CN107463572A - A kind of data handling system, method and device - Google Patents
A kind of data handling system, method and device Download PDFInfo
- Publication number
- CN107463572A CN107463572A CN201610391157.0A CN201610391157A CN107463572A CN 107463572 A CN107463572 A CN 107463572A CN 201610391157 A CN201610391157 A CN 201610391157A CN 107463572 A CN107463572 A CN 107463572A
- Authority
- CN
- China
- Prior art keywords
- data
- path
- vertex
- isomery
- user
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The embodiment of the present application discloses a kind of data handling system, method and device.This method includes：The related data of target platform and source platform is converted into isomery diagram data；Predetermined number class is set using user data as beginning vertex data, the association member path data using object data as end vertex data；The quantity of the first path in isomery diagram data using target user data as beginning vertex data and using object data to be recommended as end vertex data is determined based on the first path data of association, quantity using target user data as the second path for starting vertex data, and the quantity using object data to be recommended as the 3rd path of end vertex data；The correlation degree data of target user data and object data to be recommended are calculated according to the quantity of first path, the second path and the 3rd path.The technical scheme provided using the embodiment of the present application can be improved in cross-platform data processing procedure to the utilization rate of source platform data, the accuracy rate of raising correlation degree data.
Description
Technical field
The application is related to internet information processing technology field, more particularly to a kind of data handling system, method and device.
Background technology
With the development of internet Consumption Age, increasing people can buy in some e-commerce platforms is adapted to oneself
Commodity, e-commerce platform will also tend to based on the historical data in e-commerce platform, be inferred to happiness of the user to commodity
Like level data (the favorable rating data can include the correlation degree data between user data and merchandise news), so
Afterwards, the dependent merchandise liked to user recommended user.But for the new e-commerce platform such as existing video electric business system (with
Lower abbreviation target platform), because user has the problems such as serious cold start-up, Deta sparseness less, it can not accurately obtain user couple
The favorable rating data of commodity.Therefore, it is necessary to which a kind of cross-platform data processing technique, can be put down using existing ecommerce
The data such as user's purchaser record of platform (hereinafter referred to as source platform) and user profile, it is inferred to like journey to commodity with reference to user
Degrees of data, to solve the problems such as cold start-up existing for target platform, Deta sparseness.
Existing cross-platform data processing technique mainly include cross-platform data processing method based on collaborative filtering and
Cross-platform data processing method based on transfer learning.In the cross-platform data processing method based on collaborative filtering, it can incite somebody to action
The data quantization of source platform is relational matrix；Then, the input using the relational matrix as collaborative filtering model；Finally, exist
The happiness to determine user to commodity is analyzed and processed with certain algorithm in the collaborative filtering model to the relational matrix
Like level data., can be by the Data Migration of source platform to target in the cross-platform data processing method based on transfer learning
Platform, specifically, certain migration rules can be defined according to the corresponding relation between source platform and the data of target platform；So
Afterwards, migration process is carried out according to the migration rules, and then determines favorable rating data of the user to commodity.
During the application is realized, inventor has found that at least there are the following problems in the prior art：
The input of collaborative filtering model is relational matrix in the existing cross-platform data processing method based on collaborative filtering,
When data are quantified as relational matrix, a large amount of non-relational data will lack.The existing cross-platform number based on transfer learning
Also resulted according to the migration rules defined in processing method ignored not in the data of the migration rules, versatility is weak.Therefore,
The problems such as data user rate of source platform is low, and versatility is weak in existing cross-platform data handling procedure be present, can not be effective
Solve the problems such as cold start-up existing for target platform, Deta sparseness, lead to not what is accurately liked to user recommended user
Commodity, poor user experience.
The content of the invention
The purpose of the embodiment of the present application is to provide a kind of data handling system, method and device, can improve cross-platform number
According to, to the utilization rate of source platform data, and ensureing the standard of correlation degree data between user data and object data in processing procedure
True rate, solves the problems such as cold start-up existing for target platform, Deta sparseness., can in the application of some e-commerce platforms
To be accurately judged to favorable rating of the user to commodity, and then user's body can be improved to the commodity that user recommended user likes
Test.
In order to solve the above technical problems, the embodiment of the present application provides a kind of data handling system, method and device is so
Realize：
A kind of data handling system, including processor and memory, the memory storage is by the computing device
Programmed instruction, described program instruction include：
The object that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
Data are converted into the isomery diagram data of isomery graph model, and the isomery diagram data includes the road being made up of vertex data and side data
Footpath data, the vertex data include the object data that user data associates with user's operation behavior, and the side data include institute
State the incidence relation between vertex data；
Predetermined number class is set to include vertex data and the association member path data of side data, and the first number of path of association
User data is starts vertex data according to this, using object data as end vertex data；
First path data is associated based on the predetermined number class to determine in the isomery diagram data with the target platform
Target user data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, with
And the quantity in the determination isomery diagram data using the target user data as the second path for starting vertex data, and really
Quantity in the fixed isomery diagram data using the object data to be recommended as the 3rd path of end vertex data；
Calculated according to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
To the correlation degree data of the target user data and the object data to be recommended.
A kind of data processing method, including：
The object that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
Data are converted into the isomery diagram data of isomery graph model；The isomery diagram data includes the road being made up of vertex data and side data
Footpath data, the vertex data include the object data that user data associates with user's operation behavior, and the side data include institute
State the incidence relation between vertex data；
Predetermined number class is set to include vertex data and the association member path data of side data, and the first number of path of association
User data is starts vertex data according to this, using object data as end vertex data；
First path data is associated based on the predetermined number class to determine in the isomery diagram data with the target platform
Target user data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, with
And the quantity in the determination isomery diagram data using the target user data as the second path for starting vertex data, and really
Quantity in the fixed isomery diagram data using the object data to be recommended as the 3rd path of end vertex data；
Calculated according to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
To the correlation degree data of the target user data and the object data to be recommended.
A kind of data processing equipment, including：
Data conversion processing module, for by the user data of target platform and source platform, user's operation behavior data and
The object data of user's operation behavior association is converted into the isomery diagram data of isomery graph model；The isomery diagram data is included by pushing up
The path data of point data and side data composition, the vertex data include the object that user data associates with user's operation behavior
Data, the side data include the incidence relation between the vertex data；
First path data setup module is associated, for setting predetermined number class to include the association member of vertex data and side data
Path data, and the first path data of the association is using user data for beginning vertex data, using object data as end vertex number
According to；
Number of paths determining module, the isomery figure number is determined for associating first path data based on the predetermined number class
Using target user data in the target platform to start vertex data and using object data to be recommended as end vertex number in
According to first path quantity, and determine in the isomery diagram data using the target user data for beginning vertex data
The quantity in the second path, and determine in the isomery diagram data using the object data to be recommended as end vertex data the
The quantity in three paths；
Correlation degree data computation module, for the quantity according to the first path, the quantity in second path with
And the correlation degree number of the target user data and the object data to be recommended is calculated in the quantity in the 3rd path
According to.
The technical scheme provided from above the embodiment of the present application, the embodiment of the present application is by the way that target platform and source are put down
User data, user's operation behavior data and the object data of user's operation behavior association of platform are directly with the different of isomery graph model
The form statement of pattern data, can effectively reduce the loss of data in cross-platform data processing procedure.It is and default by setting
Quantity class is using user data as vertex data is started, the pass using the object data of user's operation behavior association as end vertex data
Join first path data, user can be quantified to the favorable rating information of object data；Then, based on the predetermined number
Class associates first path data and determined in the isomery diagram data using target user data in the target platform as beginning number of vertex
According to and using object data to be recommended as the first path of end vertex data quantity, and determine in the isomery diagram data with
The target user data is the quantity in the second path for starting vertex data, and is determined in the isomery diagram data with described
Object data to be recommended is the quantity in the 3rd path of end vertex data；Finally, according to the quantity of the first path, described
The quantity in the second path and the quantity in the 3rd path, which are calculated, can reflect that targeted customer treats recommended data
The correlation degree data of favorable rating.Compared with prior art, the technical scheme provided using the embodiment of the present application, can be improved
To the utilization rate of source platform data in cross-platform data processing procedure, and ensure that between user data and object data to be recommended
The accuracy rate of correlation degree data, can solve the problems such as cold start-up existing for target platform, Deta sparseness.In some electronics
In the application of business platform, favorable rating of the user to commodity can be accurately judged to, and then can be liked to user recommended user
The commodity of love, improve Consumer's Experience.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments described in application, for those of ordinary skill in the art, do not paying the premise of creative labor
Under, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of the embodiment for the data processing method that the application provides；
Fig. 2 is a kind of structural representation of the embodiment for the data processing equipment that the application provides；
Fig. 3 is the structural representation of another embodiment for the data processing equipment that the application provides.
Embodiment
The embodiment of the present application provides a kind of data handling system, method and device.
In order that those skilled in the art more fully understand the technical scheme in the application, it is real below in conjunction with the application
The accompanying drawing in example is applied, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described implementation
Example only some embodiments of the present application, rather than whole embodiments.It is common based on the embodiment in the application, this area
The every other embodiment that technical staff is obtained under the premise of creative work is not made, it should all belong to the application protection
Scope.
Describe the specific implementation of the embodiment of the present application in detail with several specific examples below.
Introduce a kind of embodiment of data processing method of the application first below.Fig. 1 is the data processing that the application provides
A kind of schematic flow sheet of embodiment of method, this application provides the method operating procedure as described in embodiment or flow chart,
But either it can include more or less operating procedures without performing creative labour based on conventional.The step of being enumerated in embodiment
Order is only a kind of mode in numerous step execution sequences, does not represent unique execution sequence.System in practice or
, can either method shown in the drawings order be performed or parallel performed (such as simultaneously according to embodiment when client production performs
The environment of row processor or multiple threads).Specifically as shown in figure 1, methods described can include：
S110：Target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
Object data be converted into the isomery diagram data of isomery graph model；The isomery diagram data is included by vertex data and side data group
Into path data, the vertex data includes the object data that is associated with user's operation behavior of user data, the side data
Including the incidence relation between the vertex data.
, can be by the user data of target platform and source platform, user's operation behavior data and use in the embodiment of the present application
The object data of family operation behavior association is converted into the isomery diagram data of isomery graph model.Specifically, the user data can be with
Including user basic information data, such as username information；User's operation behavior data can include user's buying behavior
The data such as information, user browsing behavior information；The object data of user's operation behavior association can be put down including ecommerce
The data such as the merchandise news in platform.In certain embodiments, when the target platform or the source platform are video electric business platform
When, user's operation behavior data can also include the data such as user video viewing behavioural information；Accordingly, the user behaviour
The data such as video information, video frame information can also be included by making the object data of behavior association.
In the embodiment of the present application, the side data in the isomery diagram data are corresponding with two vertex datas, two summits
Connected between data with corresponding side data.Specifically, the vertex data can include the target platform and source platform
User and commodity in data；In certain embodiments, when the target platform or the source platform are video electric business platform,
The vertex data at least can also include it is following in one kind：Video, key video sequence frame.Specifically, the side data can be with
Including the incidence relation between the vertex data.
Specifically, the incidence relation can include, the user data and object data of the reflection of user's operation behavior data
Between relation.Here so that object data is merchandise news as an example, for example, user's purchase or after having searched for commodity (user buy or
Search behavior data), purchase incidence relation or search incidence relation between user and commodity are similar between commodity and commodity
Incidence relation, the analogous relationship relation between user and user, incidence relation is included between video and key video sequence frame, and
When key video sequence frame includes a certain commodity picture, and user have purchased a certain commodity by the commodity picture, commodity picture
Guiding incidence relation between commodity etc. can reflect the relation that certain is contacted between vertex data.In actual applications, example
Such as, user A have purchased commodity B, have purchase incidence relation, the purchase incidence relation between vertex data A and vertex data B
Can be as the side data in the isomery diagram data.
