CN107491985A - The user's methods of marking and device of electric business platform, electronic equipment, storage medium - Google Patents

The user's methods of marking and device of electric business platform, electronic equipment, storage medium Download PDF

Info

Publication number
CN107491985A
CN107491985A CN201710648196.9A CN201710648196A CN107491985A CN 107491985 A CN107491985 A CN 107491985A CN 201710648196 A CN201710648196 A CN 201710648196A CN 107491985 A CN107491985 A CN 107491985A
Authority
CN
China
Prior art keywords
user
characteristic
mrow
scoring
equal
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
Application number
CN201710648196.9A
Other languages
Chinese (zh)
Inventor
霍文虎
蔡天慧
李腾龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ctrip Travel Network Technology Shanghai Co Ltd
Original Assignee
Ctrip Travel Network Technology Shanghai Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ctrip Travel Network Technology Shanghai Co Ltd filed Critical Ctrip Travel Network Technology Shanghai Co Ltd
Priority to CN201710648196.9A priority Critical patent/CN107491985A/en
Publication of CN107491985A publication Critical patent/CN107491985A/en
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides a kind of the user's methods of marking and device, electronic equipment, storage medium of electric business platform, including：A. the n dimensional feature data of m user are obtained from the database of the electric business platform；B. the n dimensional feature data set D=(x of the m user are formed(1), x(2)... x(m))；C. centralization is carried out to the n dimensional features data of each user；D. calculating matrix X covariance matrix Q=XXT；E. Eigenvalues Decomposition is carried out to covariance matrix Q, obtains n characteristic value and characteristic vector；F. characteristic vector corresponding to the maximum individual characteristic values of n ' of characteristic value is extracted；G. standardize characteristic vector and form n ' dimensional feature vectors matrix W '；H. the characteristic after dimensionality reduction, z are calculated(i)=WT·x(i), obtain the characteristic data set D ' after dimensionality reduction；I. the scoring score of each user is calculated at least with the characteristic data set D ' after dimensionality reduction；J. different services is provided a user according to different scoring score.Method and device provided by the invention alleviates the problem of big data redundancy and label shortage.

Description

The user's methods of marking and device of electric business platform, electronic equipment, storage medium
Technical field
The present invention relates to the user's methods of marking and dress of Computer Applied Technology field, more particularly to a kind of electric business platform Put, electronic equipment, storage medium.
Background technology
With the arrival in " internet+" and big data epoch, relevant industries are maked rapid progress.In order to preferably lift user Experience, realizes personalized recommendation and service to different user, it is necessary to be classified to each user.On the one hand, during big data Each user characteristic data information under is very huge, but redundancy and value density it is low, it is necessary to powerful machine learning algorithm The value " purification " of complete paired data；On the other hand during realizing user's classification, it is more likely that lack label data, work as mark When signing shortage of data, the multi-classification algorithm of common supervised learning will be unable to realize the classification and classification to each user.
The content of the invention
The present invention in order to overcome above-mentioned prior art to exist the defects of, there is provided a kind of user's methods of marking of electric business platform and Device, electronic equipment, storage medium, to alleviate the problem of big data redundancy and label lack.
According to an aspect of the present invention, there is provided a kind of user's methods of marking of electric business platform, including：
A. the n dimensional feature data of m user are obtained from the database of the electric business platform, m, n are the integer more than 0；
B. the n dimensional feature data set D=(x of the m user are formed(1), x(2)... x(m)), x(i)The matrix arranged for n rows 1, The n dimensional feature data of i-th of user are represented, i is the integer for being less than or equal to m more than or equal to 1；
C. centralization is carried out to the n dimensional features data of each user：To obtain square Battle array X=(x '(1), x '(2)..., x '(m))；
D. calculating matrix X covariance matrix Q=XXT；
E. Eigenvalues Decomposition is carried out to covariance matrix Q, obtains n characteristic value and characteristic vector W=(w1, w2..., wn)；
F. characteristic vector (w corresponding to the maximum individual characteristic values of n ' of characteristic value is extracted1, w2..., wn’), wherein, n ' be 1 or 2, and the Y% for the individual characteristic values of n ' and more than n characteristic value the sum extracted, Y are the constant between 65 to 75；
G. characteristic vector (w is made1, w2..., wn’) standardize and form n ' dimensional feature vectors matrix W '；
H. the characteristic after dimensionality reduction, z are calculated(i)=WT·x(i), obtain characteristic data set D '=(z after dimensionality reduction(1), z(2)..., z(m))；
I. the scoring score of each user is calculated at least with the characteristic data set D ' after dimensionality reduction；
J. different services is provided a user according to the segmentation residing for different scoring score.
Alternatively, n ' is 1, and the step f includes：
Extract characteristic vector w corresponding to 1 maximum characteristic value of characteristic value1, and extract it is 1 characteristic value and more than n The Y% of the sum of individual characteristic value.
Alternatively, the scoring score of user is calculated as follows in the step i：
Wherein, i is the integer for being less than or equal to m more than or equal to 1, and b is the maximum of scoring, and a is the minimum value of scoring, b and a For the constant more than or equal to 0.
Alternatively, the step f includes：
Extract characteristic vector w corresponding to 1 maximum characteristic value of characteristic value1If extraction it is 1 characteristic value and less than etc. In the Y% of the sum of n characteristic value, then n ' is set to be equal to 2, characteristic vector (w corresponding to 2 maximum characteristic values of extraction characteristic value1, w2), 2 characteristic values of extraction account for the f% of the sum of n characteristic value respectively and h%, f%+h% are more than the sum of n characteristic value Y%, wherein, it is the constant more than 0 that f, which is more than h, f and h,.
Alternatively, the scoring score of user is calculated as follows in the step i：
Wherein,I is the integer for being less than or equal to m more than or equal to 1, and b is the maximum of scoring, and a is scoring Minimum value, b and a are the constant more than or equal to 0.
Alternatively, the step i also includes：
It is ranked up from high to low by the scoring score of user；
Using the scoring score of user positioned at preceding 10% user as the first estate user；
The scoring score of user is located at the user of preceding 30% to preceding 10% as the second class user；
The scoring score of user is located at the user of preceding 60% to preceding 30% as tertiary gradient user；
The scoring score of user is located at the user of preceding 100% to preceding 60% as fourth estate user.
Alternatively, the characteristic includes one or more in following characteristic：
Real-name authentication, age, sex, occupation, family status, the equal volume of consumption, the consumption frequency, consumption increase rate, consumption are total Volume, account balance, account duration, bank card types, bank card quantity, account liveness, activity participation, consumption scene, disappear Expense level, comment are shared.
Alternatively, the step a also includes：
The feature of user is quantified or encoded to obtain characteristic.
According to another aspect of the invention, a kind of user's methods of marking of electric business platform, the characteristic of user are also provided It is divided into N number of classification, N is the integer more than 2, and each classification includes multiple characteristics,
A. it is down to the characteristic that 1 dimension obtains each classification as described above to each classification to each classification According to collection D '；
B. the characteristic data set D ' of N number of classification is combined into N-dimensional characteristic data set D and dropped again as described above Dimension calculates the scoring score of user, and different services is provided a user according to the segmentation residing for different scoring score
Alternatively, the characteristic of user is divided into four identity information, consumption information, fund information and Behavior preference classes Not.
According to another aspect of the invention, a kind of user's scoring apparatus of electric business platform is also provided, including：
Characteristic acquisition module, for obtaining the n dimensional feature numbers of m user from the database of the electric business platform According to m, n are the integer more than 0；
Characteristic data set forms module, for forming the n dimensional feature data set D=(x of the m user(1), x(2)... x(m)), x(i)The matrix arranged for n rows 1, represents the n dimensional feature data of i-th of user, and i is the integer for being less than or equal to m more than or equal to 1；
Centralization module, for carrying out centralization to the n dimensional features data of each user：
To obtain matrix X=(x '(1), x '(2)..., x '(m))；
Covariance matrix computing module, the covariance matrix Q=XX for calculating matrix XT；
Eigenvalues Decomposition module, for carrying out Eigenvalues Decomposition to covariance matrix Q, obtain n characteristic value and feature to Measure W=(w1, w2..., wn)；
Characteristic vector pickup module, characteristic vector (w corresponding to the individual characteristic values of n ' maximum for extracting characteristic value1, w2..., wn’), wherein, n ' be 1 or 2, and extract the individual characteristic values of n ' and more than n characteristic value sum Y%, Y for 65 to Constant between 75；
Standardized module, for making characteristic vector (w1, w2..., wn’) standardize and form n ' dimensional feature vector matrixes W’；
Dimensionality reduction module, for calculating the characteristic after dimensionality reduction, z(i)=WT·x(i), obtain the characteristic data set after dimensionality reduction D '=(z(1), z(2)..., z(m))；
Score calculation module, for calculating the scoring score of each user at least with the characteristic data set D ' after dimensionality reduction；
Service providing module, for providing a user different services according to the segmentation residing for different scoring score.
According to another aspect of the invention, a kind of electronic equipment is also provided, the electronic equipment includes：Processor；Storage Medium, is stored thereon with computer program, and the computer program performs step as described above when being run by the processor.
According to another aspect of the invention, a kind of storage medium is also provided, computer journey is stored with the storage medium Sequence, the computer program perform step as described above when being run by processor.
Compared with prior art, advantage of the invention is that：1) for the redundancy of user characteristic data under big data background, Low value density and extensive characteristic, can be effectively reduced data dimension, extract most important characteristic, then make Rational classification is made to user with rule, reduces the complexity of calculating；2) for without label data situation, common supervision Practising algorithm will fail, and the present invention is independent of label data.
Brief description of the drawings
Its example embodiment is described in detail by referring to accompanying drawing, above and other feature and advantage of the invention will become It is more obvious.
Fig. 1 shows the flow chart of user's methods of marking of electric business platform according to embodiments of the present invention.
Fig. 2 shows the schematic diagram of bidimensional characteristic according to embodiments of the present invention.
Fig. 3 shows Fig. 2 according to embodiments of the present invention bidimensional characteristic dimensionality reduction to one-dimensional schematic diagram.
Fig. 4 shows the schematic diagram of user's scoring apparatus of electric business platform according to embodiments of the present invention.
Fig. 5 schematically shows a kind of computer-readable recording medium schematic diagram in disclosure exemplary embodiment.
Fig. 6 schematically shows a kind of electronic equipment schematic diagram in disclosure exemplary embodiment.
Embodiment
Example embodiment is described more fully with referring now to accompanying drawing.However, example embodiment can be with a variety of shapes Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, these embodiments are provided so that the disclosure will more Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot Structure or characteristic can be incorporated in one or more embodiments in any suitable manner.
In addition, accompanying drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical accompanying drawing mark in figure Note represents same or similar part, thus will omit repetition thereof.Some block diagrams shown in accompanying drawing are work( Can entity, not necessarily must be corresponding with physically or logically independent entity.These work(can be realized using software form Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place These functional entitys are realized in reason device device and/or microcontroller device.
In order to solve the defects of prior art, the failing to report and missing to prevent alarm of comprehensive security incident monitoring method is realized Report, the present invention provide a kind of the user's methods of marking and device, electronic equipment, storage medium of electric business platform.
Referring first to Fig. 1, Fig. 1 shows the flow of user's methods of marking of electric business platform according to embodiments of the present invention Figure.10 steps are shown in Fig. 1 altogether：
Step S101：The n dimensional feature data of m user are obtained from the database of the electric business platform, m, n are more than 0 Integer.
Specifically, the quantity of characteristic is the dimension of characteristic.Characteristic can include following characteristic According to：Real-name authentication, age, sex, occupation, family status, the equal volume of consumption, the consumption frequency, consumption increase rate, consumption total value, account Family remaining sum, account duration, bank card types, bank card quantity, account liveness, activity participation, consumption scene, consumption layer Secondary, comment is shared.
It is appreciated that the part in features described above data can directly quantify, for example, the age, the equal volume of consumption, the consumption frequency, Consumption increase rate, consumption total value, account balance, bank card quantity, account liveness, activity participation are all directly to quantify Characteristic.And real-name authentication, sex, occupation, family status, bank card types, consumption scene, hierarchy of consumption etc. are not The characteristic that can intuitively quantify, for these characteristics, it can be encoded for different situations, and this is encoded As characteristic.For example, sex is that then numbering is 100 to man, it is 200 that sex, which is that female then numbers, sex do not fill in or other then Numbering is 300.Similarly, scene number altogether, hierachy number can be preset first by consuming scene, hierarchy of consumption, then to each use Family encodes, and than if any tri- scenes of ABC, and certain user only has consumption in scenario A, and that is encoded to 100 to the user's.
Step S102：Form the n dimensional feature data set D=(x of the m user(1), x(2)... x(m)), x(i)Arranged for n rows 1 Matrix, represent i-th of user n dimensional feature data, i be more than or equal to 1 be less than or equal to m integer.
Specifically,
Step S103：Centralization is carried out to the n dimensional features data of each user： With Obtain matrix X=(x '(1), x '(2)..., x '(m))。
Specifically,
Step S104：Calculating matrix X covariance matrix Q=XXT。
Specifically, covariance matrix Q is symmetrical matrix.
Step S105：Eigenvalues Decomposition is carried out to covariance matrix Q, obtains n characteristic value and characteristic vector W=(w1, w2..., wn)。
Various ways can be used to carry out Eigenvalues Decomposition.
Mode 1：An assuming that matrix P=XTX, if e be matrix P eigenvalue λ corresponding to characteristic vector, then have：
Pe=λ e；
XTXe=λ e；
X·XTXe=λ Xe；
Q (Xe)=λ (Xe)
Thus, Xe is also characteristic vector corresponding to matrix Q eigenvalue λ, W=(ex '(1), ex '(2)..., e x′(m))=(w1, w2..., wn)。
Mode 2：Using the mode of singular value decomposition, any one mn matrix can carry out singular value decomposition, split For the form of 3 matrix multiples.It is exactly variance because the SVD singular vectors drawn are also from the descending arrangement of singular value Maximum reference axis is exactly first singular vector, and the big reference axis of variance time is exactly second singular vector ....We can be with Singular value decomposition is carried out to Q.
Q=UDVT
Wherein, U is exactly QQTCharacteristic vector, V is exactly QTQ characteristic vector, singular value square is exactly QQ in DTAnd QTQ Characteristic value.
Step S106：Extract characteristic vector (w corresponding to the maximum individual characteristic values of n ' of characteristic value1, w2..., wn’), wherein, N ' is 1 or 2, and the Y% for the individual characteristic values of n ' and more than n characteristic value the sum extracted, Y are the constant between 65 to 75.
Step S107：Make characteristic vector (w1, w2..., wn’) standardize and form n ' dimensional feature vectors matrix W '.
Specifically, characteristic vector standardization here, is that characteristic vector is normalized, is normalized to unit Vector.What is represented in feature space due to characteristic vector is direction, so unit vector can be used to characterize.
Step S108：Calculate the characteristic after dimensionality reduction, z(i)=WT·x(i), obtain dimensionality reduction after characteristic data set D '= (z(1), z(2)..., z(m))。
Step S109：The scoring score of each user is calculated at least with the characteristic data set D ' after dimensionality reduction.
Specifically, in above-mentioned steps S107, characteristic vector corresponding to 1 maximum characteristic value of characteristic value is extracted first w1, and the 70% of 1 characteristic value and more than n characteristic value the sum extracted.
Then the scoring score of user is calculated as follows in step S109：
Wherein, i is the integer for being less than or equal to m more than or equal to 1, and b is the maximum of scoring, and a is the minimum value of scoring, b and a For the constant more than or equal to 0.
If in above-mentioned steps S107, characteristic vector w corresponding to 1 maximum characteristic value of characteristic value is extracted first1, and carry The 70% of 1 characteristic value and less than or equal to n characteristic value the sum taken, then n ' is equal to 2, extracted again in step S107 Characteristic vector (w corresponding to 2 maximum characteristic values of characteristic value1, w2), 2 characteristic values of extraction account for the sum of n characteristic value respectively F% and h%, f%+h% be more than n characteristic value sum 70%, wherein, f is more than h, f and h for the constant more than 0.
And the scoring score of user is calculated as follows in step S109：
Wherein, due to being down to bidimensional thenI is the integer for being less than or equal to m more than or equal to 1, and b is scoring Maximum, a are the minimum value of scoring, and b and a are the constant more than or equal to 0.
Above-mentioned a and b numerical value such as can be 0 and 1,0 and 10,0 and 100 so that user's scoring in 0-1,0-10 or It is distributed between 0-100.
In a specific embodiment, step S109 also includes being ranked up from high to low by the scoring score of user.Tool For body, can using the scoring score of user positioned at preceding 10% user as the first estate user；By the scoring score of user User positioned at preceding 30% to preceding 10% is as the second class user；The scoring score of user is located at preceding 60% to preceding 30% User as tertiary gradient user；The scoring score of user is located at the user of preceding 100% to preceding 60% as the fourth estate User.
Step S110：Different services is provided a user according to the segmentation residing for different scoring score.
Specifically, such as the preferential Securities of varying number and denomination can be provided to the user of different stage, difference is provided User interface, different search speed, speed of download etc. are provided.
Reference can be made to Fig. 2 and Fig. 3 illustrate dimension-reduction algorithm provided by the invention, such as realize 2-D data to the drop of one-dimensional data Dimension, it is assumed that initial data is two dimensions of X and Y, first that data are near one-dimensional, for the principal component of retention data, that is, is found out The variance maximum direction of data, it is clear that be Y-direction, Y-direction can be best represented by initial data.And in electric business platform in use, Each dimensional characteristics data are down to it is one-dimensional, that is, extract the most important characteristic of user, characterize each user using principal component. The high-dimensional characteristic of electric business platform user characteristic, but many dimensional informations do not have an impact.And user classification be by Different user is divided into each different brackets, and grade is one-dimension information.So the present invention is down to one using by user characteristics dimension Dimension, afterwards using one-dimensional characteristic, using scoring, formula is divided to user, and one-dimensional user characteristic data is divided into Each grade.In certain embodiments, also user characteristics dimension can be down to two dimension, the rear characteristic using two dimension is calculated and commented Divide to obtain one-dimensional data, using scoring, formula is divided to user, and one-dimensional data is divided into each grade
In another each embodiment of the present invention, the characteristic of user is divided into N number of classification, and N is the integer more than 2.Often Individual classification includes multiple characteristics.For example, in certain embodiments, the characteristic of user is divided into identity information, consumption letter Four breath, fund information and Behavior preference classifications.
First, each classification is carried out being down to each classification of 1 dimension acquisition by step S101 as shown in Figure 1 to step S108 Characteristic data set D '.
Then, the characteristic data set D ' of N number of classification is combined into N-dimensional characteristic data set D and by step as shown in Figure 1 Dimensionality reduction calculates the scoring score of user to S101 to step S110 again, according to the segmentation residing for different scoring score to user Different services is provided.Thus, it is possible to more accurately obtain the scoring score of user.
Referring to Fig. 4, Fig. 4 shows the signal of user's scoring apparatus of electric business platform according to embodiments of the present invention Figure.
User's scoring apparatus 200 includes characteristic acquisition module 201, characteristic data set forms module 202, centralization mould Block 203, covariance matrix computing module 204, Eigenvalues Decomposition module 205, characteristic vector pickup module 206, standardized module 207th, dimensionality reduction module 208, score calculation module 209, service providing module 210.
Characteristic acquisition module 201 is used for the n dimensional feature numbers that m user is obtained from the database of the electric business platform According to m, n are the integer more than 0；
Characteristic data set forms the n dimensional feature data set D=(x that module 202 is used to form the m user(1), x(2)... x(m)), x(i)The matrix arranged for n rows 1, represents the n dimensional feature data of i-th of user, and i is the integer for being less than or equal to m more than or equal to 1；
Centralization module 203 is used to carry out centralization to the n dimensional features data of each user：
To obtain matrix X=(x '(1), x '(2)..., x '(m))；
Covariance matrix computing module 204 is used for calculating matrix X covariance matrix Q=XXT；
Eigenvalues Decomposition module 205 is used to carry out Eigenvalues Decomposition to covariance matrix Q, obtains n characteristic value and feature Vectorial W=(w1, w2..., wn)；
Characteristic vector pickup module 206 is used to extract characteristic vector (w corresponding to the maximum individual characteristic values of n ' of characteristic value1, w2..., wn’), wherein, n ' be 1 or 2, and extract the individual characteristic values of n ' and more than n characteristic value sum Y%, Y for 65 to Constant between 75；
Standardized module 207 is used to make characteristic vector (w1, w2..., wn’) standardize and form n ' dimensional feature vector matrixes W’；
Dimensionality reduction module 208 is used to calculate the characteristic after dimensionality reduction, z(i)=WT·x(i), obtain the characteristic after dimensionality reduction Collect D '=(z(1), z(2)..., z(m))；
Score calculation module 209 is used for the scoring that each user is calculated at least with the characteristic data set D ' after dimensionality reduction score；
Service providing module 210 is used to provide a user different services according to the segmentation residing for different scoring score.
Fig. 4 is only to schematically show modules, it will be understood that the software module or reality that these modules can be virtual The hardware module on border, merging, fractionation and its increase of complementary modul block of these modules are all within protection scope of the present invention.
Compared with prior art, advantage of the invention is that：1) for the redundancy of user characteristic data under big data background, Low value density and extensive characteristic, can be effectively reduced data dimension, extract most important characteristic, then make Rational classification is made to user with rule, reduces the complexity of calculating；2) for without label data situation, common supervision Practising algorithm will fail, and the present invention is independent of label data.
In an exemplary embodiment of the disclosure, a kind of computer-readable recording medium is additionally provided, is stored thereon with meter Calculation machine program, it can realize that electronic prescription described in any one above-mentioned embodiment circulates when the program is by such as computing device The step of processing method.In some possible embodiments, various aspects of the invention are also implemented as a kind of program production The form of product, it includes program code, and when described program product is run on the terminal device, described program code is used to make institute State terminal device perform described in this specification above-mentioned electronic prescription circulation processing method part according to the various examples of the present invention The step of property embodiment.
With reference to shown in figure 5, the program product for being used to realize the above method according to the embodiment of the present invention is described 300, it can use portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device, Such as run on PC.However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be with Be it is any include or the tangible medium of storage program, the program can be commanded execution system, device either device use or It is in connection.
Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable letter Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or System, device or the device of semiconductor, or any combination above.The more specifically example of readable storage medium storing program for executing is (non exhaustive List) include：It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more wires, read-only Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer-readable recording medium can include believing in a base band or as the data that a carrier wave part is propagated Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any beyond readable storage medium storing program for executing Computer-readable recording medium, the computer-readable recording medium can send, propagate either transmit for being used by instruction execution system, device or device or Person's program in connection.The program code included on readable storage medium storing program for executing can be transmitted with any appropriate medium, bag Include but be not limited to wireless, wired, optical cable, RF etc., or above-mentioned any appropriate combination.
Can being combined to write the program operated for performing the present invention with one or more programming languages Code, described program design language include object oriented program language-Java, C++ etc., include routine Procedural programming language-such as " C " language or similar programming language.Program code can be fully in tenant Perform on computing device, partly performed in tenant's equipment, the software kit independent as one performs, is partly calculated in tenant Its upper side point is performed or performed completely in remote computing device or server on a remote computing.It is remote being related to In the situation of journey computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide area network (WAN) tenant's computing device, is connected to, or, it may be connected to external computing device (such as utilize ISP To pass through Internet connection).
In an exemplary embodiment of the disclosure, a kind of electronic equipment is also provided, the electronic equipment can include processor, And the memory of the executable instruction for storing the processor.Wherein, the processor is configured to via described in execution The step of executable instruction is to perform the circulation processing method of electronic prescription described in any one above-mentioned embodiment.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,：It is complete hardware embodiment, complete The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.), or hardware and software, can unite here Referred to as " circuit ", " module " or " system ".
The electronic equipment 600 according to the embodiment of the invention is described referring to Fig. 6.The electronics that Fig. 6 is shown Equipment 600 is only an example, should not bring any restrictions to the function and use range of the embodiment of the present invention.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap Include but be not limited to：At least one processing unit 610, at least one memory cell 620, (including the storage of connection different system component Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, the memory cell is had program stored therein code, and described program code can be held by the processing unit 610 OK so that the processing unit 610 perform described in the above-mentioned electronic prescription circulation processing method part of this specification according to this The step of inventing various illustrative embodiments.For example, the step of processing unit 610 can perform as shown in fig. 1.
The memory cell 620 can include the computer-readable recording medium of volatile memory cell form, such as random access memory Unit (RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
The memory cell 620 can also include program/practical work with one group of (at least one) program module 6205 Tool 6204, such program module 6205 includes but is not limited to：Operating system, one or more application program, other programs Module and routine data, the realization of network environment may be included in each or certain combination in these examples.
Bus 630 can be to represent the one or more in a few class bus structures, including memory cell bus or storage Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment Deng) communication, the equipment communication that can also enable tenant to be interacted with the electronic equipment 600 with one or more, and/or with causing Any equipment that the electronic equipment 600 can be communicated with one or more of the other computing device (such as router, modulation /demodulation Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with By network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.Should Understand, although not shown in the drawings, can combine electronic equipment 600 uses other hardware and/or software module, including it is but unlimited In：Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented Mode can be realized by software, can also be realized by way of software combines necessary hardware.Therefore, according to the disclosure The technical scheme of embodiment can be embodied in the form of software product, the software product can be stored in one it is non-volatile Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are to cause a calculating Equipment (can be personal computer, server or network equipment etc.) performs the above-mentioned electronics according to disclosure embodiment Prescription circulation processing method.
Compared with prior art, advantage of the invention is that：
1) on the premise of the real-time of flow cytometer showed and time dimension daily record forward-backward correlation is retained, when increase is based on long Between span blog search secondary judgement with evade wrong report；
2) due to increasing secondary judgement, can suitably reduce the first predetermined threshold set in streaming strategy, with avoid because Report by mistake and failed to report caused by the first too high predetermined threshold is set；
3) add search engine and carry out relevant historical daily record retrospect to long span, can by predetermined second predetermined threshold come Judged, the judgement of multiple judged results can be also carried out by scripting language's plug-in unit with merging；
4) third party's interface is combined, script plug-in unit calling interface can be carried out further while Search Engine Analysis result Judgement.
Those skilled in the art will readily occur to the disclosure its after considering specification and putting into practice invention disclosed herein Its embodiment.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or Person's adaptations follow the general principle of the disclosure and including the undocumented common knowledges in the art of the disclosure Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the disclosure and spirit are by appended Claim is pointed out.

Claims (13)

  1. A kind of 1. user's methods of marking of electric business platform, it is characterised in that including：
    A. the n dimensional feature data of m user are obtained from the database of the electric business platform, m, n are the integer more than 0；
    B. the n dimensional feature data set D=(x of the m user are formed(1), x(2)... x(m)), x(i)The matrix arranged for n rows 1, represent The n dimensional feature data of i-th of user, i are the integer for being less than or equal to m more than or equal to 1；
    C. centralization is carried out to the n dimensional features data of each user：To obtain matrix X= (x′(1), x '(2)..., x '(m))；
    D. calculating matrix X covariance matrix Q=XXT；
    E. Eigenvalues Decomposition is carried out to covariance matrix Q, obtains n characteristic value and characteristic vector W=(w1, w2..., wn)；
    F. characteristic vector (w corresponding to the maximum individual characteristic values of n ' of characteristic value is extracted1, w2..., wn’), wherein, n ' is 1 or 2, and The Y% of the individual characteristic values of n ' and more than n characteristic value the sum of extraction, Y are the constant between 65 to 75；
    G. characteristic vector (w is made1, w2..., wn’) standardize and form n ' dimensional feature vectors matrix W '；
    H. the characteristic after dimensionality reduction, z are calculated(i)=WT·x(i), obtain characteristic data set D '=(z after dimensionality reduction(1), z(2)..., z(m))；
    I. the scoring score of each user is calculated at least with the characteristic data set D ' after dimensionality reduction；
    J. different services is provided a user according to the segmentation residing for different scoring score.
  2. 2. user's methods of marking as claimed in claim 1, it is characterised in that n ' is 1, and the step f includes：
    Extract characteristic vector w corresponding to 1 maximum characteristic value of characteristic value1, and 1 characteristic value and more than the n feature extracted The Y% of the sum of value.
  3. 3. user's methods of marking as claimed in claim 2, it is characterised in that the step i is calculated as follows user's Score score：
    <mrow> <mi>s</mi> <mi>c</mi> <mi>o</mi> <mi>r</mi> <mi>e</mi> <mo>=</mo> <mfrac> <mrow> <mi>b</mi> <mo>-</mo> <mi>a</mi> </mrow> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> <mrow> <mo>(</mo> <mo>|</mo> <msup> <mi>z</mi> <mi>i</mi> </msup> <mo>|</mo> <mo>)</mo> </mrow> <mo>-</mo> <mi>m</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mo>|</mo> <msup> <mi>z</mi> <mi>i</mi> </msup> <mo>|</mo> <mo>)</mo> </mrow> </mrow> </mfrac> <mo>&amp;times;</mo> <mo>|</mo> <msup> <mi>z</mi> <mi>i</mi> </msup> <mo>|</mo> <mo>,</mo> </mrow>
    Wherein, i is the integer for being less than or equal to m more than or equal to 1, and b is the maximum of scoring, and a is the minimum value of scoring, and b and a are big In the constant equal to 0.
  4. 4. user's methods of marking as claimed in claim 1, it is characterised in that the step f includes：
    Extract characteristic vector w corresponding to 1 maximum characteristic value of characteristic value1If extraction is 1 characteristic value and individual less than or equal to n The Y% of the sum of characteristic value, then n ' is set to be equal to 2, characteristic vector (w corresponding to 2 maximum characteristic values of extraction characteristic value1, w2), carry 2 characteristic values taken account for the f% of the sum of n characteristic value respectively and h%, f%+h% be more than n characteristic value sum Y%, its In, it is the constant more than 0 that f, which is more than h, f and h,.
  5. 5. user's methods of marking as claimed in claim 4, it is characterised in that the step i is calculated as follows user's Score score：
    <mrow> <mi>s</mi> <mi>c</mi> <mi>o</mi> <mi>r</mi> <mi>e</mi> <mo>=</mo> <mfrac> <mrow> <mi>b</mi> <mo>-</mo> <mi>a</mi> </mrow> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> <mrow> <mo>(</mo> <mo>|</mo> <msup> <mi>z</mi> <mi>i</mi> </msup> <mo>|</mo> <mo>)</mo> </mrow> <mo>-</mo> <mi>m</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mo>|</mo> <msup> <mi>z</mi> <mi>i</mi> </msup> <mo>|</mo> <mo>)</mo> </mrow> </mrow> </mfrac> <mo>&amp;times;</mo> <mo>|</mo> <mfrac> <mi>f</mi> <mrow> <mi>f</mi> <mo>+</mo> <mi>h</mi> </mrow> </mfrac> <mo>&amp;times;</mo> <msubsup> <mi>z</mi> <mn>1</mn> <mi>i</mi> </msubsup> <mo>+</mo> <mfrac> <mi>h</mi> <mrow> <mi>f</mi> <mo>+</mo> <mi>h</mi> </mrow> </mfrac> <mo>&amp;times;</mo> <msubsup> <mi>z</mi> <mn>2</mn> <mi>i</mi> </msubsup> <mo>|</mo> <mo>,</mo> </mrow>
    Wherein,I is the integer for being less than or equal to m more than or equal to 1, and b is the maximum of scoring, and a is the minimum of scoring Value, b and a are the constant more than or equal to 0.
  6. 6. user's methods of marking as claimed in claim 1, it is characterised in that the step i also includes：
    It is ranked up from high to low by the scoring score of user；
    Using the scoring score of user positioned at preceding 10% user as the first estate user；
    The scoring score of user is located at the user of preceding 30% to preceding 10% as the second class user；
    The scoring score of user is located at the user of preceding 60% to preceding 30% as tertiary gradient user；
    The scoring score of user is located at the user of preceding 100% to preceding 60% as fourth estate user.
  7. 7. user's methods of marking as claimed in claim 1, it is characterised in that the characteristic is included in following characteristic It is one or more：
    Real-name authentication, age, sex, occupation, family status, the equal volume of consumption, the consumption frequency, consumption increase rate, consumption total value, account Family remaining sum, account duration, bank card types, bank card quantity, account liveness, activity participation, consumption scene, consumption layer Secondary, comment is shared.
  8. 8. user's methods of marking as claimed in claim 7, it is characterised in that the step a also includes：
    The feature of user is quantified or encoded to obtain characteristic.
  9. A kind of 9. user's methods of marking of electric business platform, it is characterised in that the characteristic of user is divided into N number of classification, N be more than 2 integer, each classification include multiple characteristics,
    A. the method carried out to each classification as described in any one of claim 1 to 8 is down to the characteristic that 1 dimension obtains each classification According to collection D '；
    B. the characteristic data set D ' of N number of classification is combined into N-dimensional characteristic data set D and as described in any one of claim 1 to 8 Method again dimensionality reduction calculate user scoring score, provided a user according to the segmentation residing for different scoring score different Service
  10. 10. user's methods of marking as claimed in claim 9, it is characterised in that the characteristic of user is divided into identity information, disappeared Four charge information, fund information and Behavior preference classifications.
  11. A kind of 11. user's scoring apparatus of electric business platform, it is characterised in that including：
    Characteristic acquisition module, for obtaining the n dimensional feature data of m user, m, n from the database of the electric business platform For the integer more than 0；
    Characteristic data set forms module, for forming the n dimensional feature data set D=(x of the m user(1), x(2)... x(m)), x(i)The matrix arranged for n rows 1, represents the n dimensional feature data of i-th of user, and i is the integer for being less than or equal to m more than or equal to 1；
    Centralization module, for carrying out centralization to the n dimensional features data of each user：
    To obtain matrix X=(x '(1), x '(2)..., x '(m))；
    Covariance matrix computing module, the covariance matrix Q=XX for calculating matrix XT；
    Eigenvalues Decomposition module, for carrying out Eigenvalues Decomposition to covariance matrix Q, obtain n characteristic value and characteristic vector W= (w1, w2..., wn)；
    Characteristic vector pickup module, characteristic vector (w corresponding to the individual characteristic values of n ' maximum for extracting characteristic value1, w2..., wn’), wherein, between n ' is 1 or 2, and the Y% for the individual characteristic values of n ' and more than n characteristic value the sum extracted, Y are 65 to 75 Constant；
    Standardized module, for making characteristic vector (w1, w2..., wn’) standardize and form n ' dimensional feature vectors matrix W '；
    Dimensionality reduction module, for calculating the characteristic after dimensionality reduction, z(i)=WT·x(i), obtain dimensionality reduction after characteristic data set D '= (z(1), z(2)..., z(m))；
    Score calculation module, for calculating the scoring score of each user at least with the characteristic data set D ' after dimensionality reduction；
    Service providing module, for providing a user different services according to the segmentation residing for different scoring score.
  12. 12. a kind of electronic equipment, it is characterised in that the electronic equipment includes：
    Processor；
    Storage medium, computer program is stored thereon with, such as right is performed when the computer program is run by the processor It is required that the step described in 1 to 8 any one.
  13. 13. a kind of storage medium, it is characterised in that computer program, the computer program are stored with the storage medium The step as described in any one of claim 1 to 8 is performed when being run by processor.
CN201710648196.9A 2017-08-01 2017-08-01 The user's methods of marking and device of electric business platform, electronic equipment, storage medium Pending CN107491985A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710648196.9A CN107491985A (en) 2017-08-01 2017-08-01 The user's methods of marking and device of electric business platform, electronic equipment, storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710648196.9A CN107491985A (en) 2017-08-01 2017-08-01 The user's methods of marking and device of electric business platform, electronic equipment, storage medium

Publications (1)

Publication Number Publication Date
CN107491985A true CN107491985A (en) 2017-12-19

Family

ID=60644731

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710648196.9A Pending CN107491985A (en) 2017-08-01 2017-08-01 The user's methods of marking and device of electric business platform, electronic equipment, storage medium

Country Status (1)

Country Link
CN (1) CN107491985A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110060166A (en) * 2019-03-13 2019-07-26 平安科技（深圳）有限公司 Intelligence Claims Resolution method, apparatus, computer equipment and storage medium
CN110544111A (en) * 2019-08-05 2019-12-06 北京市天元网络技术股份有限公司 ETC customer obtaining method and device based on operator big data
CN110610479A (en) * 2019-07-31 2019-12-24 华为技术有限公司 Object scoring method and device
CN110708361A (en) * 2019-09-18 2020-01-17 北京奇艺世纪科技有限公司 System, method and device for determining grade of digital content publishing user and server
CN110852846A (en) * 2019-11-11 2020-02-28 京东数字科技控股有限公司 Processing method and device for recommended object, electronic equipment and storage medium
CN111522795A (en) * 2020-04-23 2020-08-11 北京互金新融科技有限公司 Method and device for processing data
CN112200600A (en) * 2020-09-10 2021-01-08 广州半城云信息科技有限公司 Evaluation method for customer value of E-commerce and private area traffic
CN113065899A (en) * 2021-04-12 2021-07-02 上海明略人工智能(集团)有限公司 User life cycle value calculation method, system, device and storage medium
CN113706182A (en) * 2020-05-20 2021-11-26 北京沃东天骏信息技术有限公司 User classification method and device

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110060166A (en) * 2019-03-13 2019-07-26 平安科技（深圳）有限公司 Intelligence Claims Resolution method, apparatus, computer equipment and storage medium
CN112258450B (en) * 2019-07-31 2022-02-25 华为技术有限公司 Object scoring method and device
CN110610479A (en) * 2019-07-31 2019-12-24 华为技术有限公司 Object scoring method and device
CN110610479B (en) * 2019-07-31 2024-05-03 花瓣云科技有限公司 Object scoring method and device
CN112258450A (en) * 2019-07-31 2021-01-22 华为技术有限公司 Object scoring method and device
CN110544111A (en) * 2019-08-05 2019-12-06 北京市天元网络技术股份有限公司 ETC customer obtaining method and device based on operator big data
CN110708361A (en) * 2019-09-18 2020-01-17 北京奇艺世纪科技有限公司 System, method and device for determining grade of digital content publishing user and server
CN110708361B (en) * 2019-09-18 2022-06-03 北京奇艺世纪科技有限公司 System, method and device for determining grade of digital content publishing user and server
CN110852846A (en) * 2019-11-11 2020-02-28 京东数字科技控股有限公司 Processing method and device for recommended object, electronic equipment and storage medium
CN111522795A (en) * 2020-04-23 2020-08-11 北京互金新融科技有限公司 Method and device for processing data
CN113706182A (en) * 2020-05-20 2021-11-26 北京沃东天骏信息技术有限公司 User classification method and device
CN112200600A (en) * 2020-09-10 2021-01-08 广州半城云信息科技有限公司 Evaluation method for customer value of E-commerce and private area traffic
CN113065899A (en) * 2021-04-12 2021-07-02 上海明略人工智能(集团)有限公司 User life cycle value calculation method, system, device and storage medium

Similar Documents

Publication Publication Date Title
CN107491985A (en) The user&#39;s methods of marking and device of electric business platform, electronic equipment, storage medium
CN111967387B (en) Form recognition method, form recognition device, form recognition equipment and computer-readable storage medium
CN110162620B (en) Method and device for detecting black advertisements, server and storage medium
EP4040401A1 (en) Image processing method and apparatus, device and storage medium
CN108304835A (en) character detecting method and device
CN109657243A (en) Sensitive information recognition methods, system, equipment and storage medium
US20220130496A1 (en) Method of training prediction model for determining molecular binding force
CN106415594A (en) A method and a system for face verification
US20240202491A1 (en) Recommendation method, method for training recommendation model, and related product
CN112988963B (en) User intention prediction method, device, equipment and medium based on multi-flow nodes
CN110489423B (en) Information extraction method and device, storage medium and electronic equipment
CN111177367B (en) Case classification method, classification model training method and related products
CN109885697A (en) Construct method, apparatus, equipment and the medium of data model
CN110362832B (en) Paragraph merging method and device, storage medium and electronic equipment
CN107403311B (en) Account use identification method and device
EP3382596B1 (en) Human face model matrix training method and apparatus, and storage medium
CN110489424A (en) A kind of method, apparatus, storage medium and the electronic equipment of tabular information extraction
US20200019603A1 (en) Systems, methods, and computer-readable media for improved table identification using a neural network
JP2022088602A (en) Table generation method, device, electronic apparatus, storage medium and program
CN116226785A (en) Target object recognition method, multi-mode recognition model training method and device
CN114724156A (en) Form identification method and device and electronic equipment
CN108846476A (en) A kind of intelligent terminal security level classification method based on convolutional neural networks
CN116778306A (en) Fake object detection method, related device and storage medium
CN112035334A (en) Abnormal equipment detection method and device, storage medium and electronic equipment
EP4258178A1 (en) Information processing apparatus for improving robustness of deep neural network by using adversarial training and formal method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20171219

RJ01 Rejection of invention patent application after publication