CN105931068A - Cardholder consumption figure generation method and device - Google Patents
Cardholder consumption figure generation method and device Download PDFInfo
- Publication number
- CN105931068A CN105931068A CN201511025848.0A CN201511025848A CN105931068A CN 105931068 A CN105931068 A CN 105931068A CN 201511025848 A CN201511025848 A CN 201511025848A CN 105931068 A CN105931068 A CN 105931068A
- Authority
- CN
- China
- Prior art keywords
- consumption
- information
- holder
- effective
- consumption information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cardholder consumption figure generation method and device. The method includes acquiring the consumption information, including cardholder attribute information and bank card transaction information, of a cardholder; performing data cleaning of cardholder consumption information to obtain effective cardholder consumption information to be analyzed; performing cluster analysis on the effective cardholder consumption information based on the cardholder attribute information to obtain an effective consumption information set for each cardholder; determining the consumption types corresponding to the transaction information of each bankcard for each cardholder; dividing the effective consumption information set for each cardholder into effective consumption information subsets corresponding to different consumption types based on the consumption types corresponding to the transaction information of each bankcard; and determining the consumption figure of the cardholder based on the effective consumption information subsets to solve the problem that the analysis result is not comprehensive enough and inaccurate in the prior art.
Description
Technical field
The present invention relates to areas of information technology, particularly relate to a kind of holder and consume generation method and the dress of portrait
Put.
Background technology
In the case of commodity market competition, various trade companies platform is all making great efforts the various marketing of release
Strategy, the formulation of marketing strategy then depends on the mining analysis for mass data.
Traditional Marketing strategy first has to analyze the consuming behavior feature of the consumer group, such as pin in formulation process
The analysis result of consumption under consumer group's line is found, and most target customer belongs to youngster, and consumption energy
Power is higher, then can adjust marketing strategy for this situation, throws in advertisement to target customer, or increases
The consumer goods of target customer.But the method for consuming behavior feature simply letter under the line of the present analysis consumer group
Single statistics holder, at the turnover of all kinds of trade companies, stroke count of concluding the business, the most deeply excavates these transaction
Data, in turn result in the consuming behavior to holder and analyze the most accurately.
The hobby of such as consumer, merchant information etc., therefore cannot accurately draw about holder
The pass of the reflection consumption portrait such as humanized feature, weather, financial situation, hobby, daily habits
Key factor, in turn results in the analysis result of behavior characteristics of consumer not comprehensively accurately, reduces marketing
Successful.
To sum up, prior art needs a kind of method that holder's consuming behavior is accurately analyzed by lifting badly.
Summary of the invention
The embodiment of the present invention provides a kind of generation method and device consuming portrait, in order to solve in prior art
There is analysis result problem the most comprehensively and accurately.
The inventive method includes that a kind of holder consumes the generation method of portrait, and the method includes: obtains and holds
People's consumption information, described holder's consumption information includes holder's attribute information and bank card business dealing information;Will
Described holder's consumption information carries out data cleansing, obtains effective holder's consumption information to be analyzed;According to
Described holder's attribute information carries out cluster analysis to described effective holder's consumption information, obtains for each
Effective consumption information set of holder;For a holder, according to described effective holder's consumption information
In the inside merchant information of each bank card business dealing information and outside merchant information in external website, determine
The consumption type that each bank card business dealing information is corresponding;According to described each corresponding disappearing of bank card business dealing information
Take type, the consumption information set of described effective holder is divided into the consumption letter of corresponding different consumption type
Breath subclass;According to described consumption information subclass, determine the consumption portrait of described holder.
Based on same inventive concept, the embodiment of the present invention provides a kind of holder to consume portrait further
Generating means, this device includes: acquiring unit, is used for obtaining holder's consumption information, and described holder disappears
Charge information includes holder's attribute information and bank card business dealing information;Data cleansing unit, for holding described
Card people's consumption information carries out data cleansing, obtains effective holder's consumption information to be analyzed;Cluster analysis list
Unit, for dividing the carrying out cluster in described effective holder's consumption information according to described holder's attribute information
Analysis, obtains the effective consumption information set for each holder;Determine consumption type unit, for for
One holder, according to each bank card business dealing information in effective consumption information set of described holder
Outside merchant information in internal merchant information and external website, determines that each bank card business dealing information is corresponding
Consumption type;Division unit, for the consumption type corresponding according to described each bank card business dealing information, will
Effective consumption information set of described holder is divided into effective consumption information subset of corresponding different consumption type
Close;Determine consumption portrait unit, for according to described effective consumption information subclass, determine described holder
Consumption portrait.
On the one hand the embodiment of the present invention obtains the holder's consumption information in bank card adapting system, and complete right
The data cleansing of this part holder's consumption information, filters abnormal datas such as violation trade company, fraudulent tradings,
And then ensure that the accuracy of data source;On the other hand, the embodiment of the present invention is by bank card adapting system
Merchant information in holder's consumption information and outside merchant website is combined, by merchant information outside inside
Combination, in each bank card business dealing information subdivision to different consumption types, form several correspondences not
With effective consumption information subclass of consumption type, based on the analysis to effective consumption information subclass, finally
Draw the consumption portrait of holder.Visible, the embodiment of the present invention is through data cleansing, inside and outside information trade company
Information integration process, it is ensured that form the accurately completely feature that holder consumes the data source of portrait, make
The consumption portrait of the consumer that must eventually form is more accurate, the beneficially formulation of marketing strategy.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, institute in embodiment being described below
The accompanying drawing used is needed to briefly introduce, it should be apparent that, the accompanying drawing in describing below is only the present invention's
Some embodiments, from the point of view of those of ordinary skill in the art, in the premise not paying creative work
Under, it is also possible to other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 provides a kind of holder to consume the generation method flow schematic diagram of portrait for the embodiment of the present invention;
Fig. 2 provides a kind of holder to consume the generation step figure of portrait for the embodiment of the present invention;
Fig. 3 provides one to hold merchant information sorting technique for the embodiment of the present invention;
Fig. 4 provides a kind of holder to consume the generating means configuration diagram of portrait for the embodiment of the present invention.
Detailed description of the invention
In order to make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to this
Bright it is described in further detail, it is clear that described embodiment is only some embodiments of the present invention,
Rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not doing
Go out all other embodiments obtained under creative work premise, broadly fall into the scope of protection of the invention.
Shown in Figure 1, the generation method flow that the embodiment of the present invention provides a kind of holder to consume portrait shows
Being intended to, specifically implementation method includes:
Step S101, obtains holder's consumption information, and described holder's consumption information includes that holder's attribute is believed
Breath and bank card business dealing information.
Step S102, carries out data cleansing by described holder's consumption information, obtains to be analyzed effectively holding
People's consumption information.
Step S103, clusters described effective holder's consumption information according to described holder's attribute information
Analyze, obtain the effective consumption information set for each holder.
Step S104, for a holder, every according in effective consumption information set of described holder
Outside merchant information in the inside merchant information of individual bank card business dealing information and external website, determines each silver
The consumption type that row card Transaction Information is corresponding.
Step S105, according to the consumption type that described each bank card business dealing information is corresponding, by described holder
Consumption information set be divided into effective consumption information subclass of corresponding different consumption type.
Step S106, according to described effective consumption information subclass, determines the consumption portrait of described holder.
In step S101, the holder's consumption information in bank card adapting system refers to holder and passes through POS
(point of sale, point-of-sale terminal) consumption generate Transaction Information, generally include name of firm, trade company number,
Turnover, the information such as exchange hour, these Transaction Informations reflect the consumption habit of holder in terms of different
And the consuming capacity.A usual holder can have multi-bank, it is therefore desirable to by cluster analysis, will
The consumption information of same holder clusters this holder under one's name, then for this part data separate present invention
The holder implementing to provide consumes the generation method of portrait and carries out classifying and data mining.
So-called data mining (Data Mining, DM) is also known as the Knowledge Discovery (Knowledge in data base
Discover in Database, KDD), it is that current artificial intelligence, machine learning are multiple with database technology etc.
The product that subject combines, is to disclose implicit, not previously known from the mass data of data base and have
The non-trivial process of the information of potential value.Data mining is a kind of decision support processes, increasingly automatedly
Analyze the data of enterprise, make the reasoning of inductive, from mass data excavate potential, implicit, have
The knowledge being worth, by customer grouping, customer churn prediction, analyzing product association etc., carries out client's
Specific aim marketing activity, wherein data mining algorithm includes logistic regression algorithm, neural network algorithm, decision-making
The types such as tree algorithm, Apriori algorithm and K-means algorithm.
In order to ensure the accuracy of the consumption portrait ultimately produced, the embodiment of the present invention is further to acquisition
Holder's consumption information carries out data cleansing, specifically, according to the exception of history holder's consumption information statistics
Data cleansing rule set up in transaction keyword;According to described data cleansing rule from described holder's consumption information
In identify the holder of the holder consumption information relevant in violation of rules and regulations trade company and composition fraudulent trading and consume letter
Breath;The described holder consumption information relevant to trade company in violation of rules and regulations and institute is removed from described holder's consumption information
State the holder's consumption information constituting fraudulent trading, obtain described effective holder's consumption information to be analyzed.
Foundation about data cleansing rule is (wrong based on the small part swindle sample extracted from historical data
By mistake data), utilize data mining algorithm, repetitive exercise violation data identification model, and by polymorphic type number in violation of rules and regulations
According to identifying that model is combined screening, identify the wrong data of other the unknowns.Consider holder's consumption information
In abnormal data mainly include in violation of rules and regulations trade company and fraudulent trading two types, the present embodiment by be given as
The process of lower secondary cleaning, carries out citing description to the method for data cleansing, specifically includes following two steps.
Step one, by setting up in violation of rules and regulations trade company's detection model, finds out trade company in violation of rules and regulations, such as POS telephone-moving in violation of rules and regulations,
Applying mechanically MCC code violation etc., the violation trade company of each type identifies a corresponding model.Detect based on these
The illegal trade company of Model Identification, and the consumption of this part trade company is removed.
Step 2, by setting up fraudulent trading detection model, finds out fraudulent trading.Wherein, fraudulent trading mould
Type is to be combined by a series of fraud detection submodels, and these fraud detection submodels include that mould is swindled in arbitrage
The multiple fraudulent trading types such as type, pseudo-card swindle model, pre-authorization swindle model, by these submodel mistakes
Filter this part fraudulent trading data.
Visible, through the data cleansing of above-mentioned two process, the consumption letter to be analyzed in the embodiment of the present invention
In breath set, data belong to the data that arm's length dealing produces, the consumption portrait ability generated based on this data acquisition system
Enough consumption habit and consuming capacity more accurately reflecting holder.
Further, according to trade company's name of the inside merchant information of described each bank card business dealing information, determine
The classification of the outside merchant information that described trade company name is corresponding;Corresponding according to described each bank card business dealing information
The classification of internal merchant information and the classification of described outside merchant information, determine each bank card business dealing information pair
The consumption type answered.
Specifically, according to trade company's name of described bank card business dealing information, true by system Merchant Category relation table
The consumption type of each effective holder's consumption information in effective consumption information set of fixed described holder;
Described system Merchant Category relation table is the trade company by the Merchant Category in bank card system and Third party system
Classification obtains.
Obtain the title treating classified object;By the described title treating classified object and the key in mapping table
Word mates, if the match is successful, then obtain in described mapping table with the described title treating classified object
The object type corresponding to key word matched, described mapping table is used for storing key word and object class
Other corresponding relation;The classification of classified object is treated described in being defined as by the object type got.
Because the content that generally merchant information in bank card adapting system comprises is less, the classification of corresponding trade company
The most relatively coarse, such as receive a transaction from KFC, simply simply classify as food and drink type,
It is not finely divided for consumption time and area of consumption point.Therefore the embodiment of the present invention is used in combination external website
In merchant information, such as comment on from masses and website obtain product type corresponding to different name of firm, product
The price of product, the information such as position of trade company.So, by the combination of inside and outside merchant information, by every silver
Row card Transaction Information is refined as different consumption types, collects the consuming behavior of every kind of consumer correspondence the most again
Feature.
Such as, in bank card adapting system, bank card business dealing information is of a travel agency
POS consumption is the trading order form of 10,000 yuan, and therefore bank card adapting system analyzes this bank card is that tourism disappears
Taking, turnover is 10,000 yuan, and further, the embodiment of the present invention combines the letter of this tourism society in ctrip.com station
Breath, learns the service overseas trip service that this tourism society carries out, consumption grade correspondence middle and high end consumption grade
The consumer group, the therefore combination of inside and outside merchant information, classify as tourism consumption type by this consumer sale,
It is refined as consuming higher abroad tourism type.
Again such as, in bank card adapting system, many bank card business dealing information of a certain holder are about vapour
The pertinent transaction information of car, has the POS trading card from gas station, also has the maintenance transaction from 4S shop to believe
Breaths etc., utilize inside and outside data in the embodiment of the present invention to combine, by merchant information and Transaction Information to combination,
The consumption of car category can be classified as, in this big class bus attribute included below, oiling situation, drive spy
The group such as levy.
Further, for each effective consumption information subclass, according to described effective consumption information subclass
In the consumption time of each effective holder's consumption information and spending amount, calculate every class consumption type corresponding
Consuming behavior feature;Combine the consuming behavior feature that described every class consumption type is corresponding, obtain described in hold
The consumption portrait of people.
Such as, in above-mentioned example, big class is the consumption information of car category, and group comprises bus attribute, adds
The consumption information of the oil type such as situation, driving characteristics, it is possible to utilize data mining algorithm according to each group
It is modeled, utilizes data mining algorithm to draw the consuming behavior feature of this holder, example for each group
As higher by position difference, the frequency of the oiling order in gas station, show that this holder belongs to self-driving race,
Belong to high-end type brand by bus attribute, draw the more high information of the consuming capacity of this holder, based on
Consuming behavior feature corresponding to above group is combined, it can be deduced that this holder belongs in automobile consumption class
In type, the consuming capacity are high, go on a journey self-driving family frequently.
The like, for each the bank card having consumer record, it is utilized respectively card essential information and analyzes mould
Type, travelling merchants' Characteristic Analysis Model, automobile consumption Characteristic Analysis Model, food and drink consumption feature are analyzed model, are stopped
It is special that not busy abstract the recreational consumption analyzes model, motion hobby Characteristic Analysis Model, departure Characteristic Analysis Model and consumptive power
Levy 8 models such as analysis model, big data platform carries out Distributed Calculation, respectively obtains card and substantially believe
Breath table, travelling merchants' mark sheet, automobile mark sheet, food and drink mark sheet, amusement and recreation mark sheet, motion hobby spy
Levy table, departure 8 subclass detail mark sheets such as mark sheet and consumptive power mark sheet.Then artificial main to hold
Key, it can be deduced that disappearing of the different consumption type such as travelling merchants' feature of this holder, food and drink feature, hobby
Take behavior characteristics, therefore in conjunction with above consuming behavior feature, this holder can be carried out consumption portrait, thus
Draw the consuming capacity and the consumption portrait of consumption habit that this holder is complete.
Consume the generation process of portrait to describe above-mentioned holder in detail, the embodiment of the present invention is further
Fig. 2 is provided, illustrates the forming process of consumption portrait step by step.
Step 1, gathers the bank card business dealing record in bank card adapting system, fraudulent trading table, Merchant Category
The information such as table, bank card card BIN information table, then carry out data cleansing by trade company's detection model in violation of rules and regulations.
Data after above-mentioned cleaning further, are carried out secondary cleaning by step 2, use fraudulent trading detecting
Model filter falls abnormal transaction data.
Step 3, carries out the transaction data after above-mentioned cleaning internal merchant information and separates.
Step 4, carries out cluster analysis by the transaction data after above-mentioned cleaning so that a holder institute under one's name
There is bank card business dealing information all to cluster under this name, form the consumption information set of this holder.
Step 5, from outside merchant website, such as popular comment net etc. obtains the different trade company number of trade company, trade company
The information such as type of service, consumption grade.
Step 6, is integrated inside merchant information and outside merchant information by merchant information model, is formed
The multidimensional merchant information table of each trade company.
Step 7, by polymerization formed multidimensional merchant information table carry out trade company's category division demarcation, form complete business
Family information table.
Step 8, is carried out each Transaction Information table that holds, complete merchant information table and bank card incidence relation table
Integrate and layering is gone forward one by one analysis, carry out holder's consumption feature calculating.
Step 9, with the artificial major key that holds, card essential information is analyzed model, travelling merchants' Characteristic Analysis Model, vapour
Car consumption feature analyzes model, food and drink consumption feature analyzes model, amusement and recreation Consumption model, motion
Hobby Characteristic Analysis Model, departure 8 model generations such as Characteristic Analysis Model and consumptive power Characteristic Analysis Model
8 subclass detail mark sheets merge, form unified holder's consumption feature information table.Information table
Summary example (note: the secondary classification of every subclass detail mark sheet has tens detailed spies as shown in Figure 3
Levying, for convenience of description, in figure, every subclass detail mark sheet only lists 2 to 3).
Step 10, unification holder's consumption feature information table is stored in distributed data base.
After completing above-mentioned consumption portrait, it is possible to use this consumption portrait apply personalized precision marketing,
The aspects such as bank card risk prevention and control, holder individual's reference, specifically, according to the consumption picture of described holder
Picture, determines consumption habit and the consuming capacity of described holder;Consumption habit according to described holder
And the consuming capacity, generate the marketing strategy about described holder.
Such as, the above-mentioned analysis for the consuming behavior feature of holder draws, this holder belongs to young one
Race, likes self-driving, tourism, the information such as the consuming capacity are higher, then can have when product pushes or introduces
Specific aim is marketed.
Based on identical technology design, the embodiment of the present invention also provides for a kind of holder and consumes the generation dress of portrait
Putting, this device can perform said method embodiment.The device that the embodiment of the present invention provides as shown in Figure 4, wraps
Include: acquiring unit 401, data cleansing unit 402, cluster analysis unit 403, determine consumption type unit
404, division unit 405, determine consumption portrait unit 406, wherein:
Acquiring unit 401, is used for obtaining holder's consumption information, and described holder's consumption information includes holder
Attribute information and bank card business dealing information;
Data cleansing unit 402, for described holder's consumption information is carried out data cleansing, obtains to be analyzed
Effective holder's consumption information;
Cluster analysis unit 403, for consuming letter according to described holder's attribute information to described effective holder
Breath carries out cluster analysis, obtains the effective consumption information set for each holder;
Determine consumption type unit 404, for for a holder, according to effective consumption of described holder
Outside trade company letter in the inside merchant information of each bank card business dealing information in information aggregate and external website
Breath, determines the consumption type that each bank card business dealing information is corresponding;
Division unit 405, for the consumption type corresponding according to described each bank card business dealing information, by described
The consumption information set of holder is divided into effective consumption information subclass of corresponding different consumption type;
Determine consumption portrait unit 406, for according to described effective consumption information subclass, determine described in hold
The consumption portrait of people.
This device is positioned in data relay system, the big data platform of feature calculation, Data application system, wherein,
Internal source data and external data are mainly changed by the data cleansing unit 402 of data relay system,
Non-structural, the data of half structure, file are converted into the data of structure;Data are carried out form conversion and standard
Change, and carry out data cleansing and filter work.
Further, described data cleansing unit 402 specifically for: according to history holder's consumption information unite
Data cleansing rule set up in the exception transaction keyword of meter;According to described data cleansing rule from described holder
Consumption information identifies the holder consumption information relevant to trade company in violation of rules and regulations and constitutes the holder of fraudulent trading
Consumption information;From described holder's consumption information, remove the described holder relevant to trade company in violation of rules and regulations consume letter
Breath and holder's consumption information of described composition fraudulent trading, obtain described effective holder consumption to be analyzed
Information.
Additionally determine described in the big data platform of feature calculation consumption type unit 404 specifically for: according to institute
State trade company's name of the inside merchant information of each bank card business dealing information, determine the outside that described trade company name is corresponding
The classification of merchant information;Classification according to inside merchant information corresponding to described each bank card business dealing information and
The classification of described outside merchant information, determines the consumption type that each bank card business dealing information is corresponding.
Further, described determine consumption portrait unit 406 specifically for: for each effective consumption information
Subclass, during according to the consumption of each effective holder's consumption information in described effective consumption information subclass
Between and spending amount, calculate the consuming behavior feature that every class consumption type is corresponding;Combine described every class consumer
The consuming behavior feature that type is corresponding, obtains the consumption portrait of described holder.
Further, also include in Data application system: marketing strategy signal generating unit 407, for according to institute
State the consumption portrait of holder, determine consumption habit and the consuming capacity of described holder;According to described
The consumption habit of holder and the consuming capacity, generate the marketing strategy about described holder.So, precisely
Holder draw a portrait information, can be widely applied to personalized precision marketing, bank card risk prevention and control, hold
In the business such as card people individual's reference.By this system, card tissue can completely, comprehensively, accurately analyze
Each individual characteristics of holder having consumer record and living habit, form holder's portrait.Accurately
Holder draws a portrait information, can be widely applied to personalized precision marketing, bank card risk prevention and control, holds
In the business such as people individual's reference.
On the one hand the embodiment of the present invention obtains the holder's consumption information in bank card adapting system, and complete right
The data cleansing of this part holder's consumption information, filters abnormal datas such as violation trade company, fraudulent tradings,
And then ensure that the accuracy of data source;On the other hand, the embodiment of the present invention is by bank card adapting system
Merchant information in holder's consumption information and outside merchant website is combined, by merchant information outside inside
Combination, in each bank card business dealing information subdivision to different consumption types, form several correspondences not
With effective consumption information subclass of consumption type, based on the analysis to effective consumption information subclass, finally
Draw the consumption portrait of holder.Visible, the embodiment of the present invention is through data cleansing, inside and outside information trade company
Information integration process, it is ensured that form the accurately completely feature that holder consumes the data source of portrait, make
The consumption portrait of the consumer that must eventually form is more accurate, the beneficially formulation of marketing strategy.
The present invention is with reference to method, equipment (system) and computer program according to embodiments of the present invention
Flow chart and/or block diagram describe.It should be understood that can by computer program instructions flowchart and/
Or flow process in each flow process in block diagram and/or square frame and flow chart and/or block diagram and/or
The combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embedded
The processor of datatron or other programmable data processing device is to produce a machine so that pass through computer
Or the instruction that the processor of other programmable data processing device performs produces for realizing at flow chart one stream
The device of the function specified in journey or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing device
In the computer-readable memory worked in a specific way so that be stored in this computer-readable memory
Instruction produces the manufacture including command device, and this command device realizes at one flow process of flow chart or multiple stream
The function specified in journey and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices
Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one
The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know base
This creativeness concept, then can make other change and amendment to these embodiments.So, appended right is wanted
Ask and be intended to be construed to include preferred embodiment and fall into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these amendment and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprise these change and modification.
Claims (10)
1. a holder consumes the generation method of portrait, it is characterised in that the method includes:
Obtaining holder's consumption information, described holder's consumption information includes holder's attribute information and bank card
Transaction Information;
Described holder's consumption information is carried out data cleansing, obtains effective holder's consumption information to be analyzed;
According to described holder's attribute information, described effective holder's consumption information is carried out cluster analysis, obtain
Effective consumption information set for each holder;
For a holder, according to each bank card business dealing information in described effective holder's consumption information
Inside merchant information and external website in outside merchant information, determine that each bank card business dealing information is corresponding
Consumption type;
According to the consumption type that described each bank card business dealing information is corresponding, by the consumption of described effective holder
Information aggregate is divided into the consumption information subclass of corresponding different consumption type;
According to described consumption information subclass, determine the consumption portrait of described holder.
2. the method for claim 1, it is characterised in that described described holder's consumption information is entered
Row data cleansing, obtains effective holder's consumption information to be analyzed, including:
Data cleansing rule set up in exception transaction keyword according to history holder's consumption information statistics;
Identify relevant to trade company in violation of rules and regulations from described holder's consumption information according to described data cleansing rule
Holder's consumption information and holder's consumption information of composition fraudulent trading;
The described holder consumption information relevant to trade company in violation of rules and regulations and institute is removed from described holder's consumption information
State the holder's consumption information constituting fraudulent trading, obtain described effective holder's consumption information to be analyzed.
3. the method for claim 1, it is characterised in that described according to described effective holder consumption
Outside merchant information in the inside merchant information of each bank card business dealing information in information and external website,
Determine the consumption type that each bank card business dealing information is corresponding, including:
Trade company's name of the inside merchant information according to described each bank card business dealing information, determines described trade company name
The classification of corresponding outside merchant information;
Classification according to inside merchant information corresponding to described each bank card business dealing information and described outside trade company
The classification of information, determines the consumption type that each bank card business dealing information is corresponding.
4. the method for claim 1, it is characterised in that described according to described effective consumption information
Set, determines the consumption portrait of described holder, including:
For each effective consumption information subclass, have according to each in described effective consumption information subclass
The consumption time of effect holder's consumption information and spending amount, calculate the consuming behavior that every class consumption type is corresponding
Feature;
Combine the consuming behavior feature that described every class consumption type is corresponding, obtain the consumption portrait of described holder.
5. the method for claim 1, it is characterised in that described in obtain the consumption picture of described holder
As afterwards, also include:
Consumption portrait according to described holder, determines consumption habit and the consuming capacity of described holder;
Consumption habit according to described holder and the consuming capacity, generate the marketing strategy about described holder.
6. a holder consumes the generating means of portrait, it is characterised in that this device includes:
Acquiring unit, is used for obtaining holder's consumption information, and described holder's consumption information includes the Genus Homo that holds
Property information and bank card business dealing information;
Data cleansing unit, for described holder's consumption information is carried out data cleansing, obtains to be analyzed
Effectively holder's consumption information;
Cluster analysis unit, is used for according to described holder's attribute information described effective holder's consumption information
In carry out cluster analysis, obtain the effective consumption information set for each holder;
Determine consumption type unit, for for a holder, effectively consume letter according to described holder
Outside trade company letter in the inside merchant information of each bank card business dealing information in breath set and external website
Breath, determines the consumption type that each bank card business dealing information is corresponding;
Division unit, for the consumption type corresponding according to described each bank card business dealing information, holds described
Effective consumption information set of card people is divided into effective consumption information subclass of corresponding different consumption type;
Determine consumption portrait unit, for according to described effective consumption information subclass, determine described holder
Consumption portrait.
7. device as claimed in claim 6, it is characterised in that described data cleansing unit specifically for:
Data cleansing rule set up in exception transaction keyword according to history holder's consumption information statistics;
Identify relevant to trade company in violation of rules and regulations from described holder's consumption information according to described data cleansing rule
Holder's consumption information and holder's consumption information of composition fraudulent trading;
The described holder consumption information relevant to trade company in violation of rules and regulations and institute is removed from described holder's consumption information
State the holder's consumption information constituting fraudulent trading, obtain described effective holder's consumption information to be analyzed.
8. device as claimed in claim 6, it is characterised in that described determine that consumption type unit is specifically used
In:
Trade company's name of the inside merchant information according to described each bank card business dealing information, determines described trade company name
The classification of corresponding outside merchant information;
Classification according to inside merchant information corresponding to described each bank card business dealing information and described outside trade company
The classification of information, determines the consumption type that each bank card business dealing information is corresponding.
9. device as claimed in claim 6, it is characterised in that described determine that consumption portrait unit is specifically used
In:
For each effective consumption information subclass, have according to each in described effective consumption information subclass
The consumption time of effect holder's consumption information and spending amount, calculate the consuming behavior that every class consumption type is corresponding
Feature;
Combine the consuming behavior feature that described every class consumption type is corresponding, obtain the consumption portrait of described holder.
10. device as claimed in claim 6, it is characterised in that also include:
Marketing strategy signal generating unit, draws a portrait for the consumption according to described holder, determines described holder's
Consumption habit and the consuming capacity;
Consumption habit according to described holder and the consuming capacity, generate the marketing about described holder
Strategy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511025848.0A CN105931068A (en) | 2015-12-30 | 2015-12-30 | Cardholder consumption figure generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511025848.0A CN105931068A (en) | 2015-12-30 | 2015-12-30 | Cardholder consumption figure generation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105931068A true CN105931068A (en) | 2016-09-07 |
Family
ID=56840007
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511025848.0A Pending CN105931068A (en) | 2015-12-30 | 2015-12-30 | Cardholder consumption figure generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105931068A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106384253A (en) * | 2016-09-30 | 2017-02-08 | 中国银联股份有限公司 | Consumption behavior analysis method in bankcard transaction and consumption behavior analysis device thereof |
CN107274216A (en) * | 2017-05-27 | 2017-10-20 | 银联智惠信息服务(上海)有限公司 | Recognition methods, device, computer-readable medium and the system of social property |
CN107316205A (en) * | 2017-05-27 | 2017-11-03 | 银联智惠信息服务(上海)有限公司 | Recognize humanized method, device, computer-readable medium and the system of holding |
CN108268898A (en) * | 2018-01-19 | 2018-07-10 | 大象慧云信息技术有限公司 | A kind of electronic invoice user clustering method based on K-Means |
CN108572967A (en) * | 2017-03-09 | 2018-09-25 | 神州数码系统集成服务有限公司 | A kind of method and device creating enterprise's portrait |
CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
CN109299954A (en) * | 2018-08-22 | 2019-02-01 | 中国银联股份有限公司 | A kind of recognition methods of violation trade company and device |
CN109325847A (en) * | 2018-09-11 | 2019-02-12 | 上海梓颂信息科技有限公司 | The data computing system and method for network credit scoring |
CN109466176A (en) * | 2018-11-14 | 2019-03-15 | 天津市普迅电力信息技术有限公司 | A kind of energy-consuming enterprise portrait printing equipment and its working method |
CN109714381A (en) * | 2018-08-20 | 2019-05-03 | 平安普惠企业管理有限公司 | Information-pushing method, equipment, storage medium and device based on consumption tracking |
CN109816424A (en) * | 2018-12-14 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Credit card favor information recommended method and system based on customer consumption portrait |
CN109934615A (en) * | 2019-01-22 | 2019-06-25 | 中信银行股份有限公司 | Product marketing method based on depth sparse network |
CN110009364A (en) * | 2019-01-08 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of industry identification model determines method and apparatus |
CN110097451A (en) * | 2019-04-01 | 2019-08-06 | 中国银联股份有限公司 | A kind of monitoring method and device of banking |
CN111062555A (en) * | 2019-08-30 | 2020-04-24 | 京东城市(北京)数字科技有限公司 | City portrait construction method and device, medium and electronic equipment |
CN111159398A (en) * | 2019-12-05 | 2020-05-15 | 银联智策顾问(上海)有限公司 | Method and device for identifying merchant type |
CN111709843A (en) * | 2020-05-09 | 2020-09-25 | 中国人民财产保险股份有限公司 | Client portrait generation method and device and electronic equipment |
CN111899057A (en) * | 2020-08-05 | 2020-11-06 | 厦门力含信息技术服务有限公司 | Customer portrait data clustering analysis system based on edge cloud node data collection |
CN112084223A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | User portrait generation method, device, equipment and storage medium |
CN113436001A (en) * | 2021-06-25 | 2021-09-24 | 中国工商银行股份有限公司 | Credit card pushing method, device, equipment, storage medium and program product |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040158536A1 (en) * | 1998-06-01 | 2004-08-12 | Kowal David P. | Customer valuation in a resource price manager |
CN101727647A (en) * | 2009-12-14 | 2010-06-09 | 中兴通讯股份有限公司 | Multiple bank account consumption information management method and device |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104408635A (en) * | 2014-12-01 | 2015-03-11 | 银联智惠信息服务(上海)有限公司 | Method and device for recognizing class information of commercial tenant |
CN104537532A (en) * | 2014-12-12 | 2015-04-22 | 小米科技有限责任公司 | Consumption data recording method and device |
CN104714950A (en) * | 2013-12-13 | 2015-06-17 | 中国银联股份有限公司 | Method and system for correcting and supplementing information in database |
CN104820863A (en) * | 2015-03-27 | 2015-08-05 | 北京智慧图科技有限责任公司 | Consumer portrait generation method and device |
-
2015
- 2015-12-30 CN CN201511025848.0A patent/CN105931068A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040158536A1 (en) * | 1998-06-01 | 2004-08-12 | Kowal David P. | Customer valuation in a resource price manager |
CN101727647A (en) * | 2009-12-14 | 2010-06-09 | 中兴通讯股份有限公司 | Multiple bank account consumption information management method and device |
CN104090886A (en) * | 2013-12-09 | 2014-10-08 | 深圳市腾讯计算机系统有限公司 | Method and device for constructing real-time portrayal of user |
CN104714950A (en) * | 2013-12-13 | 2015-06-17 | 中国银联股份有限公司 | Method and system for correcting and supplementing information in database |
CN104408635A (en) * | 2014-12-01 | 2015-03-11 | 银联智惠信息服务(上海)有限公司 | Method and device for recognizing class information of commercial tenant |
CN104537532A (en) * | 2014-12-12 | 2015-04-22 | 小米科技有限责任公司 | Consumption data recording method and device |
CN104820863A (en) * | 2015-03-27 | 2015-08-05 | 北京智慧图科技有限责任公司 | Consumer portrait generation method and device |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106384253A (en) * | 2016-09-30 | 2017-02-08 | 中国银联股份有限公司 | Consumption behavior analysis method in bankcard transaction and consumption behavior analysis device thereof |
CN108572967A (en) * | 2017-03-09 | 2018-09-25 | 神州数码系统集成服务有限公司 | A kind of method and device creating enterprise's portrait |
CN108572967B (en) * | 2017-03-09 | 2022-03-15 | 神州数码系统集成服务有限公司 | Method and device for creating enterprise portrait |
CN107274216A (en) * | 2017-05-27 | 2017-10-20 | 银联智惠信息服务(上海)有限公司 | Recognition methods, device, computer-readable medium and the system of social property |
CN107316205A (en) * | 2017-05-27 | 2017-11-03 | 银联智惠信息服务(上海)有限公司 | Recognize humanized method, device, computer-readable medium and the system of holding |
CN108268898A (en) * | 2018-01-19 | 2018-07-10 | 大象慧云信息技术有限公司 | A kind of electronic invoice user clustering method based on K-Means |
CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
CN108805615B (en) * | 2018-05-28 | 2021-09-10 | 广州招点信息科技有限公司 | Preferential activity pushing method and system based on user consumption behaviors |
CN109714381A (en) * | 2018-08-20 | 2019-05-03 | 平安普惠企业管理有限公司 | Information-pushing method, equipment, storage medium and device based on consumption tracking |
CN109714381B (en) * | 2018-08-20 | 2022-10-14 | 平安普惠企业管理有限公司 | Consumption tracking based information pushing method, equipment, storage medium and device |
CN109299954A (en) * | 2018-08-22 | 2019-02-01 | 中国银联股份有限公司 | A kind of recognition methods of violation trade company and device |
CN109299954B (en) * | 2018-08-22 | 2022-04-15 | 中国银联股份有限公司 | Illegal commercial tenant identification method and device |
CN109325847A (en) * | 2018-09-11 | 2019-02-12 | 上海梓颂信息科技有限公司 | The data computing system and method for network credit scoring |
CN109466176A (en) * | 2018-11-14 | 2019-03-15 | 天津市普迅电力信息技术有限公司 | A kind of energy-consuming enterprise portrait printing equipment and its working method |
CN109816424A (en) * | 2018-12-14 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Credit card favor information recommended method and system based on customer consumption portrait |
TWI772673B (en) * | 2019-01-08 | 2022-08-01 | 開曼群島商創新先進技術有限公司 | Industry identification model determination method and device |
CN110009364A (en) * | 2019-01-08 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of industry identification model determines method and apparatus |
CN109934615B (en) * | 2019-01-22 | 2021-07-13 | 中信银行股份有限公司 | Product marketing method based on deep sparse network |
CN109934615A (en) * | 2019-01-22 | 2019-06-25 | 中信银行股份有限公司 | Product marketing method based on depth sparse network |
CN110097451B (en) * | 2019-04-01 | 2023-10-03 | 中国银联股份有限公司 | Bank business monitoring method and device |
CN110097451A (en) * | 2019-04-01 | 2019-08-06 | 中国银联股份有限公司 | A kind of monitoring method and device of banking |
CN111062555A (en) * | 2019-08-30 | 2020-04-24 | 京东城市(北京)数字科技有限公司 | City portrait construction method and device, medium and electronic equipment |
CN111062555B (en) * | 2019-08-30 | 2023-09-26 | 北京京东智能城市大数据研究院 | City portrait construction method, device, medium and electronic equipment |
CN111159398A (en) * | 2019-12-05 | 2020-05-15 | 银联智策顾问(上海)有限公司 | Method and device for identifying merchant type |
CN111159398B (en) * | 2019-12-05 | 2023-10-31 | 银联智策顾问(上海)有限公司 | Method and device for identifying merchant types |
CN111709843A (en) * | 2020-05-09 | 2020-09-25 | 中国人民财产保险股份有限公司 | Client portrait generation method and device and electronic equipment |
CN111709843B (en) * | 2020-05-09 | 2023-07-28 | 中国人民财产保险股份有限公司 | Customer portrait generation method and device and electronic equipment |
CN111899057A (en) * | 2020-08-05 | 2020-11-06 | 厦门力含信息技术服务有限公司 | Customer portrait data clustering analysis system based on edge cloud node data collection |
CN111899057B (en) * | 2020-08-05 | 2024-05-10 | 厦门慧企互联科技有限公司 | Customer portrait data cluster analysis system based on edge cloud node data collection |
CN112084223A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | User portrait generation method, device, equipment and storage medium |
CN113436001A (en) * | 2021-06-25 | 2021-09-24 | 中国工商银行股份有限公司 | Credit card pushing method, device, equipment, storage medium and program product |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105931068A (en) | Cardholder consumption figure generation method and device | |
CN107657267B (en) | Product potential user mining method and device | |
CN106506454B (en) | Cheat business recognition method and device | |
CN109063931A (en) | A kind of model method for predicting freight logistics driver Default Probability | |
CN105894359A (en) | Order pushing method, device and system | |
CN106384273A (en) | Malicious order scalping detection system and method | |
CN110400215B (en) | Method and system for constructing enterprise family-oriented small micro enterprise credit assessment model | |
CN107545422A (en) | A kind of arbitrage detection method and device | |
CN108985347A (en) | Training method, the method and device of shop classification of disaggregated model | |
CN109739844B (en) | Data classification method based on attenuation weight | |
US20160180264A1 (en) | Retention risk determiner | |
CN107679103B (en) | Attribute analysis method and system for entity | |
CN109636482B (en) | Data processing method and system based on similarity model | |
CN107274066B (en) | LRFMD model-based shared traffic customer value analysis method | |
CN111882431A (en) | Intelligent message pushing method based on NLP deep learning | |
JP2016206878A (en) | Salesperson raising support system and salesperson raising support method | |
CN110322335A (en) | A kind of credit customer qualification classification method passing through machine learning based on WOE conversion | |
CN104346698A (en) | Catering member big data analysis and checking system based on cloud computing and data mining | |
CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
CN115018513A (en) | Data inspection method, device, equipment and storage medium | |
CN111915368B (en) | System, method and medium for identifying customer ID in automobile industry | |
CN109191185A (en) | A kind of visitor's heap sort method and system | |
KR101960863B1 (en) | System of valuation of technology | |
CN112836996B (en) | Method for identifying potential ticket buying demand of passenger | |
CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination |