CN109491995A - Knowledge based map inquires the method and system of financial abnormal data - Google Patents
Knowledge based map inquires the method and system of financial abnormal data Download PDFInfo
- Publication number
- CN109491995A CN109491995A CN201811588282.6A CN201811588282A CN109491995A CN 109491995 A CN109491995 A CN 109491995A CN 201811588282 A CN201811588282 A CN 201811588282A CN 109491995 A CN109491995 A CN 109491995A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- information
- sample
- query
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000001228 spectrum Methods 0.000 claims abstract description 47
- 238000013507 mapping Methods 0.000 claims abstract description 42
- 241001269238 Data Species 0.000 claims abstract description 24
- 238000013461 design Methods 0.000 claims abstract description 15
- 239000000203 mixture Substances 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000000717 retained effect Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 4
- 239000010931 gold Substances 0.000 claims description 4
- 229910052737 gold Inorganic materials 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012856 packing Methods 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention discloses a kind of method and system of financial abnormal data of knowledge based map inquiry, and abnormal finance data therein is accurately and rapidly identified by the way of knowledge mapping.This method comprises: being constituted according to the structure that the query demand of financial abnormal data designs spectrum data library, the structure constitutes the statement including node and relationships between nodes;Acquire multiple sample source datas, to obtained after its data cleansing it is multiple meet spectrum data library structure composition sample datas;The sample data is imported into the spectrum data library and exports knowledge mapping, financial abnormal data is then found out from the knowledge mapping.The system includes the method that above-mentioned technical proposal is mentioned.
Description
Technical field
The present invention relates to financial anti-fraud technical fields more particularly to a kind of knowledge based map to inquire financial abnormal data
Method and system.
Background technique
With the development of internet finance, intermediary's industry of providing a loan gradually is risen, they can be to reference unregistered household, the white family of reference etc.
The crowd for usually hardly resulting in loan examination & approval packs user's material, them is helped dexterously to evade platform air control, and due to such
Client mostly be the client without normal loan repayment capacity, if therefore making loans successfully may cause bad credit to financial platform, cause finance put down
Therefore how the loss of assets of platform in order to prevent the generation of above-mentioned fraud, identifies that fraud is most important.
The prior art takes the mode of call-on back by phone or identity secondary-confirmation mainly to identify fraud, practical application
Middle discovery, the fraud that aforesaid way answers letter can play certain recognition effect, but the fraud for packing meticulously
For behavior, since it is related to complicated relational network, it is difficult by way of call-on back by phone or identity secondary-confirmation
It accurately identifies, so this also brings new challenge to fraud identification.
Summary of the invention
The purpose of the present invention is to provide the method and system that a kind of knowledge based map inquires financial abnormal data, use
The mode of knowledge mapping accurately and rapidly identifies abnormal finance data therein.
To achieve the goals above, an aspect of of the present present invention provides a kind of knowledge based map and inquires financial abnormal data
Method, comprising:
It is constituted according to the structure that the query demand of financial abnormal data designs spectrum data library, it includes section that the structure, which is constituted,
The statement of point and relationships between nodes;
Acquire multiple sample source datas, to obtained after its data cleansing it is multiple meet spectrum data library structure composition samples
Data;
The sample data is imported into the spectrum data library and exports knowledge mapping, is then searched from the knowledge mapping
Financial abnormal data out.
Preferably, include: according to the method that the structure that the query demand of financial abnormal data designs spectrum data library is constituted
The query demand of the finance abnormal data includes finding out illegal intermediary from multidigit creditor's register information
Information, creditor's register information include creditor's information, contact information, transfer accounts people's information and/or addressee information,
In, the information includes name data, phone data and identity code data;
A variety of node types are correspondingly arranged based on numerous types of data, according to the principle design drawing of the corresponding data of a node
Modal data library.
Preferably, the multiple sample source datas of acquisition, are tied to multiple spectrum data libraries that meet are obtained after its data cleansing
The method of sample data that structure is constituted includes:
More parts of creditor's register informations are obtained from database, and therefrom extract the loan in every part of creditor's register information
People's information, contact information, people's information of transferring accounts and/or addressee information are as sample source data;
To the preliminary screening of sample source data, rejecting does not include name data, phone data or identity code data
Sample source data;
Duplicate checking is carried out to the sample source data retained, deletes duplicate sample source data;
Sample source data after duplicate checking is subjected to legitimacy verifies, remove phone data and/or identity code data without
The sample source data of effect, finally retains effective sample data.
Optionally, the recognition methods of the phone data and/or identity code data invalid are as follows:
By comparing phone data and/or identity code data and standard telephone number and/or standard identity identification code
Length it is whether consistent to determine whether invalid.
Preferably, the method that financial abnormal data is identified from the knowledge mapping includes:
A variety of financial abnormal data query statements, including abnormal name lookup sentence, exception are preset using Cypher language
Help by Phone sentence or abnormal identity code query statement;
By abnormal name lookup sentence, abnormal Help by Phone sentence or abnormal identity code query statement with modular
Form is arranged on query interface, so that user inputs according to the query demand corresponding selection query statement of financial abnormal data;
Multiple sample datas are distributed with joint form and are unfolded, relationship node is associated with to form knowledge graph by index line
Spectrum;
Relationship node is filtered out from knowledge mapping according to the query statement of input, then is looked into from the relationship node filtered out
Find out illegal intermediary's information.
Optionally, relationship node is filtered out from knowledge mapping according to the query statement of input, then from the relationship filtered out
The method that illegal intermediary's information is found out in node includes:
Be arranged abnormal nodes recognition threshold, when the degree of association of relationship node be greater than the threshold value when by relationship node with institute
The consistent node output of query statement type is stated, the query result of illegal intermediary's information is obtained.
Illustratively, the degree of association is to define to obtain according to the index line quantity connecting with node.
Compared with prior art, the method that knowledge based map provided by the invention inquires financial abnormal data has following
The utility model has the advantages that
Knowledge based map provided by the invention is inquired in the method for financial abnormal data, is needed first according to user to finance
The structure in the query demand design spectrum data library of abnormal data is constituted, when the query demand of financial abnormal data is from creditor
When inquiring illegal intermediary's information in the middle, it is contemplated that illegal intermediary's information that platform can be got not only includes name, also
Including effective identity identification information such as its phone and identity code, therefore can be selected when the structure for designing spectrum data library is constituted
Three types node indicates an information data by a node, and relationship node is set using the associated mode correspondence of index line
The structure for counting spectrum data library is constituted, and is acquired multiple sample source datas from platform later, is formed spectrum data after data cleansing
Csv file is finally imported the knowledge mapping of spectrum data library building sample data, by from knowing by the identifiable csv file in library
Know map and filters out the node that the degree of association is higher than threshold value, extracting corresponding information data output in node is financial abnormal data,
Such as the effective identification data such as name, phone or identity code of illegal intermediary.
As it can be seen that the present invention takes the mode that great amount of samples data input spectrum data library is formed knowledge mapping to identify finance
Abnormal data is good at the characteristic of processing complex network relationship using knowledge mapping, by the network of multiple sample data structurings
It shows, and then therefrom fast and accurately identifies financial abnormal data.
Another aspect of the present invention provides a kind of financial abnormal data system of knowledge based map inquiry, is applied to above-mentioned skill
Knowledge based map described in art scheme is inquired in financial abnormal data systems approach, the system comprises:
Atlas Design unit, the structure for designing spectrum data library according to the query demand of financial abnormal data are constituted,
The structure constitutes the statement including node and relationships between nodes;
Sample collection unit, for acquiring multiple sample source datas, to obtaining multiple meeting map number after its data cleansing
The sample data constituted according to library structure;
Identify output unit, export knowledge mapping for the sample data to be imported the spectrum data library, then from
Financial abnormal data is identified in the knowledge mapping.
Preferably, the sample collection unit includes:
Information acquisition module for obtaining more parts of creditor's register informations from database, and therefrom extracts every part of loan
Creditor's information, contact information, people's information of transferring accounts and/or addressee information in people's register information is as sample source data;
Screening module, for the preliminary screening of sample source data, rejecting not to include name data, phone data or body
The sample source data of part identification code data;
Duplicate checking module deletes duplicate sample source data for carrying out duplicate checking to the sample source data retained;
Correction verification module removes phone data and/or identity for the sample source data after duplicate checking to be carried out legitimacy verifies
The invalid sample source data of identification code data, finally retains effective sample data.
Preferably, the identification output unit includes:
Pre-stored module, for presetting a variety of financial abnormal data query statements, including abnormal surname using Cypher language
Name query statement, abnormal Help by Phone sentence or abnormal identity code query statement;
Setup module, for inquiring abnormal name lookup sentence, abnormal Help by Phone sentence or abnormal identity code
Sentence is arranged on query interface in a modular fashion, so that query demand corresponding selection of the user according to financial abnormal data
Query statement input;
Processing module, is unfolded for being distributed multiple sample datas with joint form, and relationship node passes through index line
Association forms knowledge mapping;
Output module is inquired, filters out relationship node from knowledge mapping for the query statement according to input, then from sieve
Identify that financial abnormal data is exported in the form of query result in the relationship node selected.
Compared with prior art, knowledge based map provided by the invention inquires the beneficial effect of financial abnormal data system
It is identical as the beneficial effect that the knowledge based map that above-mentioned technical proposal provides inquires financial abnormal data method, it does not do herein superfluous
It states.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is the flow diagram that knowledge based map inquires financial abnormal data method in the embodiment of the present invention one;
Fig. 2 is the structural block diagram that knowledge based map inquires financial abnormal data system in the embodiment of the present invention two.
Appended drawing reference:
1- Atlas Design unit, 2- sample collection unit;
3- identifies output unit, 21- information acquisition module;
22- screening module, 23- duplicate checking module;
24- correction verification module, 31- are pre-stored module;
32- setup module, 33- processing module;
34- inquires output module.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, implement below in conjunction with the present invention
Attached drawing in example, technical scheme in the embodiment of the invention is clearly and completely described.Obviously, described embodiment
Only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, the common skill in this field
Art personnel all other embodiment obtained without creative labor belongs to the model that the present invention protects
It encloses.
Embodiment one
Fig. 1 is the method flow schematic diagram that knowledge based map inquires financial abnormal data in the embodiment of the present invention one.Please
Refering to fig. 1, the present embodiment provides a kind of methods that knowledge based map inquires financial abnormal data, comprising:
According to the query demand of financial abnormal data design spectrum data library structure constitute, structure constitute include node and
The statement of relationships between nodes;Multiple sample source datas are acquired, to obtaining multiple meeting spectrum data library structure after its data cleansing
The sample data of composition;Sample data is imported into spectrum data library and exports knowledge mapping, gold is then found out from knowledge mapping
Melt abnormal data.
Knowledge based map provided in this embodiment is inquired in the method for financial abnormal data, is needed first according to user to gold
The structure for melting the query demand design spectrum data library of abnormal data is constituted, when the query demand of financial abnormal data is from loan
When people inquires illegal intermediary's information in the middle, it is contemplated that illegal intermediary's information that platform can be got not only includes name,
It further include effective identity identification information such as its phone and identity code, thus it is optional when the structure for designing spectrum data library is constituted
With three types node, an information data is indicated by a node, relationship node is corresponding using the associated mode of index line
The structure for designing spectrum data library is constituted, and acquires multiple sample source datas from platform later, and map number is formed after data cleansing
According to the identifiable csv file in library, finally by csv file import spectrum data library building sample data knowledge mapping, by from
Knowledge mapping filters out the node that the degree of association is higher than threshold value, and extracting corresponding information data output in node is the abnormal number of finance
According to, such as the effective identification data such as name, phone or identity code of illegal intermediary.
As it can be seen that the present embodiment takes the mode that great amount of samples data input spectrum data library is formed knowledge mapping to identify gold
Melt abnormal data, the characteristic of processing complex network relationship is good at using knowledge mapping, by the net of multiple sample data structurings
Network shows, and then therefrom fast and accurately identifies financial abnormal data.
Specifically, it is constituted in above-described embodiment according to the structure that the query demand of financial abnormal data designs spectrum data library
Method include:
The query demand of financial abnormal data includes that illegal intermediary's information is found out from multidigit creditor's register information,
Creditor's register information includes creditor's information, contact information, transfer accounts people's information and/or addressee information, wherein packet
Include name data, phone data and identity code data;A variety of node types are correspondingly arranged based on numerous types of data, according to
The principle of the corresponding data of one node designs spectrum data library.
When it is implemented, existing in order to facilitate understanding be illustrated so that installment credit is done shopping as an example, installment credit purchase is being searched
During the movable illegal intermediary of object, must will transfer accounts artificial entrance comb from creditor, the addressee of purchased commodity and correlation
It manages suspicious clue and excavates illegal intermediary therein, since the information that platform can get above-mentioned related personnel includes surname
Name data, phone data and identity code data, therefore when the structure for designing spectrum data library is constituted, it can be in spectrum data library
In be correspondingly arranged three types node it is corresponding indicate above-mentioned three kinds of data, by the way that multiple installment credit purchase datas are known
After knowing atlas analysis, wherein the high node of the degree of association excavates suspicious illegal intermediary for screening.
Specifically, the multiple sample source datas of acquisition described in above-described embodiment, to obtaining multiple meet after its data cleansing
The method of sample data that spectrum data library structure is constituted includes:
More parts of creditor's register informations are obtained from database, and therefrom extract the loan in every part of creditor's register information
People's information, contact information, people's information of transferring accounts and/or addressee information are as sample source data;Sample source data is tentatively sieved
It looks into, rejecting does not include the sample source data of name data, phone data or identity code data;To the sample source number retained
According to duplicate checking is carried out, duplicate sample source data is deleted;Sample source data after duplicate checking is subjected to legitimacy verifies, removes telephone number
According to and/or identity code data invalid sample source data, finally retain effective sample data.
When it is implemented, after getting more parts of sample source datas, to the sample for not meeting spectrum data library structure composition
This source data, which is given, to be rejected, if same creditor, there are multiple loan documentation, platform just will record same creditor
More parts of creditor's register informations, may have duplicate creditor's register information, therefore when getting sample source data
Duplicate removal can be carried out to sample source data, can also carry out legitimacy verifies to the sample source data after duplicate checking later, remove telephone number
According to and/or identity code data invalid sample source data, finally retain effective sample data, wherein phone data and/
Or the recognition methods of identity code data invalid are as follows: by comparing phone data and/or identity code data and standard electric
Whether the length for talking about number and/or standard identity identification code is consistent to determine whether invalid, for example, to not being in sample source data
It 11 phone numbers and is not determined as in vain for 18 identity codes.
Preferably, the method for identifying financial abnormal data in above-described embodiment from knowledge mapping includes:
A variety of financial abnormal data query statements, including abnormal name lookup sentence, exception are preset using Cypher language
Help by Phone sentence or abnormal identity code query statement;By abnormal name lookup sentence, abnormal Help by Phone sentence or different
Normal identity code query statement is arranged on query interface in a modular fashion, so that user is according to financial abnormal data
The input of query demand corresponding selection query statement;Multiple sample datas are distributed with joint form and are unfolded, relationship node passes through finger
Timberline is associated with to form knowledge mapping;Relationship node is filtered out from knowledge mapping according to the query statement of input, then from filtering out
Relationship node in find out illegal intermediary's information.
When it is implemented, inquiry is required using Cypher sentence each time when being retrieved using spectrum data library inquiry
The identifiable querying command in spectrum data library is compiled, spectrum data library could correspond to output query result, it is clear that this is to non-meter
It is not allow easy-operating for the business personnel of calculation machine profession class origin, uses with inconvenience, the present embodiment is to understand
The certainly above problem is taken and presets the good enquiry module of Cypher statement editing, such as illegal intermediary on platform query interface
Name lookup module or illegal intermediary's Help by Phone module, so that business personnel is when inquiring illegal intermediary's name, it can
Directly the query frame that illegal intermediary's name lookup module is drawn to platform is searched for, program receives after inquiry instruction again from knowing
Know map and filter out relationship node, relationship node herein includes that name data, phone data and the identity of illegal intermediary is known
Other code data finally find out illegal intermediary's name data output result from relationship node.
It is unfolded it is understood that multiple sample source datas are distributed with joint form, relationship node is closed by index line
Join the method for forming knowledge mapping are as follows:
Since every part of sample data includes the data of name, phone or identity code totally 3 seed types, know in building
It can refer to every part of sample data 3 nodes of corresponding building during knowing map, so that one data of each node on behalf, simultaneously
Three nodes association in same a sample data is indicated in a manner of index line, when the corresponding node of more parts of sample datas is complete
After the completion of portion's building, then by the node duplicate removal of identical data, then by the index line being connect with deletion of node switching after duplicate removal
On the node of reservation, knowledge mapping is ultimately formed.
From above-mentioned implementation process it is found that the present embodiment has the advantages that
1, the inquiry complexity in spectrum data library can be simplified, only expert data analyzed personnel and engineer's ability in the past
The spectrum data library specific language and grammer of grasp, the business personnel for being ignorant of computer programming language now can also inquire
Operation;
2, the communication cost of business personnel and developer can be reduced, former business personnel needs by writing the demand of looking into
The cooperation process of multiple departments such as specification-research and development department's waiting-research and development department's realization demand, now only needing research and development department will
Data import spectrum data library, and subsequent use can voluntarily be completed by business personnel;
3, search efficiency is improved, the analysis result that former data analyst obtains can only use on spectrum data library
Cypher sentence realizes interaction and needs for diagram data to be reduced into data list structure and could use to business department, will scheme now general
For data lab setting on platform, business personnel can directly acquire query result, and whole process is convenient and efficient.
Further, the above-mentioned query statement according to input filters out relationship node from knowledge mapping, then from filtering out
Relationship node in find out the method for illegal intermediary's information and include:
Be arranged abnormal nodes recognition threshold, when the degree of association of relationship node be greater than threshold value when by relationship node with inquiry language
The consistent node output of sentence type, obtains the query result of illegal intermediary's information.Wherein, the degree of association is that basis is connect with node
Index line quantity define.
Embodiment two
Fig. 1 and Fig. 2 are please referred to, the present embodiment provides a kind of knowledge based maps to inquire financial abnormal data system, comprising:
Atlas Design unit 1, the structure for designing spectrum data library according to the query demand of financial abnormal data are constituted,
Structure constitutes the statement including node and relationships between nodes;
Sample collection unit 2, for acquiring multiple sample source datas, to obtaining multiple meeting map number after its data cleansing
The sample data constituted according to library structure;
It identifies output unit 3, knowledge mapping is exported for sample data to be imported spectrum data library, then from knowledge mapping
In find out financial abnormal data.
Preferably, sample collection unit 2 includes:
Information acquisition module 21 for obtaining more parts of creditor's register informations from database, and therefrom extracts every part of loan
Creditor's information, contact information, people's information of transferring accounts and/or addressee information in money people's register information is as sample source number
According to;
Screening module 22, for the preliminary screening of sample source data, rejecting not to include name data, phone data or identity
The sample source data of identification code data;
Duplicate checking module 23 deletes duplicate sample source data for carrying out duplicate checking to the sample source data retained;
Correction verification module 24 removes phone data and/or body for the sample source data after duplicate checking to be carried out legitimacy verifies
The invalid sample source data of part identification code data, finally retains effective sample source data.
Preferably, identification output unit 3 includes:
Pre-stored module 31, for presetting a variety of financial abnormal data query statements, including exception using Cypher language
Name lookup sentence, abnormal Help by Phone sentence or abnormal identity code query statement;
Setup module 32, for looking into abnormal name lookup sentence, abnormal Help by Phone sentence or abnormal identity code
It askes sentence to be arranged on query interface in a modular fashion, so that user selects according to the query demand of financial abnormal data is corresponding
Select query statement input;
Processing module 33 is unfolded for being distributed multiple sample datas with joint form, and relationship node is closed by index line
Connection forms knowledge mapping;
Output module 34 is inquired, filters out relationship node from knowledge mapping for the query statement according to input, then from
Identify that financial abnormal data is exported in the form of query result in the relationship node filtered out.
Compared with prior art, knowledge based map provided in an embodiment of the present invention inquires having for financial abnormal data system
Beneficial effect is identical as the beneficial effect that the knowledge based map that above-described embodiment one provides inquires financial abnormal data method, herein
It does not repeat them here.
It will appreciated by the skilled person that realizing that all or part of the steps in foregoing invention method is can to lead to
Program is crossed to instruct relevant hardware and complete, above procedure can store in computer-readable storage medium, the program
When being executed, each step including above-described embodiment method, and the storage medium may is that ROM/RAM, magnetic disk, CD,
Storage card etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method that knowledge based map inquires financial abnormal data characterized by comprising
Constituted according to the structure that the query demand of financial abnormal data designs spectrum data library, the structure constitute include node and
The statement of relationships between nodes;
Acquire multiple sample source datas, to obtained after its data cleansing it is multiple meet spectrum data library structure composition sample numbers
According to;
The sample data is imported into the spectrum data library and exports knowledge mapping, then finds out gold from the knowledge mapping
Melt abnormal data.
2. the method according to claim 1, wherein designing map number according to the query demand of financial abnormal data
Include: according to the method that the structure in library is constituted
The query demand of the finance abnormal data includes that illegal intermediary's information is found out from multidigit creditor's register information,
Creditor's register information includes creditor's information, contact information, transfer accounts people's information and/or addressee information, wherein institute
Stating information includes name data, phone data and identity code data;
A variety of node types are correspondingly arranged based on numerous types of data, design map number according to the principle of the corresponding data of a node
According to library.
3. according to the method described in claim 2, it is characterized in that, described acquire multiple sample source datas, to its data cleansing
Obtaining multiple methods for meeting the sample datas that spectrum data library structure is constituted afterwards includes:
More parts of creditor's register informations are obtained from database, and therefrom extract the letter of the creditor in every part of creditor's register information
Breath, contact information, people's information of transferring accounts and/or addressee information are as sample source data;
To the preliminary screening of sample source data, rejecting does not include the sample of name data, phone data or identity code data
This source data;
Duplicate checking is carried out to the sample source data retained, deletes duplicate sample source data;
Sample source data after duplicate checking is subjected to legitimacy verifies, removes phone data and/or identity code data invalid
Sample source data finally retains effective sample data.
4. according to the method described in claim 3, it is characterized in that, the phone data and/or identity code data invalid
Recognition methods are as follows:
By the length for comparing phone data and/or identity code data and standard telephone number and/or standard identity identification code
Whether degree is consistent to determine whether invalid.
5. according to the method described in claim 2, it is characterized in that, identifying financial abnormal data from the knowledge mapping
Method includes:
A variety of financial abnormal data query statements, including abnormal name lookup sentence, abnormal phone are preset using Cypher language
Query statement or abnormal identity code query statement;
In a modular fashion by abnormal name lookup sentence, abnormal Help by Phone sentence or abnormal identity code query statement
It is arranged on query interface, so that user inputs according to the query demand corresponding selection query statement of financial abnormal data;
Multiple sample datas are distributed with joint form and are unfolded, relationship node is associated with to form knowledge mapping by index line;
Relationship node is filtered out from knowledge mapping according to the query statement of input, then is found out from the relationship node filtered out
Illegal intermediary's information.
6. according to the method described in claim 5, it is characterized in that, the query statement according to input is filtered out from knowledge mapping
Relationship node, then the method for finding out from the relationship node filtered out illegal intermediary's information includes:
Abnormal nodes recognition threshold is set, will be looked into relationship node with described when the degree of association of relationship node is greater than the threshold value
The consistent node output of statement type is ask, the query result of illegal intermediary's information is obtained.
7. method according to claim 5 or 6, which is characterized in that the degree of association is according to the instruction connecting with node
Line number amount defines.
8. a kind of knowledge based map inquires financial abnormal data system characterized by comprising
Atlas Design unit, the structure for designing spectrum data library according to the query demand of financial abnormal data is constituted, described
Structure constitutes the statement including node and relationships between nodes;
Sample collection unit, for acquiring multiple sample source datas, to obtaining multiple meeting spectrum data library after its data cleansing
The sample data that structure is constituted;
It identifies output unit, knowledge mapping is exported for the sample data to be imported the spectrum data library, then from described
Financial abnormal data is found out in knowledge mapping.
9. system according to claim 8, which is characterized in that the sample collection unit includes:
Information acquisition module for obtaining more parts of creditor's register informations from database, and therefrom extracts every part of creditor and steps on
Remember creditor's information, contact information, people's information of transferring accounts and/or the addressee information in information as sample source data;
Screening module, for the preliminary screening of sample source data, rejecting not to include that name data, phone data or identity are known
The sample source data of other code data;
Duplicate checking module deletes duplicate sample source data for carrying out duplicate checking to the sample source data retained;
Correction verification module removes phone data and/or identification for the sample source data after duplicate checking to be carried out legitimacy verifies
The sample source data of code data invalid, finally retains effective sample data.
10. system according to claim 8, which is characterized in that the identification output unit includes:
Pre-stored module, for presetting a variety of financial abnormal data query statements using Cypher language, including abnormal name is looked into
Ask sentence, abnormal Help by Phone sentence or abnormal identity code query statement;
Setup module is used for abnormal name lookup sentence, abnormal Help by Phone sentence or abnormal identity code query statement
It is arranged on query interface in a modular fashion, so that user inquires according to the query demand corresponding selection of financial abnormal data
Input by sentence;
Processing module is unfolded for being distributed multiple sample datas with joint form, and relationship node is associated with by index line
Form knowledge mapping;
Output module is inquired, filters out relationship node from knowledge mapping for the query statement according to input, then from filtering out
Relationship node in identify that financial abnormal data is exported in the form of query result.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811588282.6A CN109491995A (en) | 2018-12-25 | 2018-12-25 | Knowledge based map inquires the method and system of financial abnormal data |
CA3230500A CA3230500A1 (en) | 2018-12-25 | 2019-09-18 | Method and system for querying abnormal financial data on basis of knowledge map |
CA3179620A CA3179620A1 (en) | 2018-12-25 | 2019-09-18 | Method and system for querying abnormal financial data on basis of knowledge map |
PCT/CN2019/106503 WO2020134213A1 (en) | 2018-12-25 | 2019-09-18 | Method and system for querying abnormal financial data on basis of knowledge map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811588282.6A CN109491995A (en) | 2018-12-25 | 2018-12-25 | Knowledge based map inquires the method and system of financial abnormal data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109491995A true CN109491995A (en) | 2019-03-19 |
Family
ID=65711856
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811588282.6A Pending CN109491995A (en) | 2018-12-25 | 2018-12-25 | Knowledge based map inquires the method and system of financial abnormal data |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN109491995A (en) |
CA (2) | CA3230500A1 (en) |
WO (1) | WO2020134213A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110321438A (en) * | 2019-06-14 | 2019-10-11 | 北京奇艺世纪科技有限公司 | Real-time fraud detection method, device and electronic equipment based on complex network |
CN110609905A (en) * | 2019-09-12 | 2019-12-24 | 深圳众赢维融科技有限公司 | Method and device for recognizing type of over-point and processing graph data |
CN110837538A (en) * | 2019-10-24 | 2020-02-25 | 北京中科捷信信息技术有限公司 | Financial knowledge map visual query and multidimensional analysis system |
WO2020134213A1 (en) * | 2018-12-25 | 2020-07-02 | 苏宁云计算有限公司 | Method and system for querying abnormal financial data on basis of knowledge map |
CN112686760A (en) * | 2021-01-20 | 2021-04-20 | 何青波 | Financial business processing method and platform based on big data |
TWI736233B (en) * | 2020-04-23 | 2021-08-11 | 兆豐國際商業銀行股份有限公司 | Pre-loan investigation system and pre-loan investigation method |
CN113469697A (en) * | 2021-06-30 | 2021-10-01 | 重庆富民银行股份有限公司 | Unsupervised anomaly detection method and unsupervised anomaly detection device based on knowledge graph |
CN115269879A (en) * | 2022-09-05 | 2022-11-01 | 北京百度网讯科技有限公司 | Knowledge structure data generation method, data search method and risk warning method |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112632132B (en) * | 2020-12-31 | 2024-04-12 | 中国农业银行股份有限公司 | Processing method, device and equipment for abnormal imported data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108038700A (en) * | 2017-12-22 | 2018-05-15 | 上海前隆信息科技有限公司 | A kind of anti-fraud data analysing method and system |
CN109033135A (en) * | 2018-06-06 | 2018-12-18 | 北京大学 | A kind of natural language querying method and system of software-oriented project knowledge map |
CN109064318A (en) * | 2018-08-24 | 2018-12-21 | 苏宁消费金融有限公司 | A kind of internet financial risks monitoring system of knowledge based map |
CN109064313A (en) * | 2018-07-20 | 2018-12-21 | 重庆富民银行股份有限公司 | Warning monitoring system after the loan of knowledge based graphical spectrum technology |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108280760A (en) * | 2018-01-25 | 2018-07-13 | 树根互联技术有限公司 | A kind of financial risks on-line monitoring method and apparatus |
CN108492173A (en) * | 2018-03-23 | 2018-09-04 | 上海氪信信息技术有限公司 | A kind of anti-Fraud Prediction method of credit card based on dual-mode network figure mining algorithm |
CN109002470A (en) * | 2018-06-12 | 2018-12-14 | 东方银谷(北京)投资管理有限公司 | Knowledge mapping construction method and device, client |
CN109491995A (en) * | 2018-12-25 | 2019-03-19 | 苏宁易购集团股份有限公司 | Knowledge based map inquires the method and system of financial abnormal data |
-
2018
- 2018-12-25 CN CN201811588282.6A patent/CN109491995A/en active Pending
-
2019
- 2019-09-18 CA CA3230500A patent/CA3230500A1/en active Pending
- 2019-09-18 CA CA3179620A patent/CA3179620A1/en active Pending
- 2019-09-18 WO PCT/CN2019/106503 patent/WO2020134213A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108038700A (en) * | 2017-12-22 | 2018-05-15 | 上海前隆信息科技有限公司 | A kind of anti-fraud data analysing method and system |
CN109033135A (en) * | 2018-06-06 | 2018-12-18 | 北京大学 | A kind of natural language querying method and system of software-oriented project knowledge map |
CN109064313A (en) * | 2018-07-20 | 2018-12-21 | 重庆富民银行股份有限公司 | Warning monitoring system after the loan of knowledge based graphical spectrum technology |
CN109064318A (en) * | 2018-08-24 | 2018-12-21 | 苏宁消费金融有限公司 | A kind of internet financial risks monitoring system of knowledge based map |
Non-Patent Citations (1)
Title |
---|
ERIC_XIE: "知识图谱在风控的应用", 《HTTP://WWW.WOSHIPM.COM/PD/1292806.HTML》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020134213A1 (en) * | 2018-12-25 | 2020-07-02 | 苏宁云计算有限公司 | Method and system for querying abnormal financial data on basis of knowledge map |
CN110321438A (en) * | 2019-06-14 | 2019-10-11 | 北京奇艺世纪科技有限公司 | Real-time fraud detection method, device and electronic equipment based on complex network |
CN110609905A (en) * | 2019-09-12 | 2019-12-24 | 深圳众赢维融科技有限公司 | Method and device for recognizing type of over-point and processing graph data |
CN110837538A (en) * | 2019-10-24 | 2020-02-25 | 北京中科捷信信息技术有限公司 | Financial knowledge map visual query and multidimensional analysis system |
TWI736233B (en) * | 2020-04-23 | 2021-08-11 | 兆豐國際商業銀行股份有限公司 | Pre-loan investigation system and pre-loan investigation method |
CN112686760A (en) * | 2021-01-20 | 2021-04-20 | 何青波 | Financial business processing method and platform based on big data |
CN113469697A (en) * | 2021-06-30 | 2021-10-01 | 重庆富民银行股份有限公司 | Unsupervised anomaly detection method and unsupervised anomaly detection device based on knowledge graph |
CN113469697B (en) * | 2021-06-30 | 2022-12-06 | 重庆富民银行股份有限公司 | Unsupervised anomaly detection method and unsupervised anomaly detection device based on knowledge graph |
CN115269879A (en) * | 2022-09-05 | 2022-11-01 | 北京百度网讯科技有限公司 | Knowledge structure data generation method, data search method and risk warning method |
Also Published As
Publication number | Publication date |
---|---|
WO2020134213A1 (en) | 2020-07-02 |
CA3179620A1 (en) | 2020-07-02 |
CA3230500A1 (en) | 2020-07-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109491995A (en) | Knowledge based map inquires the method and system of financial abnormal data | |
CN108520073A (en) | Air control data integration method, device, equipment and computer readable storage medium | |
Kopanas et al. | The role of domain knowledge in a large scale data mining project | |
US20090006315A1 (en) | Structured method for schema matching using multiple levels of ontologies | |
CN110162566A (en) | Association analysis method, device, computer equipment and the storage medium of business datum | |
CN107784517A (en) | A kind of customer information screening method and terminal device | |
CN106022708A (en) | Method for predicting employee resignation | |
US20060184995A1 (en) | Creating a privacy policy from a process model and verifying the compliance | |
CN115631039A (en) | Fund tracking method, device and equipment | |
CN107506412A (en) | A kind of product information screening matching system and method | |
CN111198969A (en) | Economic information consultation system and method based on network big data | |
CN107800894A (en) | A kind of phonetic prompt method and terminal device for telephony service system | |
CN110263155A (en) | The training method and system of data classification method, data classification model | |
KR101500294B1 (en) | Patent Analysis System and Method therefor and Computer Readable Recording Medium whereon Program therefor is Recorded | |
CN104699790B (en) | A kind of bank data relation establishing method and device | |
CN112396437A (en) | Trade contract verification method and device based on knowledge graph | |
CN109670933A (en) | Identify method, user equipment, storage medium and the device of user role | |
CN109408601B (en) | Data model conversion method based on graph data and graph data structure converter | |
CN110246033A (en) | Credit risk monitoring method, device, equipment and storage medium | |
CN107368500A (en) | Data pick-up method and system | |
CN112801784A (en) | Bit currency address mining method and device for digital currency exchange | |
Weiß et al. | A metamodel based perspective on the adaptation of a semantic business process modeling language to the financial sector | |
Becker et al. | Constructing a semantic business process modelling language for the banking sector-an evolutionary dyadic design science approach | |
CN110956445B (en) | Method and device for generating risk file | |
CN111368550A (en) | Public opinion information management system |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210729 Address after: Room 834, Yingying building, No.99, Tuanjie Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu Province Applicant after: Nanjing Xingyun Digital Technology Co.,Ltd. Address before: 210000, 1-5 story, Jinshan building, 8 Shanxi Road, Nanjing, Jiangsu. Applicant before: SUNING.COM Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |
|
RJ01 | Rejection of invention patent application after publication |