CN110348519A - Financial product cheats recognition methods and the device of clique - Google Patents
Financial product cheats recognition methods and the device of clique Download PDFInfo
- Publication number
- CN110348519A CN110348519A CN201910630766.0A CN201910630766A CN110348519A CN 110348519 A CN110348519 A CN 110348519A CN 201910630766 A CN201910630766 A CN 201910630766A CN 110348519 A CN110348519 A CN 110348519A
- Authority
- CN
- China
- Prior art keywords
- user
- similarity
- background image
- user group
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Finance (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses recognition methods, device, electronic equipment and the computer readable storage mediums of a kind of financial product fraud clique, the method comprise the steps that obtaining the user images of multiple users；Background image is obtained from the user images；Obtain the similarity between the background image；Obtain at least one user group that the similarity between the background image is greater than predetermined threshold.
Description
Technical field
The present invention relates to techno-financial technical fields, and in particular to a kind of recognition methods of financial product fraud clique, dress
It sets, server and computer readable storage medium.
Background technique
The identification for cheating clique is always the key points and difficulties in financial air control field.Existing financial product application usually exists
Also obtain the location information of user when receiving the business application request of user, by the centrality of acquired location information come
Identification fraud clique.However, fraud clique is empty often through technological means analog position information, received by server end
False location information, so that fraud clique can not be identified by the centrality of location information.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of recognition methods of financial product fraud clique, device, server
And computer readable storage medium, doubtful fraud clique is detected in financial product user automatically.
According in a first aspect, the embodiment of the invention provides a kind of recognition methods of financial product fraud clique, comprising: obtain
Take the user images of multiple users；Background image is obtained from the user images；It obtains similar between the background image
Degree；Obtain at least one user group that the similarity between the background image is greater than predetermined threshold.
Optionally, the similarity obtained between the background image, comprising: obtain the knot between the background image
At least one of structure similarity, cosine similarity and histogram similarity.
Optionally, the similarity obtained between the background image, comprising: detected in the background image respectively
Target；The similarity between the background image is determined according to the target registration in the background image.
Optionally, at least one user group of predetermined threshold is greater than in the similarity obtained between the background image
Later, the method also includes: judge whether the user in each user group belongs to the same family；Exclusion belongs to together
The user group of one family.
Optionally, at least one user group of predetermined threshold is greater than in the similarity obtained between the background image
Later, the method also includes: obtain at least one business application information of the user in each user group；Statistics
The quantity that similarity between the business application information of each user is greater than the set value；Calculate each user's
The ratio for the number of users in quantity and the user group that similarity between the business application information is greater than the set value；It will
The ratio is labeled as doubtful fraud clique user group beyond the user group of preset range.
Optionally, the method also includes: similarity between the business application information is greater than the setting value
Increase between user node for indicating the similar side of business application information.
Optionally, the method also includes: between each user node in the user group increase for indicate back
The similar side of scape image.
According to second aspect, the embodiment of the invention provides a kind of identification devices of financial product fraud clique, comprising: figure
As acquiring unit, for obtaining the user images of multiple users；Background image unit, for obtaining back from the user images
Scape image；Similarity unit, for obtaining the similarity between the background image；User group unit, for obtaining the back
Similarity between scape image is greater than at least one user group of predetermined threshold.
According to the third aspect, the embodiment of the invention provides a kind of servers, comprising: memory and processor, it is described to deposit
Connection is communicated with each other between reservoir and the processor, computer instruction is stored in the memory, and the processor passes through
The computer instruction is executed, thereby executing method described in any one of above-mentioned first aspect.
It is described computer-readable the embodiment of the invention provides a kind of computer readable storage medium according to fourth aspect
Storage medium is stored with computer instruction, and the computer instruction is any in above-mentioned first aspect for executing the computer
Method described in.
The recognition methods of financial product according to an embodiment of the present invention fraud clique, device, server and computer-readable
Storage medium can be grouped user according to the similarity of background image in acquired user images, due to fraud group
The member of partner usually has centrality in position, is cheated in same place, and usually will not often replace place, therefore
By being grouped according to the similarity of background image to user, facilitate it is subsequent these user groups are audited, so as to from
Fraud clique is identified in mass users.
Detailed description of the invention
The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, and attached drawing is schematically without that should manage
Solution is carries out any restrictions to the present invention, in the accompanying drawings:
Fig. 1 shows the flow chart of the recognition methods of financial product fraud according to an embodiment of the present invention clique；
Have Fig. 2 shows according to an embodiment of the present invention for indicating showing for the chart database on the similar side of background image
Example；
Fig. 3 shows the flow chart of the recognition methods of financial product fraud according to another embodiment of the present invention clique；
Fig. 4 shows the chart database according to an embodiment of the present invention having for indicating the similar side of business application information
Example；
Fig. 5 shows the schematic diagram of the identification device of financial product fraud according to an embodiment of the present invention clique；
Fig. 6 shows the schematic diagram of server according to an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 shows the recognition methods of financial product fraud according to an embodiment of the present invention clique, and this method can be by taking
Business device executes, and may include steps of:
S101. the user images of multiple users are obtained.
User can initiate business application request to some financial product by the various user terminals of mobile phone etc., such as
Loan requests are initiated, corresponding application can carry out In vivo detection to user, to carry out authentication to user, it is ensured that initiate business
Application request is user, thus the available user images to mass users of server end.
S102. background image is obtained from user images.
Interested target can be detected from user images by algorithm of target detection such as Mask R-CNN,
That is portrait, so as to extract portrait from user images by pixel, to obtain background image.
S103. the similarity between background image is obtained.
Server can be compared acquired magnanimity background image using various algorithms, with obtain background image it
Between similarity.
S104. at least one user group that the similarity between background image is greater than predetermined threshold is obtained.
Server is after being compared magnanimity background image, such as the similarity of discovery background image P1, P2, P3 are greater than
User belonging to background image P1, P2, P3 can be then classified as a user group by predetermined threshold；If it was found that background image P4,
The similarity of P5, P6 are greater than predetermined threshold, then user belonging to background image P4, P5, P6 can be classified as to a user group, often
There is similar background image in the user images of a user group.Wherein, predetermined threshold can rationally be set according to the actual situation
It sets, does not do any restriction herein.
In financial air control field, it will usually store user information using chart database, chart database uses node and side
It indicates the incidence relation between user and each element, especially can intuitively show the incidence relation between each user
Clearly to show the social networks of user.In some optional embodiments of the embodiment of the present invention, by same user
Increase between each user node of group for indicating the similar side of background, so as to be established between the similar user of background
Connection, in order to analyze the user group.As shown in Figure 2, it is assumed that certain user group includes user A, user B and user C, when
It, can be in figure when server gets the similarity between user A, user B and the background image of user C greater than predetermined threshold
Increase for indicating the similar side of background image, to intuitively connect the similar user of background image, to carry out
It analyzes in next step.
Through the above steps, server can according to background image in acquired user images similarity to user into
Row grouping is cheated, and usually will not since the member of fraud clique usually has centrality in position in same place
Often replacement place, therefore by being grouped according to the similarity of background image to user, facilitate subsequent to these users
Group is audited, to identify fraud clique from mass users.
In some optional embodiments of the embodiment of the present invention, above-mentioned steps S103 may include: the knot for obtaining image
In structure similarity (SSIM, Structural Similarity Index), cosine similarity, histogram similarity etc. at least
One.
Wherein, structural similarity is a kind of image quality evaluation index referred to entirely, can respectively from brightness, contrast,
Three aspects of structure measure image similarity；Cosine similarity is image to be expressed as a vector, by calculating each vector
Between COS distance characterize the similarity between two images；Histogram similarity is then based on the face between two images
The similitude of color distribution characterizes the similarity between image.The above part calculation for only listing part and obtaining image similarity
Method, other algorithms for obtaining image similarity are also feasible, naturally it is also possible to be characterized between image in conjunction with many algorithms
Similarity, such as different weights can be assigned to the different obtained similarity values of algorithm, thus comprehensive many algorithms
Measure the similarity between image.
In other optional embodiments of the embodiment of the present invention, above-mentioned steps S103 may include:
S103a. the target in background image is detected respectively.
In above-mentioned steps S102, algorithm of target detection can also detect that other senses are emerging while detecting portrait
Target of interest, such as various furniture in background image, electric appliance, ornament etc..
S103b. the similarity between the background image is determined according to the target registration in background image.
Such as whether similar between background image, two width can be determined according to the target registration in each background image
Target registration between image is higher, then image similarity is higher.Information content contained by different targets is different, for
For off-the-air picture, such as information content contained by blank wall is less, because off-the-air picture all can include blank wall, to such
Target can assign lesser weight；Target biggish for information contained amount assigns biggish weight, especially known fraud
The target that usually will appear in the place of clique, therefore as a kind of optional embodiment, it can be to the different target detected
Different weights is assigned, target registration between weighted calculation two images measures the similarity between image.
In some other optional embodiment of the embodiment of the present invention, the above-mentioned structure according to image can be combined with
At least one in similarity (SSIM, Structural Similarity Index), cosine similarity, histogram similarity etc.
A acquired both image similarity and the image similarity according to acquired in the target registration in each background image,
Carry out the similarity between common metrics image.Such as it can be to structural similarity (SSIM, the Structural according to image
Similarity Index), cosine similarity, image similarity assigns acquired at least one of histogram similarity etc.
Some weight, and some weight is also assigned to the image similarity according to acquired in the target registration in each background image,
Then the similarity between image is characterized with weighted calculation obtained similarity.
Fig. 3 shows the recognition methods of financial product according to another embodiment of the present invention fraud clique, and this method can be with
It is executed, be may include steps of by server:
S201. the user images of multiple users are obtained, particular content may refer to the description of step S101.
S202. background image is obtained from user images, particular content may refer to the description of step S102.
S203. the similarity between background image is obtained, particular content may refer to the description of step S103.
S204. at least one user group that the similarity between background image is greater than predetermined threshold is obtained, particular content can
Referring to the description of step S104.
S205. judge whether the user in each user group belongs to the same family.
In practical applications, it is understood that there may be a kind of situation is that the multiple of the same family are asked with proposing business application per family
It asks, it, should not although background image is similar between the user node of these users since these users belong to the same family
Think that they belong to doubtful fraud clique.
As described above, it is same whether the user that again may be by chart database to judge in each user group belongs to
Family.It is back to Fig. 2, as can be seen from Figure 2 existing between user A, user B and the node of user C indicates kinship
Side shows that user B is mother of user A in figure, user C is the father of user A, and user B and user C are conjugal relation, and
The home address of these three users is identical, if the kinship of these three users and home address were verified or submitted card
Bright material, then the weighted value on corresponding side is larger, then can confirm user A, user B and user C for relatives pass by diagram data
The accuracy of system is higher, to assert that they belong to the same family.
S206. the user group for belonging to the same family is excluded.
The case where the same family is belonged to for the user in user group, it will be understood that the Background of the user in the user group
As it is similar be it is reasonable, should not be assumed that they belong to doubtful fraud clique, should be excluded, so as to reduce subsequent point
The workload of analysis.
S207. at least one business application information of the user in each user group is obtained.
In the present embodiment, business application information can be server and mentioned by the collected user of user terminal institute energy
Various information when business application is requested out, such as may include applying for used facility information, application time information, application
Geographical location information etc. when channel information, applied financial product information, application, those skilled in the art should be noted that
Above business application information is not exhaustive.
S208. the quantity that the similarity between the business application information of each user is greater than the set value is counted.
If multiple users propose to use equipment identical when business application, it may be considered that facility information used by applying
It is similar；If time when multiple users propose business application is close, then it is assumed that application time information is similar etc., herein no longer
It repeats.
For including the user group of user A, user B and user C, it is assumed that acquired business application information includes application
Used facility information and application time information, user A and B, user B and C application used by between facility information
Similarity is greater than the set value, user A and C, user B and C application time information between similarity be greater than the set value, then count
The quantity that the similarity in the user group between the business application information of user is greater than the set value out is 4.
As described above, it again may be by chart database intuitively to indicate the business letter of application of user in the user group
The case where similarity between breath is greater than the set value, still uses above example, as shown in figure 4, due to user A and B, user
Similarity between facility information used by the application of B and C is greater than the set value, can be between user A and B, user B and C
Increase the similar side of facility information used by applying；Due to user A and C, user B and C application time information between phase
It is greater than the set value like degree, the similar side of facility information used by application, system can be increased between user A and C, user B and C
The quantity for counting increased side is 4, and the similarity between business application information so as to intuitively count each user is greater than
The quantity of setting value.
S209. the quantity and the user group that the similarity between the business application information of each user is greater than the set value are calculated
The ratio of interior number of users.
S210. ratio is labeled as doubtful fraud clique user group beyond the user group of preset range.
The similarity of the business application information of each user in the similar user group of background image is more, the user
Group more may be fraud clique.
S205 and step S206 through the above steps, server can exclude to belong in acquired user group same
The user group in front yard, to reduce erroneous judgement；S207 to S210 through the above steps, server can be according to acquired customer services
Application information further verifies acquired user group, so as to mark doubtful fraud clique user group.
Correspondingly, as shown in figure 5, the embodiment of the invention also provides a kind of identification device of financial product fraud clique,
It may include:
Image acquisition unit 301, for obtaining the user images of multiple users, particular content may refer to step S101's
Description；
Background image unit 302, for obtaining background image from user images, particular content may refer to step S102
Description；
Similarity unit 303, for obtaining the similarity between background image, particular content may refer to step S103's
Description；
User group unit 304, at least one user for being greater than predetermined threshold for obtaining the similarity between background image
Group, particular content may refer to the description of step S104.
It, can be according to the similarity of background image in acquired user images to user by above-mentioned each component units
It is grouped, since the member of fraud clique usually has centrality in position, is cheated in same place, and usually not
Place can be often replaced, therefore by being grouped according to the similarity of background image to user, is facilitated subsequent to these use
Family group is audited, to identify fraud clique from mass users.
The detail of each component units of the identification device of financial product fraud clique in the present embodiment can be right
Corresponding associated description and effect in embodiment shown in -4 refering to fig. 1 is answered to be understood that details are not described herein again.
As shown in fig. 6, the server may include 401 He of processor the embodiment of the invention also provides a kind of server
Memory 402, wherein processor 401 can be connected with memory 402 by bus or other modes, by total in Fig. 6
For line connection.
Processor 401 can be central processing unit (Central Processing Unit, CPU).Processor 401 may be used also
Think other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.
Memory 402 is used as a kind of non-transient computer readable storage medium, can be used for storing non-transient software program, non-
Transient computer executable program and module, the recognition methods institute such as the financial product fraud clique in the embodiment of the present invention are right
The program instruction answered.The non-transient software instruction that processor 401 is stored in memory 402 by operation, thereby executing processing
The various function application and data processing of device, i.e., the identification side of the financial product fraud clique in realization above method embodiment
Method.
Memory 402 may include high-speed random access memory, can also include non-transient memory, for example, at least one
A disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, memory 402 is optional
Including the memory remotely located relative to processor 401, these remote memories can pass through network connection to processor
401.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
The detail of above-mentioned server can correspond to corresponding associated description in embodiment referring to FIG. 1 to 4
Understood with effect, details are not described herein again.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of the process in above-described embodiment method
Computer program is crossed to instruct relevant hardware and complete, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can for magnetic disk,
CD, read-only memory (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), flash memory (Flash Memory), hard disk (Hard Disk Drive, abbreviation: HDD) or solid state hard disk
(Solid-State Drive, SSD) etc.；The storage medium can also include the combination of the memory of mentioned kind.
Although being described in conjunction with the accompanying the embodiment of the present invention, those skilled in the art can not depart from the present invention
Spirit and scope in the case where various modifications and variations can be made, such modifications and variations are each fallen within by appended claims institute
Within the scope of restriction.
Claims (10)
1. a kind of recognition methods of financial product fraud clique characterized by comprising
Obtain the user images of multiple users；
Background image is obtained from the user images；
Obtain the similarity between the background image；
Obtain at least one user group that the similarity between the background image is greater than predetermined threshold.
2. the method according to claim 1, wherein the similarity obtained between the background image, packet
It includes:
Obtain at least one of structural similarity, cosine similarity and the histogram similarity between the background image.
3. the method according to claim 1, wherein the similarity obtained between the background image, packet
It includes:
The target in the background image is detected respectively；
The similarity between the background image is determined according to the target registration in the background image.
4. the method according to claim 1, wherein big in the similarity obtained between the background image
After at least one user group of predetermined threshold, further includes:
Judge whether the user in each user group belongs to the same family；
Exclude the user group for belonging to the same family.
5. the method according to claim 1, wherein big in the similarity obtained between the background image
After at least one user group of predetermined threshold, further includes:
Obtain at least one business application information of the user in each user group；
Count the quantity that the similarity between the business application information of each user is greater than the set value；
Calculate the quantity and the user that the similarity between the business application information of each user is greater than the set value
The ratio of number of users in group；
The ratio is labeled as doubtful fraud clique user group beyond the user group of preset range.
6. according to the method described in claim 5, it is characterized by further comprising:
Similarity between the business application information, which is greater than between the user node of the setting value, to be increased for indicating industry
The similar side of application information of being engaged in.
7. method according to claim 1 to 6, which is characterized in that further include:
Increase between each user node in the user group for indicating the similar side of background image.
8. a kind of identification device of financial product fraud clique characterized by comprising
Image acquisition unit, for obtaining the user images of multiple users；
Background image unit, for obtaining background image from the user images；
Similarity unit, for obtaining the similarity between the background image；
User group unit, at least one user group for being greater than predetermined threshold for obtaining the similarity between the background image.
9. a kind of server characterized by comprising memory and processor, between the memory and the processor mutually
Connection is communicated, computer instruction is stored in the memory, the processor, which passes through, executes the computer instruction, thus
Perform claim requires method described in any one of 1-7.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to
It enables, the computer instruction is used to that the computer perform claim to be made to require method described in any one of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910630766.0A CN110348519A (en) | 2019-07-12 | 2019-07-12 | Financial product cheats recognition methods and the device of clique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910630766.0A CN110348519A (en) | 2019-07-12 | 2019-07-12 | Financial product cheats recognition methods and the device of clique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110348519A true CN110348519A (en) | 2019-10-18 |
Family
ID=68176007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910630766.0A Pending CN110348519A (en) | 2019-07-12 | 2019-07-12 | Financial product cheats recognition methods and the device of clique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110348519A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401959A (en) * | 2020-03-18 | 2020-07-10 | 多点(深圳)数字科技有限公司 | Risk group prediction method and device, computer equipment and storage medium |
| CN111860369A (en) * | 2020-07-24 | 2020-10-30 | 河南中原消费金融股份有限公司 | Fraud identification method and device and storage medium |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| CN112418167A (en) * | 2020-12-10 | 2021-02-26 | 深圳前海微众银行股份有限公司 | Image clustering method, device, equipment and storage medium |
| CN113689292A (en) * | 2021-09-18 | 2021-11-23 | 杭银消费金融股份有限公司 | User aggregation identification method and system based on image background identification |
| CN116071089A (en) * | 2023-02-10 | 2023-05-05 | 成都新希望金融信息有限公司 | Fraud identification method and device, electronic equipment and storage medium |
| CN116543181A (en) * | 2023-05-10 | 2023-08-04 | 北京微聚智汇科技有限公司 | Anti-partner fraud method and system based on image background feature recognition |
| CN116823451A (en) * | 2023-08-10 | 2023-09-29 | 杭银消费金融股份有限公司 | Credit risk control method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134765A (en) * | 1999-11-09 | 2001-05-18 | Canon Inc | Method and device for retrieving image |
| US20080152225A1 (en) * | 2004-03-03 | 2008-06-26 | Nec Corporation | Image Similarity Calculation System, Image Search System, Image Similarity Calculation Method, and Image Similarity Calculation Program |
| CN104662490A (en) * | 2012-09-24 | 2015-05-27 | 高通股份有限公司 | Integrated display and management of data objects based on social, temporal and spatial parameters |
| CN108229335A (en) * | 2017-12-12 | 2018-06-29 | 深圳市商汤科技有限公司 | It is associated with face identification method and device, electronic equipment, storage medium, program |
| CN109063967A (en) * | 2018-07-03 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of processing method, device and the electronic equipment of air control scene characteristic tensor |
| CN109191281A (en) * | 2018-08-21 | 2019-01-11 | 重庆富民银行股份有限公司 | A kind of group's fraud identifying system of knowledge based map |
| CN109271418A (en) * | 2018-08-14 | 2019-01-25 | 阿里巴巴集团控股有限公司 | Suspicious clique's recognition methods, device, equipment and computer readable storage medium |
| CN109615116A (en) * | 2018-11-20 | 2019-04-12 | 中国科学院计算技术研究所 | A kind of telecommunication fraud event detecting method and detection system |
| CN109684516A (en) * | 2018-12-03 | 2019-04-26 | 武汉烽火众智智慧之星科技有限公司 | One kind being based on public security big data personage specific behavior cooccurrence relation map generation method |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
-
2019
- 2019-07-12 CN CN201910630766.0A patent/CN110348519A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134765A (en) * | 1999-11-09 | 2001-05-18 | Canon Inc | Method and device for retrieving image |
| US20080152225A1 (en) * | 2004-03-03 | 2008-06-26 | Nec Corporation | Image Similarity Calculation System, Image Search System, Image Similarity Calculation Method, and Image Similarity Calculation Program |
| CN104662490A (en) * | 2012-09-24 | 2015-05-27 | 高通股份有限公司 | Integrated display and management of data objects based on social, temporal and spatial parameters |
| CN108229335A (en) * | 2017-12-12 | 2018-06-29 | 深圳市商汤科技有限公司 | It is associated with face identification method and device, electronic equipment, storage medium, program |
| CN109063967A (en) * | 2018-07-03 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of processing method, device and the electronic equipment of air control scene characteristic tensor |
| CN109271418A (en) * | 2018-08-14 | 2019-01-25 | 阿里巴巴集团控股有限公司 | Suspicious clique's recognition methods, device, equipment and computer readable storage medium |
| CN109191281A (en) * | 2018-08-21 | 2019-01-11 | 重庆富民银行股份有限公司 | A kind of group's fraud identifying system of knowledge based map |
| CN109615116A (en) * | 2018-11-20 | 2019-04-12 | 中国科学院计算技术研究所 | A kind of telecommunication fraud event detecting method and detection system |
| CN109684516A (en) * | 2018-12-03 | 2019-04-26 | 武汉烽火众智智慧之星科技有限公司 | One kind being based on public security big data personage specific behavior cooccurrence relation map generation method |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
Non-Patent Citations (2)
| Title |
|---|
| JINGMENG HE ET AL.: "SRN: The Movie Character Relationship Analysis via Social Network", 《SPRINGER INTERNATIONAL PUBLISHING AG 2018》 * |
| 周源: "社交媒体中人物关系的挖掘与识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401959A (en) * | 2020-03-18 | 2020-07-10 | 多点(深圳)数字科技有限公司 | Risk group prediction method and device, computer equipment and storage medium |
| CN111401959B (en) * | 2020-03-18 | 2023-09-29 | 多点(深圳)数字科技有限公司 | Risk group prediction method, apparatus, computer device and storage medium |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| CN111860369A (en) * | 2020-07-24 | 2020-10-30 | 河南中原消费金融股份有限公司 | Fraud identification method and device and storage medium |
| CN112418167A (en) * | 2020-12-10 | 2021-02-26 | 深圳前海微众银行股份有限公司 | Image clustering method, device, equipment and storage medium |
| CN113689292A (en) * | 2021-09-18 | 2021-11-23 | 杭银消费金融股份有限公司 | User aggregation identification method and system based on image background identification |
| CN116071089A (en) * | 2023-02-10 | 2023-05-05 | 成都新希望金融信息有限公司 | Fraud identification method and device, electronic equipment and storage medium |
| CN116071089B (en) * | 2023-02-10 | 2023-12-05 | 成都新希望金融信息有限公司 | Fraud identification method and device, electronic equipment and storage medium |
| CN116543181A (en) * | 2023-05-10 | 2023-08-04 | 北京微聚智汇科技有限公司 | Anti-partner fraud method and system based on image background feature recognition |
| CN116823451A (en) * | 2023-08-10 | 2023-09-29 | 杭银消费金融股份有限公司 | Credit risk control method and system |
| CN116823451B (en) * | 2023-08-10 | 2024-03-26 | 杭银消费金融股份有限公司 | Credit risk control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348519A (en) | Financial product cheats recognition methods and the device of clique | |
| CN110365996A (en) | Management method, live streaming management platform, electronic equipment and storage medium is broadcast live | |
| CN110163076A (en) | A kind of image processing method and relevant apparatus | |
| WO2018184301A1 (en) | Business outlet sales service system, method, server and storage medium | |
| CN110969170B (en) | Image theme color extraction method and device and electronic equipment | |
| CN109241084B (en) | Data query method, terminal equipment and medium | |
| CN108900924A (en) | The method and apparatus of commending friends in direct broadcasting room | |
| CN109508405B (en) | Method and device for determining recommended video, electronic equipment and storage medium | |
| CN111047264B (en) | Logistics task distribution method and device | |
| CN105243098B (en) | The clustering method and device of facial image | |
| CN109858441A (en) | A kind of monitoring abnormal state method and apparatus for construction site | |
| CN108764100B (en) | Target behavior detection method and server | |
| CN110264497B (en) | Method and device for determining tracking duration, storage medium and electronic device | |
| CN110475124A (en) | Video cardton detection method and device | |
| CN110175849A (en) | Cashing method, device, equipment, server and system | |
| CN111476596A (en) | Family population data processing method, system and storage medium based on homologous equipment | |
| CN111898765A (en) | Feature binning method, device, equipment and readable storage medium | |
| CN108134944A (en) | A kind of recognition methods, device and electronic equipment for taking in abnormal main broadcaster user | |
| CN110428368A (en) | A kind of algorithm evaluation method, device, electronic equipment and readable storage medium storing program for executing | |
| CN109495378A (en) | Detect method, apparatus, server and the storage medium of abnormal account number | |
| CN110505490A (en) | Multi-medium data recognition methods and system | |
| CN108171570A (en) | A kind of data screening method, apparatus and terminal | |
| CN110505438B (en) | Queuing data acquisition method and camera | |
| CN111179023B (en) | Order identification method and device | |
| CN111461595B (en) | Pricing template generation method, device, equipment 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |