CN110390526A - A kind of network trading analysis method and system - Google Patents
A kind of network trading analysis method and system Download PDFInfo
- Publication number
- CN110390526A CN110390526A CN201810347857.9A CN201810347857A CN110390526A CN 110390526 A CN110390526 A CN 110390526A CN 201810347857 A CN201810347857 A CN 201810347857A CN 110390526 A CN110390526 A CN 110390526A
- Authority
- CN
- China
- Prior art keywords
- transaction
- credible
- confidence levels
- sample data
- sample
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 42
- 230000008569 process Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012954 risk control Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
Abstract
The invention discloses a kind of network trading analysis method and system, under the premise of not being obviously improved leakage and killing rate, the intercepted transaction in part is let off, and then reduce and manslaughter, promote user experience.The network trading analysis method, comprising: collecting sample data establish sample database；The sample data includes the case data of arm's length dealing data and abnormal exchanges；According to the transaction index that the sample data records, confidence levels division is carried out to transaction, constructs trust model；The real-time deal information that system is intercepted, inputs in the trust model, calculates whether the real-time deal belongs to high confidence levels, if belonging to, trade；If being not belonging to, transaction interception is carried out.
Description
Technical field
The invention belongs to big data technical field of risk control, it particularly relates to a kind of network trading analysis method and
System.
Background technique
With the fast development that internet is done shopping, more and more offenders pay close attention to Third-party payment platform.Crime point
Son is sought loopholes using some loopholes of platform, is stolen platform account, is stolen platform user fund etc., very big damage is brought to client
It loses.With the growth and growth of Third-party payment platform, the high loyal client of part high quality can be cultivated, but is similarly had big
Measure the behavior of fraud.Although Third-party payment platform availability risk intercepting system can effectively intercept abnormal transaction, protection client is closed
Method property safety, but inevitably also stop many arm's length dealings, affect certain customers' experience.How normal friendship is reduced
Easily intercepted probability improves user experience, is the technical problem that those skilled in the art face.
Summary of the invention
The embodiment of the present invention provides a kind of network trading analysis method and system, in the premise for not being obviously improved leakage and killing rate
Under, the intercepted transaction in part is let off, and then reduce and manslaughter, promotes user experience.
In order to solve the above technical problems, the embodiment of the present invention uses following technical scheme:
In a first aspect, the embodiment of the present invention provides a kind of network trading analysis method, which comprises
Collecting sample data, establish sample database；The sample data includes arm's length dealing data and abnormal exchanges
Case data；According to the transaction index that the sample data records, confidence levels division is carried out to transaction, constructs credible mould
Type；
The real-time deal information that system is intercepted, inputs in the trust model, calculates whether the real-time deal belongs to
High confidence levels are traded if belonging to；If being not belonging to, transaction interception is carried out.
With reference to first aspect, as the first achievable scheme, the transaction according to sample data record refers to
Mark carries out confidence levels division to transaction, constructs trust model, comprising:
Credible element of transaction is screened from the transaction index that the sample data records；
According to correlation rule, the credible indexes of the credible element of transaction are calculated；The credible indexes include support, set
Reliability and promotion degree；
According to the credible indexes, confidence levels division will be carried out comprising the transaction of the credible element of transaction, building can
Believe model；Confidence levels include high confidence levels.
The achievable scheme of with reference to first aspect the first, as second of achievable scheme, described in the calculating
The credible indexes of credible element of transaction, comprising:
To the credible element of transaction according to combining form, credible indexes are calculated.
The achievable scheme of with reference to first aspect the first, as the third achievable scheme, described in the calculating
The support process of credible element of transaction are as follows:
If credible element of transaction is m, m is the integer more than or equal to 1；
If in sample database simultaneously including m credible element of transaction, the key element in element of transaction credible for one
Arm's length dealing quantity be S '；
If the transaction amount amount in sample database is S；
Support W1=S '/S.
The third achievable scheme with reference to first aspect, as the 4th kind of achievable scheme, described in the calculating
The confidence process of credible element of transaction are as follows:
If the number of transaction simultaneously containing the key element in m credible element of transaction in sample database is S1；
Confidence level W2=S '/S1。
The 4th kind of achievable scheme with reference to first aspect, as the 5th kind of achievable scheme, described in the calculating
Journey is spent in the promotion of credible element of transaction are as follows:
If arm's length dealing amount is N, promotion degree W3=W2/ (N/S) in sample database.
Second aspect, the embodiment of the present invention provide a kind of network trading analysis system, comprising:
Construction part module: collecting sample data are used for, sample database is established；Referred to according to the transaction that the sample data records
Mark carries out confidence levels division to transaction, constructs trust model；
Trust model: the real-time deal information for being intercepted to system, calculate the real-time deal whether belong to it is high credible
Rank is traded if belonging to；If being not belonging to, transaction interception is carried out.
In conjunction with second aspect, as the first achievable scheme, the construction part module, comprising:
Acquisition unit: collecting sample data are used for, sample database is established；The sample data includes arm's length dealing data
With the case data of abnormal exchanges；
Screening unit: for screening credible element of transaction from the transaction index that the sample data records；
Computing unit: for calculating the credible indexes of the credible element of transaction according to correlation rule；The credible indexes
Including support, confidence level and promotion degree；
Division unit: for according to the credible indexes, credible element of transaction to be carried out confidence levels division, confidence levels
Including high confidence levels.
The first achievable scheme in conjunction with second aspect, as second of achievable scheme, the computing unit: tool
Body is used to calculate credible indexes according to combining form to the credible element of transaction.
The first achievable scheme in conjunction with second aspect, as the third achievable scheme, the computing unit: tool
Body is used to calculate support according to following methods:
If credible element of transaction is m, m is the integer more than or equal to 1；
If in sample database simultaneously including m credible element of transaction, the key element in element of transaction credible for one
Arm's length dealing quantity be S '；
If the transaction amount amount in sample database is S；
Support W1=S '/S.
The first achievable scheme in conjunction with second aspect, as the 4th kind of achievable scheme, the computing unit: tool
Body is used to calculate confidence level according to following methods:
If the number of transaction simultaneously containing the key element in m credible element of transaction in sample database is S1；
Confidence level W2=S '/S1。
The first achievable scheme in conjunction with second aspect, as the 5th kind of achievable scheme, the computing unit: tool
Body is used to calculate promotion degree according to following methods:
If arm's length dealing amount is N, promotion degree W3=W2/ (N/S) in sample database.
Compared with prior art, the network trading analysis method and system of the embodiment of the present invention, is killed not being obviously improved leakage
Under the premise of rate, the intercepted transaction in part is let off, and then reduce and manslaughter, promote user experience.The method of the embodiment
In, firstly, carrying out confidence levels division according to the transaction index that sample data records to transaction, constructing trust model；Then,
The real-time deal information that system is intercepted, inputs in the trust model, calculates whether the real-time deal belongs to high credible grade
Not, it if belonging to, trades；If being not belonging to, transaction interception is carried out.This method carries out the real-time deal intercepted by system
Judgement, if belong to the transaction of high confidence levels, if belonged to, allow to trade.This method can be greatly reduced normally
The probability that transaction is accidentally blocked by risk system reduces the rate of bothering to client, and reduction is manslaughtered, and promotes air control accuracy rate, to mention
Rise user experience.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is system architecture schematic diagram provided in an embodiment of the present invention；
Fig. 2 is method flow block diagram provided in an embodiment of the present invention；
Fig. 3 is the flow diagram of step 10) in the method for the embodiment of the present invention；
Fig. 4 is the transaction index exemplary diagram generated in whole network transaction flow；
Fig. 5 is in the embodiment of the present invention, and transaction level divides exemplary diagram；
Fig. 6 is the structural block diagram of specific example provided in an embodiment of the present invention.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, with reference to the accompanying drawing and specific embodiment party
Present invention is further described in detail for formula.Embodiments of the present invention are described in more detail below, the embodiment is shown
Example is shown in the accompanying drawings, and in which the same or similar labels are throughly indicated same or similar element or has identical or class
Like the element of function.It is exemplary below with reference to the embodiment of attached drawing description, for explaining only the invention, and cannot
It is construed to limitation of the present invention.Those skilled in the art of the present technique are appreciated that unless expressly stated, odd number shape used herein
Formula " one ", "one", " described " and "the" may also comprise plural form.It is to be further understood that specification of the invention
Used in wording " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that
In the presence of or add other one or more features, integer, step, operation, element, component and/or their group.It should be understood that
When we say that an element is " connected " or " coupled " to another element, it can be directly connected or coupled to other elements, or
There may also be intermediary elements.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Here make
Wording "and/or" includes one or more associated any cells for listing item and all combinations.The art
Technical staff is appreciated that unless otherwise defined all terms (including technical terms and scientific terms) used herein have
Meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.It should also be understood that such as general
Those terms, which should be understood that, defined in dictionary has a meaning that is consistent with the meaning in the context of the prior art, and
Unless defined as here, it will not be explained in an idealized or overly formal meaning.
Risk control system is typically provided in existing network platform transaction.The risk control system carries out suspicious transaction
It intercepts.Although the system can intercept abnormal transaction, part arm's length dealing is also intercepted.Knot of the embodiment of the present invention
Big data and related analysis technology are closed, is traded according to existing arm's length dealing and case, is weighed according to the relevant informational element of transaction
Amount gives the confidence level of transaction.Transaction credible for the height intercepted by system is let pass.
The embodiment of the present invention may be implemented in a kind of system as shown in Figure 1.The system includes user terminal, trades and put down
Platform, trust model, trading information data library.
User terminal is specifically as follows an independent system, or is integrated in a variety of different medium data playing systems,
Such as smart phone, tablet computer (Tablet Personal Computer), laptop computer (Laptop Computer) or
Person's personal digital assistant (personal digital assistant, abbreviation PDA) etc..Installation can be passed through on user terminal
Application program (such as browser) or APP, by the webpage of user terminal access, specifically can be to load and show webpage
The page that operation system (such as online shopping platform, promotion website, financial marketing platform etc.) is shown to user, these pages can be by
The server system operation for running operation system, can also be run, i.e., the described server apparatus by the server apparatus in system
It can integrate in the server system of operation operation system.
Transaction platform can be individual server apparatus, such as: rack, blade, tower or cabinet-type service
Device equipment can also have stronger computing capability hardware device using work station, mainframe computer etc.；It is also possible to by multiple clothes
The server cluster of device equipment of being engaged in composition.Transaction platform is for carrying out network trading.
Trust model can be individual server apparatus, also can integrate in the server system of transaction platform.It can
Letter model is for judging intercepted real-time deal, if belongs to high confidence levels.
Trading information data library is for storing and managing historical trading data.Database Systems, which specifically can be, to be individually made
, the server apparatus of management, storage for data is also possible to the server cluster being made of multiple server apparatus.
The database that corresponding server equipment is run on the hardware device of Database Systems, for manage simultaneously storage server equipment
Data.Common network database (Network Database), relational database (Relational can specifically be used
Database), tree shaped data library (Hierarchical Database), object-oriented database (Object-oriented
) and big data system architecture of new generation Database.
In above system, trust model is according to the historical trading data in trading information data library, component model, and to quilt
The transaction that transaction platform intercepts is judged, if belongs to high credible transaction.
A kind of network trading analysis method of the embodiment of the present invention, as shown in Figure 2, comprising:
S10 collecting sample data, establish sample database；The sample data includes arm's length dealing data and improper friendship
Easy case data；According to the transaction index that the sample data records, confidence levels division is carried out to transaction, constructs credible mould
Type；
The real-time deal information that S20 intercepts system, inputs in the trust model, calculates whether the real-time deal belongs to
In high confidence levels, if belonging to, trade；If being not belonging to, transaction interception is carried out.
The method of above-described embodiment, the real-time deal information intercept to system and not all interception, forbid trading.This method
By being analyzed to intercepted real-time deal information, judge whether the real-time deal information belongs to high confidence levels.As belonged to
It in high confidence levels, then abandons intercepting, allows to trade.High confidence levels are such as not belonging to, then carry out transaction interception.Above-mentioned side
Method analyzes the real-time deal information intercepted by system again, and based on the analysis results, to the reality for belonging to high confidence levels
When trade, no longer intercept, allow to trade.This is conducive to the progress for ensuring arm's length dealing, promotes user experience.
In step S10, sample data includes the case data of arm's length dealing data and abnormal exchanges.Split data into two
Class, one kind are arm's length dealing data, and another kind of is abnormal exchanges data.Abnormal exchanges data are as case data.This two
Class data can be internally sourced, can also be from outside.Two class data of acquisition are added in database.In addition, sample data
It is renewable, to improve the precision of trust model analysis.For example, after real-time deal, either arm's length dealing, also right and wrong
The secondary transaction data can be all stored in sample data by arm's length dealing.
Information data source in sample data is including but not limited to following data source: order details, payment are detailed
Thin information, shipping address information, device-fingerprint information, the registration information of transaction agent.
The method of above-described embodiment analyzes the real-time deal information intercepted by system by building trust model.
As preference, as shown in figure 3, the building trust model, comprising:
S101 screens credible element of transaction from the transaction index that the sample data records.
In step S101, credible element of transaction is the most transaction of user identifier in the transaction index of system record
Index.With the development of technology, while a transaction occurs, transaction system will record many transaction indexs.Such as Fig. 4 institute
Show, the issuable transaction index example in whole network transaction flow.As preference, by address, cell-phone number, identity card
Number, bank's card number, IP address, wifimac, device number, mailbox be as credible element of transaction.It, can constructing as technology develops
When believing model, the credible element of transaction of use can change.
S102 calculates the credible indexes of the credible element of transaction according to correlation rule.
After determining credible element of transaction, according to correlation rule, to independent credible element of transaction and the credible friendship of combination
Easy element calculates separately its credible indexes.Credible indexes include support, confidence level and promotion degree.Preferably, to described credible
Element of transaction calculates credible indexes according to combining form.The use of the highest trust data of integration factor is better than independent element
It uses.Integration factor can mutually support that reduction is manslaughtered between each other, promote air control and intercept accuracy rate, utmostly to promote use
Family experience.
Preferably, the method for support is calculated are as follows:
If credible element of transaction is m, m is the integer more than or equal to 1.If credible comprising m simultaneously in sample database
Element of transaction, the arm's length dealing quantity of the key element in element of transaction credible for one are S '；If the friendship in sample database
Easy total quantity is S；Support W1=S '/S.When m is 1, indicate that credible element of transaction is one.When m is greater than 1, expression can
Believe that element of transaction is multiple.Element is the element for the embodiment user characteristics attribute that can be collected into process of exchange.Key element is
The element of user characteristics attribute can be embodied, such as device number, the address ip, cell-phone number for trading etc..
Preferably, the method for confidence level is calculated are as follows:
If the number of transaction simultaneously containing the key element in m credible element of transaction in sample database is S1；Confidence
Spend W2=S '/S1。
Preferably, the method for promotion degree is calculated are as follows:
If arm's length dealing amount is N in sample database；Promotion degree W3=W2/ (N/S).
Below as one example, illustrate the calculating process of support, confidence level and promotion degree.
If cell-phone number A has traded 8 times, a case.Address B trades 12 times, a case.Mobile phone A+address B goes out simultaneously
It is 6 times existing, without case.If total number of transactions number is 20 in database, arm's length dealing quantity is 18.
(1) using address B and mobile phone A as credible element of transaction, i.e., integration factor is as credible element of transaction:
Support W1=6/20=0.3
Confidence level W2=6/6=1
Promotion degree W3=1/ (18/20)=1.11
(2) using mobile phone A as credible element of transaction, i.e., single element is as credible element of transaction:
Support W1=7/20=0.35
Confidence level W2=7/8=0.875
Promotion degree W3=0.875/0.9=0.972.
It is 0.1 that confidence threshold, which is arranged, otherwise it is low confidence that being greater than threshold value, which is high confidence level,.Promotion degree threshold value is 1, greatly
It is high promotion degree in threshold value, is otherwise low promotion degree.Support is sorted according to sixteen threshold values by height on earth, and preceding 5% is height,
It is low lower than 20% in 5%-20%.
It to sum up, is high confidence level, high promotion degree using address B and mobile phone A as the transaction of credible element of transaction.If branch
Degree of holding enters preceding 5%, then the transaction belongs to high confidence levels, allows to trade.Using mobile phone A as the transaction of credible element of transaction,
For high confidence level, low promotion degree.Even if the support of the transaction enters preceding 5%, then the transaction is also not belonging to high confidence levels, hands over
It is easily intercepted.
It, can be more acurrate from examples detailed above as can be seen that the multiple credible element of transaction of combination carry out the calculating of credible indexes
The risk for reflecting transaction prevents transaction from being intercepted by mistake.
S103 will carry out confidence levels division comprising the transaction of the credible element of transaction according to the credible indexes, can
Believe that rank includes high confidence levels.
By credible indexes, transaction is divided into several ranks.The rank includes high confidence levels.When credible element of transaction
Corresponding transaction belongs to high confidence levels, then system allows the transaction to carry out.As preference, as shown in figure 5, transaction is divided into
Five ranks, respectively high insincere rank, low insincere rank, low confidence levels, middle confidence levels and high confidence levels.Tool
For body, transaction is divided by four classes according to promotion degree and confidence level, then segment by support:
The low promotion of low confidence: case rate is higher, can be set as high-risk list；
The high low promotion of confidence and low confidence height are promoted: being had arm's length dealing also to have case, be can be considered gray list；
High confidence height is promoted: the partial amount is larger, and case did not occurred, for such transaction, then will by support
The transaction of this classification is divided into three classes according to high support, middle support and low support.
The confidence level of classification is respectively as follows: from high to low
50 points: high confidence level+height promotion degree+high support；
40 points: high confidence level+height promotion degree+middle support；
30 points: high confidence level+height promotion degree+low support；
20 points: high confidence level+low promotion degree and low confidence+height promotion degree；
10 points: low confidence+low promotion degree；
For the metric form of credible element of transaction, the judgment criteria of credible element of transaction can be freely configured, is freely arranged
Metric threshold.Confidence level, promotion degree and support are to be carried out dividing according to the threshold value of setting belonging to high-level or low level.
High insincere rank corresponds to score value 10, and low insincere rank corresponds to score value 20, and low confidence levels correspond to score value 30, middle confidence levels
Corresponding score value 40, high confidence levels correspond to score value 50.
Currently, the mistake of normal account can be brought to intercept using air control means while intercepting high-risk account trading.For
The interception to normal account trading is reduced, by carrying out the association analysis of case to particular transaction element, credible transaction wanted
Element is divided into several major class, no longer intercepts to high believable transaction is belonged to, allowing to trade goes on smoothly, to reduce the mistake of arm's length dealing
It intercepts.
In the method for above-described embodiment, big data and related analysis technology are combined, related analysis technology is applied to wind
Dangerous control field.The method of above-described embodiment helps to reduce and manslaughter, subtract for analyzing the transaction intercepted by system
It is few that the use of normal users is bothered, and the workload of risk auditor can be reduced, improve the accuracy that risk intercepts.
The balancing method of transaction confidence level is to comprehensively consider most representative credible element of transaction under payment whole scene, meter
Calculate support, promotion degree and the confidence level of credible element of transaction.Single dimension element and integration factor are judged, will most may be used
The part of letter is as the foundation for reducing mistake interception.
This method will bring following technical effect to transaction risk control: available a variety of most user identifiers
Credible element of transaction can be combined with each other into more effective integration factor between credible element of transaction.Single dimension element with
Integration factor all may act on actual production.Integration factor also avoids the one-sidedness of single element, can utmostly identify and be missed
The arm's length dealing killed.In addition, calculating separately single element of transaction can recognize with the confidence level of element of transaction, confidence level the pick of is combined
For low-risk client, then accidentally blocked when, is let off, and is bothered with reducing arm's length dealing, is promoted user experience.
As shown in fig. 6, the embodiment of the present invention also provides a kind of network trading analysis system, comprising:
Construction part module: collecting sample data are used for, sample database is established；The sample data includes arm's length dealing data
With the case data of abnormal exchanges；According to the transaction index that the sample data records, confidence levels division is carried out to transaction,
Construct trust model.
Trust model: the real-time deal information for being intercepted to system, calculate the real-time deal whether belong to it is high credible
Rank is traded if belonging to；If being not belonging to, transaction interception is carried out.
The system of above-described embodiment forbids trading to intercepted real-time deal information and not all interception.The system is logical
Trust model is crossed to intercepted real-time deal information, is analyzed, judges whether the real-time deal information belongs to high credible grade
Not.Such as belong to high confidence levels, then abandon intercepting, allows to trade.High confidence levels are such as not belonging to, then carries out transaction and blocks
It cuts.This is conducive to the progress for ensuring arm's length dealing, promotes user experience.
As preference, the building module, comprising:
Acquisition unit: collecting sample data are used for, sample database is established；The sample data includes arm's length dealing data
With the case data of abnormal exchanges；
Screening unit: for screening credible element of transaction from the transaction index that the sample data records；
Computing unit: for calculating the credible indexes of the credible element of transaction according to correlation rule；The credible indexes
Including support, confidence level and promotion degree；
Division unit: for according to the credible indexes, credible element of transaction to be carried out confidence levels division, confidence levels
Including high confidence levels.
Preferably, computing unit calculates credible indexes to the credible element of transaction according to combining form.It is multiple credible
Element of transaction combines, and carries out the calculating of credible indexes, more accurately can carry out partition of the level for transaction.
In above-mentioned computing unit, support, confidence level and promotion degree are calculated according to following methods:
If credible element of transaction is m, m is the integer more than or equal to 1；Simultaneously comprising m credible friendships in sample database
Easy element, the arm's length dealing quantity of the key element in element of transaction credible for one are S '；If containing simultaneously in sample database
The number of transaction for having the key element in m credible element of transaction is S1；If the transaction amount amount in sample database is S；If
Arm's length dealing amount is N in sample database.
Support W1=S '/S.Confidence level W2=S '/S1.Promotion degree W3=W2/ (N/S).
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for equipment reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.
Those skilled in the art should know, realize the method or system of above-described embodiment, can pass through computer journey
Sequence instructs to realize.The computer program instructions are loaded into programmable data processing device, such as computer, thus that can compile
Corresponding instruction is executed on journey data processing equipment, for realizing the function of method or the system realization of above-described embodiment.
Those skilled in the art can carry out non-creative technological improvement according to above-described embodiment to the application, without
It is detached from Spirit Essence of the invention.These improvement still should be regarded as within the protection scope of the claim of this application.
Claims (12)
1. a kind of network trading analysis method, which is characterized in that the described method includes:
Collecting sample data, establish sample database；The sample data includes the case of arm's length dealing data and abnormal exchanges
Number of packages evidence；According to the transaction index that the sample data records, confidence levels division is carried out to transaction, constructs trust model；
By system intercept real-time deal information, input in the trust model, calculate the real-time deal whether belong to height can
Letter rank is traded if belonging to；If being not belonging to, transaction interception is carried out.
2. according to the method for claim 1, which is characterized in that the transaction index recorded according to the sample data,
Confidence levels division is carried out to transaction, constructs trust model, comprising:
Credible element of transaction is screened from the transaction index that the sample data records；
According to correlation rule, the credible indexes of the credible element of transaction are calculated；The credible indexes include support, confidence level
With promotion degree；
According to the credible indexes, confidence levels division will be carried out comprising the transaction of the credible element of transaction, construct credible mould
Type；Confidence levels include high confidence levels.
3. according to the method for claim 2, which is characterized in that the credible indexes for calculating the credible element of transaction,
Include:
To the credible element of transaction according to combining form, credible indexes are calculated.
4. according to the method for claim 2, which is characterized in that the support process for calculating the credible element of transaction
Are as follows:
If credible element of transaction is m, m is the integer more than or equal to 1；
If in sample database simultaneously including m credible element of transaction, the key element in element of transaction credible for one is just
Normal number of transaction is S '；
If the transaction amount amount in sample database is S；
Support W1=S '/S.
5. according to the method for claim 4, which is characterized in that the confidence process for calculating the credible element of transaction
Are as follows:
If the number of transaction simultaneously containing the key element in m credible element of transaction in sample database is S1；
Confidence level W2=S '/S1。
6. according to the method for claim 5, which is characterized in that journey is spent in the promotion for calculating the credible element of transaction
Are as follows:
If arm's length dealing amount is N, promotion degree W3=W2/ (N/S) in sample database.
7. a kind of network trading analysis system characterized by comprising
Construction part module: collecting sample data are used for, sample database is established；According to the sample data record transaction index,
Confidence levels division is carried out to transaction, constructs trust model；
Trust model: the real-time deal information for intercepting to system calculates whether the real-time deal belongs to high confidence levels,
If belonging to, trade；If being not belonging to, transaction interception is carried out.
8. system according to claim 7, which is characterized in that the construction part module, comprising:
Acquisition unit: collecting sample data are used for, sample database is established；The sample data includes arm's length dealing data and non-
The case data of arm's length dealing；
Screening unit: for screening credible element of transaction from the transaction index that the sample data records；
Computing unit: for calculating the credible indexes of the credible element of transaction according to correlation rule；The credible indexes include
Support, confidence level and promotion degree；
Division unit: for credible element of transaction being carried out confidence levels division, confidence levels include according to the credible indexes
High confidence levels.
9. system according to claim 8, which is characterized in that the computing unit: being specifically used for the credible transaction
Element calculates credible indexes according to combining form.
10. system according to claim 8, which is characterized in that the computing unit: being specifically used for according to following methods meter
Calculate support:
If credible element of transaction is m, m is the integer more than or equal to 1；
If in sample database simultaneously including m credible element of transaction, the key element in element of transaction credible for one is just
Normal number of transaction is S '；
If the transaction amount amount in sample database is S；
Support W1=S '/S.
11. system according to claim 8, which is characterized in that the computing unit: being specifically used for according to following methods meter
Calculate confidence level:
If the number of transaction simultaneously containing the key element in m credible element of transaction in sample database is S1；
Confidence level W2=S '/S1。
12. system according to claim 8, which is characterized in that the computing unit: being specifically used for according to following methods meter
Calculate promotion degree:
If arm's length dealing amount is N, promotion degree W3=W2/ (N/S) in sample database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810347857.9A CN110390526A (en) | 2018-04-18 | 2018-04-18 | A kind of network trading analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810347857.9A CN110390526A (en) | 2018-04-18 | 2018-04-18 | A kind of network trading analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110390526A true CN110390526A (en) | 2019-10-29 |
Family
ID=68282590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810347857.9A Pending CN110390526A (en) | 2018-04-18 | 2018-04-18 | A kind of network trading analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110390526A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164474A (en) * | 2011-12-15 | 2013-06-19 | 中国移动通信集团贵州有限公司 | Method for analyzing data service |
| CN105279691A (en) * | 2014-07-25 | 2016-01-27 | 中国银联股份有限公司 | Financial transaction detection method and equipment based on random forest model |
| CN105512781A (en) * | 2014-09-26 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Transaction processing method and transaction processing device |
| CN105976242A (en) * | 2016-04-21 | 2016-09-28 | 中国农业银行股份有限公司 | Transaction fraud detection method and system based on real-time streaming data analysis |
| CN107767138A (en) * | 2017-10-20 | 2018-03-06 | 杭州呯嘭智能技术有限公司 | On-line payment is counter to cheat method and system |
| CN108537671A (en) * | 2018-04-27 | 2018-09-14 | 广州品唯软件有限公司 | A kind of transaction risk appraisal procedure and system |
| CN109544163A (en) * | 2018-11-30 | 2019-03-29 | 华青融天(北京)软件股份有限公司 | A kind of risk control method, device, equipment and the medium of user's payment behavior |
-
2018
- 2018-04-18 CN CN201810347857.9A patent/CN110390526A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164474A (en) * | 2011-12-15 | 2013-06-19 | 中国移动通信集团贵州有限公司 | Method for analyzing data service |
| CN105279691A (en) * | 2014-07-25 | 2016-01-27 | 中国银联股份有限公司 | Financial transaction detection method and equipment based on random forest model |
| CN105512781A (en) * | 2014-09-26 | 2016-04-20 | 阿里巴巴集团控股有限公司 | Transaction processing method and transaction processing device |
| CN105976242A (en) * | 2016-04-21 | 2016-09-28 | 中国农业银行股份有限公司 | Transaction fraud detection method and system based on real-time streaming data analysis |
| CN107767138A (en) * | 2017-10-20 | 2018-03-06 | 杭州呯嘭智能技术有限公司 | On-line payment is counter to cheat method and system |
| CN108537671A (en) * | 2018-04-27 | 2018-09-14 | 广州品唯软件有限公司 | A kind of transaction risk appraisal procedure and system |
| CN109544163A (en) * | 2018-11-30 | 2019-03-29 | 华青融天(北京)软件股份有限公司 | A kind of risk control method, device, equipment and the medium of user's payment behavior |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210174440A1 (en) | Providing virtual markers based upon network connectivity | |
| US20210232608A1 (en) | Trust scores and/or competence ratings of any entity | |
| US11023963B2 (en) | Detection of compromise of merchants, ATMs, and networks | |
| US10467631B2 (en) | Ranking and tracking suspicious procurement entities | |
| EP3125186A1 (en) | Systems and user interfaces for holistic, data-driven investigation of bad actor behavior based on clustering and scoring of related data | |
| US20190087821A1 (en) | Hierarchical profiling inputs and self-adaptive fraud detection system | |
| US20210287303A9 (en) | Scoring trustworthiness, competence, and/or compatibility of any entity for activities including recruiting or hiring decisions, composing a team, insurance underwriting, credit decisions, or shortening or improving sales cycles | |
| CN106033575A (en) | Risk account identification method and apparatus | |
| CN109213857A (en) | A kind of fraud recognition methods and device | |
| CN109313541A (en) | For showing and the user interface of comparison attacks telemetering resource | |
| Salau et al. | Data cooperatives for neighborhood watch | |
| CN111598713A (en) | Cluster recognition method and device based on similarity weight updating and electronic equipment | |
| KR102042442B1 (en) | Regtech platform apparatus for digital compliance and risk management, method for risk management of financial transactions and computer program for the same | |
| Zhang | Risk assessment of supply chain finance with intuitionistic fuzzy information | |
| US20220164874A1 (en) | Privacy Separated Credit Scoring System | |
| Mou et al. | Microlending on mobile social credit platforms: an exploratory study using Philippine loan contracts | |
| US20180365687A1 (en) | Fraud detection | |
| CN110428240A (en) | The suspicious transaction automatic identification of one kind and processing method, terminal and server | |
| CA3033793C (en) | Scoring trustworthiness, competence, and/or compatibility of any entity for activities including recruiting or hiring decisions, skip tracing, insurance underwriting, credit decisions, or shortening or improving sales cycles | |
| CN206497498U (en) | A kind of integrated system of credit rating information data based on enterprise's reference business | |
| US20210357942A1 (en) | Method and apparatus for identifying risky vertices | |
| Chatterjee et al. | Next Generation Financial Services: Role of Blockchain enabled Federated Learning and Metaverse | |
| CN110390526A (en) | A kind of network trading analysis method and system | |
| KR20200112622A (en) | Regtech platform apparatus for digital compliance and risk management, method for risk management of financial transactions and computer program for the same | |
| Shirazi et al. | A New Model for Information Security Risk Management |
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: 20210730 Address after: Room 834, Yingying building, 99 Tuanjie Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu 210000 Applicant after: Nanjing Xingyun Digital Technology Co.,Ltd. Address before: 210042 Suning Headquarters, No. 1 Suning Avenue, Xuanwu District, Nanjing City, Jiangsu Province Applicant before: SUNING.COM Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191029 |
|
| RJ01 | Rejection of invention patent application after publication |