Furthermore, it is necessary to explanation, the incidence relation described in the embodiment of the present application between vertex data are not limited in
Above-mentioned purchase incidence relation, search incidence relation, analogous relationship relation, comprising incidence relation and guiding incidence relation,
In practical application, other incidence relations can also be included according to the actual association situation between vertex data, for example, user with
Viewing incidence relation between video etc., it is not limited in the embodiment of the present application with above-mentioned.
Specifically, the vertex data and side data in isomery diagram data described in the embodiment of the present application have diversity, institute
State the mulitpath data that isomery diagram data can include being made up of vertex data and side data.In a specific embodiment
In, isomery diagram data described in the embodiment of the present application includes but is not limited to the data of the target platform and source platform to have
The data represented to diagram form.For example, the isomery diagram data can be expressed as digraph G=(A, R), wherein G represents isomery
Diagram data, A represent vertex data, and R represents side data, and | A |>1or|R|>1 (vertex data described in the isomery diagram data
Or the type of the side data is at least above 1).Accordingly, the path data p in the isomery diagram data can be defined as follows：Here Ai∈A,Ri∈ R and A0=dom (R1)=dom (p) (is represented
Vertex data A0It is side data R1Beginning vertex data, and be path data p beginning vertex data), Ai=range (Ri)
=range (p) (represents vertex data AiIt is side data RiEnd vertex data, and be path data p end vertex number
According to), and Ai-1=range (Ri-1)=dom (Ri) represent vertex data Ai-1It is side data Ri-1End vertex data, and be
Side data RiBeginning vertex data).
S120：Predetermined number class is set to include vertex data and the association member path data of side data, and the association member
Path data is using user data as vertex data is started, using object data as end vertex data.
In the embodiment of the present application, predetermined number class can be set to include the association member number of path of vertex data and side data
According to, and the first path data of the association is using user data for beginning vertex data, using object data as end vertex data.Specifically
, the first path data of association can include reflecting user to object data favorable rating by vertex data and side data
The path of composition, and the first path data of association can include at least two vertex datas, and at least one side data.
In practical application, the first path data of association can set different type, different types of association according to practical situations
The user of first path data reflection is different to the favorable rating of object data.
The first path data of association described in the embodiment of the present application is described in detail with specific example below, it is assumed here that number of objects
According to for merchandise news, specifically, can be expressed as：
1、
Above-mentioned association member path data p1User A (user can be expressed asA) it have purchased commodity B (productB), use here
Purchase incidence relation be present in family A and commodity B；The first path data p of association1Vertex data include user A and commodity B, and
The first path data p of association1Using user A as vertex data is started, using commodity B as end vertex data.Therefore, the association
First path data p1The path data formed by the side data of purchase incidence relation and respective vertices data be present can be expressed as.
2、
Above-mentioned association member path data p2User A (user can be expressed asA) it have purchased commodity B1 (productB1), and business
Product B1 and commodity B2 (productB2) similar, here there is purchase incidence relation in user A and commodity B, and commodity B1 deposits with commodity B2
In analogous relationship relation；The first path data p of association2Vertex data include user A, commodity B1 and commodity B2, it is and described
Associate first path data p2Using user A as vertex data is started, using commodity B2 as end vertex data.Therefore, the association member
Path data p2It can be expressed as by the side data and respective vertices data group of purchase incidence relation and analogous relationship relation be present
Into path data.
3、
Above-mentioned association member path data p3User A (user can be expressed asA) it have viewed video B (videoB), in video B
Including key video sequence frame C (keyrrameC), key video sequence frame contains the picture D (picture of commodityD), contained seeing
User A have purchased commodity E (product after the picture D of commodityE), here there is viewing incidence relation in user A and video B, depending on
Exist between frequency B and key video sequence frame C comprising incidence relation, exist between key video sequence frame C and picture D comprising incidence relation,
Guiding incidence relation between picture D and commodity E be present；The first path data p of association3Vertex data include user A, video
B, key video sequence frame C, picture D and commodity E, and the first path data p of association3Using user A as vertex data is started, with commodity
E is end vertex data.Therefore, the first path data p of association2It can be expressed as by purchase incidence relation be present, comprising pass
The path data of the side data and respective vertices data composition of connection relation and guiding incidence relation.
Above-mentioned association member path data p1、p2And p3It is made up of different types of side data and vertex data, accordingly, can
To reflect that user likes situation to the different degrees of of corresponding commodity.Finally buy commodity
B；And the user A have purchased commodity C, then commodity B situation is associated with by commodity C with certain incidence relation and is compared.Typically
, it is believed that the former the user A of this final directly purchase reflection is higher to commodity B favorable rating.Accordingly, for example, on
The association member path data p stated1Side between the commodity corresponding with end vertex data of user corresponding to middle beginning vertex data
Data are directly purchase incidence relation；Above-mentioned association member path data p2User corresponding to middle beginning vertex data is with terminating
Between commodity corresponding to vertex data is connected by another commodity, and the side data of purchase incidence relation and analogous relationship relation
Connect, and user does not buy commodity corresponding to end vertex data finally；So, generally it can be thought that associating first number of path
According to p1Relative to the first path data p of association2The user of reflection is higher to commodity favorable rating.
Furthermore, it is necessary to explanation, the first path data of association described in the embodiment of the present application is not limited in above-mentioned pass
Join first path data p1、p2And p3, in actual applications, can combine specific side data and respective vertices data includes other
Association member path data, be not limited with above-mentioned in the embodiment of the present application.
S130：First path data is associated based on the predetermined number class to determine to put down with the target in the isomery diagram data
Target user data is to start vertex data and the number using object data to be recommended as the first path of end vertex data in platform
Amount, and the quantity in the isomery diagram data using the target user data as the second path for starting vertex data is determined,
And the quantity in the determination isomery diagram data using the object data to be recommended as the 3rd path of end vertex data.
In the embodiment of the present application, step S110 and step S120 obtain isomery diagram data with associate first path data it
Afterwards, the first path data of predetermined number class association can be based on to determine in the isomery diagram data with mesh in the target platform
Mark user data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, and
The quantity using the target user data as the second path for starting vertex data in the isomery diagram data is determined, and is determined
Quantity in the isomery diagram data using the object data to be recommended as the 3rd path of end vertex data.Specifically, can
With including：
Obtained in the isomery diagram data using the target user data as beginning vertex data, and with object to be recommended
Data are the path data of end vertex data, are obtained from the path data and associate first number of path with the predetermined number class
According to the path data to match, the quantity using the quantity of the path data to match as the first path；
And obtained in the isomery diagram data using the target user data as beginning vertex data, and with reference pair
Image data is the path data of end vertex data, is obtained from the path data and associates first path with the predetermined number class
The path data of data match, the quantity using the quantity of the path data to match as second path；
And obtained in the isomery diagram data using reference user data as beginning vertex data, and with described to be recommended
Object data is the path data of end vertex data, is obtained from the path data and associates first road with the predetermined number class
The path data of footpath data match, the quantity using the quantity of the path data to match as the 3rd path.
Specifically, the target user data, which can include any one in the target platform, can carry out object data
The user of recommendation；The object data to be recommended, which can include any one needs in the target platform and the source platform, to be pushed away
Recommend the object data to user；The references object data include whole object datas in the target platform and source platform；
The user data of the whole users included with reference to user data in the target platform；
In a specific embodiment, to associate first path data as above-mentioned p1Exemplified by, and assume in target platform
Target user data is Q, and object data to be recommended is O.The first path can include：Exist when in the isomery diagram data
Using target user data Q as vertex data is started, using the object data O to be recommended as end vertex data, and the target
User data Q is corresponding path data when O has purchase incidence relation with the object data to be recommended.Accordingly, it is described
Second path can include：When in the isomery diagram data exist using target user data Q for beginning vertex data, and with institute
The object data that target user data Q is stated in the presence of purchase incidence relation is path data corresponding to end vertex data；Described
Three paths can include：When in the isomery diagram data exist using the object data O to be recommended as end vertex data, and with
User data with the object data O presence purchase incidence relation to be recommended is path data corresponding to beginning vertex data.
In certain embodiments, it is described that the isomery diagram data is determined based on the first path data of predetermined number class association
In using target user data in the target platform to start vertex data and using object data to be recommended as end vertex data
First path quantity, and determine in the isomery diagram data using the target user data for beginning vertex data the
The quantity in two paths, and determine in the isomery diagram data using the object data to be recommended as the 3rd of end vertex data
The quantity in path can include：
Obtained in the isomery diagram data using the target user data as beginning vertex data, and with object to be recommended
Data are the path data of end vertex data, are obtained respectively from the path data and associate first road with the predetermined number class
The path data of footpath data match, the quantity of the path data to match is multiplied by respectively and associates first number of path accordingly
According to influence coefficient, the quantity using obtained product as the first path；
And obtained in the isomery diagram data using the target user data as beginning vertex data, and with reference pair
Image data is the path data of end vertex data, is obtained from the path data and associates first path with the predetermined number class
The path data of data match, the quantity using the quantity of the path data to match as second path；
And obtained in the isomery diagram data using reference user data as beginning vertex data, and with described to be recommended
Object data is the path data of end vertex data, is obtained from the path data and associates first road with the predetermined number class
The path data of footpath data match, the quantity using the quantity of the path data to match as the 3rd path.
Specifically, the value for influenceing coefficient starts vertex data and end with corresponding associating in member path data
Correlation degree between vertex data is directly proportional.
Specifically, the influence coefficient can associate first number of path according to practical situations with reference to the predetermined number class
Pre-set according to the correlation degree between corresponding beginning vertex data and end vertex data.In actual applications, the pass
It is user to join beginning vertex data in first path data, and end vertex data corresponding to the first path data of association are business
Product, accordingly, the correlation degree started between vertex data and end vertex data can reflect happiness of the user to commodity
Love degree (correlation degree is directly proportional to the favorable rating).Therefore, the influence coefficient of the first path data of the association
Value is also directly proportional to the favorable rating of object data (commodity) to user, then is obtaining using the target user data to open
Beginning vertex data, and after the path data using object data to be recommended as end vertex data, can obtain respectively and every class
The quantity for the path data that first path data matches is associated, the number of path that first path data matches is associated with often class by described
According to quantity be multiplied by associate the influence coefficient of first path data accordingly respectively, using obtained product as the first path
Quantity.It so can more accurately reflect favorable rating of the user to a certain object data (commodity).
Specifically, it is described determine in the isomery diagram data using the target user data for beginning vertex data second
The quantity in path can include obtaining using the road of target user data vertex data as since the isomery diagram data
The quantity of footpath data.Accordingly, it is described to determine in the isomery diagram data using the object data to be recommended as end vertex number
According to the 3rd path quantity can include from the isomery diagram data obtain using the object data to be recommended for terminate top
The quantity of the path data of point data.
S140：According to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
The correlation degree data of the target user data and the object data to be recommended are calculated.
In the embodiment of the present application, after step s 130, quantity that can be according to the first path, second path
Quantity and the quantity in the 3rd path pass of the target user data and the object data to be recommended is calculated
Join level data.Specifically, it can include the product of the quantity of the first path and preset ratio coefficient divided by described the
The business that the quantity in two paths and the quantity sum in the 3rd path obtain as the target user data with it is described to be recommended
The correlation degree data of object data.Specifically, the correlation degree data, which are calculated, can include using public affairs are calculated as below
Formula：
In above formula, L (s, t) can represent the correlation degree number between target user data s and object data t to be recommended
According to；S (s, t) can represent the quantity of first path；S(s,:) quantity in the second path can be represented；S(:, t) and can be represented
The quantity in three paths；A represents preset ratio coefficient, and the preset ratio coefficient can be set previously according to practical situations,
In a specific embodiment, the preset ratio coefficient a=2, preset ratio coefficient described in the embodiment of the present application not with
This is limited.
In certain embodiments, after step s 140, methods described can also include：
Correlation degree data based on the target user data and the object data to be recommended are in the target platform
Carry out recommendation process.
The technical scheme that a kind of embodiment of the data processing method provided from above the application provides, the application are led to
It is straight to cross the object data for associating target platform with user data, user's operation behavior data and the user's operation behavior of source platform
Connect and stated in the form of the isomery diagram data of isomery graph model, can effectively reduce the damage of data in cross-platform data processing procedure
Lose.And by setting predetermined number class using user data as beginning vertex data, the pass using object data as end vertex data
Join first path data, user can be quantified to the favorable rating information of object data；Then, based on the predetermined number
Class associates first path data and determined in the isomery diagram data using target user data in the target platform as beginning number of vertex
According to and using object data to be recommended as the first path of end vertex data quantity, and determine in the isomery diagram data with
The target user data is the quantity in the second path for starting vertex data, and is determined in the isomery diagram data with described
Object data to be recommended is the quantity in the 3rd path of end vertex data；Finally, according to the quantity of the first path, described
The quantity in the second path and the quantity in the 3rd path, which are calculated, can reflect the targeted customer to described to be recommended
The correlation degree data of object data favorable rating.Subsequently, the target user data and the object to be recommended can be based on
The correlation degree data of data carry out recommendation process in target platform, efficiently solve cold start-up existing for target platform, data
The problems such as openness.Compared with prior art, the technical scheme provided using the embodiment of the present application, can improve cross-platform data
To the utilization rate of source platform data in processing procedure, and it ensure that correlation degree number between user data and object data to be recommended
According to accuracy rate, solve the problems such as cold start-up existing for target platform, Deta sparseness.In answering for some e-commerce platforms
In, favorable rating of the user to commodity can be accurately judged to, and then can improve to the commodity that user recommended user likes
Consumer's Experience.
The application also provides a kind of embodiment of data handling system, and the system includes processor and memory, described
By the programmed instruction of the computing device, described program instructs to be included memory storage：
The object that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
Data are converted into the isomery diagram data of isomery graph model, and the isomery diagram data includes the road being made up of vertex data and side data
Footpath data, the vertex data include the object data that user data associates with user's operation behavior, and the side data include institute
State the incidence relation between vertex data；
Predetermined number class is set to include vertex data and the association member path data of side data, and the first number of path of association
User data is starts vertex data according to this, using object data as end vertex data；
First path data is associated based on the predetermined number class to determine in the isomery diagram data with the target platform
Target user data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, with
And the quantity in the determination isomery diagram data using the target user data as the second path for starting vertex data, and really
Quantity in the fixed isomery diagram data using the object data to be recommended as the 3rd path of end vertex data；
Calculated according to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
To the correlation degree data of the target user data and the object data to be recommended.
The application also provides a kind of embodiment of data processing equipment, and Fig. 2 is the data processing equipment that the application provides
A kind of structural representation of embodiment, as shown in Fig. 2 described device 200 can include：
Data conversion processing module 210, it can be used for the user data of target platform and source platform, user's operation behavior
Data and the object data of user's operation behavior association are converted into the isomery diagram data of isomery graph model；The isomery diagram data bag
The path data being made up of vertex data and side data is included, the vertex data associates including user data with user's operation behavior
Object data, the side data include the vertex data between incidence relation；
First path data setup module 220 is associated, can be used for setting predetermined number class to include vertex data and side data
Association member path data, and the first path data of the association is using user data to start vertex data, using object data to tie
Bunchy top point data；
Number of paths determining module 230, it can be used for associating described in first path data determination based on the predetermined number class
Using target user data in the target platform to start vertex data and using object data to be recommended as knot in isomery diagram data
The quantity of the first path of bunchy top point data, and determine in the isomery diagram data using the target user data to start to push up
The quantity in the second path of point data, and determine in the isomery diagram data using the object data to be recommended as end vertex
The quantity in the 3rd path of data；
Correlation degree data computation module 240, it can be used for the quantity according to the first path, second path
Associating for the target user data and the object data to be recommended is calculated in quantity and the quantity in the 3rd path
Level data.
In a preferred embodiment, the number of paths determining module 230 can include：
First quantity determining unit, it can be used for obtaining using the target user data to open in the isomery diagram data
Beginning vertex data, and the path data using references object data as end vertex data, acquisition and institute from the path data
State predetermined number class and associate the path data that first path data matches, using the quantity of the path data to match as institute
State the quantity in the second path；
Second quantity determining unit, can be used for obtaining in the isomery diagram data using with reference to user data to start to push up
Point data, and the path data using the object data to be recommended as end vertex data, from the path data obtain with
The predetermined number class associates the path data that first path data matches, using the quantity of the path data to match as
The quantity in the 3rd path.
In a preferred embodiment, the number of paths determining module 230 can also include：
3rd quantity determining unit, it can be used for obtaining using the target user data to open in the isomery diagram data
Beginning vertex data, and the path data using object data to be recommended as end vertex data, from the path data obtain with
The predetermined number class associates the path data that first path data matches, using the quantity of the path data to match as
The quantity of the first path；
Or,
4th quantity determining unit, it can be used for obtaining using the target user data to open in the isomery diagram data
Beginning vertex data, and the path data using object data to be recommended as end vertex data, are obtained respectively from the path data
Take and the path data that first path data matches is associated with the predetermined number class, by the quantity of the path data to match
The influence coefficient for associating first path data accordingly is multiplied by respectively, the quantity using obtained product as the first path；
Wherein, the value for influenceing coefficient starts vertex data with corresponding associating and terminates to push up in member path data
Correlation degree between point data is directly proportional.
In a preferred embodiment, the correlation degree data computation module 240 can include：
Data Computation Unit, it can be used for the product of the quantity of the first path and preset ratio coefficient divided by described
The business that the quantity in the second path and the quantity sum in the 3rd path obtain waits to push away as the target user data with described
Recommend the correlation degree data of object data.
In a preferred embodiment, the vertex data at least can also include it is following in one kind：
Video, key video sequence frame.
The application also provides a kind of another embodiment of data processing equipment, and Fig. 3 is the data processing dress that the application provides
The structural representation for another embodiment put, as shown in figure 3, described device 300 can include：
Recommendation process module 250, it can be used for the pass based on the target user data Yu the object data to be recommended
Join level data and carry out recommendation process in the target platform.
The technical scheme that a kind of data handling system, the embodiment of method and device provided by above the application provides can
See, the application is by the way that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
Object data stated directly in the form of the isomery diagram data of isomery graph model, can effectively reduce cross-platform data and treat
The loss of data in journey.And by setting predetermined number class using user data as vertex data is started, using object data as end
The association member path data of vertex data, user can be quantified to the favorable rating information of object data；Then, it is based on
The predetermined number class associates first path data and determined in the isomery diagram data with target user data in the target platform
Quantity for beginning vertex data and using object data to be recommended as the first path of end vertex data, and determine described different
Quantity in pattern data using the target user data as the second path for starting vertex data, and determine the isomery figure
Quantity in data using the object data to be recommended as the 3rd path of end vertex data；Then, according to the first via
The quantity of the quantity in footpath, the quantity in second path and the 3rd path, which is calculated, can reflect the targeted customer
To the correlation degree data of the object data favorable rating to be recommended.Finally, the target user data and institute can be based on
The correlation degree data for stating object data to be recommended carry out recommendation process in target platform, efficiently solve existing for target platform
Cold start-up, the problems such as Deta sparseness.Compared with prior art, the technical scheme provided using the embodiment of the present application, Ke Yiti
To the utilization rate of source platform data in high cross-platform data processing procedure, and ensure that user data and object data to be recommended it
Between correlation degree data accuracy rate, solve the problems such as cold start-up existing for target platform, Deta sparseness.In some electronics
In the application of business platform, favorable rating of the user to commodity can be accurately judged to, and then can be liked to user recommended user
The commodity of love, improve Consumer's Experience.
In the 1990s, the improvement for a technology can clearly distinguish be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And as the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow is programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, PLD
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, its logic function is determined by user to device programming.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, without asking chip maker to design and make
Special IC chip 2.Moreover, nowadays, substitution manually makes IC chip, and this programming is also used instead mostly
" logic compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development
Seemingly, and the source code before compiling also handy specific programming language is write, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but have many kinds, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog2.Those skilled in the art
It will be apparent to the skilled artisan that only need method flow slightly programming in logic and being programmed into integrated circuit with above-mentioned several hardware description languages
In, it is possible to it is readily available the hardware circuit for realizing the logical method flow.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
Device and storage can by the computer of the computer readable program code (such as software or firmware) of (micro-) computing device
Read medium, gate, switch, application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller include but is not limited to following microcontroller
Device：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.
It is also known in the art that in addition to realizing controller in a manner of pure computer readable program code, it is complete
Entirely can by by method and step carry out programming in logic come controller with gate, switch, application specific integrated circuit, may be programmed
The form of logic controller and embedded microcontroller etc. realizes identical function.Therefore this controller is considered one kind
Hardware component, and it is used to realize that the device of various functions can also to be considered as the structure in hardware component to what is included in it.Or
Even, it not only can be able to will be the software module of implementation method for realizing that the device of various functions is considered as but also can be Hardware Subdivision
Structure in part.
System, device, module or the unit that above-described embodiment illustrates, it can specifically be realized by computer chip or entity,
Or realized by the product with certain function.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, this is being implemented
The function of each unit can be realized in same or multiple softwares and/or hardware during application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
Realized by the mode of software plus required general hardware platform.Based on such understanding, the technical scheme essence of the application
On the part that is contributed in other words to prior art can be embodied in the form of software product, in a typical configuration
In, computing device includes one or more processors (CPU), input/output interface, network interface and internal memory.The computer is soft
Part product can include some instructions make it that a computer equipment (can be personal computer, server, or network
Equipment etc.) perform method described in some parts of each embodiment of the application or embodiment.The computer software product can
To be stored in internal memory, internal memory may include the volatile memory in computer-readable medium, random access memory
(RAM) and/or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer
The example of computer-readable recording medium.Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by
Any method or technique come realize information store.Information can be computer-readable instruction, data structure, the module of program or its
His data.The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM
(SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read-only storage
(ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc are read-only
Memory (CD-ROM), digital versatile disc (DVD) or other optical storages, magnetic cassette tape, tape magnetic rigid disk storage or
Other magnetic storage apparatus or any other non-transmission medium, the information that can be accessed by a computing device available for storage.According to
Herein defines, and computer-readable medium does not include of short duration computer readable media (transitory media), such as modulation
Data-signal and carrier wave.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for system
For applying example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
The application can be used in numerous general or special purpose computing system environments or configuration.Such as：Personal computer, clothes
Business device computer, handheld device or portable set, laptop device, multicomputer system, the system based on microprocessor, put
Top box, programmable consumer-elcetronics devices, network PC, minicom, mainframe computer including any of the above system or equipment
DCE etc..
The application can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes performing particular task or realizes routine, program, object, the group of particular abstract data type
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these DCEs, by
Task is performed and connected remote processing devices by communication network.In a distributed computing environment, program module can be with
In the local and remote computer-readable storage medium including storage device.
Although depicting the application by embodiment, it will be appreciated by the skilled addressee that the application have it is many deformation and
Change is without departing from spirit herein, it is desirable to which appended claim includes these deformations and changed without departing from the application's
Spirit.
Claims (13)
1. a kind of data handling system, including processor and memory, the memory storage by the computing device journey
Sequence instructs, it is characterised in that described program instruction includes：
The object data that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
The isomery diagram data of isomery graph model is converted into, the isomery diagram data includes the number of path being made up of vertex data and side data
According to the vertex data includes the object data that user data associates with user's operation behavior, and the side data include the top
Incidence relation between point data；
Setting predetermined number class includes vertex data and the association member path data of side data, and the first path data of association with
User data is starts vertex data, using object data as end vertex data；
First path data is associated based on the predetermined number class to determine in the isomery diagram data with target in the target platform
User data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, and really
Quantity in the fixed isomery diagram data using the target user data as the second path for starting vertex data, and determine institute
State the quantity using the object data to be recommended as the 3rd path of end vertex data in isomery diagram data；
Institute is calculated according to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
State the correlation degree data of target user data and the object data to be recommended.
A kind of 2. data processing method, it is characterised in that including：
The object data that target platform is associated with user data, user's operation behavior data and the user's operation behavior of source platform
The isomery diagram data of isomery graph model is converted into, the isomery diagram data includes the number of path being made up of vertex data and side data
According to the vertex data includes the object data that user data associates with user's operation behavior, and the side data include the top
Incidence relation between point data；
Setting predetermined number class includes vertex data and the association member path data of side data, and the first path data of association with
User data is starts vertex data, using object data as end vertex data；
First path data is associated based on the predetermined number class to determine in the isomery diagram data with target in the target platform
User data is to start vertex data and the quantity using object data to be recommended as the first path of end vertex data, and really
Quantity in the fixed isomery diagram data using the target user data as the second path for starting vertex data, and determine institute
State the quantity using the object data to be recommended as the 3rd path of end vertex data in isomery diagram data；
Institute is calculated according to the quantity of the quantity of the first path, the quantity in second path and the 3rd path
State the correlation degree data of target user data and the object data to be recommended.
3. according to the method for claim 2, it is characterised in that described that first path data is associated based on the predetermined number class
Determine in the isomery diagram data using target user data in the target platform as beginning vertex data and with object to be recommended
Data are the quantity of the first path of end vertex data, and are determined in the isomery diagram data with the target user data
To start the quantity in the second path of vertex data, and determine in the isomery diagram data using the object data to be recommended as
The quantity in the 3rd path of end vertex data includes：
Obtained in the isomery diagram data using the target user data as beginning vertex data, and with object data to be recommended
For the path data of end vertex data, obtained from the path data and associate first path data phase with the predetermined number class
The path data of matching, the quantity using the quantity of the path data to match as the first path；
And obtained in the isomery diagram data using the target user data as beginning vertex data, and with references object number
According to the path data for end vertex data, obtained from the path data and associate first path data with the predetermined number class
The path data to match, the quantity using the quantity of the path data to match as second path；
And obtained in the isomery diagram data using reference user data as beginning vertex data, and with the object to be recommended
Data are the path data of end vertex data, are obtained from the path data and associate first number of path with the predetermined number class
According to the path data to match, the quantity using the quantity of the path data to match as the 3rd path.
4. according to the method for claim 2, it is characterised in that described that first path data is associated based on the predetermined number class
Determine in the isomery diagram data using target user data in the target platform as beginning vertex data and with object to be recommended
Data are the quantity of the first path of end vertex data, and are determined in the isomery diagram data with the target user data
To start the quantity in the second path of vertex data, and determine in the isomery diagram data using the object data to be recommended as
The quantity in the 3rd path of end vertex data includes：
Obtained in the isomery diagram data using the target user data as beginning vertex data, and with object data to be recommended
For the path data of end vertex data, obtained respectively from the path data and associate first number of path with the predetermined number class
According to the path data to match, the quantity of the path data to match is multiplied by respectively and associates first path data accordingly
Influence coefficient, the quantity using obtained product as the first path；
And obtained in the isomery diagram data using the target user data as beginning vertex data, and with references object number
According to the path data for end vertex data, obtained from the path data and associate first path data with the predetermined number class
The path data to match, the quantity using the quantity of the path data to match as second path；
And obtained in the isomery diagram data using reference user data as beginning vertex data, and with the object to be recommended
Data are the path data of end vertex data, are obtained from the path data and associate first number of path with the predetermined number class
According to the path data to match, the quantity using the quantity of the path data to match as the 3rd path.
5. according to the method for claim 4, it is characterised in that the value for influenceing coefficient associates member road with corresponding
The correlation degree started in the data of footpath between vertex data and end vertex data is directly proportional.
6. according to the method described in claim 2 to 5 any one, it is characterised in that the number according to the first path
Amount, the quantity in second path and the quantity in the 3rd path are calculated the target user data and wait to push away with described
Recommending the correlation degree data of object data includes：
By the product divided by the quantity in second path and the described 3rd of the quantity of the first path and preset ratio coefficient
Correlation degree data of the business that the quantity sum in path obtains as the target user data and the object data to be recommended.
7. according to the method described in claim 2 to 5 any one, it is characterised in that under the vertex data at least also includes
One kind in stating：
Video, key video sequence frame.
8. according to the method described in claim 2 to 5 any one, it is characterised in that methods described also includes：
Correlation degree data based on the target user data and the object data to be recommended are carried out in the target platform
Recommendation process.
A kind of 9. data processing equipment, it is characterised in that including：
Data conversion processing module, for by the user data of target platform and source platform, user's operation behavior data and user
The object data of operation behavior association is converted into the isomery diagram data of isomery graph model；The isomery diagram data is included by number of vertex
According to the path data formed with side data, the vertex data includes the number of objects that user data associates with user's operation behavior
According to the side data include the incidence relation between the vertex data；
First path data setup module is associated, for setting predetermined number class to include the association member path of vertex data and side data
Data, and the first path data of the association is using user data for beginning vertex data, using object data as end vertex data；
Number of paths determining module, determined for associating first path data based on the predetermined number class in the isomery diagram data
Using target user data in the target platform to start vertex data and using object data to be recommended as end vertex data
The quantity of first path, and determine in the isomery diagram data using the target user data for beginning vertex data second
The quantity in path, and determine the 3rd tunnel in the isomery diagram data using the object data to be recommended as end vertex data
The quantity in footpath；
Correlation degree data computation module, for the quantity according to the first path, the quantity in second path and institute
The correlation degree data of the target user data and the object data to be recommended are calculated in the quantity for stating the 3rd path.
10. device according to claim 9, it is characterised in that the number of paths determining module includes：
First quantity determining unit, for being obtained in the isomery diagram data using the target user data as beginning number of vertex
According to, and the path data using references object data as end vertex data, obtained and the present count from the path data
Amount class associates the path data that first path data matches, using the quantity of the path data to match as second tunnel
The quantity in footpath；
Second quantity determining unit, for being obtained in the isomery diagram data using reference user data as beginning vertex data,
And the path data using the object data to be recommended as end vertex data, obtain from the path data and preset with described
Quantity class associates the path data that first path data matches, using the quantity of the path data to match as the described 3rd
The quantity in path；
The number of paths determining module also includes：
3rd quantity determining unit, for being obtained in the isomery diagram data using the target user data as beginning number of vertex
According to, and the path data using object data to be recommended as end vertex data, obtain from the path data and preset with described
Quantity class associates the path data that first path data matches, using the quantity of the path data to match as described first
The quantity in path；
Or,
4th quantity determining unit, for being obtained in the isomery diagram data using the target user data as beginning number of vertex
According to, and the path data using object data to be recommended as end vertex data, obtained respectively from the path data with it is described
Predetermined number class associates the path data that first path data matches, and the quantity of the path data to match is multiplied by respectively
The influence coefficient of first path data is associated accordingly, the quantity using obtained product as the first path；
Wherein, the value for influenceing coefficient starts vertex data and end vertex number with corresponding associating in member path data
Correlation degree between is directly proportional.
11. according to the device described in any one of claim 9 or 10, it is characterised in that the correlation degree data calculate mould
Block includes：
Data Computation Unit, for by the product of the quantity of the first path and preset ratio coefficient divided by second path
Quantity and the 3rd path the obtained business of quantity sum as the target user data and the number of objects to be recommended
According to correlation degree data.
12. according to the device described in any one of claim 9 or 10, it is characterised in that the vertex data at least also includes
One kind in following：
Video, key video sequence frame.
13. according to the device described in any one of claim 9 or 10, it is characterised in that described device also includes：
Recommendation process module, exist for the correlation degree data based on the target user data and the object data to be recommended
The target platform carries out recommendation process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610391157.0A CN107463572B (en) | 2016-06-03 | 2016-06-03 | Data processing system, method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610391157.0A CN107463572B (en) | 2016-06-03 | 2016-06-03 | Data processing system, method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107463572A true CN107463572A (en) | 2017-12-12 |
| CN107463572B CN107463572B (en) | 2020-12-08 |
Family
ID=60545852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610391157.0A Active CN107463572B (en) | 2016-06-03 | 2016-06-03 | Data processing system, method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463572B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241380A (en) * | 2018-11-28 | 2020-06-05 | 富士通株式会社 | Method and apparatus for generating recommendations |
| CN111461826A (en) * | 2020-03-30 | 2020-07-28 | 京东数字科技控股有限公司 | Information pushing method and device, storage medium and electronic device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293035A1 (en) * | 2009-05-15 | 2010-11-18 | Athellina Athsani | Map advertising system interface |
| CN104679866A (en) * | 2015-03-04 | 2015-06-03 | 重庆理工大学 | Recommendation method of semi-supervised learning based on graph consistency model |
| CN105446973A (en) * | 2014-06-20 | 2016-03-30 | 华为技术有限公司 | User recommend model establishment and application method and device in social network |
-
2016
- 2016-06-03 CN CN201610391157.0A patent/CN107463572B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293035A1 (en) * | 2009-05-15 | 2010-11-18 | Athellina Athsani | Map advertising system interface |
| CN105446973A (en) * | 2014-06-20 | 2016-03-30 | 华为技术有限公司 | User recommend model establishment and application method and device in social network |
| CN104679866A (en) * | 2015-03-04 | 2015-06-03 | 重庆理工大学 | Recommendation method of semi-supervised learning based on graph consistency model |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111241380A (en) * | 2018-11-28 | 2020-06-05 | 富士通株式会社 | Method and apparatus for generating recommendations |
| CN111241380B (en) * | 2018-11-28 | 2023-10-03 | 富士通株式会社 | Method and apparatus for generating recommendations |
| CN111461826A (en) * | 2020-03-30 | 2020-07-28 | 京东数字科技控股有限公司 | Information pushing method and device, storage medium and electronic device |
| CN111461826B (en) * | 2020-03-30 | 2024-04-09 | 京东科技控股股份有限公司 | Information pushing method and device, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107463572B (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9354790B2 (en) | Dynamically selecting and ordering facets and facet values in a user interface based on user preference | |
| CN110020188A (en) | Recommended based on the Global Vector of implicit interactions and profile data | |
| CN112313697A (en) | System and method for generating interpretable description-based recommendations describing angle augmentation | |
| US20170091319A1 (en) | Bayesian visual interactive search | |
| CN108509436A (en) | A kind of method, apparatus and computer storage media of determining recommended | |
| CN108921566A (en) | A kind of wash sale recognition methods and device based on graph structure model | |
| CN107679700A (en) | Business flow processing method, apparatus and server | |
| CN106445971A (en) | Application recommendation method and system | |
| CN105824830A (en) | Page displaying method, client and equipment | |
| CN107480153A (en) | A kind of page data processing method, client and terminal device | |
| US11682068B2 (en) | Automating the creation of listings using augmented reality computer technology | |
| US20170329840A1 (en) | Computerized system and method for performing a feature-based search and displaying an interactive dynamically updatable, multidimensional user interface therefrom | |
| CN107391540A (en) | A kind of small routine methods of exhibiting, device and grader | |
| US11720622B2 (en) | Machine learning multiple features of depicted item | |
| CN107517393B (en) | Information pushing method, device and system | |
| CN107766349A (en) | A kind of method, apparatus, equipment and client for generating text | |
| CN103530357A (en) | Video retrieval method and system | |
| CN107562613A (en) | Program testing method, apparatus and system | |
| CN109389412A (en) | A kind of method and device of training pattern | |
| US10282474B2 (en) | Category constrained queries | |
| CN107402953A (en) | A kind of method for page jump and device | |
| US20210192000A1 (en) | Searching using changed feature of viewed item | |
| CN107463572A (en) | A kind of data handling system, method and device | |
| CN107515896A (en) | A kind of resource recommendation method, device and equipment | |
| CN107451157A (en) | Disorder data recognition method, apparatus and system, searching method and device |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1247676 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |