CN109087138A - Data processing method and system, computer system and readable storage medium storing program for executing - Google Patents
Data processing method and system, computer system and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109087138A CN109087138A CN201810838841.8A CN201810838841A CN109087138A CN 109087138 A CN109087138 A CN 109087138A CN 201810838841 A CN201810838841 A CN 201810838841A CN 109087138 A CN109087138 A CN 109087138A
- Authority
- CN
- China
- Prior art keywords
- financial product
- user
- scoring
- different user
- destination
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Abstract
Present disclose provides a kind of data processing methods, it include: acquisition historical data, wherein, historical data includes the operation data generated after different user operates one or more financial products, every kind of financial product has corresponding one or more indexs, wherein, one or more indexs are used for the reference factor as evaluation user behavior preference；According to the corresponding one or more indexs of historical data and every kind of financial product, scoring of the different user to every kind of financial product is determined；The similarity between different user is determined to the scoring of every kind of financial product according to each user, wherein similarity is used to characterize the similitude of Behavior preference between different user；The potential user of destination financial product is determined according to the similarity between different user.The disclosure additionally provides a kind of data processing system, a kind of computer system and a kind of computer readable storage medium.
Description
Technical field
This disclosure relates to field of computer technology, more particularly, to a kind of data processing method and system, a kind of calculating
Machine system and a kind of computer readable storage medium.
Background technique
Infiltration with internet in financial field, the various internet financial products such as insurance, stock, fund are gradually big
Crowd approves and receives.During financial product precision marketing, target user is oriented by modes such as short message, mails and is launched,
To improve conversion ratio.The method for screening target group in the related technology for different financial products may include according to business personnel
Experience, hard Rules Filtering is carried out to user, such as: the age, the conditions such as income > 5000 met these conditions between 20 to 40
Then it is considered target user.But it is excessively extensive according to the mode that the experience of business personnel is screened, not only increased cost but also had influenced to use
Family experience is unfavorable for effectively contacting those really to the interested user of the financial product, so that marketing precision is low, effect
Difference.Alternatively, the relevant technologies can be directed to corresponding financial product, using the method for traditional classification model construction, extract training set and
Test set, screening feature, training pattern, then according to trained model judge user to the interested probability of the financial product,
The user that screening probability is greater than threshold value launches.The mode of traditional classification modeling perhaps can finally obtain relatively good positioning
Effect, but a complete modeling procedure has regular hour cost and resources costs, poor in timeliness；And different products is all
It needs to model respectively, for example, insurance draws new and fund to draw newly, requires to screen corresponding training set and correlated characteristic is built
Mould, and the subdivision of financial product is varied, is difficult to accomplish all to spend every kind of product certain manpower and time to go to model.
During realizing disclosure design, at least there are the following problems in the related technology for inventor's discovery: using phase
Pass technology spends application at high cost, and not being suitable for a variety of financial products by different financial products screening target group
Scene.
Summary of the invention
In view of this, present disclose provides a kind of data processing method and systems, a kind of computer system and a kind of calculating
Machine readable storage medium storing program for executing.
An aspect of this disclosure provides a kind of data processing method, including obtains historical data, wherein above-mentioned history
Data include the operation data generated after different user operates one or more financial products, and every kind of financial product has
Corresponding one or more index, wherein said one or multiple indexs are used for the reference as evaluation user behavior preference
Factor；According to the corresponding one or more indexs of above-mentioned historical data and above-mentioned every kind of financial product, different user pair is determined
The scoring of above-mentioned every kind of financial product；The scoring of above-mentioned every kind of financial product is determined between different user according to each user
Similarity, wherein above-mentioned similarity is used to characterize the similitude of Behavior preference between different user；According to above-mentioned different user it
Between similarity determine the potential user of destination financial product.
In accordance with an embodiment of the present disclosure, the above method further includes the financial product for obtaining target user and trading；In judgement
Whether state in the financial product that target user traded includes above-mentioned destination financial product；It is not including above-mentioned destination financial product
In the case where, determine above-mentioned target user to above-mentioned destination financial product according to the similarity of above-mentioned target user and other users
Scoring；And whether above-mentioned user, which is above-mentioned target, is determined to the scoring of above-mentioned destination financial product according to above-mentioned target user
The potential customers of financial product.
In accordance with an embodiment of the present disclosure, above-mentioned use is determined to the scoring of above-mentioned destination financial product according to above-mentioned target user
It includes: to judge whether above-mentioned other users traded above-mentioned destination financial that whether family, which is the potential customers of above-mentioned destination financial product,
Product；In the case where above-mentioned other users traded above-mentioned destination financial product, scoring threshold value is determined；And in above-mentioned target
In the case that user is greater than or equal to above-mentioned scoring threshold value to the scoring of above-mentioned destination financial product, determine that above-mentioned user is above-mentioned
The potential customers of destination financial product.
In accordance with an embodiment of the present disclosure, after determining different user to the scoring of above-mentioned every kind of financial product, above-mentioned side
Method further includes generating rating matrix to the scoring of above-mentioned every kind of financial product according to above-mentioned different user, wherein above-mentioned scoring square
The dimension of battle array is U × I, and above-mentioned U indicates that number of users, above-mentioned I indicate financial product quantity；Dimensionality reduction is carried out to above-mentioned rating matrix
Processing obtains the dimensionality reduction rating matrix that dimension is U × K；And it is determined between different user based on above-mentioned dimensionality reduction rating matrix
Similarity.
In accordance with an embodiment of the present disclosure, determine that the similarity between different user includes: based on above-mentioned dimensionality reduction rating matrix
Above-mentioned dimensionality reduction rating matrix is split into multiple submatrixs；And above-mentioned multiple submatrixs are handled using parallel computation mode, with
Determine the similarity between different user.
In accordance with an embodiment of the present disclosure, the above method further includes determining that above-mentioned every kind of finance produces according to above-mentioned historical data
The corresponding one or more indexs of condition.
Another aspect of the disclosure provides a kind of data processing system, including first obtains module, the first determining mould
Block, the second determining module and third determining module.First acquisition module is for obtaining historical data, wherein above-mentioned historical data
The operation data generated after operating including different user to one or more financial products, every kind of financial product have opposite
The one or more indexs answered, wherein said one or multiple indexs are used for the reference factor as evaluation user behavior preference；
First determining module is used to be determined according to the corresponding one or more indexs of above-mentioned historical data and above-mentioned every kind of financial product
Scoring of the different user to above-mentioned every kind of financial product；Second determining module is used to produce above-mentioned every kind of finance according to each user
The scoring of product determines the similarity between different user, wherein above-mentioned similarity is for characterizing Behavior preference between different user
Similitude；Third determining module is used to determine the potential use of destination financial product according to the similarity between above-mentioned different user
Family.
In accordance with an embodiment of the present disclosure, above system further include the second acquisition module, judgment module, the 4th determining module and
5th determining module.Second acquisition module is for obtaining the financial product that target user traded；Judgment module is for judging
Whether state in the financial product that target user traded includes above-mentioned destination financial product；4th determining module is not for including
In the case where above-mentioned destination financial product, above-mentioned target user couple is determined according to the similarity of above-mentioned target user and other users
The scoring of above-mentioned destination financial product；And the 5th determining module be used for according to above-mentioned target user to above-mentioned destination financial product
Scoring determine above-mentioned user whether be above-mentioned destination financial product potential customers.
In accordance with an embodiment of the present disclosure, above-mentioned 5th determining module includes that judging unit, the first determination unit and second are true
Order member.Judging unit is for judging whether above-mentioned other users traded above-mentioned destination financial product；First determination unit is used
In in the case where above-mentioned other users traded above-mentioned destination financial product, the threshold value that scores is determined；And second determination unit
For determining in the case where above-mentioned target user is greater than or equal to above-mentioned scoring threshold value to the scoring of above-mentioned destination financial product
Above-mentioned user is the potential customers of above-mentioned destination financial product.
In accordance with an embodiment of the present disclosure, above system further includes generation module, processing module and the 6th determining module.It generates
Module is used for after determining different user to the scoring of above-mentioned every kind of financial product, according to above-mentioned different user to every kind above-mentioned
The scoring of financial product generates rating matrix, wherein and the dimension of above-mentioned rating matrix is U × I, and above-mentioned U indicates number of users, on
Stating I indicates financial product quantity；Processing module is used to carry out dimension-reduction treatment to above-mentioned rating matrix, obtains the drop that dimension is U × K
Tie up rating matrix；And the 6th determining module be used to based on above-mentioned dimensionality reduction rating matrix determine the similarity between different user.
In accordance with an embodiment of the present disclosure, above-mentioned 6th determining module includes split cells and processing unit.Split cells is used
In above-mentioned dimensionality reduction rating matrix is split into multiple submatrixs；And processing unit is above-mentioned for being handled using parallel computation mode
Multiple submatrixs, to determine the similarity between different user.
In accordance with an embodiment of the present disclosure, above system further includes the 7th determining module.7th determining module be used for according to
Historical data is stated, determines the corresponding one or more indexs of above-mentioned every kind of financial product.
Another aspect of the disclosure provides a kind of computer system, including one or more processors；Memory is used
In the one or more programs of storage, wherein when said one or multiple programs are executed by said one or multiple processors, make
It obtains said one or multiple processors realizes data processing method as described above.
Another aspect of the disclosure provides a kind of computer readable storage medium, is stored thereon with executable instruction,
The instruction makes processor realize data processing method as described above when being executed by processor.
Another aspect of the present disclosure provides a kind of computer program, and the computer program, which includes that computer is executable, to be referred to
It enables, described instruction is when executed for realizing data processing method as described above.
In accordance with an embodiment of the present disclosure, user is determined to the scoring of every kind of financial product according to different user because using
Between similarity, the technological means of the potential user of destination financial product is determined according to the similarity between different user, it is right
It determines that the potential user of various financial products is all suitable for, without being modeled respectively for every kind of financial product, therefore saves
Regular hour cost and human cost, so at least partially overcoming use the relevant technologies to screen for different financial products
Target group is spent at high cost, and the technical issues of be not suitable for the application scenarios of a variety of financial products, and then is reduced
By the technical effect for the cost that different financial products screening target group spends.
Detailed description of the invention
By referring to the drawings to the description of the embodiment of the present disclosure, the above-mentioned and other purposes of the disclosure, feature and
Advantage will be apparent from, in the accompanying drawings:
Fig. 1 diagrammatically illustrate according to the embodiment of the present disclosure can be with application data processing method and the exemplary system of system
System framework；
Fig. 2 diagrammatically illustrates the flow chart of the data processing method according to the embodiment of the present disclosure；
Fig. 3 diagrammatically illustrates the flow chart of the data processing method according to another embodiment of the disclosure；
Fig. 4 diagrammatically illustrates determining to the scoring of destination financial product according to target user according to the embodiment of the present disclosure
User whether be destination financial product potential customers flow chart；
Fig. 5 diagrammatically illustrates the flow chart of the data processing method according to another embodiment of the disclosure；
Fig. 6 diagrammatically illustrates the phase determined between different user based on dimensionality reduction rating matrix according to the embodiment of the present disclosure
Like the flow chart of degree；
Fig. 7 diagrammatically illustrates the flow chart of the fractionation rating matrix according to the embodiment of the present disclosure；
Fig. 8 diagrammatically illustrates the flow chart of the determination potential user according to the embodiment of the present disclosure；
Fig. 9 diagrammatically illustrates the block diagram of the data processing system according to the embodiment of the present disclosure；
Figure 10 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure；
Figure 11 diagrammatically illustrates the block diagram of the 5th determining module according to the embodiment of the present disclosure；
Figure 12 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure；
Figure 13 diagrammatically illustrates the block diagram of the 6th determining module according to the embodiment of the present disclosure；
Figure 14 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure；And
Figure 15 diagrammatically illustrates the computer system for being adapted for carrying out method as described above according to the embodiment of the present disclosure
Block diagram.
Specific embodiment
Hereinafter, will be described with reference to the accompanying drawings embodiment of the disclosure.However, it should be understood that these descriptions are only exemplary
, and it is not intended to limit the scope of the present disclosure.In the following detailed description, to elaborate many specific thin convenient for explaining
Section is to provide the comprehensive understanding to the embodiment of the present disclosure.It may be evident, however, that one or more embodiments are not having these specific thin
It can also be carried out in the case where section.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid
Unnecessarily obscure the concept of the disclosure.
Term as used herein is not intended to limit the disclosure just for the sake of description specific embodiment.It uses herein
The terms "include", "comprise" etc. show the presence of the feature, step, operation and/or component, but it is not excluded that in the presence of
Or add other one or more features, step, operation or component.
There are all terms (including technical and scientific term) as used herein those skilled in the art to be generally understood
Meaning, unless otherwise defined.It should be noted that term used herein should be interpreted that with consistent with the context of this specification
Meaning, without that should be explained with idealization or excessively mechanical mode.
It, in general should be according to this using statement as " at least one in A, B and C etc. " is similar to
Field technical staff is generally understood the meaning of the statement to make an explanation (for example, " system at least one in A, B and C "
Should include but is not limited to individually with A, individually with B, individually with C, with A and B, with A and C, have B and C, and/or
System etc. with A, B, C).Using statement as " at least one in A, B or C etc. " is similar to, generally come
Saying be generally understood the meaning of the statement according to those skilled in the art to make an explanation (for example, " having in A, B or C at least
One system " should include but is not limited to individually with A, individually with B, individually with C, with A and B, have A and C, have
B and C, and/or the system with A, B, C etc.).It should also be understood by those skilled in the art that substantially arbitrarily indicating two or more
The adversative conjunction and/or phrase of optional project shall be construed as either in specification, claims or attached drawing
A possibility that giving including one of these projects, either one or two projects of these projects.For example, phrase " A or B " should
A possibility that being understood to include " A " or " B " or " A and B ".
Embodiment of the disclosure provides a kind of data processing method and system, and this method includes obtaining historical data,
In, historical data includes the operation data generated after different user operates one or more financial products, every kind of finance
Product has corresponding one or more indexs, wherein one or more indexs are used for as evaluation user behavior preference
Reference factor；According to the corresponding one or more indexs of historical data and every kind of financial product, determine different user to every kind
The scoring of financial product；The similarity between different user is determined to the scoring of every kind of financial product according to each user, wherein
Similarity is used to characterize the similitude of Behavior preference between different user；Target gold is determined according to the similarity between different user
Melt the potential user of product.
Fig. 1 diagrammatically illustrate according to the embodiment of the present disclosure can be with application data processing method and the exemplary system of system
System framework.It should be noted that being only the example that can apply the system architecture of the embodiment of the present disclosure shown in Fig. 1, to help this
Field technical staff understands the technology contents of the disclosure, but be not meant to the embodiment of the present disclosure may not be usable for other equipment,
System, environment or scene.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network according to this embodiment
104 and server 105.Network 104 between terminal device 101,102,103 and server 105 to provide communication link
Medium.Network 104 may include various connection types, such as wired and or wireless communications link etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 101,102,103
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client and/or social platform softwares.
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to the use received
The data such as family request analyze etc. processing, and by processing result (such as according to user's request or the webpage of generation, believe
Breath or data etc.) feed back to terminal device.
It should be noted that data processing method provided by the embodiment of the present disclosure can generally be executed by server 105.
Correspondingly, data processing system provided by the embodiment of the present disclosure generally can be set in server 105.The embodiment of the present disclosure
Provided data processing method can also by be different from server 105 and can with terminal device 101,102,103 and/or clothes
The server or server cluster that business device 105 communicates execute.Correspondingly, data processing system provided by the embodiment of the present disclosure
It can be set in the service that is different from server 105 and can be communicated with terminal device 101,102,103 and/or server 105
In device or server cluster.Alternatively, data processing method provided by the embodiment of the present disclosure can also by terminal device 101,
102 or 103 execute, or can also be executed by other terminal devices for being different from terminal device 101,102 or 103.Accordingly
Ground, data processing system provided by the embodiment of the present disclosure also can be set in terminal device 101,102 or 103, or setting
In other terminal devices for being different from terminal device 101,102 or 103.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Fig. 2 diagrammatically illustrates the flow chart of the data processing method according to the embodiment of the present disclosure.
As shown in Fig. 2, this method includes operation S201~S204.
In operation S201, historical data is obtained, wherein historical data includes different user to one or more financial products
The operation data generated after being operated, every kind of financial product have corresponding one or more indexs, wherein one or more
A index is used for the reference factor as evaluation user behavior preference.
In accordance with an embodiment of the present disclosure, the operation data that user generates after operating to one or more financial products can
To include but is not limited to the operation datas such as browsing, click, consumption that user carries out one or more financial products.
In accordance with an embodiment of the present disclosure, in the historical data values of acquisition, if having some long-term not in website or visitor
There is the user of any behavior to be actually probably lost on the end of family, the meaning studied to these users is not
Greatly, it is based on this situation, it can be using any active ues of platform as research object.
In accordance with an embodiment of the present disclosure, the index of financial product includes but is not limited to that user is right in nearly three months, half a year
The browsing time of the financial product, browsing duration, maximum are held position the amount of money, average yield etc., these indexs are used as
Evaluate the reference factor of user behavior preference.The corresponding one or more indexs of different financial products can be identical or not
Together, for example, the index of financing type of financial product A includes browsing duration and average yield, the index of credit type of financial product B include
Browsing duration, browsing time and maximum are held position the amount of money.
In accordance with an embodiment of the present disclosure, the corresponding one or more of every kind of financial product can be determined according to historical data
Index.Such as it is filtered out from the initial data such as the browsing data, order data, avail data of different user and can embody user
The index of Behavior preference, financial business line that can be all using on platform extract the corresponding index of different business line as benchmark,
These indexs can quantify user to the preference or loyalty of certain financial product to a certain extent.
When determining the corresponding one or more indexs of every kind of financial product by historical data, platform can be covered as far as possible
Upper all financial business lines, such model can have very strong compatibility；Simultaneously it is noted that financial product periodicity, such as
When extracting the trimestral browsing time of certain financial product, if the financial product is offline in second month, extract at this time
Trimestral browsing time is exactly inaccuracy.
It is determined different in operation S202 according to the corresponding one or more indexs of historical data and every kind of financial product
Scoring of the user to every kind of financial product.
In accordance with an embodiment of the present disclosure, due to including frequency data, duration data and value data etc. in historical data, divide
Be not the data of not commensurate, therefore when calculating correlation, can first uniform units, such as to each under each financial product
A index does segment processing, and different weights is assigned to different indexs, and multiple indexs are then unified for a scoring and are referred to
Mark.Specific calculation may is that
For example, financial product A, there is n index, this n index is all now divided into 100 sections, by the correspondence of each index
Data be mapped in each section, then i-th user, j-th of index mapping are as follows:
Wherein max (xj) be index j maximum value, min (xj) be index j minimum value, yijIt is whole between ∈ [0,100]
It counts, then final score of the user i on financial product A are as follows:
Wherein, wjIndicate that the weight of the corresponding different type index of financial product A, weight neglect greatly index to financial product
The significance level of A determines, such as browsing time weight 0.1, amount of money class 0.5.
All indexs of each financial product are as above operated, available different user is to every kind of financial product
Scoring.
In operation S203, the similarity between different user is determined to the scoring of every kind of financial product according to each user,
Wherein, similarity is used to characterize the similitude of Behavior preference between different user.
In accordance with an embodiment of the present disclosure, the correlation degree between two users can be reflected with cosine similarity.User u and
The similarity of user v is as follows:
Wherein, ruiIt is scoring of the user u on product i, rviIt is scoring of the user v on product i.
In operation S204, the potential user of destination financial product is determined according to the similarity between different user.
In accordance with an embodiment of the present disclosure, between the similarity characterization different user between different user Behavior preference it is similar
Property, usual similar user will also tend to have similar interest orientation, although user may not generate all products
Consumer behavior determines the similar users of the user according to the similarity between different user, then according to the consumption of similar users
Behavior goes to predict its preference to the financial product that do not consume.
By embodiment of the disclosure, user is determined to the scoring of every kind of financial product according to different user because using
Between similarity, the technological means of the potential user of destination financial product is determined according to the similarity between different user, it is right
It determines that the potential user of various financial products is all suitable for, without being modeled respectively for every kind of financial product, therefore saves
Regular hour cost and human cost, so at least partially overcoming use the relevant technologies to screen for different financial products
Target group is spent at high cost, and the technical issues of be not suitable for the application scenarios of a variety of financial products, and then is reduced
By the technical effect for the cost that different financial products screening target group spends.
Below with reference to Fig. 3~Fig. 8, method shown in Fig. 2 is described further in conjunction with specific embodiments.
Fig. 3 diagrammatically illustrates the flow chart of the data processing method according to another embodiment of the disclosure.
As shown in figure 3, this method includes operation S205~S208.
In operation S205, the financial product that target user traded is obtained.
In operation S206, judge in financial product that target user traded whether to include destination financial product.
It is similar to other users according to target user in the case where not including destination financial product in operation S207
Spend the scoring for determining target user to destination financial product.
In accordance with an embodiment of the present disclosure, if in the financial product that target user traded including destination financial product,
It no longer needs to carry out corresponding marketing measures, such as telemarketing, advertisement marketing etc. to the target user.
In accordance with an embodiment of the present disclosure, if in the financial product that target user traded not including destination financial product,
Then target user can be determined to target gold the scoring of destination financial product according to the higher user of target user's similarity
Melt the scoring of product.For example, the similarity of target user and user C are 80%, user C is 90 to the scoring of destination financial product
Point, then it can be the scoring of 90 points of determining target users to the scoring of destination financial product according to user C.For example, target user
Scoring be also 90 points or 80 points etc..
In operation S208, whether user, which is destination financial product, is determined to the scoring of destination financial product according to target user
Potential customers.
In accordance with an embodiment of the present disclosure, target user can be compared the scoring of destination financial product with threshold value,
If more than or equal to threshold value, it is determined that the target user is the potential customers of destination financial product, if being less than threshold value, it is determined that should
Target user is not the potential customers of destination financial product.
By embodiment of the disclosure, according to the target user of destination financial product and the phase of other users of not trading
Like the scoring for determining target user to the product is spent, so that it is determined that whether the user is potential user, due to judging that the user does not have
It traded destination financial product, the accuracy of determining potential customers can be improved.
Fig. 4 diagrammatically illustrates determining to the scoring of destination financial product according to target user according to the embodiment of the present disclosure
User whether be destination financial product potential customers flow chart.
As shown in figure 4, determining whether user is destination financial product to the scoring of destination financial product according to target user
Potential customers include operation S2081~S2083.
In operation S2081, judge whether other users traded destination financial product.
In operation S2082, in the case where other users traded destination financial product, scoring threshold value is determined.
In accordance with an embodiment of the present disclosure, in the case where other users traded destination financial product, scoring can be determined
Threshold value.
In accordance with an embodiment of the present disclosure, it in the case where other users did not trade destination financial product, can determine
The other users are 50 points to the scoring of destination financial product, and target user may be 50 to the scoring of destination financial product
Point, the potential customers of determining destination financial product more difficult at this time can incite somebody to action to improve the accuracy of determining potential customers
The target user and other users are determined as client non-potential.
In operation S2083, in the case where target user is greater than or equal to scoring threshold value to the scoring of destination financial product,
Determine that user is the potential customers of destination financial product.
In accordance with an embodiment of the present disclosure, for example, in the drawing new projects of Elder Security danger financial product, detection time is selected
Point, such as on January 1st, 2018, found in any active ues this day and before do not bought the user of Elder Security danger, to it
It is calculated as follows:
Wherein cuiThe cosine similarity of user u and i-th of association user are indicated, if i-th of association user nest egg is protected
Hinder dangerous user, then rui=1, otherwise rui=0.
Setting scoring threshold epsilon, the r if user scoresu> ε, then user u very maximum probability can also buy Elder Security danger, institute
It is the potential user of the drawing new projects of Elder Security danger financial product with user u.
By embodiment of the disclosure, to the financial product setting scoring threshold value that target user did not trade, Ke Yiti
Height determines the accuracy of potential customers.
Fig. 5 diagrammatically illustrates the flow chart of the data processing method according to another embodiment of the disclosure.
As shown in figure 5, this method includes operation S209~S211.
In operation S209, after determining different user to the scoring of every kind of financial product, according to different user to every kind
The scoring of financial product generates rating matrix, wherein the dimension of rating matrix is U × I, and U indicates that number of users, I indicate finance
Product quantity.
In operation S210, dimension-reduction treatment is carried out to rating matrix, obtains the dimensionality reduction rating matrix that dimension is U × K.
In operation S211, the similarity between different user is determined based on dimensionality reduction rating matrix.
In accordance with an embodiment of the present disclosure, since user usually generally scores to fraction financial product, when data are non-
When often sparse, two users have been difficult to identical or approximate scoring.The method of Data Dimensionality Reduction can solve the problem, lead to
It crosses and financial product score is mapped to latent variables space to obtain feature outstanding between user, significant associations more in this way
Also it can be found.
The rating matrix for being U × I for dimension, full-rank factorization are as follows:
RU×I=PU×kQk×I (5)
Wherein U indicates that total research number of users, I indicate the financial product quantity of screening.
In accordance with an embodiment of the present disclosure, the product that can use the known scoring fitting P and Q in rating matrix R, wherein instructing
Practicing error can be defined as minimizing square Frobenius norm:
Error is minimized by training, then PQ can preferably be fitted R, then matrix P is commenting after dimensionality reduction
Sub-matrix, dimension also drop to k from I.
By embodiment of the disclosure, rating matrix after decomposition is reduced to less dimension from multiple dimensions, and storage is empty
Between it is smaller, computational efficiency is also higher.
Fig. 6 diagrammatically illustrates the phase determined between different user based on dimensionality reduction rating matrix according to the embodiment of the present disclosure
Like the flow chart of degree.
As shown in fig. 6, based on dimensionality reduction rating matrix determine the similarity between different user include operation S2111~
S2112。
In operation S2111, dimensionality reduction rating matrix is split into multiple submatrixs.
In operation S2112, multiple submatrixs are handled using parallel computation mode, it is similar between different user to determine
Degree.
In accordance with an embodiment of the present disclosure, after it have passed through rating matrix dimensionality reduction, without the feature of I dimension, problem turns
It turns to for user u and user v, finds the coordinate of user u and user v on k dimension unit spherical surface, user u and user v are in ball
It is closer on face, then user u and user v are more close to the scoring of the same article.
Fig. 7 diagrammatically illustrates the flow chart of the fractionation rating matrix according to the embodiment of the present disclosure.
As shown in fig. 7, the quantity N of user is usually a very big numerical value when practical calculating, if with the method for circulation
User's similitude is calculated, the time complexity of O (n2) is needed, so the method using matrix multiple calculates, cosine phase above
It is split like degree formula (3) as follows:
Can vector value to each user divided by root sum square, matrix form is as follows:
CN×NThe i-th row jth column of the user's similarity matrix for as needing to solve, matrix indicate between user i and user j
Cosine similarity.
Under normal circumstances, since number of users is very more, in the case that N is million grades or more, server memory is also very
The matrix multiplication hard to tolerate for receiving this magnitude, it is possible to matrix PN×kIt is split, obtains multiple submatrixs, such as permanent moment
Battle array line number is 100, is split as altogetherA submatrix, as follows:
In accordance with an embodiment of the present disclosure, multiple submatrixs can be handled using parallel computation mode, to determine different user
Between similarity.
In accordance with an embodiment of the present disclosure, under normal circumstances, it does not need to retain N number of similarity of each user, only need
Retain the certain customers of strong correlation, for example, can be with maximum preceding 1000 association users of retention relationship.In order to improve
Relevance threshold can be arranged in the efficiency of sequence in advance, filter out the user that a part of similarity is greater than threshold value, then arranged
Sequence after completing sequence, the matrix calculation result after fractionation is polymerize to get matrix of consequence C is arrivedN×1000, so far customer relationship
Estimate exploitation to complete.
Fig. 8 diagrammatically illustrates the flow chart of the determination potential user according to the embodiment of the present disclosure.
As shown in figure 8, in the case where determining any active ues is research object, it can be according to the browsing number of any active ues
Rating matrix is generated according to, order data and avail data, dimensionality reduction then is carried out to matrix, calculates the degree of correlation between user, it will
The user that user's score is greater than threshold value is determined as potential target user.
By embodiment of the disclosure, dimensionality reduction rating matrix is split into multiple submatrixs, it can be with parallel computation, to mention
Computationally efficient.
Fig. 9 diagrammatically illustrates the block diagram of the data processing system according to the embodiment of the present disclosure.
As shown in figure 9, data processing system 400 obtains module 401 including first, the first determining module 402, second determines
Module 403 and third determining module 404.
First acquisition module 401 is for obtaining historical data, wherein historical data includes different user to one or more
The operation data that financial product generates after being operated, every kind of financial product have corresponding one or more indexs, wherein
One or more indexs are used for the reference factor as evaluation user behavior preference.
First determining module 402 is used for according to the corresponding one or more indexs of historical data and every kind of financial product,
Determine scoring of the different user to every kind of financial product.
Second determining module 403 is used to determine between different user the scoring of every kind of financial product according to each user
Similarity, wherein similarity is used to characterize the similitude of Behavior preference between different user.
Third determining module 404 is used to determine the potential use of destination financial product according to the similarity between different user
Family.
By embodiment of the disclosure, user is determined to the scoring of every kind of financial product according to different user because using
Between similarity, the technological means of the potential user of destination financial product is determined according to the similarity between different user, it is right
It determines that the potential user of various financial products is all suitable for, without being modeled respectively for every kind of financial product, therefore saves
Regular hour cost and human cost, so at least partially overcoming use the relevant technologies to screen for different financial products
Target group is spent at high cost, and the technical issues of be not suitable for the application scenarios of a variety of financial products, and then is reduced
By the technical effect for the cost that different financial products screening target group spends.
Figure 10 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure.
As shown in Figure 10, data processing system 400 further includes the second acquisition module 405, the determination of judgment module the 406, the 4th
Module 407 and the 5th determining module 408.
Second acquisition module 405 is for obtaining the financial product that target user traded.
Judgment module 406 is used to judge in financial product that target user traded whether including destination financial product.
4th determining module 407 is used in the case where not including destination financial product, according to target user and other use
The similarity at family determines scoring of the target user to destination financial product.
5th determining module 408 is used to determine whether user is target to the scoring of destination financial product according to target user
The potential customers of financial product.
By embodiment of the disclosure, according to the target user of destination financial product and the phase of other users of not trading
Like the scoring for determining target user to the product is spent, so that it is determined that whether the user is potential user, due to judging that the user does not have
It traded destination financial product, the accuracy of determining potential customers can be improved.
Figure 11 diagrammatically illustrates the block diagram of the 5th determining module according to the embodiment of the present disclosure.
As shown in figure 11, the 5th determining module 408 is determined including judging unit 4081, the first determination unit 4082 and second
Unit 4083.
Judging unit 4081 is for judging whether other users traded destination financial product.
First determination unit 4082 is used in the case where other users traded destination financial product, determines scoring threshold
Value.
Second determination unit 4083 is used to be greater than or equal to scoring threshold value to the scoring of destination financial product in target user
In the case where, determine that user is the potential customers of destination financial product.
By embodiment of the disclosure, to the financial product setting scoring threshold value that target user did not trade, Ke Yiti
Height determines the accuracy of potential customers.
Figure 12 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure.
As shown in figure 12, data processing system further includes generation module 409, processing module 410 and the 6th determining module
411。
Generation module 409 is used for after determining different user to the scoring of every kind of financial product, according to different user pair
The scoring of every kind of financial product generates rating matrix, wherein the dimension of rating matrix is U × I, and U indicates that number of users, I indicate
Financial product quantity.
Processing module 410 is used to carry out dimension-reduction treatment to rating matrix, obtains the dimensionality reduction rating matrix that dimension is U × K.
6th determining module 411 is used to determine the similarity between different user based on dimensionality reduction rating matrix.
By embodiment of the disclosure, rating matrix after decomposition is reduced to less dimension from multiple dimensions, and storage is empty
Between it is smaller, computational efficiency is also higher.
Figure 13 diagrammatically illustrates the block diagram of the 6th determining module according to the embodiment of the present disclosure.
As shown in figure 13, the 6th determining module 411 includes split cells 4111 and processing unit 4112.
Split cells 4111 is used to dimensionality reduction rating matrix splitting into multiple submatrixs.
Processing unit 4112 is used to handle multiple submatrixs using parallel computation mode, to determine the phase between different user
Like degree.
By embodiment of the disclosure, dimensionality reduction rating matrix is split into multiple submatrixs, it can be with parallel computation, to mention
Computationally efficient.
Figure 14 diagrammatically illustrates the block diagram of the data processing system according to another embodiment of the disclosure.
As shown in figure 14, in accordance with an embodiment of the present disclosure, data processing system 400 further includes the 7th determining module 412.
7th determining module 412 is used to determine that the corresponding one or more of every kind of financial product refers to according to historical data
Mark.
When determining the corresponding one or more indexs of every kind of financial product by historical data, platform can be covered as far as possible
Upper all financial business lines, such model can have very strong compatibility；Simultaneously it is noted that financial product periodicity, such as
When extracting the trimestral browsing time of certain financial product, if the financial product is offline in second month, extract at this time
Trimestral browsing time is exactly inaccuracy.
It is module according to an embodiment of the present disclosure, submodule, unit, any number of or in which any more in subelement
A at least partly function can be realized in a module.It is single according to the module of the embodiment of the present disclosure, submodule, unit, son
Any one or more in member can be split into multiple modules to realize.According to the module of the embodiment of the present disclosure, submodule,
Any one or more in unit, subelement can at least be implemented partly as hardware circuit, such as field programmable gate
Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity
Road (ASIC), or can be by the hardware or firmware for any other rational method for integrate or encapsulate to circuit come real
Show, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several appropriately combined next reality
It is existing.Alternatively, can be at least by part according to one or more of the module of the embodiment of the present disclosure, submodule, unit, subelement
Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.
For example, first obtain module 401, the first determining module 402, the second determining module 403, third determining module 404,
Second obtains module 405, judgment module 406, the 4th determining module 407, the 5th determining module 408, generation module 409, processing
Module 410, the 6th determining module 411, the 7th determining module 412, judging unit 4081, the first determination unit 4082, second are really
It is single that any number of in order member 4083, split cells 4111 and processing unit 4112 may be incorporated in a module/unit/son
It is realized in member or any one module/unit/subelement therein can be split into multiple module/unit/subelements.
Alternatively, one or more modules/unit/subelement at least partly function in these module/unit/subelements can be with it
He combines module/unit/subelement at least partly function, and realizes in a module/unit/subelement.According to this
Disclosed embodiment, first obtain module 401, the first determining module 402, the second determining module 403, third determining module 404,
Second obtains module 405, judgment module 406, the 4th determining module 407, the 5th determining module 408, generation module 409, processing
Module 410, the 6th determining module 411, the 7th determining module 412, judging unit 4081, the first determination unit 4082, second are really
At least one of order member 4083, split cells 4111 and processing unit 4112 can at least be implemented partly as hardware electricity
Road, such as field programmable gate array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, encapsulation
On system, specific integrated circuit (ASIC), or can be by carrying out any other reasonable side that is integrated or encapsulating to circuit
The hardware such as formula or firmware realize, or with any one in three kinds of software, hardware and firmware implementations or with wherein any
It is several appropriately combined to realize.Alternatively, first obtains module 401, the first determining module 402, the second determining module 403, the
Three determining modules 404, second obtain module 405, judgment module 406, the 4th determining module 407, the 5th determining module 408, life
It is determined at module 409, processing module 410, the 6th determining module 411, the 7th determining module 412, judging unit 4081, first single
At least one of first 4082, second determination unit 4083, split cells 4111 and processing unit 4112 can be at least by parts
Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.
It should be noted that in embodiment of the disclosure in data processing system part and embodiment of the disclosure at data
Reason method part be it is corresponding, the description of data processing system part is with specific reference to data processing method part, herein no longer
It repeats.
Figure 15 diagrammatically illustrates the computer system for being adapted for carrying out method as described above according to the embodiment of the present disclosure
Block diagram.Computer system shown in Figure 15 is only an example, should not function and use scope to the embodiment of the present disclosure
Bring any restrictions.
It as shown in figure 15, include processor 501 according to the computer system of the embodiment of the present disclosure 500, it can be according to depositing
Storage is loaded into random access storage device (RAM) 503 in the program in read-only memory (ROM) 502 or from storage section 508
Program and execute various movements appropriate and processing.Processor 501 for example may include general purpose microprocessor (such as CPU),
Instruction set processor and/or related chip group and/or special microprocessor (for example, specific integrated circuit (ASIC)), etc..Place
Reason device 501 can also include the onboard storage device for caching purposes.Processor 501 may include for executing according to the disclosure
Single treatment unit either multiple processing units of the different movements of the method flow of embodiment.
In RAM 503, it is stored with system 500 and operates required various programs and data.Processor 501, ROM 502 with
And RAM 503 is connected with each other by bus 504.Processor 501 is held by executing the program in ROM 502 and/or RAM 503
The various operations gone according to the method flow of the embodiment of the present disclosure.It is noted that described program also can store except ROM 502
In one or more memories other than RAM 503.Processor 501 can also be stored in one or more of by execution
Program in memory executes the various operations of the method flow according to the embodiment of the present disclosure.
In accordance with an embodiment of the present disclosure, system 500 can also include input/output (I/O) interface 505, input/output
(I/O) interface 505 is also connected to bus 504.System 500 can also include be connected to I/O interface 505 with one in lower component
Item is multinomial: the importation 506 including keyboard, mouse etc.；Including such as cathode-ray tube (CRT), liquid crystal display (LCD)
Deng and loudspeaker etc. output par, c 507；Storage section 508 including hard disk etc.；And including such as LAN card, modulatedemodulate
Adjust the communications portion 509 of the network interface card of device etc..Communications portion 509 executes communication process via the network of such as internet.
Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as disk, CD, magneto-optic disk, semiconductor
Memory etc. is mounted on as needed on driver 510, in order to be pacified as needed from the computer program read thereon
It is packed into storage section 508.
In accordance with an embodiment of the present disclosure, computer software journey may be implemented as according to the method flow of the embodiment of the present disclosure
Sequence.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer readable storage medium
Computer program, which includes the program code for method shown in execution flow chart.In such implementation
In example, which can be downloaded and installed from network by communications portion 509, and/or from detachable media 511
It is mounted.When the computer program is executed by processor 501, the above-mentioned function limited in the system of the embodiment of the present disclosure is executed
Energy.In accordance with an embodiment of the present disclosure, system as described above, unit, module, unit etc. can pass through computer program
Module is realized.
The disclosure additionally provides a kind of computer readable storage medium, which can be above-mentioned reality
It applies included in equipment/device/system described in example；Be also possible to individualism, and without be incorporated the equipment/device/
In system.Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are performed
When, realize the method according to the embodiment of the present disclosure.
In accordance with an embodiment of the present disclosure, computer readable storage medium can be computer-readable signal media or calculating
Machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, portable of one or more conducting wires
Formula computer disk, hard disk, random access storage device (RAM), 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
The above-mentioned any appropriate combination of person.In the disclosure, computer readable storage medium can be it is any include or storage program
Tangible medium, which can be commanded execution system, device or device use or in connection.And in this public affairs
In opening, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer readable storage medium other than storage medium, the computer readable storage medium can send, propagate or pass
It is defeated to be used for by the use of instruction execution system, device or device or program in connection.Computer-readable storage medium
The program code for including in matter can transmit with any suitable medium, including but not limited to: wireless, wired, optical cable, radio frequency letter
Number etc. or above-mentioned any appropriate combination.
For example, in accordance with an embodiment of the present disclosure, computer readable storage medium may include above-described ROM 502
And/or one or more memories other than RAM 503 and/or ROM 502 and RAM 503.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
It will be understood by those skilled in the art that the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations or/or combination, even if such combination or combination are not expressly recited in the disclosure.Particularly, exist
In the case where not departing from disclosure spirit or teaching, the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination.All these combinations and/or combination each fall within the scope of the present disclosure.
Embodiment of the disclosure is described above.But the purpose that these embodiments are merely to illustrate that, and
It is not intended to limit the scope of the present disclosure.Although respectively describing each embodiment above, but it is not intended that each reality
Use cannot be advantageously combined by applying the measure in example.The scope of the present disclosure is defined by the appended claims and the equivalents thereof.It does not take off
From the scope of the present disclosure, those skilled in the art can make a variety of alternatives and modifications, these alternatives and modifications should all fall in this
Within scope of disclosure.
Claims (14)
1. a kind of data processing method, comprising:
Obtain historical data, wherein the historical data includes after different user operates one or more financial products
The operation data of generation, every kind of financial product have corresponding one or more indexs, wherein one or more of indexs
For the reference factor as evaluation user behavior preference；
According to the corresponding one or more indexs of the historical data and every kind of financial product, determine different user to institute
State the scoring of every kind of financial product；
The similarity between different user is determined to the scoring of every kind of financial product according to each user, wherein the phase
Like the similitude spent for characterizing Behavior preference between different user；
The potential user of destination financial product is determined according to the similarity between the different user.
2. according to the method described in claim 1, wherein, the method also includes:
Obtain the financial product that target user traded；
Judge in financial product that the target user traded whether to include the destination financial product；
In the case where not including the destination financial product, institute is determined according to the similarity of the target user and other users
State scoring of the target user to the destination financial product；And
Whether the user, which is that the destination financial produces, is determined to the scoring of the destination financial product according to the target user
The potential customers of product.
3. true according to scoring of the target user to the destination financial product according to the method described in claim 2, wherein
Whether the fixed user is that the potential customers of the destination financial product include:
Judge whether the other users traded the destination financial product；
In the case where the other users traded the destination financial product, scoring threshold value is determined；And
In the case where the target user is greater than or equal to the scoring threshold value to the scoring of the destination financial product, determine
The user is the potential customers of the destination financial product.
4. according to the method described in claim 1, wherein, determine different user to the scoring of every kind of financial product it
Afterwards, the method also includes:
Rating matrix is generated to the scoring of every kind of financial product according to the different user, wherein the rating matrix
Dimension is U × I, and the U indicates that number of users, the I indicate financial product quantity；
Dimension-reduction treatment is carried out to the rating matrix, obtains the dimensionality reduction rating matrix that dimension is U × K；And
The similarity between different user is determined based on the dimensionality reduction rating matrix.
5. according to the method described in claim 1, wherein, being determined based on the dimensionality reduction rating matrix similar between different user
Degree includes:
The dimensionality reduction rating matrix is split into multiple submatrixs；And
The multiple submatrix is handled using parallel computation mode, to determine the similarity between different user.
6. according to the method described in claim 1, wherein, the method also includes:
According to the historical data, the corresponding one or more indexs of every kind of financial product are determined.
7. a kind of data processing system, comprising:
First obtains module, for obtaining historical data, wherein the historical data includes different user to one or more gold
Melt the operation data generated after product is operated, every kind of financial product has corresponding one or more indexs, wherein institute
One or more indexs are stated for the reference factor as evaluation user behavior preference；
First determining module, for being referred to according to the historical data and the corresponding one or more of every kind of financial product
Mark, determines scoring of the different user to every kind of financial product；
Second determining module, for determining the phase between different user to the scoring of every kind of financial product according to each user
Like degree, wherein the similarity is used to characterize the similitude of Behavior preference between different user；
Third determining module, for determining the potential user of destination financial product according to the similarity between the different user.
8. system according to claim 7, wherein the system also includes:
Second obtains module, the financial product traded for obtaining target user；
Judgment module, for judging in financial product that the target user traded whether to include the destination financial product；
4th determining module, in the case where not including the destination financial product, according to the target user and other
The similarity of user determines scoring of the target user to the destination financial product；And
5th determining module, for whether determining the user to the scoring of the destination financial product according to the target user
For the potential customers of the destination financial product.
9. system according to claim 8, wherein the 5th determining module includes:
Judging unit, for judging whether the other users traded the destination financial product；
First determination unit, in the case where the other users traded the destination financial product, determining scoring threshold
Value；And
Second determination unit, for being greater than or equal to the scoring to the scoring of the destination financial product in the target user
In the case where threshold value, determine that the user is the potential customers of the destination financial product.
10. system according to claim 7, wherein the system also includes:
Generation module, for after determining different user to the scoring of every kind of financial product, according to the different user
Rating matrix is generated to the scoring of every kind of financial product, wherein the dimension of the rating matrix is U × I, and the U is indicated
Number of users, the I indicate financial product quantity；
Processing module obtains the dimensionality reduction rating matrix that dimension is U × K for carrying out dimension-reduction treatment to the rating matrix；And
6th determining module, for determining the similarity between different user based on the dimensionality reduction rating matrix.
11. system according to claim 7, wherein the 6th determining module includes:
Split cells, for the dimensionality reduction rating matrix to be split into multiple submatrixs；And
Processing unit, it is similar between different user to determine for handling the multiple submatrix using parallel computation mode
Degree.
12. system according to claim 7, wherein the system also includes:
7th determining module, for determining the corresponding one or more of every kind of financial product according to the historical data
Index.
13. a kind of computer system, comprising:
One or more processors；
Memory, for storing one or more programs,
Wherein, when one or more of programs are executed by one or more of processors, so that one or more of
Processor realizes data processing method described in any one of claims 1 to 6.
14. a kind of computer readable storage medium, is stored thereon with executable instruction, which makes to handle when being executed by processor
Device realizes data processing method described in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810838841.8A CN109087138A (en) | 2018-07-26 | 2018-07-26 | Data processing method and system, computer system and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810838841.8A CN109087138A (en) | 2018-07-26 | 2018-07-26 | Data processing method and system, computer system and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109087138A true CN109087138A (en) | 2018-12-25 |
Family
ID=64831185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810838841.8A Pending CN109087138A (en) | 2018-07-26 | 2018-07-26 | Data processing method and system, computer system and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087138A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162714A (en) * | 2019-01-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Content delivery method, calculates equipment and computer readable storage medium at device |
| CN110377522A (en) * | 2019-07-22 | 2019-10-25 | 中国工商银行股份有限公司 | The test method for scene of trading, calculates equipment and medium at device |
| CN110888945A (en) * | 2019-11-28 | 2020-03-17 | 上海风秩科技有限公司 | User behavior prediction method and device, electronic equipment and storage medium |
| CN110895564A (en) * | 2019-11-05 | 2020-03-20 | 泰康保险集团股份有限公司 | Potential customer data processing method and device |
| CN110969201A (en) * | 2019-11-28 | 2020-04-07 | 广州云徙科技有限公司 | Method for identifying and matching relationship between enterprise member and hidden customer |
| CN112148987A (en) * | 2020-10-12 | 2020-12-29 | 平安科技（深圳）有限公司 | Message pushing method based on target object activity and related equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799656A (en) * | 2012-07-03 | 2012-11-28 | 复旦大学 | Target-user-oriented individualized product package extracting method |
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| US9633081B1 (en) * | 2013-09-30 | 2017-04-25 | Google Inc. | Systems and methods for determining application installation likelihood based on user network characteristics |
| CN107220303A (en) * | 2017-05-10 | 2017-09-29 | 努比亚技术有限公司 | Recommendation method, device and the computer-readable medium of a kind of application |
| CN107688988A (en) * | 2017-09-02 | 2018-02-13 | 广东奡风科技股份有限公司 | A kind of financial product real-time recommendation method |
| CN107871269A (en) * | 2017-11-08 | 2018-04-03 | 广东奡风科技股份有限公司 | A kind of KNN of client's factor based on financial product Interactive matrix recommends method |
-
2018
- 2018-07-26 CN CN201810838841.8A patent/CN109087138A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799656A (en) * | 2012-07-03 | 2012-11-28 | 复旦大学 | Target-user-oriented individualized product package extracting method |
| US9633081B1 (en) * | 2013-09-30 | 2017-04-25 | Google Inc. | Systems and methods for determining application installation likelihood based on user network characteristics |
| CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
| CN107220303A (en) * | 2017-05-10 | 2017-09-29 | 努比亚技术有限公司 | Recommendation method, device and the computer-readable medium of a kind of application |
| CN107688988A (en) * | 2017-09-02 | 2018-02-13 | 广东奡风科技股份有限公司 | A kind of financial product real-time recommendation method |
| CN107871269A (en) * | 2017-11-08 | 2018-04-03 | 广东奡风科技股份有限公司 | A kind of KNN of client's factor based on financial product Interactive matrix recommends method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162714A (en) * | 2019-01-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Content delivery method, calculates equipment and computer readable storage medium at device |
| CN110162714B (en) * | 2019-01-30 | 2023-11-14 | 腾讯科技（深圳）有限公司 | Content pushing method, device, computing equipment and computer readable storage medium |
| CN110377522A (en) * | 2019-07-22 | 2019-10-25 | 中国工商银行股份有限公司 | The test method for scene of trading, calculates equipment and medium at device |
| CN110377522B (en) * | 2019-07-22 | 2023-10-03 | 中国工商银行股份有限公司 | Transaction scene testing method, device, computing equipment and medium |
| CN110895564A (en) * | 2019-11-05 | 2020-03-20 | 泰康保险集团股份有限公司 | Potential customer data processing method and device |
| CN110888945A (en) * | 2019-11-28 | 2020-03-17 | 上海风秩科技有限公司 | User behavior prediction method and device, electronic equipment and storage medium |
| CN110969201A (en) * | 2019-11-28 | 2020-04-07 | 广州云徙科技有限公司 | Method for identifying and matching relationship between enterprise member and hidden customer |
| CN112148987A (en) * | 2020-10-12 | 2020-12-29 | 平安科技（深圳）有限公司 | Message pushing method based on target object activity and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210173711A1 (en) | Integrated value chain risk-based profiling and optimization | |
| CN109087138A (en) | Data processing method and system, computer system and readable storage medium storing program for executing | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN107729937A (en) | For determining the method and device of user interest label | |
| CN109840730B (en) | Method and device for data prediction | |
| CN107609890A (en) | A kind of method and apparatus of order tracking | |
| CN107767070A (en) | method and device for information popularization | |
| CN109214730A (en) | Information-pushing method and device | |
| CN110335140A (en) | Method, apparatus, electronic equipment based on the black intermediary of social networks prediction loan | |
| CN110866625A (en) | Promotion index information generation method and device | |
| CN110309293A (en) | Text recommended method and device | |
| CN110245684A (en) | Data processing method, electronic equipment and medium | |
| CN109978306B (en) | Data processing method and device | |
| CN110443265A (en) | A kind of behavioral value method and apparatus based on corporations | |
| CN113094602B (en) | Hotel recommendation method, system, equipment and medium | |
| CN110827044A (en) | Method and device for extracting user interest mode | |
| CN115392361A (en) | Intelligent sorting method and device, computer equipment and storage medium | |
| CN112231299A (en) | Method and device for dynamically adjusting feature library | |
| CN110119784A (en) | A kind of order recommended method and device | |
| CN109726882A (en) | The method and apparatus that a kind of pair of object is evaluated | |
| CN116911913B (en) | Method and device for predicting interaction result | |
| CN109740054A (en) | It is a kind of for determining the method and apparatus of the association financial information of target user | |
| CN116703498B (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN108846743B (en) | Method and apparatus for generating information | |
| CN112990954A (en) | Method and device for distributing coupons |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Beijing Daxing District, Beijing Applicant after: Jingdong Digital Technology Holding Co., Ltd. Address before: Room 221, 2nd floor, Block C, 18 Kechuang 11th Street, Daxing Economic and Technological Development Zone, Beijing, 100176 Applicant before: Beijing Jingdong Financial Technology Holding Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |