior art keywords
- subsystem
- data
- rule
- big data
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The present invention relates to a kind of anti-fake system of medical insurance excavated based on big data, it includes following subsystem：Data pick-up, conversion, load subsystem, big data storage subsystem, data mining subsystem, rule base and knowledge base subsystem, real-time streams computing subsystem and visual subsystem, the data pick-up, conversion, loading subsystem is connected with big data storage subsystem, big data storage subsystem is connected with data mining subsystem, data mining subsystem is connected with rule base and knowledge base subsystem, rule base and knowledge base subsystem are connected with real-time streams subsystem, big data storage subsystem, rule base and knowledge base subsystem and real-time streams computing subsystem are connected with visual subsystem respectively again.The beneficial effects of the invention are as follows：Set up more objectively regular by data mining, adapt to business scenario change, rule base can be set up and be updated to the technology based on data mining automatically, without external disturbance, can recognize more complicated, more hidden fraudulent mean.
Description
Technical field
Technology technical field is analyzed and processed the present invention relates to big data, and in particular to a kind of medical insurance excavated based on big data
Anti- fake system.
Background technology
What portion of people society was announced《2014 annual human resources and social benefit undertakings statistical communique of development》It has been shown that, 2014 complete
968,700,000,000 yuan of year urban basic health insurance programs fund total income, pays 813,400,000,000 yuan, increases by 17.4% and 19.6% than last year respectively,
Although receiving still above branch, income amplification occurs significantly lower than expenditure amplification, and urban employees' medical insurance fund in many areas
The situation for not supporting branch is received, medical insurance fund can't bear the heavy load, and every Medical Benefits Fund expenditure growth rate exceedes and received now
Enter growth rate.The reason for causing medical insurance financial strain situation is huge with addition to aging population except population base, passes through various hands
Section gains that the waste that medical insurance fund causes is particularly important by cheating, and according to the preliminary statistics, the fund that medical insurance fraud is caused, which is wasted, accounts for total medical insurance money
5% ~ 10% or so of gold expenditure.These fraudulent means include：Hang bed patient；Patient and doctor conspire forgery data, resell at a profit usury
Demulcen product；Got cash by trickery using medical insurance card, marketable securities or purchase commodity, food；Forge, alter diagnosis proof, case history, place
The testimonial materials such as side or false medical bill, charge detail gain basic medical insurance fund expenditure etc. by cheating.
For supervision medical insurance fund expenditure, various regions government establishes the anti-fake system of medical insurance, and these systems are mainly by knowing
The series of rules storehouse that medical insurance professional knowledge and the expert for having anti-fraud detection experience set up, this kind of system is referred to as advising based on business
Expert system then.The rule of this kind of anti-fake system is general relatively simple, such as the medical insurance of common cold patient is submitted an expense account
Significantly beyond local common cold treatment average cost when, it is believed that be fraud.There is following scarce limit in such anti-fake system of medical insurance：
Only known fraudulent policies are worked, it is impossible to find new fraudulent policies automatically；It is difficult to safeguard and updates, when new policy is put into effect
When, it is necessary to rule base is updated manually；New fraudulent policies are easy to bypass the internal rule defined；It is limited to the knowledge water of expert
It is flat, the scene such as what usual None- identified such as doctor and patient conspired to cheat.
The content of the invention
It is it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of counter cheat of the medical insurance based on big data
System, solves the anti-fake system of the medical insurance based on business rules and depends on expertise level and new medical insurance policies unduly and new
The problem of fraudulent policies are impacted to existed system.
The purpose of the present invention is achieved through the following technical solutions：It is a kind of that system is cheated based on the medical insurance that big data is excavated
System, it includes following subsystem：Data pick-up, conversion, loading subsystem (ETL), big data storage subsystem, data mining
System, rule base and knowledge base subsystem, real-time streams computing subsystem and visual subsystem, the data pick-up, conversion, plus
Subsystems (ETL) are connected with big data storage subsystem, and big data storage subsystem is connected with data mining subsystem, data
Excavate subsystem to be connected with rule base and knowledge base subsystem, rule base and knowledge base subsystem are connected with real-time streams subsystem,
Big data storage subsystem, rule base and knowledge base subsystem and real-time streams computing subsystem again respectively with visual subsystem
Connection.
Data pick-up, conversion, the data that loading subsystem (ETL) is extracted from its exterior database, conversion is required, and
Data after processing are loaded into big data storage subsystem；The external data base includes relevant database, non-relation
Type database and journal file.
Big data storage subsystem is used to store the number after data pick-up, conversion, loading subsystem (ETL) processing
According to data storage type includes structuring, unstructured and semi-structured data；Storage mode used includes Distributed Relational
Type mode, non-relational database mode and distributed file system mode.
Data mining subsystem includes classification, cluster, correlation rule and social network diagram analysis module；Required for it is excavated
Data come from above-mentioned big data storage subsystem, rule base and knowledge base subsystem, to being stored in big data storage subsystem
Excavated, formed with the technology such as data application prediction, cluster, the social networks map analysis in rule base and knowledge base subsystem
Model, rule or knowledge, the rule excavated, model and knowledge store to rule base and knowledge base subsystem；Data mining
System also includes the function that scheduling updates rule, model and knowledge.
Rule base is used for data storage and excavates model, rule or knowledge that subsystem is excavated, and to data mining subsystem
Existing rule or knowledge are provided, its storage mode includes unit or distribution；Knowledge base subsystem is excavated for data storage
Model, rule or knowledge that subsystem is excavated, and provide existing rule or knowledge, its storage mode to data mining subsystem
Including unit or distribution, memory technology includes relation or non-relational database and document storage system.
Rule or knowledge in real-time streams computing subsystem applying rules storehouse and knowledge base subsystem are submitted an expense account new medical insurance
Data enter mark, labeled as normal or fraud, the data of real-time streams computing subsystem input include it is above-mentioned be stored in rule base and
The reimbursement data of rule, model or knowledge and external service system newly in knowledge base subsystem；With the number of external service system
Include according to coffret：Message queue interface and WebSocket interfaces；Individually using Storm frameworks, individually using Spark frames
Frame and Storm frameworks, Spark frameworks both of which are used.
Reimbursement data with mark result in real-time streams computing subsystem have three flow directions：Return to medical insurance business in real time
System, medical insurance operation system can carry out relevant treatment according to mark result, such as refuse to pay medical insurance fund etc.；Store big number
According to being used in storage system as historical data for data mining subsystem；Will be in visual beggar labeled as the reimbursement record of fraud
Shown in fraud scoreboard in system.
Visual subsystem is used to show that the data source of visualization display is in big data to system data progress visualization
Storage subsystem, rule base and knowledge base subsystem and real-time streams computing subsystem, the mode of visual presentation include all kinds of figures,
Table, the hardware device of display is external display device；The visual subsystem includes display and beaten through real-time streams computing subsystem
Target cheats spy in the fraud scoreboard of reimbursement record, in addition to the data item shown to visualization, the interactive function of lower brill.
Visual subsystem history in big data storage subsystem is carried out simple statistical analysis and with scheme or table shape
Formula is shown；Rule base and knowledge base are shown by the form of table or figure；It is to take advantage of to the mark of real-time streams computing subsystem
The medical insurance reimbursement record of swindleness carries out visualization and shown.
Fraud scoreboard, which uses but is not limited to red, the eye-catching mode of runic, shows fraud reimbursement record, will can also take advantage of
Swindleness reimbursement recording-related information is pushed to exterior terminal in the way of short message and voice.
Thesaurus includes relational database, non-relational database and document storage system.
The beneficial effects of the invention are as follows：
1）The present invention is the anti-fraud detection system of medical insurance based on big data digging technology, solves tradition based on business rules
It is higher than the limitation dependent on expertise level in expert system, the rule set up by data mining is compared with the rule that expert sets up
It is more objective；
2）Technology of the invention based on data mining solves traditional expert system based on business rules and is difficult in adapt to business
The situation of scape change, such as new medical insurance policies, new fraudulent policies and scene solve the expert system based on business rules
The manual rule base that updates is needed to cause problem of the system in disarmed state before Policy Updates in face of change, due near real-time
Model learning and renewal this system is made reflection to various change near real-time；
3）The present invention is from including medical insurance reimbursement data, hospital outpatient, hospitalization data, patient's electronic health record, pharmacy's sales data etc.
Brainstrust is excavated in multidimensional big data with data mining technologies such as machine learning, neutral net, social network analysis to be difficult to
It was found that model or knowledge, more complicated, more hidden fraudulent mean is can recognize that using system；
4）The present invention solves the expert system based on business rules and sets up rule and Policy Updates and whole anti-fake system
Rule base can be set up and be updated to the problem of separation, the technology based on data mining automatically, without outside interference.
Brief description of the drawings
Fig. 1 is present system Organization Chart；
Fig. 2 is present system data flow figure.
Embodiment
Technical scheme is described in further detail with reference to specific embodiment, but protection scope of the present invention is not
It is confined to as described below.As shown in figure 1, a kind of anti-fake system of medical insurance excavated based on big data, it includes following subsystem：
1. data pick-up, conversion, loading (ETL) subsystem
The main function of ETL subsystems is (to include the relational data of various storage service data from the database of its exterior
The NoSql databases such as storehouse, document-type, key assignments type, pattern) or file (such as record user access IP address information system or
Business diary file) the required data of middle extraction, and necessary cleaning and conversion are carried out to data, it is then stored into big data
In storage system.
The method of extraction includes but is not limited to following technology：
1）The merging data from multiple tables of same database
2）Merging data in different tables, set from the database of multiple same types
3）From multiple different types of database combining data
4）The drawing-out structure data from unstructured or semi-structured data
5）Field used or the subset of attribute are extracted from former record or document
The method of cleaning and conversion includes but is not limited to following technology：
1）Remove the record repeated
2）Delete the record of the significant field of missing or attribute
3）Remove different field name or attribute-name but implication identical field or attribute
4）Field or the type of attribute are changed, date type is such as converted into UTC integers
5）Continuous value type is converted into discrete type, hundred-mark system achievement is such as converted into grade
The composition of ETL system includes but is not limited to following technology：
1）Flume
2）Kafka
3） Sqoop
2. big data memory module
For storing the data after ETL subsystem processes.
Big data storage system includes but is not limited to following distributed storage technology：
1）HDFS
2）Hive
3）Hbase
4）ElasticSearch
5）Cassandra
3. data mining subsystem
Data application prediction, cluster, social activity to being stored in big data storage subsystem and rule base and knowledge base subsystem
The technologies such as network map analysis are excavated, and form model, rule or knowledge, and deposit obtained model, rule or knowledge is excavated
Storage is updated into rule base and knowledge base subsystem.
Data mining subsystem includes but is not limited to in machine learning and data mining algorithm and its mutation：
1）Classical decision tree
2）Naive Bayesian
3）SVMs
4）DBSCAN
5）KMeans
6）KNN
7）FP-Growth
8）Each neural network
4. rule base and knowledge base subsystem
Model, rule or knowledge that subsystem is excavated are excavated for data storage, and provides existing to data mining subsystem
Rule or knowledge.
Rule and knowledge base include but is not limited to following technology：
1）Relevant database
2）HDFS
3）Hive
4）HBase
5）ElasticSearch
6）PMML files
7）Else Rule and knowledge store form
5. real-time streams computing subsystem
Rule or knowledge in main applying rules storehouse and knowledge base subsystem enter mark to new medical insurance reimbursement data, are labeled as
Normal or fraud.Reimbursement data with mark result have three flow directions：Return to medical insurance operation system, medical insurance business system in real time
System can carry out relevant treatment according to mark result, such as refuse to pay medical insurance fund etc.；Store in big data storage system and make
Used for historical data for data mining subsystem；The fraud in visual subsystem is remembered labeled as the reimbursement record of fraud
Divide on plate and show.
Real-time streams computing subsystem can be used including but not limited to following technology：
1）Spark
2）Storm
6. visual subsystem
It is main that simple statistical analysis is carried out to history in big data storage subsystem and is shown with the form of figure or table；It is right
Rule base and knowledge base are shown by the form of table or figure；Note is submitted an expense account for the medical insurance of fraud to the mark of real-time streams computing subsystem
Record carries out visualization and shown.
As shown in Fig. 2 anti-fake system is with business data flow direction：It is by counter cheat of the medical insurance excavated based on big data
The reimbursement record of mark after system processing is input to medical insurance reimbursement operation system, and medical insurance reimbursement operation system will newly submit an expense account record and pass
It is defeated by the anti-fake system of medical insurance excavated based on big data and handles.
Embodiment 1
The anti-fake system of medical insurance excavated based on big data as shown in Figure 1, in actual implementation system, ETL subsystems can be with
Constituted with Flume and Kafka, big data storage subsystem can select Hbase, by will be each outside Kafka deployment systems
On individual Service Database server, the data that can in real time extract, change in each Service Database, and by the number after processing
Used according to storage into Hbase for data mining subsystem.
When system is initial, the content of rule base and knowledge base is sky, can be by the existing expert based on business rules
Rule base in system is imported into the rule base of system, and data mining subsystem maintenance data digging technology is from being stored in big number
Excavated according to the data in storage subsystem.For the data in big data storage subsystem whether have labeled as fraud or just
Normal feature, can be divided into two kinds of method for digging：
1）The marker samples of feature whether are cheated without band
With such as Kmeas clustering algorithms are included but is not limited to, the record of reimbursement is clustered, the record of minority class is transferred to manually
Audit investigation is determined whether to cheat, and the tag field is appended in former data, can be used for training in advance so as to be formed
Survey the sample set of the tape label of model；Then these sample training forecast models are used.
2）Have whether band cheats the marker samples of feature
With such as decision Tree algorithms are included but is not limited to, forecast model is directly set up.
In addition to prediction algorithm, data mining subsystem can include but is not limited to individual with social network diagram analytical technology
Property PageRank scheduling algorithms excavate social networks between doctor and patient, find suspicious fraud clique, be original sample
The new feature of increase.
If the forecast model being established above can be converted into rule, storage or renewal rule base；If can not, directly will
Model is stored into knowledge base in the form of including but not limited to PMML files.
Medical insurance is submitted an expense account can be with including but do not limit between operation system and the anti-fake system of medical insurance excavated based on big data
Data are transmitted in message systems such as Kafka.When the real-time streams computing subsystem in the anti-fake system of medical insurance, to receive operation system new
Medical insurance reimbursement new data after, real-time streams computing system applying rules storehouse and knowledge base are predicted to reimbursement record, and will be pre-
Reimbursement record after survey returns to medical insurance operation system in real time（As shown in accompanying drawing two）, medical insurance operation system does according to predicting the outcome
Corresponding processing, includes but is not limited to such as：Refusal to pay, updates, delay support etc..Real-time streams computing subsystem will be marked
Be pushed to fraud scoreboard in visual subsystem for the reimbursement record of fraud, fraud scoreboard can with including but not limited to
The list display of red font is such as used, auditor can in more detail be operated to the reimbursement record in fraud scoreboard,
Record or statistical information, the historical record of the doctor involved by the reimbursement are submitted an expense account including but not limited to the history for such as browsing the patient
Or statistical information.Meanwhile, real-time streams computing subsystem by the new reimbursement data Cun Chudao big data storage subsystems of processing, and
Other information is updated, including but not limited to associated statistical information of patient and doctor etc. as involved by updating the record.
Visual subsystem includes but is not limited to be shown greatly with forms such as charts in addition to above-mentioned fraud scoreboard function, also
Historical statistical information in data storage subsystem：
1）The information such as the total amount of the history reimbursement of a certain patient, the doctor's number being related to, different hospital's numbers
2）The history that a certain doctor is related to submits an expense account the information such as total amount, the patient's number being related to
Visual subsystem can also show the information in rule base and knowledge base, include but is not limited to
1）Specific rule
2）The relevant information of model
3）Suspicious fraud clique social network relationships
There is two ways to update rule, model or knowledge inside the anti-fake system of medical insurance excavated based on big data：
1) periodically update
Data mining subsystem can be regularly updated by dispatching algorithm, and this method includes two kinds again：
A, set time frequency, such as update once fixed newly-increased data volume daily, such as the reimbursement data newly increased reach 1
A model or rule are updated at ten thousand；
B, real-time update.
Data interaction between the anti-fake system subsystems of medical insurance and subsystem that are excavated based on big data can be with
Different technologies are flexibly selected according to different hardware environments, such as real-time stream calculation subsystem can select Storm, also may be used
To select Spark.
It is apparent to those skilled in the art that, for convenience of description and succinctly, the side of foregoing description
The specific work process of method, system and module, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
Disclosed herein method, system and module, can realize by another way.For example, described above
Embodiment be only illustrative, it is actual to realize for example, the division of the module, can be only a kind of division of logic function
When can have other dividing mode, such as multiple module or components can combine or be desirably integrated into another system, or
Some features can be ignored, or not perform.Another, shown or discussed coupling or direct-coupling or communication each other
Connection is it may be said that by some interfaces, the INDIRECT COUPLING or communication connection of system or module can be electrical, machinery or other
Form.
The module that the discrete parts illustrates can be or may not be physically separate, be shown as module
Part can be or can not be physical module, you can with positioned at a place, or can also be distributed to multiple network moulds
On block.Some or all of module therein can be selected according to the actual needs to realize the scheme purpose of the present embodiment.
In addition, each functional subsystem in each of the invention embodiment can with it is integrated in a system or
Subsystems are individually physically present, can also two or more subsystems it is integrated in a system.
Described above is only the preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form, is not to be taken as the exclusion to other embodiment, and available for various other combinations, modification and environment, and can be at this
In the text contemplated scope, it is modified by the technology or knowledge of above-mentioned teaching or association area.And those skilled in the art are entered
Capable change and change does not depart from the spirit and scope of the present invention, then all should appended claims of the present invention protection domain
It is interior.
Claims (10)
1. a kind of anti-fake system of medical insurance excavated based on big data, it is characterised in that it includes following subsystem：Data are taken out
Take, change, load subsystem, big data storage subsystem, data mining subsystem, rule base and knowledge base subsystem, in real time
Flowmeter Operator Systems and visual subsystem, the data pick-up, conversion, loading subsystem and big data storage subsystem connect
Connect, big data storage subsystem is connected with data mining subsystem, data mining subsystem and rule base and knowledge base subsystem
Connection, rule base and knowledge base subsystem are connected with real-time streams subsystem, the big data storage subsystem, rule base and knowledge
Storehouse subsystem and real-time streams computing subsystem are connected with visual subsystem respectively.
2. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that the number
According to extracting, conversion, loading subsystem extracted from its exterior database, the data required for conversion, and by the data after processing
It is loaded into big data storage subsystem；The external data base includes relevant database, non-relational database and daily record
File.
3. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that described big
Data storage subsystem is used to store the data after data pick-up, conversion, loading subsystem processes, data storage type bag
Include structuring, unstructured and semi-structured data；Storage mode used includes Distributed Relational type mode, non-relational number
According to storehouse mode and distributed file system mode.
4. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that the number
Include sort module, cluster module, correlation rule and social network diagram analysis module according to subsystem is excavated；Number required for excavating
According to from above-mentioned big data storage subsystem, rule base and knowledge base subsystem, the rule excavated, model and knowledge store are arrived
Rule base and knowledge base subsystem；Data mining subsystem also includes the function that scheduling updates rule, model and knowledge.
5. a kind of anti-fake system of medical insurance excavated based on big data according to claim 4, it is characterised in that the tune
The function that degree updates rule, model or knowledge includes two kinds of scheduling modes：Dispatched with setting time gap periods and with new
Data increase to the quantitative scheduling of setting.
6. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that the rule
Then storehouse is used for model, rule or the knowledge that data storage excavates subsystem excavation, and provides existing to data mining subsystem
Rule or knowledge, its storage mode include unit or distribution；The knowledge base subsystem is used for data storage and excavates subsystem
Model, rule or the knowledge of excavation, and existing rule or knowledge are provided to data mining subsystem, its storage mode includes single
Machine or distribution.
7. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that the reality
Rule or knowledge in Shi Liuji Operator Systems applying rules storehouses and knowledge base subsystem enter mark to new medical insurance reimbursement data
（It is described separately）, labeled as normal or fraud, the data of real-time streams computing subsystem input include it is above-mentioned be stored in rule base and
The reimbursement data of rule, model or knowledge and external service system newly in knowledge base subsystem；With the number of external service system
Include according to coffret：Message queue interface and WebSocket interfaces；Real-time streams Computational frame includes：Individually use Storm frames
Frame, individually use Spark frameworks and Storm frameworks, Spark frameworks both of which are used.
8. it is according to claim 1 it is a kind of based on big data excavate the anti-fake system of medical insurance, it is characterised in that it is described can
It is used to show that the data source for visualizing display stores subsystem in big data to system data progress visualization depending on sub-systems
System, rule base and knowledge base subsystem and real-time streams computing subsystem, the mode of visual presentation include all kinds of figures, table, display
Hardware device be external display device；The visual subsystem includes fraud of the display through real-time streams computing subsystem mark
The fraud scoreboard recorded is submitted an expense account, in addition to the data item of visualization display visit and lower brill.
9. a kind of anti-fake system of medical insurance excavated based on big data according to claim 8, it is characterised in that described to take advantage of
Swindleness scoreboard, which uses but is not limited to red, the eye-catching mode of runic, shows fraud reimbursement record, can also be by fraud reimbursement record
Relevant information is pushed to exterior terminal in the way of short message and voice.
10. a kind of anti-fake system of medical insurance excavated based on big data according to claim 1, it is characterised in that storage
Storehouse includes relational database, non-relational database and document storage system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710329362.9A CN107145587A (en) | 2017-05-11 | 2017-05-11 | A kind of anti-fake system of medical insurance excavated based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710329362.9A CN107145587A (en) | 2017-05-11 | 2017-05-11 | A kind of anti-fake system of medical insurance excavated based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107145587A true CN107145587A (en) | 2017-09-08 |
Family
ID=59777665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710329362.9A Pending CN107145587A (en) | 2017-05-11 | 2017-05-11 | A kind of anti-fake system of medical insurance excavated based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107145587A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993139A (en) * | 2017-11-15 | 2018-05-04 | 华融融通（北京）科技有限公司 | A kind of anti-fake system of consumer finance based on dynamic regulation database and method |
| CN108021809A (en) * | 2017-12-19 | 2018-05-11 | 北京明朝万达科技股份有限公司 | A kind of data processing method and system |
| CN108038700A (en) * | 2017-12-22 | 2018-05-15 | 上海前隆信息科技有限公司 | A kind of anti-fraud data analysing method and system |
| CN108364233A (en) * | 2018-01-12 | 2018-08-03 | 中国平安人寿保险股份有限公司 | A kind of declaration form methods of risk assessment, device, terminal device and storage medium |
| CN108921359A (en) * | 2018-07-26 | 2018-11-30 | 安徽大学 | A kind of distribution gas density prediction technique and device |
| CN108933785A (en) * | 2018-06-29 | 2018-12-04 | 平安科技（深圳）有限公司 | Network risks monitoring method, device, computer equipment and storage medium |
| 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 |
| CN109636632A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning |
| CN109710674A (en) * | 2018-12-26 | 2019-05-03 | 重庆誉存大数据科技有限公司 | A kind of rule engine system of semi-structured text data and preposition cut-in method |
| CN109977125A (en) * | 2019-04-09 | 2019-07-05 | 福建奇点时空数字科技有限公司 | A kind of big data safety analysis plateform system based on network security |
| CN110110172A (en) * | 2017-12-28 | 2019-08-09 | 北京京东尚科信息技术有限公司 | Information displaying method and device |
| CN110348516A (en) * | 2019-07-11 | 2019-10-18 | 同盾控股有限公司 | Data processing method, device, storage medium and electronic equipment |
| CN110674174A (en) * | 2019-09-24 | 2020-01-10 | 北京九章云极科技有限公司 | Data real-time processing method and data real-time processing system |
| CN110675220A (en) * | 2019-09-12 | 2020-01-10 | 深圳前海大数金融服务有限公司 | Method, system and computer readable storage medium for identifying fraudulent user |
| TWI686760B (en) * | 2018-04-12 | 2020-03-01 | 香港商阿里巴巴集團服務有限公司 | Data processing method, device, equipment and server for insurance fraud identification |
| CN110943985A (en) * | 2019-11-26 | 2020-03-31 | 武汉虹信通信技术有限责任公司 | Security audit system and method based on 5G mobile communication network |
| CN111209299A (en) * | 2020-04-20 | 2020-05-29 | 四川新网银行股份有限公司 | Real-time judgment method for anti-fraud of finance |
| WO2020119386A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Big data-based abnormal data identification method and device, and storage medium and apparatus |
| CN111696650A (en) * | 2020-06-10 | 2020-09-22 | 杭州联众医疗科技股份有限公司 | Medical insurance charge control system based on historical image data comparison |
| CN112506983A (en) * | 2020-09-18 | 2021-03-16 | 上海欣方智能系统有限公司 | Anti-fraud method based on big data support |
| WO2021051938A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Data anomaly analysis method and system employing graph analysis and computer device |
| CN112905582A (en) * | 2021-03-22 | 2021-06-04 | 杭州联众医疗科技股份有限公司 | Data bank system based on medical data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945235A (en) * | 2011-08-16 | 2013-02-27 | 句容今太科技园有限公司 | Data mining system facing medical insurance violation and fraud behaviors |
| CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
| CN106339451A (en) * | 2016-08-26 | 2017-01-18 | 成都汉康信息产业有限公司 | Data mining system based on large data |
| CN106815338A (en) * | 2016-12-25 | 2017-06-09 | 北京中海投资管理有限公司 | A kind of real-time storage of big data, treatment and inquiry system |
-
2017
- 2017-05-11 CN CN201710329362.9A patent/CN107145587A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102945235A (en) * | 2011-08-16 | 2013-02-27 | 句容今太科技园有限公司 | Data mining system facing medical insurance violation and fraud behaviors |
| CN105095653A (en) * | 2015-07-13 | 2015-11-25 | 湖南互动传媒有限公司 | Basic service system for medical large data application |
| CN106339451A (en) * | 2016-08-26 | 2017-01-18 | 成都汉康信息产业有限公司 | Data mining system based on large data |
| CN106815338A (en) * | 2016-12-25 | 2017-06-09 | 北京中海投资管理有限公司 | A kind of real-time storage of big data, treatment and inquiry system |
Non-Patent Citations (1)
| Title |
|---|
| 王小妮: "《数据挖掘技术》", 31 August 2014 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993139A (en) * | 2017-11-15 | 2018-05-04 | 华融融通（北京）科技有限公司 | A kind of anti-fake system of consumer finance based on dynamic regulation database and method |
| CN108021809A (en) * | 2017-12-19 | 2018-05-11 | 北京明朝万达科技股份有限公司 | A kind of data processing method and system |
| CN108038700A (en) * | 2017-12-22 | 2018-05-15 | 上海前隆信息科技有限公司 | A kind of anti-fraud data analysing method and system |
| CN110110172A (en) * | 2017-12-28 | 2019-08-09 | 北京京东尚科信息技术有限公司 | Information displaying method and device |
| CN108364233A (en) * | 2018-01-12 | 2018-08-03 | 中国平安人寿保险股份有限公司 | A kind of declaration form methods of risk assessment, device, terminal device and storage medium |
| TWI686760B (en) * | 2018-04-12 | 2020-03-01 | 香港商阿里巴巴集團服務有限公司 | Data processing method, device, equipment and server for insurance fraud identification |
| 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 |
| WO2020000763A1 (en) * | 2018-06-29 | 2020-01-02 | 平安科技（深圳）有限公司 | Network risk monitoring method and apparatus, computer device and storage medium |
| CN108933785A (en) * | 2018-06-29 | 2018-12-04 | 平安科技（深圳）有限公司 | Network risks monitoring method, device, computer equipment and storage medium |
| CN108921359A (en) * | 2018-07-26 | 2018-11-30 | 安徽大学 | A kind of distribution gas density prediction technique and device |
| CN108921359B (en) * | 2018-07-26 | 2022-03-11 | 安徽大学 | Distributed gas concentration prediction method and device |
| CN109636632A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning |
| WO2020119386A1 (en) * | 2018-12-13 | 2020-06-18 | 平安医疗健康管理股份有限公司 | Big data-based abnormal data identification method and device, and storage medium and apparatus |
| CN109710674A (en) * | 2018-12-26 | 2019-05-03 | 重庆誉存大数据科技有限公司 | A kind of rule engine system of semi-structured text data and preposition cut-in method |
| CN109977125A (en) * | 2019-04-09 | 2019-07-05 | 福建奇点时空数字科技有限公司 | A kind of big data safety analysis plateform system based on network security |
| CN110348516A (en) * | 2019-07-11 | 2019-10-18 | 同盾控股有限公司 | Data processing method, device, storage medium and electronic equipment |
| CN110348516B (en) * | 2019-07-11 | 2021-05-11 | 同盾控股有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
| CN110675220A (en) * | 2019-09-12 | 2020-01-10 | 深圳前海大数金融服务有限公司 | Method, system and computer readable storage medium for identifying fraudulent user |
| WO2021051938A1 (en) * | 2019-09-16 | 2021-03-25 | 平安科技（深圳）有限公司 | Data anomaly analysis method and system employing graph analysis and computer device |
| CN110674174A (en) * | 2019-09-24 | 2020-01-10 | 北京九章云极科技有限公司 | Data real-time processing method and data real-time processing system |
| CN110943985A (en) * | 2019-11-26 | 2020-03-31 | 武汉虹信通信技术有限责任公司 | Security audit system and method based on 5G mobile communication network |
| CN110943985B (en) * | 2019-11-26 | 2022-03-22 | 武汉虹旭信息技术有限责任公司 | Security audit system and method based on 5G mobile communication network |
| CN111209299A (en) * | 2020-04-20 | 2020-05-29 | 四川新网银行股份有限公司 | Real-time judgment method for anti-fraud of finance |
| CN111696650A (en) * | 2020-06-10 | 2020-09-22 | 杭州联众医疗科技股份有限公司 | Medical insurance charge control system based on historical image data comparison |
| CN112506983A (en) * | 2020-09-18 | 2021-03-16 | 上海欣方智能系统有限公司 | Anti-fraud method based on big data support |
| CN112905582A (en) * | 2021-03-22 | 2021-06-04 | 杭州联众医疗科技股份有限公司 | Data bank system based on medical data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107145587A (en) | A kind of anti-fake system of medical insurance excavated based on big data | |
| Pinotti | The economic costs of organised crime: Evidence from Southern Italy | |
| CN110717828B (en) | Abnormal account detection method and system based on frequent transaction mode | |
| Bord et al. | Large banks and small firm lending | |
| CN109977151A (en) | A kind of data analysing method and system | |
| CN106339942A (en) | Financial information processing method and system | |
| CN109461078A (en) | A kind of abnormal transaction identification method and system based on funds transaction network | |
| KR20180060044A (en) | Security System for Cloud Computing Service | |
| US8706587B1 (en) | Statistical prioritization and detection of potential financial crime events | |
| US20090327036A1 (en) | Decision support systems using multi-scale customer and transaction clustering and visualization | |
| KR20180060005A (en) | Security System for Cloud Computing Service | |
| Bhandari et al. | An artificial intelligence ATM forecasting system for hybrid neural networks | |
| CN112419030B (en) | Method, system and equipment for evaluating financial fraud risk | |
| CN115204881A (en) | Data processing method, device, equipment and storage medium | |
| Palshikar et al. | Financial security against money laundering: A survey | |
| CN109636627B (en) | Insurance product management method, device, medium and electronic equipment based on block chain | |
| Zhai et al. | Big data analysis of accounting forecasting based on machine learning | |
| CN117033431A (en) | Work order processing method, device, electronic equipment and medium | |
| CN110942391A (en) | Method for determining main activity label of multi-activity label user in block chain | |
| Keon et al. | Call Center Call Count Prediction Model by Machine Learning | |
| WO2022143431A1 (en) | Method and apparatus for training anti-money laundering model | |
| CN110619564A (en) | Anti-fraud feature generation method and device | |
| Yang et al. | Reform and competitive selection in China: An analysis of firm exits | |
| CN114819494A (en) | Enterprise risk early warning method, device, equipment and medium | |
| CN112884593A (en) | Medical insurance fraud and insurance behavior detection method and early warning device based on graph cluster analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170908 |