CN106991598A - Data push method and its system - Google Patents
Data push method and its system Download PDFInfo
- Publication number
- CN106991598A CN106991598A CN201710224488.XA CN201710224488A CN106991598A CN 106991598 A CN106991598 A CN 106991598A CN 201710224488 A CN201710224488 A CN 201710224488A CN 106991598 A CN106991598 A CN 106991598A
- Authority
- CN
- China
- Prior art keywords
- user
- service product
- product
- similarity
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The present invention discloses a kind of data push method and its system, and wherein methods described includes：Obtain the multiple service product information associated with the first user；The similarity between the multiple service product is calculated, the first service product and the second service product that similarity is more than preset value is obtained；Do not associated if second user is associated with first service product with second service product, set the second user to be associated with second service product, and second service product is pushed into the second user；Wherein described first user has identical or related attribute information to the second user.Intellectuality, automation and personalization that service product is recommended are realized by the present invention.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of data push method and its system.
Background technology
At present, the personal investment finance product of business bank is either from circulation or from issuing scale, all
Constantly expansion with surprising rapidity.Management of personal money product is brisk for supply and demand, and the kind and investment scope of finance product business are also increasingly
It is abundant.Therefore, information technology how is made full use of, the intelligence degree of service is improved, follow-up client produces to Investment ＆ Financing in time
The changes in demand of product is each suitable finance product of client's well-chosen and carries out personalized recommendation, is thrown as bank individual
Provide finance services in very core the problem of.
The main sales mode of bank investment finance product of the prior art is operated on marketing line under line.The pipe of flow
The artificial control of reason head office, formulates specific sales target and examination total amount in lines, and subbranch assigns financing manager actively to contact visitor
Family.Customer manager need irregularly by phone, short message, wechat and face to face link up etc. mode, set up moderately good with client
Service relation, actively recommends sale finance product.In addition, bank can also release exclusive product for specific crowd research and development does rationed marketing
Purposes, such as payroll credit client are exclusive, the exclusive product of loan customer.
However, there are many drawbacks in the way of recommendation of the One-to-one marketing under this line.Although customer service is experienced,
Human cost is too high, and the easy presence service blind area of customer manager.Customer manager is usually required while being responsible for 300-500 visitor
Family, but because energy is limited, the client of the relatively high net value in itself objective group can only be paid close attention to, can often contact effectively safeguard
Between 10%~20%, and selectivity neglects most long-tail client.
And the overall way of recommendation safeguarded of prior art, such as bulk SMS and Mobile banking's page presentation, to target
The division of objective group is relatively rough, and personalized difference is small.More seriously, recommend more product-oriented, it is impossible to accomplish
It is market-oriented, give lead referral real product interested.
In addition, also there is the unbalanced problem of Asset Allocation.Total branch of business bank has clearly to most of subbranch
Various product sales target inventory, renewal frequency is indefinite.Because each Marketing Strategy is different, the customer manager of branch bank
Assets equilibrium allocation is not often considered, is tended to selection product that is single, easily marketing one of convenience and is promoted,
It is easily caused Asset Allocation unbalanced.
In summary, different clients how to be met in the structure of finance product, time limit, mobility, security, earning rate etc.
The Demand perference difference of aspect, provides intelligentized personalized finance product for client and recommends, as bank individual Investment ＆ Financing
Business is promoting IT application, urgent problem to be solved in intelligent Process.
The content of the invention
It is a primary object of the present invention to provide a kind of data push method and its system, with solve it is of the prior art not
The problem of being pushes customer individual business product.
A kind of data processing method is provided according to embodiments of the present invention, and it includes：Obtain associated with the first user many
Individual service product information；The similarity between the multiple service product is calculated, the first industry that similarity is more than preset value is obtained
Business product and the second service product；Do not closed if second user is associated with first service product with second service product
Connection, then set the second user to be associated with second service product, and second service product is pushed into described the
Two users；Wherein described first user has identical or related attribute information to the second user.
Alternatively, methods described also includes：The attribute information of the multiple service product in the scheduled time is obtained, according to
The multiple service product is divided into multiple classifications by the attribute information；It is similar between service product in calculating same category
Degree.
Alternatively, methods described also includes：The attribute information for obtaining user simultaneously carries out a point group to user, wherein, described the
One user and the second user belong to same customers.
Alternatively, the similarity calculated between the multiple service product, including：
The user profile associated with each service product is counted respectively, according to the user associated with each service product
Information calculates the similarity between the multiple service product.
Alternatively, before multiple service product information that the acquisition is associated with the first user, methods described is also wrapped
Include：The multiple service product information associated with first user are determined according to the behavioural information of first user, wherein
The service product information includes：The amount of money, time.
A kind of data delivery system is provided according to embodiments of the present invention, and it includes：Acquisition module, is used for obtaining with first
The associated multiple service product information in family；Computing module, for calculating the similarity between the multiple service product, is obtained
Similarity is more than the first service product and the second service product of preset value；Processing module is pushed, if for second user and institute
State the association of the first service product not associate with second service product, then the second user and second business are set
Product is associated, and second service product is pushed into the second user；Wherein described first user and described second uses
Family has identical or related attribute information.
Alternatively, the system also includes：The acquisition module, is additionally operable to obtain the multiple business in the scheduled time
The attribute information of product, is divided into multiple classifications according to the attribute information by the multiple service product；The computing module, also
For calculating the similarity between the service product in same category.
Alternatively, the system also includes：Also include：Customer clustering module, for obtaining the attribute information of user and right
User carries out a point group, wherein, first user and the second user belong to same customers.
Alternatively, the computing module is used for, and the user profile associated with each service product is counted respectively, according to
The associated user profile of each service product calculates the similarity between the multiple service product.
Alternatively, the system also includes：Also include：Related product determining module, for according to first user's
Behavioural information determines the multiple service product information associated with first user, wherein the service product information includes：
The amount of money, time.
Technique according to the invention scheme, by using the collaborative filtering based on article, precisely, rapidly calculates and uses
Family personalized product is recommended, and client is pushed in the form of differentiation, and the intelligence that service product is recommended can be realized well
Change, automate and personalized.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the present invention, this hair
Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of data processing method according to embodiments of the present invention；
Fig. 2 shows the stream of the investment and financing products personalized recommendation method according to embodiments of the present invention based on customer grouping
Cheng Tu；
Fig. 3 is original data source dimension schematic diagram according to embodiments of the present invention；
Fig. 4 is data conversion treatment process schematic according to embodiments of the present invention；
Fig. 5 is the structured flowchart of data delivery system according to embodiments of the present invention.
Embodiment
The present invention relates to the individual character to service product (including the bank investment such as financing, fund, insurance, noble metal manage money matters class)
Change and push.The present invention in objective group by according to dimensional characteristics cluster subdivision customer group, then using and being based on product client
Collaborative filtering, precisely, rapidly calculate customer personalized finance product and recommend, then be subject to banking rule adjustment,
And to be illustrated in the form of differentiation in the recommendation page of client, the intelligence that finance services product is pushed can be realized well
Change, automate and personalized.
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the specific embodiment of the invention and
Technical solution of the present invention is clearly and completely described corresponding accompanying drawing.Obviously, described embodiment is only the present invention one
Section Example, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not doing
Go out the every other embodiment obtained under the premise of creative work, belong to the scope of protection of the invention.
Below in conjunction with accompanying drawing, the technical scheme that various embodiments of the present invention are provided is described in detail.
A kind of data processing method is provided according to embodiments of the present invention, applied to smart mobile phone, tablet personal computer, computer etc.
Client.Fig. 1 is the flow chart of data processing method according to an embodiment of the invention, as shown in figure 1, methods described bag
Include：
Step S102, obtains the multiple service product information associated with the first user.
In the present invention, it can be determined by the behavioural information of first user associated with first user many
Individual service product information.The buying behavior of user illustrates the user to the preference of certain service product or likes program.For example, with
First user's traffic associated product can be the bank financing class product of the first user purchase.It is associated with user in acquisition
, it is necessary to classify to service product before service product information, mainly according to the type of product, risk class, the time limit, rise
The product attributes such as purchase threshold, distributing and releasing corporation are classified to product.In this step, obtain associated with the first user multiple
Service product information, can be the product category of each service product in the multiple service product information for obtain the first user purchase
Property.Wherein, the service product can be bank financial product.
Step S104, calculates the similarity between the multiple service product, obtains similarity is more than preset value first
Service product and the second service product.
First, the attribute information of the multiple service product associated with the first user in the scheduled time is obtained, according to
The multiple service product is divided into multiple classifications by the attribute information.Then, between the service product in calculating same category
Similarity, obtain similarity be more than preset value the first service product and the second service product.That is, first industry
Be engaged in product and second service product can belong to same category of service product.
Step S106, is not associated if second user is associated with first service product with second service product,
Then set the second user to be associated with second service product, and second service product is pushed to described second and use
Family；Wherein described first user has identical or related attribute information to the second user.
In this step or before, it is necessary to classify according to the attribute information of user to client, same customers are adhered to separately
Consumer possess a certain degree of similitude, and there is obvious otherness between different subdivision customers.
By the embodiment of the present invention, every client is logged in after Mobile banking, and system is by according to the offline of backstage recommended models
Calculate, capture the product class of its preference, select the product of high expected year income/history return rate to be put into every class and push away in order
Recommend in position.
The embodiment of the present invention is described in detail with reference to Fig. 2.Fig. 2 shows according to embodiments of the present invention based on customer grouping
Investment and financing products personalized recommendation method flow chart, as shown in Fig. 2 including：
Step S202, acquisition includes the data message of full dose user and the user of small customers.Mainly include client properties
(or being user property), product attribute, trading activity (or being transaction journal) three broad aspects.With reference to Fig. 3, client properties master
To include age, sex, region, time of opening an account, average daily assets etc.；Product attribute mainly include type, risk class, the time limit,
Play purchase threshold etc.；Trading activity includes time buying, product IDs, amount of money etc..For example, obtaining a timing by database mode
The product attribute information of all investment and financing products of interior (in nearest 1 year) user, and above-mentioned data are analyzed.
In practice, the investment and financing products of business bank generally include break even finance product, common finance product, base
Several major classes such as gold, insurance, gold.Because bank financial product has cycle on sale short particularity, the embodiment of the present invention exists
Primary concern product subclass rather than specific product in commending system.The Expressive Features of product subclass are broadly divided into product time limit, wind
All finance products are carried out classification subdivision, as shown in table 1 by dangerous grade, purchase threshold, distributing and releasing corporation etc. based on this.
Table 1 shows the subclass feature of part finance product.In embodiments of the present invention, type that can be according to product, wind
Dangerous grade, time limit, the one or more pair of product risen in purchase threshold, distributing and releasing corporation are classified.For example, such as being carried out according to type
Classification, can be a class by CC10001-CC10005 points；Such as classified according to type and distributing and releasing corporation, can be by product
It is a class that CC30001-CC30005 points, which are a class, products C C40001-CC40005 divides；Such as classified by the time limit, can be by
CC10001 and CC10007 points are a class.Further, it is also possible to be classified according to other one or more attributes, no longer go to live in the household of one's in-laws on getting married herein
State.
Table 1
| Product subclass ID | Type | Risk class | Time limit | Play purchase threshold | Distributing and releasing corporation |
| CC10001 | Common financing | - | 0-30 days | 50000 | - |
| CC10002 | Common financing | - | 31-90 days | 50000 | - |
| CC10003 | Common financing | - | 90-180 days | 50000 | - |
| CC10004 | Common financing | - | 181-360 days | 50000 | - |
| CC10005 | Common financing | - | More than 360 days | 50000 | - |
| CC10006 | Common financing | - | Without fixed term | 50000 | - |
| CC10007 | Common financing | - | 0-30 days | 100000 | - |
| … | … | … | … | … | … |
| CC30001 | Monetary fund | 1 | - | - | A Fund Companies |
| CC30002 | Monetary fund | 2 | - | - | A Fund Companies |
| CC30003 | Monetary fund | 3 | - | - | A Fund Companies |
| CC30004 | Monetary fund | 4 | - | - | A Fund Companies |
| CC30005 | Monetary fund | 5 | - | - | A Fund Companies |
| … | … | … | … | … | … |
| CC40001 | Equity fund | 1 | - | - | A Fund Companies |
| CC40002 | Equity fund | 2 | - | - | A Fund Companies |
| CC40003 | Equity fund | 3 | - | - | A Fund Companies |
| CC40004 | Equity fund | 4 | - | - | A Fund Companies |
| CC40005 | Equity fund | 5 | - | - | A Fund Companies |
| … | … | … | … | … | … |
Data are pre-processed by step S204 according to user property, trading activity and context data.
Wherein, for full dose data pre-process mainly including：
(1) Data Integration, including：Heterologous form or unit unification, correlating validation；
(2) data cleansing, including：Missing values are abandoned, are filled up etc. with processing；To format content carry out space, mask,
The cleaning treatments such as duplicate removal；The cleaning treatments such as denoising (branch mailbox), fix errors value are carried out to logical value；
(3) data conversion, including：The processing such as extensive, normalization；
(4) data regularization, including：The processing such as dimension reduction, numerical value reduction, discretization, dualization.
It is data conversion treatment process schematic with reference to Fig. 4.For example, during to carrying out extensive processing in lines belonging to client, can
So that according to per capita income, the level of consumption, this feature is divided into east, the north, western part, 4, the middle part factor.It is larger in data volume
When, it is extensive to simplify the difference calculated and between the prominent factor.
Step S206, extracts the dimensional characteristics such as user's base attribute, management assets, active degree.
Step S208, Customer clustering analysis.
Investment ＆ Financing client is classified according to the attribute of client, the consumer for adhering to same customers separately possesses certain journey
The similitude of degree, and there is obvious otherness between different subdivision customers.Wherein, client properties can substantially be believed comprising user
Breath, management assets, several big dimensions of money transfer transactions, can be specific to the sex of user, age, average daily assets, savings remaining sum, monthly generation
Pay out wages, the attribute field such as credit line, monthly transfer amounts, Net silver login times, network bank business number of times.
Predictability subdivision is carried out by supervised learning, i.e., (such as flowed in the characterizing definition of known each client's sub-group
Lose client and non-attrition customer) on the basis of, subdivision characteristic value is purposefully found to distinguish user；And clustering is then to use
The mode of unsupervised learning is divided to user, i.e., in the case of no clearly subdivision purpose, if user is divided into
Ganlei, gathers the general character that the user in same class has some aspects.
In the present invention, cluster (also known as K mean cluster) algorithm using K-means to classify to user, it thinks substantially
Lu Shi：Clustered centered on K point, to the object categorization near them, by the method for iteration, gradually update each poly-
The value of class central point, until algorithmic statement obtains best cluster result.
Specific algorithm comprises the following steps：
Input information is the number K of cluster and the dimension variable for including n object, and output information is K cluster so that square mistake
Poor criterion is minimum.
(1) initial center point of K class is suitably selected；
(2) in the T times iteration, to any one sample, it is asked to the distance at K center, by the sample according to minimum
Distance principle is assigned to closest classification；
(3) sample average calculated in each class is used as new cluster centre；
(4) repeat step (2) (3) no longer changes until cluster centre, it is believed that algorithmic statement；
(5) terminate, obtain K cluster.
Because the selection of initial center point, and K-means algorithms have certain randomness in itself, it is impossible to ensure that algorithm is every
It is secondary all to converge to globally optimal solution, locally optimal solution can only be ensured.So, to same K values, K-means several times is repeated, is selected
It is squared and minimum once as final cluster result.
Step S208, the collaborative filtering based on article.
To the user of same objective group, the similarity between product subclass is calculated, using the neighbouring collaborative filterings based on article of K
(ItemCF) algorithm, the product class to the investment preference of client is predicted.
The personalized recommendation of bank product mainly has some following difference compared with common electric business Products Show.One is
Repeatability, for finance product, if product feature and year earning rate meet the requirement of client, client can be carried out in investment
Bought again after additional or redemption.And for electric business product, in addition to food products, the probability client of very little can buy same commodity twice and
More than.Two be timeliness, for bank client, when product expires or during the maximally effective investment of recommendation by redemption interval scale
Between point.And for electric business client, this time point is difficult to catch.So the bank product for this embodiment of the present invention is pushed away
Recommending will refine to model, the characteristics of considering its own comprehensively.
In the present invention, using collaborative filtering (Item Collaboration Filter, abbreviation based on article
ItemCF) as main proposed algorithm.ItemCF algorithms mainly calculate the similarity of article by analyzing the behavior of client.For example
Product A, B have very high similarity, are because liking most of product A client also all to like product B.
Specifically, step S208 mainly includes the following aspects：
(1) article similarity.
When calculating the similarity of service product, the co-user of two product purchases is more, shows that the two products are got over
It is similar.The span of product A, B similarity is [0,1], and when two products are completely similar, similarity is 1.In this implementation
In example, calculated using cosine similarity：
Wherein, N (A) represents purchase product A number of users, and N (B) represents purchase product B number of users.
In formula (2), molecule is represented while buying product A and B number of users, that is to say, that formula (2) has punished heat
The weight of door product, reduces the hot product possibility similar with many products, it is to avoid the problem of recommending hot product,
Long-tail characteristic is broken away from.
(2) time effect of user behavior.
In historical trading data, user is for the purchase amount of money of product, and number of times, time all illustrates user to this product
Favorable rating.Temporal information has been used in the model of the embodiment of the present invention.Because the liking of user is changed over time, when
Between benefit describe gradient attributes well.In addition, product is also to have life cycle, when sometime recommending user
, it is necessary to consider whether the product is out-of-date during individual product, when expressing user behavior, it should strengthen the weight of recent behavior.
Behaviors of the user u to product A is defined as：
Wherein, t is the time that user u buys product A,The product A amount of money is bought in time i for user u, α is
Time decay factor.
Based on user in the finance product transaction journal data of each channel, statistical summaries user is thin in each product respectively
Sub-category investment behavior, calculates corresponding value and the investment preference of product category is scored as this user, set up a User-
Item rating matrixs, as shown in table 2：
Table 2
| Product 1 | Product 2 | Product 3 | Product 4 | |
| User 1 | 4 | 3 | 5 | 4 |
| User 2 | 4 | 2 | - | - |
| User 3 | 4 | 3 | 3 | 4 |
| User 4 | 2 | 1 | - | - |
| User 5 | 5 | 1 | - | - |
(3) KNN customer priorities.
Specifically, the present invention predicts preferences of the client u to article B using the collaborative filtering based on article of k nearest neighbor：
Wherein, N (u) is the article set that client u merchandises, and H (B, K) is K most like article set of article B, Sim
(A, B) is article A, B similarity, Transu(A) it is degree of liking of the client u to article A.
Step S210, in the preference result that algorithm model is provided, is subject to further business reorganization.Every client logs in
After Mobile banking, the off-line calculation according to backstage recommended models is captured the product class of its preference by system, selects high in every class
Recommend in order in position it is expected that the product of year income/history return rate is put into.
In practice, list of preferences is set up to the preference of product to model sequencing according to user, system is arranged from preference
The product subclass of n (such as 3,4 or other numerals) is selected before ranking to recommend client u in table, front end system can be according to product
The effective investment and financing products of subclass Rules Filtering, and select prospective earnings highest product introduction to be pushed away to client in every class
Recommend the page.
The process for the Products Show for incorporating bank product rule is detailed below.Assuming that recommending the page to set up three altogether
Recommend position to be shown, P1, P2 and P3 respectively are by relative importance value.The product rule incorporated is needed to be divided into following three class：
A. product is unconditionally pushed away by force
The first recommendation position P1 is directly occupied, archetype recommendation results postpone backward.
B. product is pushed away based on product category preference by force
As fruit product belongs to the first recommended products major class (financing/insurance/fund ...), then P1 is placed on；
As fruit product belongs to the second recommended products major class, then P2 is placed on；
As fruit product belongs to the 3rd recommended products major class, then P3 is placed on；
C. product is pushed away based on product group preference by force
As fruit product belongs to the first recommended products group (threshold/time limit/risk ...), then P1 is placed on；
As fruit product belongs to the second recommended products group, then P2 is placed on；
As fruit product belongs to the 3rd recommended products group, then P3 is placed on；
Table 3
Table 3 shows bank's appointed product example, including product is reached the standard grade date, applicable client group, recommendation rules, priority
Deng.On the basis of the product subclass that commending system is provided, involvement appointed product is every client under three recommendation position P1~P3
Most suitable product or product subclass is found, and exports result (recommendation results for incorporating business rule) as shown in table 3.Front end
Table 4 and table 1 (finance product subclass mark sheet) will be read, under each recommendation position, when " appointed product " is not sky, displaying will be referred to
Fixed output quota product；It is shown conversely, then finding prospective earnings highest product in product subclass.
Table 4
In practice, recommendation effect is estimated, tuning processing, Zhi Houzai is then carried out to model according to Evaluated effect
Products Show is carried out based on new model.Recommendation effect is described with reference to example to assess.
The statistical modeling time point of the embodiment of the present invention is designated as T days.Collecting training data goes over 1 year, i.e. T-360 to T-1
The client at moment and transaction data；Test data chooses future 3 months, i.e. T+1 to T+90 transaction journal data.
Assessed for bank product recommendation effect and define 5 indexs, including：Lead referral hit rate, Products Show hit
Rate, Products Show recall rate, successful referral investment accounting, recommended products coverage rate.
(1) lead referral hit rate：In testing time window, the number that client have purchased recommended products accounts for all client's numbers
Ratio.
(2) Products Show hit rate：In testing time window, the product number that client have purchased recommended products accounts for all clients
Recommended products number ratio.
(3) Products Show recall rate：In testing time window, the product number that client have purchased recommended products accounts for all clients
Products transactions number ratio.
(4) successful referral investment accounting：In testing time window, the turnover that client have purchased recommended products accounts for total friendship
The ratio of easy volume.
(5) recommended products coverage rate：In testing time window, the product subclass of recommendation accounts for the ratio of all product subclasses.
Based on above index, the embodiment of the present invention is tested and assessed to recommendation results.Assessment result is as shown in table 5：Work as displaying
During three recommendation positions, the client for having 85% successfully have purchased recommended products, and corresponding Products Show recall rate is 76%, and
The product trading volume of recommendation accounts for total turnover 68%.Find out from result, this commending system has been fitted the preference of client exactly,
Success prediction goes out the Investment Trend of client in testing time window.And all product subclasses have recommendation, and coverage rate is
100%, product long-tail is solved the problems, such as well, has reached expected level.
In order to which multi-angle is estimated to commending system, the embodiment of the present invention to lead referral 1,2,3 product subclasses, and
It is estimated respectively, it is as a result as follows.If, can from following table as can be seen that every client recommends 3 product subclasses
Cause Products Show radix big, the reduction of product hit rate；Even and if every client only recommends 1 product subclass, also there is 57%
Client successfully have purchased recommended products, and product shoots straight up to 59%, and recommended products investment accounts for 33%.
Table 5
| Preference evaluation | 1 recommendation position | 2 recommendation positions | 3 recommendation positions |
| User recommends hit rate | 57% | 75% | 85% |
| Products Show recall rate | 45% | 63% | 76% |
| Products Show hit rate | 59% | 41% | 33% |
| Successful referral investment accounting | 33% | 54% | 68% |
| Product coverage rate | 100% | 100% | 100% |
According to every assessment result, it can be seen that the recommended models of the embodiment of the present invention have effectively caught the behavior of client
With the whole network article correlation, recommended exactly at the T+N moment.
A kind of data delivery system is also provided according to embodiments of the present invention, as shown in figure 5, the system includes：
Acquisition module 51, for obtaining the multiple service product information associated with the first user；
Computing module 52, for calculating the similarity between the multiple service product, obtains similarity and is more than preset value
The first service product and the second service product；
Push processing module 53, if for second user associated with first service product not with second business
Product is associated, then sets the second user to be associated with second service product, and second service product is pushed to
The second user；Wherein described first user has identical or related attribute information to the second user.
In one embodiment of the invention, the acquisition module 51 is additionally operable to obtain the multiple industry in the scheduled time
The attribute information of business product, is divided into multiple classifications according to the attribute information by the multiple service product；The computing module
52, it is additionally operable to calculate the similarity between the service product in same category.
Further, the computing module 52 counts the user profile associated with each service product respectively, according to it is every
The associated user profile of individual service product calculates the similarity between the multiple service product.
Further, the system also includes：
Customer clustering module (not shown), for obtaining the attribute information of user and carrying out a point group to user, wherein, it is described
First user and the second user belong to same customers.
Related product determining module (not shown), for being determined and described first according to the behavioural information of first user
Multiple service product information that user is associated, wherein the service product information includes：The amount of money, time.
The operating procedure of the method for the present invention is corresponding with the architectural feature of system, no longer can one by one be repeated with cross-referenced.
Technique according to the invention scheme, by using the collaborative filtering based on article, precisely, rapidly calculates and uses
Family personalized product is recommended, and client is pushed in the form of differentiation, and the intelligence that service product is recommended can be realized well
Change, automate and personalized, the conversion of client, the undertaking etc. that expires are controlled and improved for business bank's marketing cost control to be had
Significance.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can be used in one or more computers for wherein including computer usable program code
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of key elements are not only including those key elements, but also wrap
Include other key elements being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Also there is other identical element in process, method, commodity or the equipment of element.
It will be understood by those skilled in the art that embodiments of the invention can be provided as method, system or computer program product.
Therefore, the present invention can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.Deposited moreover, the present invention can use to can use in one or more computers for wherein including computer usable program code
The shape for the computer program product that storage media is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
Embodiments of the invention are the foregoing is only, are not intended to limit the invention.For those skilled in the art
For, the present invention can have various modifications and variations.It is all any modifications made within spirit and principles of the present invention, equivalent
Replace, improve etc., it should be included within scope of the presently claimed invention.
Claims (10)
1. a kind of data processing method, it is characterised in that including：
Obtain the multiple service product information associated with the first user；
The similarity between the multiple service product is calculated, the first service product and second that similarity is more than preset value is obtained
Service product；
Do not associated if second user is associated with first service product with second service product, set described second
User is associated with second service product, and second service product is pushed into the second user；Wherein described
One user has identical or related attribute information to the second user.
2. according to the method described in claim 1, it is characterised in that also include：
The attribute information of the multiple service product in the scheduled time is obtained, according to the attribute information by the multiple business
Product is divided into multiple classifications；
Calculate the similarity between the service product in same category.
3. according to the method described in claim 1, it is characterised in that also include：
Obtain the attribute information of user and a point group is carried out to user, wherein, first user and the second user belong to same
One customers.
4. according to the method described in claim 1, it is characterised in that similar between the multiple service product of calculating
Degree, including：
The user profile associated with each service product is counted respectively, according to the user profile associated with each service product
Calculate the similarity between the multiple service product.
5. according to the method described in claim 1, it is characterised in that obtain the multiple business associated with the first user described
Before product information, methods described also includes：
The multiple service product information associated with first user are determined according to the behavioural information of first user, wherein
The service product information includes：The amount of money, time.
6. a kind of data delivery system, it is characterised in that including：
Acquisition module, for obtaining the multiple service product information associated with the first user；
Computing module, for calculating the similarity between the multiple service product, obtains similarity is more than preset value first
Service product and the second service product；
Processing module is pushed, is not closed if being associated for second user with first service product with second service product
Connection, then set the second user to be associated with second service product, and second service product is pushed into described the
Two users；Wherein described first user has identical or related attribute information to the second user.
7. system according to claim 6, it is characterised in that
The acquisition module, is additionally operable to obtain the attribute information of the multiple service product in the scheduled time, according to the category
The multiple service product is divided into multiple classifications by property information；
The computing module, is additionally operable to calculate the similarity between the service product in same category.
8. system according to claim 6, it is characterised in that also include：
Customer clustering module, for obtaining the attribute information of user and carrying out a point group to user, wherein, first user and institute
State second user and belong to same customers.
9. system according to claim 6, it is characterised in that the computing module is used for, is counted and each business respectively
The associated user profile of product, according to the user profile calculating the multiple service product associated with each service product it
Between similarity.
10. system according to claim 6, it is characterised in that also include：
Related product determining module, it is associated with first user for being determined according to the behavioural information of first user
Multiple service product information, wherein the service product information includes：The amount of money, time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710224488.XA CN106991598A (en) | 2017-04-07 | 2017-04-07 | Data push method and its system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710224488.XA CN106991598A (en) | 2017-04-07 | 2017-04-07 | Data push method and its system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106991598A true CN106991598A (en) | 2017-07-28 |
Family
ID=59416065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710224488.XA Pending CN106991598A (en) | 2017-04-07 | 2017-04-07 | Data push method and its system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106991598A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107798608A (en) * | 2017-10-19 | 2018-03-13 | 深圳市耐飞科技有限公司 | A kind of investment product combined recommendation method and system |
| CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技（深圳）有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
| CN108985935A (en) * | 2018-07-06 | 2018-12-11 | 兴业证券股份有限公司 | Financial product recommended method and storage medium |
| CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109636538A (en) * | 2018-12-20 | 2019-04-16 | 成都知数科技有限公司 | Bank product recommended method, device and server |
| CN109727086A (en) * | 2018-06-01 | 2019-05-07 | 平安普惠企业管理有限公司 | Loan product method for pushing, equipment, storage medium and device |
| WO2019085300A1 (en) * | 2017-10-31 | 2019-05-09 | 平安科技（深圳）有限公司 | User fund monitoring and following method, apparatus and device, and readable storage medium |
| CN109962956A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | For recommending the method and system of communication service to user |
| CN110135898A (en) * | 2019-04-25 | 2019-08-16 | 上海淇毓信息科技有限公司 | Method, apparatus and electronic equipment are recalled in client's marketing based on configuration |
| CN110163662A (en) * | 2019-04-26 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of business model training method, device and equipment |
| CN110245977A (en) * | 2019-05-21 | 2019-09-17 | 中国平安人寿保险股份有限公司 | A kind of upgrading service method, equipment and computer readable storage medium |
| CN110555745A (en) * | 2018-05-31 | 2019-12-10 | 北京京东尚科信息技术有限公司 | information pushing method and system, computer system and computer readable storage medium |
| CN110942350A (en) * | 2019-11-28 | 2020-03-31 | 中国银行股份有限公司 | Data processing method, device, equipment and storage medium |
| CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
| CN110969486A (en) * | 2019-11-29 | 2020-04-07 | 中国银行股份有限公司 | Advertisement putting method, user terminal, server, system and storage medium |
| CN111080376A (en) * | 2019-12-30 | 2020-04-28 | 深圳市云积分科技有限公司 | Method and device for improving sociability of user based on information sharing |
| CN111144996A (en) * | 2019-12-30 | 2020-05-12 | 深圳市云积分科技有限公司 | Shopping social method and device |
| CN111161033A (en) * | 2019-12-31 | 2020-05-15 | 深圳市云积分科技有限公司 | Method and device for expanding shopping social contact range |
| CN111383049A (en) * | 2020-02-21 | 2020-07-07 | 中国平安财产保险股份有限公司 | Product recommendation method, device and storage medium |
| CN111817948A (en) * | 2020-07-22 | 2020-10-23 | 中国银行股份有限公司 | Message pushing method and device |
| CN112785280A (en) * | 2021-02-05 | 2021-05-11 | 福建省农村信用社联合社 | Device for pushing certain deposit product based on secondary legal person mode |
| CN113269610A (en) * | 2021-05-25 | 2021-08-17 | 索信达(北京)数据技术有限公司 | Bank product recommendation method and device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| US20140172626A1 (en) * | 2012-12-13 | 2014-06-19 | Kabushiki Kaisha Toshiba | Recommendation-information providing apparatus and recommendation-information providing method |
| CN104391849A (en) * | 2014-06-30 | 2015-03-04 | 浙江大学苏州工业技术研究院 | Collaborative filtering recommendation method for integrating time contextual information |
| US20160284007A1 (en) * | 2015-03-25 | 2016-09-29 | Nec Corporation | Information processing apparatus, information processing method, and recording medium |
| CN106296270A (en) * | 2016-07-29 | 2017-01-04 | 北京小米移动软件有限公司 | Method of Commodity Recommendation and device |
| CN106294727A (en) * | 2016-08-09 | 2017-01-04 | 北京千安哲信息技术有限公司 | A kind of method and apparatus of recommendation information |
| CN106447372A (en) * | 2015-08-10 | 2017-02-22 | 北京奇虎科技有限公司 | Product information pushing method and product information pushing device |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
-
2017
- 2017-04-07 CN CN201710224488.XA patent/CN106991598A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| US20140172626A1 (en) * | 2012-12-13 | 2014-06-19 | Kabushiki Kaisha Toshiba | Recommendation-information providing apparatus and recommendation-information providing method |
| CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
| CN103617540A (en) * | 2013-10-17 | 2014-03-05 | 浙江大学 | E-commerce recommendation method of tracking user interest changes |
| CN104391849A (en) * | 2014-06-30 | 2015-03-04 | 浙江大学苏州工业技术研究院 | Collaborative filtering recommendation method for integrating time contextual information |
| US20160284007A1 (en) * | 2015-03-25 | 2016-09-29 | Nec Corporation | Information processing apparatus, information processing method, and recording medium |
| CN106447372A (en) * | 2015-08-10 | 2017-02-22 | 北京奇虎科技有限公司 | Product information pushing method and product information pushing device |
| CN106296270A (en) * | 2016-07-29 | 2017-01-04 | 北京小米移动软件有限公司 | Method of Commodity Recommendation and device |
| CN106294727A (en) * | 2016-08-09 | 2017-01-04 | 北京千安哲信息技术有限公司 | A kind of method and apparatus of recommendation information |
| CN106548255A (en) * | 2016-11-24 | 2017-03-29 | 山东浪潮云服务信息科技有限公司 | A kind of Method of Commodity Recommendation based on mass users behavior |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技（深圳）有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
| CN107798608A (en) * | 2017-10-19 | 2018-03-13 | 深圳市耐飞科技有限公司 | A kind of investment product combined recommendation method and system |
| WO2019085300A1 (en) * | 2017-10-31 | 2019-05-09 | 平安科技（深圳）有限公司 | User fund monitoring and following method, apparatus and device, and readable storage medium |
| CN109962956A (en) * | 2017-12-26 | 2019-07-02 | 中国电信股份有限公司 | For recommending the method and system of communication service to user |
| CN110555745A (en) * | 2018-05-31 | 2019-12-10 | 北京京东尚科信息技术有限公司 | information pushing method and system, computer system and computer readable storage medium |
| CN109727086A (en) * | 2018-06-01 | 2019-05-07 | 平安普惠企业管理有限公司 | Loan product method for pushing, equipment, storage medium and device |
| CN108985935A (en) * | 2018-07-06 | 2018-12-11 | 兴业证券股份有限公司 | Financial product recommended method and storage medium |
| CN109447728A (en) * | 2018-09-07 | 2019-03-08 | 平安科技（深圳）有限公司 | Financial product recommended method, device, computer equipment and storage medium |
| CN109636538A (en) * | 2018-12-20 | 2019-04-16 | 成都知数科技有限公司 | Bank product recommended method, device and server |
| CN110135898A (en) * | 2019-04-25 | 2019-08-16 | 上海淇毓信息科技有限公司 | Method, apparatus and electronic equipment are recalled in client's marketing based on configuration |
| CN110163662A (en) * | 2019-04-26 | 2019-08-23 | 阿里巴巴集团控股有限公司 | A kind of business model training method, device and equipment |
| CN110163662B (en) * | 2019-04-26 | 2024-04-05 | 创新先进技术有限公司 | Service model training method, device and equipment |
| CN110245977A (en) * | 2019-05-21 | 2019-09-17 | 中国平安人寿保险股份有限公司 | A kind of upgrading service method, equipment and computer readable storage medium |
| CN110245977B (en) * | 2019-05-21 | 2023-10-20 | 中国平安人寿保险股份有限公司 | Service upgrading method, equipment and computer readable storage medium |
| CN110942350A (en) * | 2019-11-28 | 2020-03-31 | 中国银行股份有限公司 | Data processing method, device, equipment and storage medium |
| CN110969486A (en) * | 2019-11-29 | 2020-04-07 | 中国银行股份有限公司 | Advertisement putting method, user terminal, server, system and storage medium |
| CN110969486B (en) * | 2019-11-29 | 2024-02-27 | 中国银行股份有限公司 | Advertisement putting method, user, server, system and storage medium |
| CN110969512B (en) * | 2019-12-02 | 2022-11-15 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
| CN110969512A (en) * | 2019-12-02 | 2020-04-07 | 深圳市云积分科技有限公司 | Commodity recommendation method and device based on user purchasing behavior |
| CN111144996A (en) * | 2019-12-30 | 2020-05-12 | 深圳市云积分科技有限公司 | Shopping social method and device |
| CN111144996B (en) * | 2019-12-30 | 2022-12-23 | 深圳市云积分科技有限公司 | Method and device for social shopping |
| CN111080376A (en) * | 2019-12-30 | 2020-04-28 | 深圳市云积分科技有限公司 | Method and device for improving sociability of user based on information sharing |
| CN111161033A (en) * | 2019-12-31 | 2020-05-15 | 深圳市云积分科技有限公司 | Method and device for expanding shopping social contact range |
| CN111383049A (en) * | 2020-02-21 | 2020-07-07 | 中国平安财产保险股份有限公司 | Product recommendation method, device and storage medium |
| CN111817948A (en) * | 2020-07-22 | 2020-10-23 | 中国银行股份有限公司 | Message pushing method and device |
| CN112785280A (en) * | 2021-02-05 | 2021-05-11 | 福建省农村信用社联合社 | Device for pushing certain deposit product based on secondary legal person mode |
| CN112785280B (en) * | 2021-02-05 | 2022-06-14 | 福建省农村信用社联合社 | Device for pushing deposit products based on secondary legal person mode |
| CN113269610A (en) * | 2021-05-25 | 2021-08-17 | 索信达(北京)数据技术有限公司 | Bank product recommendation method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106991598A (en) | Data push method and its system | |
| Hsieh | An integrated data mining and behavioral scoring model for analyzing bank customers | |
| Han et al. | Segmentation of telecom customers based on customer value by decision tree model | |
| Tsai et al. | Customer segmentation issues and strategies for an automobile dealership with two clustering techniques | |
| US20210264448A1 (en) | Privacy preserving ai derived simulated world | |
| CN109300039A (en) | The method and system of intellectual product recommendation are carried out based on artificial intelligence and big data | |
| Yao et al. | Combining visual customer segmentation and response modeling | |
| Djurisic et al. | Bank CRM optimization using predictive classification based on the support vector machine method | |
| Kim et al. | Reference-dependent preferences on smart phones in South Korea: Focusing on attributes with heterogeneous preference direction | |
| US20150332292A1 (en) | System and method for monitoring market information for deregulated utilities based on transaction data | |
| Salazar et al. | An approach for the identification of cross-sell and up-sell opportunities using a financial services customer database | |
| Suh | Machine learning based customer churn prediction in home appliance rental business | |
| US8255316B2 (en) | Integrated business decision-making system and method | |
| Ishigaki et al. | Personalized market response analysis for a wide variety of products from sparse transaction data | |
| CN113610521A (en) | Method and apparatus for detecting anomalies in behavioral data | |
| Valero-Fernandez et al. | Towards accurate predictions of customer purchasing patterns | |
| Hsieh et al. | Enhancing consumer behavior analysis by data mining techniques | |
| Rezaeinia et al. | An integrated AHP-RFM method to banking customer segmentation | |
| Bošnjak et al. | Credit users segmentation for improved customer relationship management in banking | |
| CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
| Das et al. | Knowing your customers using customer segmentation | |
| Chen et al. | Construction of the Luxury Marketing Model Based on Machine Learning Classification Algorithm | |
| Granov | Customer loyalty, return and churn prediction through machine learning methods: for a Swedish fashion and e-commerce company | |
| Ebrahimi et al. | A predictive analytics approach to improve the dealers-manufacturer relationship in the after-sales service network; case study in the automotive industry | |
| Abebe et al. | Modeling inflation rate factors on present consumption price index in Ethiopia: threshold autoregressive models approach |
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 |
Address after: 100080 No.101, 1st floor, building 14, No.27, Jiancai Chengzhong Road, Haidian District, Beijing Applicant after: Beijing PERCENT Technology Group Co.,Ltd. Address before: 100080 15 / F, block a, China Technology Trading Building, 66 North Fourth Ring Road West, Haidian District, Beijing Applicant before: BEIJING BAIFENDIAN INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170728 |
|
| RJ01 | Rejection of invention patent application after publication |