CN109658109A - Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely - Google Patents
Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely Download PDFInfo
- Publication number
- CN109658109A CN109658109A CN201811272390.2A CN201811272390A CN109658109A CN 109658109 A CN109658109 A CN 109658109A CN 201811272390 A CN201811272390 A CN 201811272390A CN 109658109 A CN109658109 A CN 109658109A
- Authority
- CN
- China
- Prior art keywords
- medical insurance
- card
- detected
- group
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 230000001680 brushing effect Effects 0.000 claims abstract description 133
- 238000012544 monitoring process Methods 0.000 claims abstract description 82
- 230000002159 abnormal effect Effects 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 22
- 238000005516 engineering process Methods 0.000 abstract 1
- 239000003814 drug Substances 0.000 description 15
- 238000011176 pooling Methods 0.000 description 13
- 238000012216 screening Methods 0.000 description 12
- 230000005856 abnormality Effects 0.000 description 11
- 238000012550 audit Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 229940079593 drug Drugs 0.000 description 6
- 238000005065 mining Methods 0.000 description 5
- 230000009885 systemic effect Effects 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013434 data augmentation Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The present invention provides a kind of detection method that medical insurance is swiped the card extremely, device, terminal and storage medium, this method comprises: obtaining first brushing card data in default monitoring month, and extracts medical insurance number to be detected from first brushing card data according to default extracting rule；The degree of association between the medical insurance number to be detected of any predetermined number is calculated according to first brushing card data and preset algorithm, wherein the predetermined number is greater than or equal to two；The medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, the target medical insurance group after being grouped；The medical insurance number for belonging to target medical insurance group is subjected to abnormal marking.The present invention is based on relational network analytical technologies to obtain relational network between medical insurance number to be detected, realizes the identification to violation brush medical insurance card group.
Description
Technical field
The present invention relates to medical insurance technical field of data processing more particularly to a kind of detection methods that medical insurance is swiped the card extremely, dress
It sets, terminal and storage medium.
Background technique
Medical insurance is mandatory social insurance, is a kind of insurance to compensate medical expense brought by disease, in insured people
When disease, medical insurance can provide necessary medical services for it or substance helps.Social medical insurance card (abbreviation medical insurance card) is ginseng
The daily important documents for seeing a doctor purchase medicine of guarantor person, are the carriers of Personal Account of Medical Insurance, for recording insured people's essential information,
The basic medical insurance paid by employing unit taken, be divided into according to regulation ratio including the basic medical insurance that individual pays
Take, spend situation etc..
Universal with social medical services and medical insurance card, more and more people enjoy a series of correlations using medical insurance card
Medical services, according to relevant regulations, medical insurance card, which can only limit, to be used in person and is only used in medical services, but some
Criminal carries out deceiving brush by the actual medical insurance card for renting, usurping other people, or deceives a large amount of drugs of brush and peddle trying to gain
Benefit, these abnormal behaviours all destroy the operating specification of medical insurance card, therefore, existing medical insurance audit need it is a kind of swipe the card it is abnormal
Recognition methods, to contain the improper activity in medical insurance card use.
Summary of the invention
The main purpose of the present invention is to provide a kind of detection methods that medical insurance is swiped the card extremely, it is intended to solve existing medical insurance and examine
Core can not identify the technical issues of medical insurance card uses extremely.
To achieve the above object, the present invention provides a kind of detection method that medical insurance is swiped the card extremely, which is characterized in that the doctor
Guarantor swipes the card extremely, and detection method includes the following steps:
First brushing card data in default monitoring month is obtained, and according to default extracting rule from first brushing card data
Extract medical insurance number to be detected；
It is calculated between the medical insurance number to be detected of any predetermined number according to first brushing card data and preset algorithm
The degree of association, wherein the predetermined number be greater than or equal to two；
The medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, the target after being grouped
Medical insurance group；
The medical insurance number for belonging to target medical insurance group is subjected to abnormal marking.
Optionally, first brushing card data for obtaining default monitoring month, and according to default extracting rule from described the
The step of extracting medical insurance to be detected in one brushing card data include:
First brushing card data in default monitoring month is obtained, each medical insurance number is described in statistics first brushing card data
The number of swiping the card in default monitoring month；
It extracts medical insurance number of the number greater than preset times of swiping the card in first brushing card data and is used as medical insurance number to be detected.
Optionally, described to extract number of swiping the card in first brushing card data greater than the medical insurance number of preset times as to be checked
Survey medical insurance the step of include:
The medical insurance number that number of swiping the card in first brushing card data is greater than preset times is extracted, regard the medical insurance number as first
Class medical insurance number；
The first kind medical insurance number is obtained in default month second brushing card data adjacent with the default monitoring month,
From in first brushing card data and second brushing card data, extract that the first kind medical insurance number is corresponding to swipe the card the date；
Based on the first kind medical insurance number corresponding swipe the card date and preset frequent item set algorithm, frequent item is obtained
Collection；
The medical insurance number for belonging to the Frequent Item Sets in the first kind medical insurance number is extracted as medical insurance number to be detected.
Optionally, the association calculated based on preset algorithm between the medical insurance number to be detected of any predetermined number
Degree, wherein the predetermined number includes: more than or equal to two steps
Total number of days of preset time period is obtained, and it is daily in the preset time period to obtain the medical insurance number to be detected
It swipes the card the amount of money；
Degree of association formula is obtained, based on the degree of association formula, total number of days of preset time period and the medical insurance to be detected
Number amount of money of swiping the card daily within a preset period of time calculates the medical insurance to be detected of any predetermined number within a preset period of time
The degree of association between number, wherein if the predetermined number is two, the degree of association formula are as follows:
Wherein,
RijFor the degree of association between i-th of medical insurance number to be detected and j-th of medical insurance number to be detected, n is preset time period
Total number of days,For i-th of medical insurance number kth day the amount of money of swiping the card,For j-th of medical insurance number kth day the amount of money of swiping the card.
Optionally, described that the described to be checked of any predetermined number is calculated according to first brushing card data and preset algorithm
Survey the degree of association between medical insurance number, wherein the predetermined number includes: more than or equal to two steps
The medical insurance number to be detected is obtained in default month second brushing card data adjacent with default monitoring month, by institute
It states default monitoring month and default month adjacent with the default monitoring month is used as month to be detected；
The institute of any predetermined number is calculated according to first brushing card data and second brushing card data and preset algorithm
State the degree of association between medical insurance number to be detected, wherein the predetermined number is greater than or equal to two.
Optionally, the medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, obtains
The step of target medical insurance group after grouping includes:
It is that corresponding medical insurance No. first is established in center medical insurance number respectively with each medical insurance number to be detected based on the degree of association
Group includes all medical insurances number to be detected for being greater than preset threshold with the center medical insurance degree of association in the first medical insurance group；
Compare all first medical insurance groups, it, should if in any two the first medical insurance group including identical medical insurance number
Two the first medical insurance groups generate the first new medical insurance group after merging, and repeat more all first medical insurance groups
Step, until without identical medical insurance number between all first medical insurance groups；
It will be from each other without the first medical insurance group of identical medical insurance number as target medical insurance group.
Optionally, the medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, obtains
The step of target medical insurance group after grouping includes:
Based on the degree of association, corresponding second medical insurance group of each month to be detected is established respectively；
Compare all second medical insurance groups, it, should if in any two the second medical insurance group including identical medical insurance number
Two the second medical insurance groups generate the second new medical insurance group after merging, and repeat more all second medical insurance groups
Step, until without identical medical insurance number between all second medical insurance groups；
It will be from each other without the second medical insurance group of identical medical insurance number as target medical insurance group.
In addition, to achieve the above object, the present invention also provides a kind of detection device that medical insurance is swiped the card extremely, the medical insurance is different
The detection device often swiped the card includes:
Module is obtained, for obtaining first brushing card data in default monitoring month, and according to default extracting rule from described
Medical insurance number to be detected is extracted in first brushing card data；
Computing module, for according to first brushing card data and preset algorithm calculate any predetermined number it is described to
Detect the degree of association between medical insurance number, wherein the predetermined number is greater than or equal to two；
Grouping module, the medical insurance number to be detected for the degree of association to be greater than preset threshold are divided into same grouping, obtain
Target medical insurance group after must being grouped；
Abnormal marking module, the medical insurance number for that will belong to target medical insurance group carry out abnormal marking.
In addition, to achieve the above object, the present invention also provides a kind of detection terminal, the detection terminal include processor,
Memory and it is stored in the detection program that can be swiped the card on the memory and extremely by the medical insurance that the processor executes,
Described in the detection program swiped the card extremely of medical insurance when being executed by the processor, realize the detection swiped the card extremely such as above-mentioned medical insurance
The step of method.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, being stored with medical insurance on the storage medium
Extremely the detection program swiped the card, wherein realizing when the detection program that the medical insurance is swiped the card extremely is executed by processor as above-mentioned
The step of detection method that medical insurance is swiped the card extremely.
The embodiment of the present invention is by obtaining first brushing card data in default monitoring month, and according to default extracting rule from institute
It states and extracts medical insurance number to be detected in the first brushing card data；It is calculated according to first brushing card data and preset algorithm any default
The degree of association between the medical insurance number to be detected of number, wherein the predetermined number is greater than or equal to predetermined number；It will be described
The medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, the target medical insurance group after being grouped；It will belong to
Abnormal marking is carried out in the medical insurance number of target medical insurance group, i.e. the present embodiment is calculated by carrying out sample process to brushing card data
The degree of association between medical insurance number to be detected, and medical insurance number to be detected is grouped based on the degree of association, it realizes to medical insurance to be detected
The analysis of relational network between number, and then realize the identification to violation brush medical insurance card group.
Detailed description of the invention
Fig. 1 is the detection terminal structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram for the detection method first embodiment that medical insurance of the present invention is swiped the card extremely；
Fig. 3 is the flow diagram for the detection method 3rd embodiment that medical insurance of the present invention is swiped the card extremely；
Fig. 4 is the schematic diagram for the detection method Frequent Pattern Mining that medical insurance of the present invention is swiped the card extremely；
Process signal in the 5th embodiment of detection method that Fig. 5 swipes the card extremely for medical insurance of the present invention after step S30 refinement
Figure；
Fig. 6 is the functional block diagram for the detection device first embodiment that medical insurance of the present invention is swiped the card extremely.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Figure 1, Fig. 1 is the hardware structural diagram of detection terminal provided by the present invention.
The detection terminal can be PC, be also possible to smart phone, tablet computer, portable computer, desktop computer
Etc. device end having data processing function, optionally, the detection terminal can be server apparatus, and there are medical insurance exceptions
The rear end management system of brushing card data detection, medical insurance auditor carry out pipe to detection terminal by the rear end management system
Reason, optionally, the detection terminal can be the audit terminal of medical expense in medicare system simultaneously, and medical insurance of the present invention is brushed extremely
The detection method of card runs on the audit terminal of the medical expense, the knowledge for the abnormal brushing card data in the audit of medical expense
Not.
The detection terminal may include: the components such as processor 10 and memory 20.It is described in the detection terminal
Processor 10 is connect with the memory 20, and the detection program that medical insurance is swiped the card extremely, processor are stored on the memory 20
The 10 detection programs that the medical insurance stored in memory 20 can be called to swipe the card extremely, and realize the inspection swiped the card extremely such as following medical insurances
The step of each embodiment of survey method.
The memory 20 can be used for storing software program and various data.Memory 20 can mainly include storage journey
Sequence area and storage data area, wherein storing program area can the (ratio of application program needed for storage program area, at least one function
The detection program that such as medical insurance is swiped the card extremely)；Storage data area may include database, such as the present invention can be obtained from database
First brushing card data in default monitoring month.In addition, memory 20 may include high-speed random access memory, can also include
Nonvolatile memory, for example, at least a disk memory, flush memory device or other volatile solid-state parts.
Processor 10 is the control centre for detecting terminal, entirely detects each of terminal using various interfaces and connection
A part by running or execute the software program and/or module that are stored in memory 20, and calls and is stored in memory
Data in 20 execute the various functions and processing data of detection terminal, to carry out integral monitoring to detection terminal.In this hair
In bright, the detection program and related data that processor 10 can call the medical insurance stored in memory 20 to swipe the card extremely are executed hereafter
Each embodiment of middle the method for the present invention.Processor 10 may include one or more processing units；Optionally, processor 10 can collect
At application processor and modem processor, wherein the main processing operation system of application processor, user interface and apply journey
Sequence etc., modem processor mainly handle wireless communication.It is understood that above-mentioned modem processor can not also collect
At into processor 10.
It will be understood by those skilled in the art that detection terminal structure shown in Fig. 1 does not constitute the limit to detection terminal
It is fixed, it may include perhaps combining certain components or different component layouts than illustrating more or fewer components.
Based on above-mentioned hardware configuration, the hereinafter each embodiment of the method for the present invention is proposed.
Present inventor by deceive brush, drug is peddled etc., and medical insurance cards Misuse sample carefully analyzes, discovery ginseng
With deceive brush, drug is peddled etc. swipe the card in violation of rules and regulations behavior medical insurance number when in use between upper registration it is higher, be embodied in and swipe the card on the same day
Or it is higher in the ratio of the number of days Zhan not swiped the card on the same day total statistics number of days.
Therefore, be brush is deceived in identification, drug is peddled etc. more medical insurance groups unlawful practice, based on deceive brush, that drug is peddled etc. is more
The features described above of medical insurance group unlawful practice, the present invention provide a kind of detection method that medical insurance is swiped the card extremely.
Referring to Fig. 2, Fig. 2 is the flow diagram for the detection method first embodiment that medical insurance of the present invention is swiped the card extremely.
In the present embodiment, the medical insurance is swiped the card extremely, and detection method includes the following steps:
Step S10 obtains first brushing card data in default monitoring month, and is brushed according to default extracting rule from described first
Medical insurance number to be detected is extracted in card data；
Default monitoring refers in month: the current month for carrying out data exception detection, can be the current time in system by system default
The upper January, can also be inputted according to user and determine that specific one or multiple months are default monitoring month.Brushing card data
Refer to the relative recording that medical insurance card is swiped the card, including but not limited to: medical insurance number, charge time, the amount of money of swiping the card swipe the card and purchases pharmacopoeia class or examine
Treatment project and diagnostic result etc..For convenient for distinguishing, in the present embodiment, the first brushing card data refers to the part in default monitoring month
Or whole brushing card datas, " part " here, which refers to, to be instructed according to the customized screening of systemic presupposition or user from default monitoring month
In all brushing card datas in the part brushing card data for meeting screening conditions that filters out, such as filter out all Grade A hospitals
Brushing card data.
Optionally, when obtaining first brushing card data in default monitoring month, detection terminal output data screens interface, number
According to may include default or customized brushing card data screening conditions in screening interface, for selection by the user or customized screening item
Part, for filtering out the first brushing card data from whole brushing card datas in default monitoring month.Wherein, brushing card data screening conditions
Including but not limited to: time (month and/or the date of swiping the card), hospital name or hospital code (referring to some specific hospital),
Hospital Grade (can be common Hospital Grade, such as Grade A hospital, diformazan hospital) can be medical insurance number, be also possible to brush
The card amount of money (amount of money range), number of swiping the card etc..
Brushing card data is sent to medical insurance audit end by hospital end, can be sent directly to detection terminal, so that detection terminal exists
When carrying out the detection of abnormal brushing card data, the first of default monitoring month is directly obtained in the memory of detection terminal and is swiped the card number
According to medical insurance at this time audits end and includes at least detection terminal；Medical insurance audit end can also be sent to and be exclusively used in storage brushing card data
Data storage terminal/cloud, so that detection terminal is when carrying out the detection of abnormal brushing card data, from data storage terminal/cloud
Obtain first brushing card data in default monitoring month, medical insurance at this time audit end include at least detection terminal and data storage terminal/
Cloud.
Medical insurance number is the medical insurance account of insured people, is the medical insurance identification number of each insured people, can according to medical insurance number
Therefore in embodiments of the present invention, using medical insurance number as the mark of insured people, also made with inquiring unique, specific insured people
For the mark of single brushing card data.It include multiple medical insurances number, medical insurance number to be detected in first brushing card data in default monitoring month
It can be all medical insurances number or part medical insurance number therein, can be screened from the first brushing card data according to systemic presupposition extracting rule
Medical insurance number to be detected out, default extracting rule may include one or more screening conditions, for sieving from the first brushing card data
The medical insurance number to be detected for meeting screening conditions is selected, screening conditions can be customized by the user, it is also possible to system default setting,
Screening conditions can be with are as follows: the purchase medicine total amount of preset time period, swipe the card risk-pooling fund and number of swiping the card etc..
Terminal is detected when detecting detection instruction, starts the detection program that medical insurance of the present invention is swiped the card extremely, detection instruction
It can be triggered manually by auditor, it can also be by detection terminal automatic trigger, such as clocked flip.Optionally, the present invention is to doctor
The detection swiped the card extremely is protected, can be one or more flow nodes in medical expense auditing flow, it can be by flow nodes
Circulate automatic trigger abnormality detection.
Step S20 calculates the doctor to be detected of any predetermined number according to first brushing card data and preset algorithm
The degree of association between guarantor number, wherein the predetermined number is greater than or equal to two；
The degree of association is used to characterize the correlation between medical insurance number, it may be assumed that the medical insurance number of predetermined number is all carried out interior on the same day
The number of days Zhan to swipe the card always counts the ratio of number of days, alternatively, all having carried out swiping the card and all do not swipe the card on the same day
Number of days Zhan always count the ratio of number of days.The degree of association is higher between the medical insurance number of any predetermined number, is more likely to belong to batch
Swipe the card clique.
Predetermined number is greater than or equal to two, can also be customized by the user setting by systemic presupposition.
Preset algorithm can be pre-stored in system, and preset algorithm, which can be, directly calculates predetermined number medical insurance number same
The Zhan that carried out swiping the card in one day always counts the ratio of number of days,
R(a1,a2,a3...am) it is medical insurance a to be detected1、a2、a3...amBetween the degree of association, a1、a2、a3...amAll divide
Not referring to arbitrary mutually different medical insurance number to be detected, n is total statistics number of days,For aiA medical insurance number is swiped the card kth day
The amount of money.Refer to medical insurance a to be detected1、a2、a3...amIt is not 0 in the amount of money of swiping the card of kth day.
The medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, is grouped by step S30
Target medical insurance group afterwards；
After calculating the degree of association between obtaining any predetermined number medical insurance number to be detected, according to the degree of association to medical insurance to be detected
It number is grouped, when only the degree of association between the medical insurance number to be detected of predetermined number is greater than certain value, the predetermined number
Medical insurance number to be detected is possible to belong to the clique that swipes the card in violation of rules and regulations, and in the present embodiment, preset threshold can be by systemic presupposition or user
It is default.
In one embodiment, after the medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, obtain
The degree of association be greater than preset threshold medical insurance number to be detected form medical insurance group be target medical insurance group；In another embodiment,
After the medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, obtained grouping is continued subsequent
Data processing operation, obtain final target medical insurance group.
The medical insurance number for belonging to target medical insurance group is carried out abnormal marking by step S40.
Target medical insurance group refers to the medical insurance group with abnormal suspicion of swiping the card in the present embodiment, finally obtain one or
Multiple target medical insurance groups.When target medical insurance group has multiple, the medical insurance number in all target medical insurance groups can be carried out
Identical abnormal marking can also carry out corresponding to different abnormal markings to different target medical insurance groups.
The present embodiment is by obtaining first brushing card data in default monitoring month, and according to default extracting rule from described the
Medical insurance number to be detected is extracted in one brushing card data；Any predetermined number is calculated according to first brushing card data and preset algorithm
The medical insurance number to be detected between the degree of association, wherein the predetermined number be greater than or equal to predetermined number；By the association
The medical insurance number to be detected that degree is greater than preset threshold is divided into same grouping, the target medical insurance group after being grouped；Mesh will be belonged to
The medical insurance number for marking medical insurance group carries out abnormal marking, i.e. the present embodiment is calculated to be checked by carrying out sample process to brushing card data
Survey the degree of association between medical insurance number, and medical insurance number to be detected be grouped based on the degree of association, realize to medical insurance number to be detected it
Between relational network analysis, and then realize identification to violation brush medical insurance card group.
Further, in the detection method second embodiment that medical insurance of the present invention is swiped the card extremely, the step S10 includes:
Step S11 obtains first brushing card data in default monitoring month, counts each medical insurance in first brushing card data
Number it is described it is default monitoring month number of swiping the card；
In first brushing card data in default monitoring month, and not all brushing card data is required by subsequent degree of correlation meter
Calculation can just carry out abnormal judgement, the abnormal obvious off-note of brushing card data general satisfaction, such as: swipe the card often, the amount of money of swiping the card
It is big etc., therefore, it is possible to screen out the brushing card data for not having obvious off-note by off-note.
In the present embodiment, by swiping the card, the medical insurance number to be detected that number carries out abnormality detection needs is screened.Arbitrarily
A possibility that medical insurance number is corresponding when swiping the card number less than certain number, and the medical insurance number is abnormal or corresponding brushing card data is abnormal is very
It is small, which can be screened out away.
The corresponding brush of each medical insurance number can be determined by the frequency of occurrence of each medical insurance number in the first brushing card data of statistics
Card number.
Step S12 extracts number of swiping the card in first brushing card data greater than the medical insurance number of preset times as to be detected
Medical insurance number.
After having counted the number of swiping the card of each medical insurance number, the medical insurance number that number of wherein swiping the card is greater than preset times is obtained,
It extracts the medical insurance number of the number greater than preset times of swiping the card and is used as medical insurance number to be detected, carry out subsequent abnormality detection operation.And
The medical insurance number that number of swiping the card in first brushing card data is less than or equal to preset times is extracted not as medical insurance number to be detected, that is, is sieved
Except going out, operated without subsequent abnormality detection.
Preset times in the present embodiment can default setting, can also be independently arranged by user, for example, 15 times.
The present embodiment counts each in first brushing card data by obtaining default the first brushing card data for monitoring month
Swipe the card number of the medical insurance number in the default monitoring month；Number of swiping the card in first brushing card data is extracted greater than preset times
Medical insurance number be used as medical insurance number to be detected, i.e., the data for being unsatisfactory for obvious off-note are screened out based on number of swiping the card, after can reducing
The data processing amount of continuous step, promotes detection efficiency.
Optionally, the step S12 includes:
The medical insurance number that number of swiping the card in first brushing card data is greater than preset times is extracted, regard the medical insurance number as first
Class medical insurance number；According to first brushing card data, the pool base in the first kind medical insurance number corresponding default monitoring month is extracted
The amount of money；All medical insurances number that the risk-pooling fund amount of money is greater than threshold amount are filtered out from the first kind medical insurance number；It will
All medical insurances number that the risk-pooling fund amount of money is greater than threshold amount are extracted as medical insurance number to be detected.
The risk-pooling fund amount of money in default monitoring month refers in the document payment information in default monitoring month by risk-pooling fund branch
The amount of money held, threshold amount in the present embodiment can default setting, can also be independently arranged by user, such as may be configured as being 1000
Member.If the default monitoring month risk-pooling fund amount of money is less than threshold amount, although number of swiping the card is more, its public base spent
A possibility that gold is less, and there are cliques to deceive brush, drug is peddled is smaller.
After carrying out first time scalping to the first brushing card data based on number of swiping the card, according to the risk-pooling fund amount of money to for the first time
The first kind medical insurance number obtained after scalping carries out second of scalping, and the default monitoring month risk-pooling fund amount of money is less than threshold amount
Medical insurance number screen out, subsequent abnormality detection operation is no longer carried out to this part medical insurance related data, by default monitoring month
The medical insurance number that the risk-pooling fund amount of money is greater than threshold amount is retained as medical insurance number to be detected and extracts.
The present embodiment passes through using the default monitoring month risk-pooling fund amount of money as one of screening conditions of medical insurance number to be detected,
The small data of abnormal possibility can be screened out away, the data processing amount of subsequent step can be reduced, promote detection efficiency.
When the total amount of swiping the card in default monitoring month is too small, then abnormal possibility may also be smaller.Optionally, it is being based on
Swipe the card number to the first brushing card data carry out first time scalping, based on the risk-pooling fund amount of money to first obtained after first time scalping
After class medical insurance number carries out second of scalping, be also based on default monitoring month swipes the card what total amount obtained second of scalping
Medical insurance number carries out third time scalping, it may be assumed that the default monitoring month is filtered out from the medical insurance number that second of scalping obtains
Swipe the card total amount be greater than preset cost all medical insurances number；The total amount that will swipe the card is greater than the medical insurance number of preset cost as to be checked
Medical insurance number is surveyed to extract.
Although being based on number of swiping the card, alternatively, swipe the card number and the risk-pooling fund amount of money, or number of swiping the card, risk-pooling fund
After the amount of money and total amount of swiping the card carry out scalping to the first brushing card data, the lesser medical insurance number of the abnormal possibility in part has been screened out, but
In order to screen out more normal medical insurances number, the data volume of subsequent operation is reduced, the specific aim of subsequent operation is improved, improves abnormal data
The accuracy of detection, based on the above embodiment, it is further proposed that the detection method 3rd embodiment that medical insurance of the present invention is swiped the card extremely.
In third embodiment of the invention, as shown in figure 3, the step S12 includes:
Step S121 extracts the medical insurance number that number of swiping the card in first brushing card data is greater than preset times, by the medical insurance
Number be used as first kind medical insurance number；
Step S122 obtains the first kind medical insurance number in preset a month second adjacent with the default monitoring month
It is corresponding to extract the first kind medical insurance number from first brushing card data and second brushing card data for brushing card data
It swipes the card the date；
As soon as medical insurance card, every brush once has a record of swiping the card, and record of swiping the card includes but is not limited to: medical insurance number is swiped the card
The amount of money, date of swiping the card etc., a medical insurance number may correspond to a plurality of record of swiping the card, and correspondence is multiple to swipe the card the date, such as: medical insurance number
There were 2018-1-4,2018-1-6,2018-1-9 on 10010 corresponding dates of swiping the card, and meaning is the medical insurance of medical insurance number 10010
Card has brushed card in 2018-1-4,2018-1-6,2018-1-9 respectively in the past few days.
The present embodiment promotes the accuracy of abnormality detection by the data volume of increase data.First kind medical insurance number is obtained to exist
Default month second brushing card data adjacent with default monitoring month, on the basis of the first brushing card data and the second brushing card data
On, first kind medical insurance number is extracted in default monitoring month, and adjacent with default monitoring month default month swipes the card the date.
Optionally, the mapping table on swipe the card date and first kind medical insurance number is established, for incidence relation between subsequent progress medical insurance number
Excavation.
Step S123 is obtained based on the first kind medical insurance number corresponding swipe the card date and preset frequent item set algorithm
Frequent Item Sets；
Frequent item set algorithm, is used for Mining Association Rules, preset frequent item set algorithm can for FP-Growth algorithm or
Apriori algorithm is obtained using the first kind medical insurance number and its corresponding date of swiping the card as input parameter based on first kind medical insurance
Number generate all Frequent Item Sets.
Frequent Item Sets refer to that support is greater than the Item Sets of minimum support, specific in the present embodiment, Frequent Item Sets
Refer to that within a preset period of time (generally as unit of one month), number of days of swiping the card on the same day is greater than all medical insurances number of preset number of days,
In, support refers to that number of days of swiping the card on the same day, minimum support refer to preset number of days.For example, minimum support is 3, medical insurance A, B, C,
Three is greater than 3 in the number of days that default monitoring is swiped the card in month on the same day, then { A, B, C } is a Frequent Item Sets.
Optionally, the medical insurance number concentrated according to each frequent item that frequent item set algorithm determines is obtained, by its Chinese medicine
The Frequent Item Sets that guarantor's number is less than preset number screen out, and not as the object of subsequent operation, retain medical insurance number and are greater than
Equal to the Frequent Item Sets of preset number.For example, preset number is 8, then because of { A, B, C } Frequent Item Sets in a upper example
Only there are three medical insurances number, it should screen out { A, B, C }, not as the object of subsequent operation.If because of the doctor of Frequent Item Sets
Guarantor's number is less, then abnormal possibility is smaller.
Step S124 extracts the medical insurance number for belonging to the Frequent Item Sets in the first kind medical insurance number as doctor to be detected
Guarantor number.
Belong to the medical insurance number of Frequent Item Sets, because related belonging to same Frequent Item Sets on the time of appearance to other
Property it is larger, so, will belong to the Frequent Item Sets medical insurance number be used as medical insurance number to be detected.
Optionally, there may be multiple Frequent Item Sets in first kind medical insurance number, carry out subsequent calculation of relationship degree step
Before rapid, the multiple Frequent Item Sets duplicate removal can be merged into a Frequent Item Sets, the medical insurance number that frequent item is concentrated
Input parameter as calculation of relationship degree.
The medical insurance number for belonging to Frequent Item Sets in first kind medical insurance number is extracted as medical insurance number to be detected, will not belong to frequency
The medical insurance number of numerous Item Sets screens out away, not as medical insurance number to be detected.
The medical insurance number that the present embodiment is greater than preset times by extracting number of swiping the card in first brushing card data, by the doctor
Guarantor number is used as first kind medical insurance number；The first kind medical insurance number is obtained at default month adjacent with the default monitoring month
It is right to extract the first kind medical insurance number from first brushing card data and second brushing card data for second brushing card data
That answers swipes the card the date；Based on the first kind medical insurance number corresponding swipe the card date and preset frequent item set algorithm, obtain frequently
Item Sets；The medical insurance number for belonging to the Frequent Item Sets in the first kind medical insurance number is extracted as medical insurance number to be detected, can be sieved
Except more normal medical insurances number, the data volume of subsequent abnormality detection is reduced, the specific aim of subsequent abnormality detection is improved, improves abnormal number
According to the accuracy of detection.
Further, for ease of understanding in the present invention by preset frequent item set algorithm, Frequent Item Sets is obtained, are now tied
The embodiment of the present invention is closed to briefly introduce to FP-Growth algorithm.
If project set I=a1, a2 ... am }, database D B=T1, T2 ... Tn } (T is known as affairs, includes for one group
The Item Sets of some projects).For given Mode A (A is one group of Item Sets comprising some projects), support is equal to DB
In include A transactions, if the support of A be greater than preset minimum support, A is referred to as frequent mode, also referred to as frequent episode
Mesh collection.In the present embodiment, medical insurance number is project, and the medical insurance number set occurred in each period is one group of affairs, is owned
Period is combined i.e. one transaction database of composition.
It is described by preset frequent item set algorithm, the step of obtaining Frequent Item Sets includes:
(1) medical insurance number for corresponding to the same date of swiping the card in the first kind medical insurance number is obtained, and generates and respectively swipes the card the date pair
The medical insurance number combination answered；That is: for the brushing card data of first kind medical insurance number and/or first kind medical insurance number, according to daily grouping, system
The medical insurance number occurred daily is counted, medical insurance number here is project.
For ease of understanding, an example is provided:
| Date | Medical insurance number |
| 2014-1-1 | R、Z、H、J、P |
| 2014-1-2 | Z、Y、X、W、V、U、T、S |
| 2014-1-3 | Z |
| 2014-1-4 | R、X、N、O、S |
| 2014-1-5 | Y、R、X、Z、Q、T、P |
| 2014-1-6 | Y、Z、X、E、Q、S、T、M |
(2) minimum support is obtained, frequent doctor is filtered out from all medical insurance number combinations according to the minimum support
Guarantor number, and generate date corresponding frequent medical insurance list of respectively swiping the card；
Minimum support is preset support threshold, and the support in the present embodiment refers to the number of days that medical insurance number occurs, right
Database is scanned, if minimum support is 3 (minimum when excavating to actual database here only as example
Support can be customized by the user setting, can also call directly preset support threshold, and support threshold can be 50,
At least to occur in 50 days), then following frequently medical insurance table is obtained, the support of a certain medical insurance number is that the medical insurance number goes out
Existing number of days:
| Medical insurance number | Z | X | R | Y | T | S |
| Support | 5 | 4 | 3 | 3 | 3 | 3 |
Frequent medical insurance number is extracted to all dates, and sorts from large to small by frequent item support that (support is equal
According to the sequence of medical insurance carry out sequence) obtain the frequent medical insurance list on each date:
Frequent pattern tree (fp tree) is generated based on the frequent medical insurance list, all frequent moulds are excavated based on the frequent pattern tree (fp tree)
Formula；
Root node T is created, and enables it for Null；Insert_tree ({ Z, R }, T) is executed to 2014-1-1, since T does not have
Child node creates a new node Z, if its original frequency is counted as 1, and is linked on father node T.It continues to execute
Insert_tree ({ R }, Z) creates a new node R since Z does not have child node, if its frequency counting is 1, and links to
On father node Z.2014-1-1 is finished.Insert_tree ({ Z, X, Y, S, T }, T) is executed to 2014-1-2, since T has son
Node Z then enables the frequency counting of Z add 1.Insert_tree ({ X, Y, S, T }, Z) is continued to execute, since Z does not have child node, wound
A new nodes X is built, if its original frequency is counted as 1, and is linked on father node Z.And so on 2014-1-2 is executed
It finishes.Following frequent pattern tree (fp tree) is generated after having executed by above-mentioned steps to all dates:
In order to achieve the purpose that efficient quick, Frequent Pattern Mining is generally carried out using frequent pattern-growth algorithm.Institute
It calls frequent mode to increase, refers to the frequent medical insurance number collection excavated first comprising 1 medical insurance number, later along on frequent pattern tree (fp tree)
The conditional pattern base and condition frequent pattern tree (fp tree) of above-mentioned frequent medical insurance number collection are established in path, then to newly-established condition frequent mode
Tree continues to excavate the fuzzy frequent itemsets comprising 1 medical insurance number, and so on, until the entire path on traversal frequent pattern tree (fp tree).
In this way, excacation can gradually rise to and collect comprising multiple medical insurances number since the frequent medical insurance number collection insured comprising 1
Frequent medical insurance number collection, to excavate all frequent modes.Specific excavation step is carried out below with reference to example before
Explanation.
(1) since the bottom end of frequent pattern tree (fp tree) head table, in this example i.e. since medical insurance T, according to node chain in frequency
Corresponding node (T:2) and (T:1) are found in numerous scheme-tree.
(2) for medical insurance T, it is clear that (T:3) is a frequent mode, and the frequent mode more closed with T-phase needs logical
Two prefix paths (Z:5, X:3, Y:3, S:2) of excavation T upwards and (Z:5, X:3, Y:3, R:1) are crossed to obtain.
(3) frequency counting every in prefix path is adjusted to consistent with the frequency counting of T (because this represent other
The number that each medical insurance number occurs simultaneously with T), prefix path adjusted, constitute T conditional pattern base (ZXYS:2),
(ZXYR:1)}.According to the conditional pattern base of T, can be constructed according to the method for 2.3.2 T condition frequent pattern tree (fp tree) (Z:3, X:
3, Y:3) } | T.
(4) the condition frequent pattern tree (fp tree) of T is continued to excavate, each node in tree is combined to obtain frequently respectively with T
Mode (YT:3), (XT:3), (ZT:3) are obtained respective conditional pattern base { (ZX:3) }, { (Z:3) }, φ according to preceding method,
And corresponding condition frequent pattern tree (fp tree) { (Z:3, X:3) } | YT, { (Z:3) } | XT, φ.
(5) to YT, the condition frequent pattern tree (fp tree) of XT continues to excavate, by taking YT as an example, obtain first frequent mode (XYT:
3), (ZYT:3), conditional pattern base { (Z:3) }, φ and condition frequent pattern tree (fp tree) { (Z:3) } | XYT, φ.Similarly, the digging of XT
Pick result is frequent mode (ZXT:3), and conditional pattern base and condition frequent pattern tree (fp tree) are sky.
(6) the condition frequent pattern tree (fp tree) of XYT is continued to excavate, obtains frequent mode (ZXYT:3), conditional pattern base
It is sky with condition frequent pattern tree (fp tree).
(7) so far, by gradually increasing the number of medical insurance number since the frequent mode (T:3) comprising 1 medical insurance number,
Progressive excavate arrives the frequent mode (ZXYT:3) comprising 4 medical insurances number, has obtained all frequent modes closed with T-phase: (T:3),
(YT:3), (XT:3), (ZT:3), (XYT:3), (ZYT:3), (ZXYT:3).Whole process is illustrated in fig. 4 shown below.
(8) similarly, are carried out by the Frequent Pattern Mining same with T-phase, obtains all frequent modes by S, Y, X, R, Z respectively.This
In repeat no more, only list the conditional pattern base and condition frequent pattern tree (fp tree) of each medical insurance number:
After excavating whole frequent modes, a step screening is also carried out again, it will be comprising medical insurance number in certain amount
Frequent mode below screens out.In the present embodiment, medical insurance number 8 or more are only remained in the result (Frequent Set is most
Small pattern length of swiping the card on the same day) frequent mode.
Further, based on the above embodiment, in the detection method fourth embodiment that medical insurance of the present invention is swiped the card extremely, institute
It states in step S20 and the degree of association between the medical insurance number to be detected of any predetermined number is calculated based on preset algorithm, wherein institute
Predetermined number, which is stated, more than or equal to two includes:
Step S21, obtains total number of days of preset time period, and obtains the medical insurance number to be detected in the preset time period
The interior daily amount of money of swiping the card；
Preset time period refers to statistical time range, can also can be customized by users setting by systemic presupposition, preset time period may
It is one month, it is also possible to the predetermined number month adjacent with default monitoring month.
Because obtaining the daily amount of money of swiping the card of each medical insurance number is to obtain each medical insurance number to carry out subsequent calculation of relationship degree
After the daily amount of money of swiping the card, amount of money substitution subsequent association degree formula of actually swiping the card can be directly based upon and calculated, it can also be in reality
When the amount of money is swiped the card greater than 0 in border, the amount of money of actually swiping the card is set 1, when the amount of money of actually swiping the card is equal to 0, the amount of money of actually swiping the card is set 0,
Value after 0/1 being set again substitutes into degree of association formula and calculates, and reduces data operation quantity, improving operational speed.
For example, if the degree of association in the statistics part of in August, 2018-September part between medical insurance number to be detected, then obtain 2018
The total number of days of August part-September part, and obtain medical insurance number to be detected the swipe the card amount of money daily in the part of in August, 2018-September part.
Step S22, obtain degree of association formula, based on the degree of association formula, preset time period total number of days and it is described to
Detect the medical insurance number daily amount of money of swiping the card within a preset period of time, calculate any predetermined number within a preset period of time it is described to
Detect the degree of association between medical insurance number, wherein if the predetermined number is two, the degree of association formula are as follows:
Wherein,
RijFor the degree of association between i-th of medical insurance number to be detected and j-th of medical insurance number to be detected, n is preset time period
Total number of days,For i-th of medical insurance number kth day the amount of money of swiping the card,For j-th of medical insurance number kth day the amount of money of swiping the card.
That is, when i-th of medical insurance number and j-th of medical insurance number on the same day it is interior all carried out swiping the card purchase medicine or all do not brushed
Card purchase medicine, i.e.,orWhen, Ck=1, otherwise Ck=0, RijRefer to two medical insurances number on the same day all
Swipe the card purchase medicine or all do not carry out swiping the card purchase medicine number of days account for preset time period total number of days ratio.
Further, there are a kind of situation, i-th of medical insurance number is not all brushed with j-th of medical insurance number interior on the same day
The number of days of card purchase medicine accounts for relatively high, then i-th of medical insurance number and j-th of medical insurance number number that may all swipe the card are less, rather than have very
Big association.In the present embodiment, before calculating the degree of association between preset time period medical insurance number to be detected, preset time period is screened out
Purchase medicine total amount be less than or equal to certain numerical value (default value: 100 yuan) medical insurance number, to avoid because equally existing a large amount of blank numbers
According to and lead to highly relevant situation, avoid erroneous detection.
The present embodiment obtains the medical insurance number to be detected when described default by obtaining total number of days of preset time period
Between the amount of money of swiping the card daily in section；Degree of association formula is obtained, based on the degree of association formula, total number of days of preset time period and institute
The medical insurance number to be detected daily amount of money of swiping the card within a preset period of time is stated, the institute of any predetermined number within a preset period of time is calculated
State the degree of association between medical insurance number to be detected.The calculating to the degree of association can be achieved, so that the subsequent degree of association that is based on is to doctor to be detected
Guarantor number is grouped.
Further, based on the above embodiment, in the 5th embodiment of detection method that medical insurance of the present invention is swiped the card extremely, institute
Stating step S20 includes:
Step S23, obtain the medical insurance number to be detected at default month adjacent with default monitoring month second are swiped the card
Data regard the default monitoring month and default month adjacent with the default monitoring month as month to be detected；
For the accuracy for promoting abnormality detection, wrong report to accidental character condition is reduced, in the present embodiment, not only obtain default
The brushing card data in month is monitored, the default default month brushing card data adjacent with default monitoring month is also obtained, that is, passes through increasing
Big detection sample data, promotes the accuracy of Outlier mining.
Default month adjacent with default monitoring month is arranged by system default, can also be customized by the user setting, example
Such as, with default monitoring month adjacent 3 months, presetting monitoring month is October, preset monitoring month and with default monitoring month
Adjacent default month is the 7-8-9-10-12-11-1 month.
For ease of description, default monitoring month and default month adjacent with default monitoring month are referred to as moon sight to be checked
Part, medical insurance number to be detected is claimed in default monitoring month and default month all brushing card datas adjacent with default monitoring month
As the second brushing card data.
Step S24 is calculated any default according to first brushing card data and second brushing card data and preset algorithm
The degree of association between the medical insurance number to be detected of number, wherein the predetermined number is greater than or equal to two.
When being based on previously described calculation of relationship degree formula calculating correlation, will calculate the data augmentation that is based on to
Default monitoring month adjacent default month the second brushing card data.For example, as in fourth embodiment, it is assumed that preset time period is
It default monitoring month and default month adjacent with default monitoring month, then needs from the first brushing card data and the second brushing card data
The middle calculating for obtaining data and being used for the degree of association.
The present embodiment is by obtaining the medical insurance number to be detected in preset a month second adjacent with default monitoring month
Brushing card data regard the default monitoring month and default month adjacent with the default monitoring month as moon sight to be checked
Part, according to first brushing card data and second brushing card data and preset algorithm calculate any predetermined number it is described to
The degree of association between medical insurance number is detected, the accuracy of abnormality detection can be promoted, reduces the wrong report to accidental character condition.
Further, to further clarify grouping step, such as Fig. 5, in one embodiment, the step S30 is refined are as follows:
Step S31 is based on the degree of association, is that center medical insurance number establishes corresponding the respectively with each medical insurance number to be detected
One medical insurance group includes all doctors to be detected for being greater than preset threshold with the center medical insurance degree of association in the first medical insurance group
Guarantor number；
The degree of association in the present embodiment, be based in month to be detected the first brushing card data and the second brushing card data calculate
, therefore, the preset time period in calculation of relationship degree formula refers to all months to be detected.
One group is established to each medical insurance number to be detected, i.e., the first medical insurance group in the present embodiment, the first medical insurance group
It, can comprising all preset thresholds for being greater than preset threshold with the medical insurance number to be detected and all medical insurance degrees of association to be detected
Selection of land deletes the group if the medical insurance number of the group is less than preset value (such as 3).
Step S32, more all first medical insurance groups, if in any two the first medical insurance group including identical medical insurance
Number, then the first new medical insurance group is generated after merging this two the first medical insurance groups, repeats described more all first
The step of medical insurance group, until without identical medical insurance number between all first medical insurance groups；
Compare all the first obtained medical insurance groups, if including identical medical insurance number in any two groups, by two combinations
And and delete duplicate medical insurance number, repeat aforesaid operations until without identical medical insurance number between all medical insurance group.
For example, the first obtained medical insurance group has: { 1,2 } and { 2,3 } is then closed in { 1,2 }, { 2,3 }, { 3,4 }, { 2,8 }
And obtain { 1,2,3 }, then { 1,2,3 } is the first new medical insurance group, continue for { 1,2,3 } and { 3,4 } to be compared, merge,
{ 1,2,3,4 } is obtained, { 1,2,3,4 } is the first new medical insurance group, continues for { 1,2,3,4 } and { 2,8 } to be compared, merge
Obtain { 1,2,3,4,8 }.
Step S33, will be from each other without the first medical insurance group of identical medical insurance number as target medical insurance group.
For ease of understanding, an example is now provided:
There is medical insurance 1-10, the first medical insurance group established based on the degree of association:
{ 1,2 }, { 2,3 }, { 3,4 }, { 5,7 }, { 5,10 }, { 2,8 }
Resulting first medical insurance group is subjected to above-mentioned comparison, union operation, is obtained from each other without identical medical insurance
Number the first medical insurance group:
A:{ 1,2,3,4,8 } B:{ 5,7,10 }
The present embodiment is that correspondence is established in center medical insurance number respectively with each medical insurance number to be detected by being based on the degree of association
The first medical insurance group, it is to be checked greater than preset threshold with the center medical insurance degree of association comprising all in the first medical insurance group
Survey medical insurance number；Compare all first medical insurance groups, it, should if in any two the first medical insurance group including identical medical insurance number
Two the first medical insurance groups generate the first new medical insurance group after merging, and repeat more all first medical insurance groups
Step, until without identical medical insurance number between all first medical insurance groups；It will be from each other without the of identical medical insurance number
One medical insurance group can complete the grouping to medical insurance number to be detected, the target doctor of acquisition as target medical insurance group according to the degree of association
It is greater than the medical insurance number to be detected of certain value in guarantor's group for the degree of association, that is, there is abnormal medical insurance number to be detected, finally realize different
Often detection.
Further, based on the above embodiment, in the detection method sixth embodiment that medical insurance of the present invention is swiped the card extremely, institute
Stating step S30 includes:
Step S34 is based on the degree of association, establishes corresponding second medical insurance group of each month to be detected respectively；
Corresponding second medical insurance group is established to each month to be detected respectively, now optional one is worked as from all months to be detected
Preceding statistics month explains as example, and relevant explanation is suitable for each month to be detected.
The second medical insurance group in the present embodiment refers to that the brushing card data based on current statistic month calculates the degree of association obtained
It is grouped the medical insurance group of acquisition, is specifically as follows:
It is that corresponding second medical insurance group, second medical insurance are established in center medical insurance number respectively with each medical insurance number to be detected
Include all medical insurances number to be detected for being greater than preset threshold with the center medical insurance degree of association in number group, wherein the degree of association here
Refer to the degree of association of medical insurance number to be detected under current statistic month.For example, being default monitoring month in current statistic month, preset a
Number is two, degree of association formula are as follows:
Wherein,When, wherein when n is default
Between section total number of days, preset time period here refers to default monitoring month.
It is directed to calculate in each month to be detected respectively based on above-mentioned steps and obtains medical insurance number to be detected in each month to be detected
Between the degree of association.
Step S35, more all second medical insurance groups, if in any two the second medical insurance group including identical medical insurance
Number, then the second new medical insurance group is generated after merging this two the second medical insurance groups, repeats described more all second
The step of medical insurance group, until without identical medical insurance number between all second medical insurance groups；
After obtaining all month corresponding second medical insurance groups to be detected, step is carried out to the second medical insurance group
Comparison described in S35 and union operation, more all the second obtained medical insurance groups, if including identical doctor in any two groups
Guarantor number, then by two groups of merging, and delete duplicate medical insurance number, and repeat aforesaid operations does not have up between all medical insurance groups
Identical medical insurance number.
For example, the second obtained medical insurance group has: { 1,2 } and { 2,3 } is then closed in { 1,2 }, { 2,3 }, { 3,4 }, { 2,8 }
And obtain { 1,2,3 }, then { 1,2,3 } is the second new medical insurance group, continue for { 1,2,3 } and { 3,4 } to be compared, merge,
{ 1,2,3,4 } is obtained, { 1,2,3,4 } is the second new medical insurance group, continues for { 1,2,3,4 } and { 2,8 } to be compared, merge
Obtain { 1,2,3,4,8 }.
Step S36, will be from each other without the second medical insurance group of identical medical insurance number as target medical insurance group.
Between each other without the second medical insurance group of identical medical insurance number, it may be possible to belong to different violations and swipes the card clique, it can
To be done differentiable abnormal mark, to be defeated in detail under line, all second medical insurance groups can also be merged into
One medical insurance number carries out abnormal mark.
The present embodiment establishes corresponding second medical insurance group of each month to be detected by being based on the degree of association respectively；Than
More all second medical insurance groups cure this two second if in any two the second medical insurance group including identical medical insurance number
The step of guarantor's group generates the second new medical insurance group, repeats more all second medical insurance groups after merging, until
Without identical medical insurance number between all second medical insurance groups；It will be from each other without the second medical insurance group of identical medical insurance number
As target medical insurance group, the grouping to medical insurance number to be detected can be completed according to the degree of association, is in the target medical insurance group of acquisition
The degree of association is greater than the medical insurance number to be detected of certain value, that is, has abnormal medical insurance number to be detected, finally realize abnormality detection.
In addition, that the present invention also provides a kind of corresponding medical insurances of each step of the detection method swiped the card extremely with above-mentioned medical insurance is abnormal
The detection device swiped the card.
Referring to Fig. 6, Fig. 6 is the functional block diagram for the detection device first embodiment that medical insurance of the present invention is swiped the card extremely.
In the present embodiment, the detection device that medical insurance of the present invention is swiped the card extremely includes:
Module 10 is obtained, for obtaining first brushing card data in default monitoring month, and according to default extracting rule from institute
It states and extracts medical insurance number to be detected in the first brushing card data；
Computing module 20, for calculating the described of any predetermined number according to first brushing card data and preset algorithm
The degree of association between medical insurance number to be detected, wherein the predetermined number is greater than or equal to two；
Grouping module 30, the medical insurance number to be detected for the degree of association to be greater than preset threshold are divided into same grouping,
Target medical insurance group after being grouped；
Abnormal marking module 40, the medical insurance number for that will belong to target medical insurance group carry out abnormal marking.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
Number statistical module counts first brushing card data for obtaining first brushing card data in default monitoring month
In each medical insurance number it is described it is default monitoring month number of swiping the card；
Extraction module, for extract swipe the card in first brushing card data number greater than preset times medical insurance number as to
Detect medical insurance number.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
The extraction module, the medical insurance number for being greater than preset times for extracting number of swiping the card in first brushing card data,
It regard the medical insurance number as first kind medical insurance number；
First data acquisition module, for obtain the first kind medical insurance number with default monitoring month adjacent pre-
If a month the second brushing card data, from first brushing card data and second brushing card data, the first kind is extracted
Medical insurance number is corresponding to swipe the card the date；
Module is frequently excavated, for being based on corresponding date and the preset frequent item set of swiping the card of the first kind medical insurance number
Algorithm obtains Frequent Item Sets；
The extraction module is also used to extract the medical insurance number work for belonging to the Frequent Item Sets in the first kind medical insurance number
For medical insurance number to be detected.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
Second data acquisition module for obtaining total number of days of preset time period, and obtains the medical insurance number to be detected and exists
The daily amount of money of swiping the card in the preset time period；
The computing module 20, is also used to obtain degree of association formula, based on the degree of association formula, preset time period it is total
Number of days and the medical insurance number to be detected daily amount of money of swiping the card within a preset period of time, calculate any default within a preset period of time
The degree of association between the medical insurance number to be detected of number, wherein if the predetermined number is two, the degree of association formula
Are as follows:
Wherein,
RijFor the degree of association between i-th of medical insurance number to be detected and j-th of medical insurance number to be detected, n is preset time period
Total number of days,For i-th of medical insurance number kth day the amount of money of swiping the card,For j-th of medical insurance number kth day the amount of money of swiping the card.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
Third data acquisition module, for obtaining the medical insurance number to be detected at default adjacent with default monitoring month
Month the second brushing card data, will the default monitoring month and default month adjacent with the default monitoring month as to
Detect month；
The computing module 20 is also used to according to first brushing card data and second brushing card data, and pre- imputation
Method calculates the degree of association between the medical insurance number to be detected of any predetermined number, wherein the predetermined number is greater than or equal to
Two.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
First grouping module is that center medical insurance number is built respectively with each medical insurance number to be detected for being based on the degree of association
Corresponding first medical insurance group is found, includes that all and center medical insurance degree of association is greater than preset threshold in the first medical insurance group
Medical insurance number to be detected；
First comparison module is used for more all first medical insurance groups, if in any two the first medical insurance group including phase
Same medical insurance number then will generate the first new medical insurance group after this two the first medical insurance groups merging, and repeat the comparison
The step of all first medical insurance groups, until without identical medical insurance number between all first medical insurance groups；
First abnormal determining module, for that will be cured from each other without the first medical insurance group of identical medical insurance number as target
Guarantor's group.
Optionally, the detection device that the medical insurance is swiped the card extremely further include:
Second packet module establishes the corresponding medical insurance No. second of each month to be detected for being based on the degree of association respectively
Group；
Second comparison module is used for more all second medical insurance groups, if in any two the second medical insurance group including phase
Same medical insurance number then will generate the second new medical insurance group after this two the second medical insurance groups merging, and repeat the comparison
The step of all second medical insurance groups, until without identical medical insurance number between all second medical insurance groups；
Second abnormal determining module, for that will be cured from each other without the second medical insurance group of identical medical insurance number as target
Guarantor's group.
The present invention also proposes a kind of storage medium, is stored thereon with computer program.The storage medium can be Fig. 1's
The memory 20 in terminal is detected, is also possible to such as ROM (Read-Only Memory, read-only memory)/RAM (Random
Access Memory, random access memory), magnetic disk, at least one of CD, the storage medium includes some instructions
With so that a terminal device with processor (can be mobile phone, computer, server, the network equipment or the present invention are real
Apply the detection terminal etc. in example) execute method described in each embodiment of the present invention.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the server-side that include a series of elements not only include those elements,
It but also including other elements that are not explicitly listed, or further include for this process, method, article or server-side institute
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wrapping
Include in process, method, article or the server-side of the element that there is also other identical elements.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of detection method that medical insurance is swiped the card extremely, which is characterized in that the detection method that the medical insurance is swiped the card extremely include with
Lower step:
First brushing card data in default monitoring month is obtained, and is extracted from first brushing card data according to default extracting rule
Medical insurance number to be detected；
The pass between the medical insurance number to be detected of any predetermined number is calculated according to first brushing card data and preset algorithm
Connection degree, wherein the predetermined number is greater than or equal to two；
The medical insurance number to be detected that the degree of association is greater than preset threshold is divided into same grouping, the target medical insurance after being grouped
Number group；
The medical insurance number for belonging to target medical insurance group is subjected to abnormal marking.
2. the detection method that medical insurance as described in claim 1 is swiped the card extremely, which is characterized in that described to obtain default monitoring month
The first brushing card data, and the step of medical insurance to be detected is extracted from first brushing card data according to default extracting rule packet
It includes:
The first brushing card data for obtaining default monitoring month counts each medical insurance number in first brushing card data and presets described
Monitor the number of swiping the card in month；
It extracts medical insurance number of the number greater than preset times of swiping the card in first brushing card data and is used as medical insurance number to be detected.
3. the detection method that medical insurance as claimed in claim 2 is swiped the card extremely, which is characterized in that the extraction described first is swiped the card
Number of swiping the card in data is greater than the step of medical insurance number of preset times is as medical insurance to be detected and includes:
The medical insurance number that number of swiping the card in first brushing card data is greater than preset times is extracted, which is cured as the first kind
Guarantor number；
The first kind medical insurance number is obtained in default month second brushing card data adjacent with the default monitoring month, from institute
It states in the first brushing card data and second brushing card data, extracts that the first kind medical insurance number is corresponding to swipe the card the date；
Based on the first kind medical insurance number corresponding swipe the card date and preset frequent item set algorithm, Frequent Item Sets are obtained；
The medical insurance number for belonging to the Frequent Item Sets in the first kind medical insurance number is extracted as medical insurance number to be detected.
4. the detection method that medical insurance as described in claim 1 is swiped the card extremely, which is characterized in that described to be calculated based on preset algorithm
The degree of association between the medical insurance number to be detected of any predetermined number, wherein the predetermined number is greater than or equal to two
Step includes:
Total number of days of preset time period is obtained, and obtains that the medical insurance number to be detected is daily in the preset time period to swipe the card
The amount of money；
Degree of association formula is obtained, is existed based on the degree of association formula, total number of days of preset time period and the medical insurance number to be detected
The daily amount of money of swiping the card in preset time period, calculate any predetermined number within a preset period of time the medical insurance number to be detected it
Between the degree of association, wherein if the predetermined number be two, the degree of association formula are as follows:
Wherein,
RijFor the degree of association between i-th of medical insurance number to be detected and j-th of medical insurance number to be detected, n is total day of preset time period
Number,For i-th of medical insurance number kth day the amount of money of swiping the card,For j-th of medical insurance number kth day the amount of money of swiping the card.
5. the detection method that medical insurance according to any one of claims 1 to 4 is swiped the card extremely, which is characterized in that the basis
First brushing card data and preset algorithm calculate the degree of association between the medical insurance number to be detected of any predetermined number,
In, step of the predetermined number more than or equal to two includes:
The medical insurance number to be detected is obtained in default month second brushing card data adjacent with default monitoring month, it will be described pre-
If monitoring month and default month adjacent with the default monitoring month being used as month to be detected；
According to first brushing card data and second brushing card data and preset algorithm calculate any predetermined number it is described to
Detect the degree of association between medical insurance number, wherein the predetermined number is greater than or equal to two.
6. the detection method that medical insurance as claimed in claim 5 is swiped the card extremely, which is characterized in that described to be greater than the degree of association
The step of medical insurance number to be detected of preset threshold is divided into same grouping, target medical insurance group after being grouped include:
It is that corresponding first medical insurance group is established in center medical insurance number respectively with each medical insurance number to be detected based on the degree of association,
Include all medical insurances number to be detected for being greater than preset threshold with the center medical insurance degree of association in the first medical insurance group；
Compare all first medical insurance groups, if including identical medical insurance number in any two the first medical insurance group, by this two
First medical insurance group generates the first new medical insurance group after merging, and repeats the step of more all first medical insurance groups
Suddenly, until without identical medical insurance number between all first medical insurance groups；
It will be from each other without the first medical insurance group of identical medical insurance number as target medical insurance group.
7. the detection method that medical insurance as claimed in claim 5 is swiped the card extremely, which is characterized in that described to be greater than the degree of association
The step of medical insurance number to be detected of preset threshold is divided into same grouping, target medical insurance group after being grouped include:
Based on the degree of association, corresponding second medical insurance group of each month to be detected is established respectively；
Compare all second medical insurance groups, if including identical medical insurance number in any two the second medical insurance group, by this two
Second medical insurance group generates the second new medical insurance group after merging, and repeats the step of more all second medical insurance groups
Suddenly, until without identical medical insurance number between all second medical insurance groups；
It will be from each other without the second medical insurance group of identical medical insurance number as target medical insurance group.
8. a kind of detection device that medical insurance is swiped the card extremely, which is characterized in that the detection device that the medical insurance is swiped the card extremely includes:
Module is obtained, for obtaining first brushing card data in default monitoring month, and according to default extracting rule from described first
Medical insurance number to be detected is extracted in brushing card data；
Computing module, for calculating the described to be detected of any predetermined number according to first brushing card data and preset algorithm
The degree of association between medical insurance number, wherein the predetermined number is greater than or equal to two；
Grouping module, the medical insurance number to be detected for the degree of association to be greater than preset threshold are divided into same grouping, are divided
Target medical insurance group after group；
Abnormal marking module, the medical insurance number for that will belong to target medical insurance group carry out abnormal marking.
9. a kind of detection terminal, which is characterized in that the detection terminal includes processor, memory and is stored in described deposit
On reservoir and the detection program that can be swiped the card extremely by the medical insurance that the processor executes, wherein the detection that the medical insurance is swiped the card extremely
When program is executed by the processor, the detection method that the medical insurance as described in any one of claims 1 to 7 is swiped the card extremely is realized
The step of.
10. a kind of storage medium, which is characterized in that the detection program that medical insurance is swiped the card extremely is stored on the storage medium,
Described in the detection program swiped the card extremely of medical insurance when being executed by processor, realize the doctor as described in any one of claims 1 to 7
The step of protecting the detection method swiped the card extremely.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811272390.2A CN109658109A (en) | 2018-10-29 | 2018-10-29 | Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811272390.2A CN109658109A (en) | 2018-10-29 | 2018-10-29 | Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109658109A true CN109658109A (en) | 2019-04-19 |
Family
ID=66110531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811272390.2A Pending CN109658109A (en) | 2018-10-29 | 2018-10-29 | Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658109A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458508A (en) * | 2019-07-05 | 2019-11-15 | 中国平安财产保险股份有限公司 | Processing method, processing unit and the Related product of document information |
| CN111210356A (en) * | 2020-01-14 | 2020-05-29 | 平安医疗健康管理股份有限公司 | Medical insurance data analysis method and device, computer equipment and storage medium |
| CN111274231A (en) * | 2020-01-14 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Abnormal medical insurance data checking method and device, computer equipment and storage medium |
| CN112001805A (en) * | 2020-09-07 | 2020-11-27 | 平安科技（深圳）有限公司 | Medical insurance data processing method, device, equipment and medium based on fixed time window |
| CN112884593A (en) * | 2021-02-01 | 2021-06-01 | 浙江大学山东工业技术研究院 | Medical insurance fraud and insurance behavior detection method and early warning device based on graph cluster analysis |
| CN113706181A (en) * | 2021-10-30 | 2021-11-26 | 杭银消费金融股份有限公司 | Service processing detection method and system based on user behavior characteristics |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104537764A (en) * | 2014-12-31 | 2015-04-22 | 浙江大学 | Method and system for detecting abnormal usage of medical insurance cards |
| CN106408481A (en) * | 2015-07-28 | 2017-02-15 | 平安科技（深圳）有限公司 | Abnormal card consumption personnel information automatic extraction system and method |
| CN106874658A (en) * | 2017-01-18 | 2017-06-20 | 天津艾登科技有限公司 | A kind of medical insurance fraud recognition methods based on Principal Component Analysis Algorithm |
| CN108055281A (en) * | 2017-12-27 | 2018-05-18 | 百度在线网络技术（北京）有限公司 | Account method for detecting abnormality, device, server and storage medium |
| CN108460693A (en) * | 2018-03-29 | 2018-08-28 | 平安健康保险股份有限公司 | Insure character surveillance method and device, storage medium and the terminal of chain hospital |
-
2018
- 2018-10-29 CN CN201811272390.2A patent/CN109658109A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134092A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Medical insurance reimbursement behavior monitoring system and method |
| CN104537764A (en) * | 2014-12-31 | 2015-04-22 | 浙江大学 | Method and system for detecting abnormal usage of medical insurance cards |
| CN106408481A (en) * | 2015-07-28 | 2017-02-15 | 平安科技（深圳）有限公司 | Abnormal card consumption personnel information automatic extraction system and method |
| CN106874658A (en) * | 2017-01-18 | 2017-06-20 | 天津艾登科技有限公司 | A kind of medical insurance fraud recognition methods based on Principal Component Analysis Algorithm |
| CN108055281A (en) * | 2017-12-27 | 2018-05-18 | 百度在线网络技术（北京）有限公司 | Account method for detecting abnormality, device, server and storage medium |
| CN108460693A (en) * | 2018-03-29 | 2018-08-28 | 平安健康保险股份有限公司 | Insure character surveillance method and device, storage medium and the terminal of chain hospital |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458508A (en) * | 2019-07-05 | 2019-11-15 | 中国平安财产保险股份有限公司 | Processing method, processing unit and the Related product of document information |
| CN111210356A (en) * | 2020-01-14 | 2020-05-29 | 平安医疗健康管理股份有限公司 | Medical insurance data analysis method and device, computer equipment and storage medium |
| CN111274231A (en) * | 2020-01-14 | 2020-06-12 | 平安医疗健康管理股份有限公司 | Abnormal medical insurance data checking method and device, computer equipment and storage medium |
| CN111274231B (en) * | 2020-01-14 | 2023-02-07 | 平安医疗健康管理股份有限公司 | Abnormal medical insurance data checking method and device, computer equipment and storage medium |
| CN111210356B (en) * | 2020-01-14 | 2023-03-21 | 平安医疗健康管理股份有限公司 | Medical insurance data analysis method and device, computer equipment and storage medium |
| CN112001805A (en) * | 2020-09-07 | 2020-11-27 | 平安科技（深圳）有限公司 | Medical insurance data processing method, device, equipment and medium based on fixed time window |
| CN112001805B (en) * | 2020-09-07 | 2023-08-22 | 平安科技（深圳）有限公司 | Medical insurance data processing method, device, equipment and medium based on fixed time window |
| CN112884593A (en) * | 2021-02-01 | 2021-06-01 | 浙江大学山东工业技术研究院 | Medical insurance fraud and insurance behavior detection method and early warning device based on graph cluster analysis |
| CN113706181A (en) * | 2021-10-30 | 2021-11-26 | 杭银消费金融股份有限公司 | Service processing detection method and system based on user behavior characteristics |
| CN113706181B (en) * | 2021-10-30 | 2022-02-08 | 杭银消费金融股份有限公司 | Service processing detection method and system based on user behavior characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658109A (en) | Detection method, device, terminal and the storage medium that medical insurance is swiped the card extremely | |
| CN109636623A (en) | Medical data method for detecting abnormality, device, equipment and storage medium | |
| CN107704834A (en) | Householder method, device and storage medium are examined in micro- expression face | |
| CN109635007B (en) | Behavior evaluation method and device and related equipment | |
| CN107886366A (en) | Generation method, sex fill method, terminal and the storage medium of Gender Classification model | |
| CN110009417A (en) | Target customer's screening technique, device, equipment and computer readable storage medium | |
| CN109299995A (en) | A kind of virtual objects sending method, device, server and storage medium | |
| CN106408481A (en) | Abnormal card consumption personnel information automatic extraction system and method | |
| CN106651547A (en) | Data processing method and apparatus | |
| CN107993056A (en) | With reference to weekly wage and the emolument delivery system and method for monthly pay | |
| CN108776857A (en) | NPS short messages method of investigation and study, system, computer equipment and storage medium | |
| CN104731937B (en) | The processing method and processing device of user behavior data | |
| CN109670934A (en) | Personal identification method, equipment, storage medium and device based on user behavior | |
| CN108197885A (en) | The Work attendance method and device of employee | |
| CN103336800B (en) | The method of the fingerprint storage comparison that Behavior-based control is analyzed | |
| CN108009752A (en) | emolument batch delivery system and method | |
| CN107944841A (en) | Emolument computing system and method | |
| CN110245985A (en) | A kind of information processing method and device | |
| CN106227661A (en) | Data processing method and device | |
| CN106874286A (en) | A kind of method and device for screening user characteristics | |
| CN109376138A (en) | A kind of unusual combination detection method and device of multidimensional data | |
| CN110010231A (en) | A kind of data processing system and computer readable storage medium | |
| CN114065194A (en) | Method and device for detecting abnormal interface application, electronic equipment and storage medium | |
| CN108108901A (en) | Weekly wage delivery system and method | |
| CN109697224A (en) | A kind of bill message treatment method, device and 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: 20190419 |
|
| RJ01 | Rejection of invention patent application after publication |