CN109739603A - A kind of open platform skin layout method and system based on clustering - Google Patents
A kind of open platform skin layout method and system based on clustering Download PDFInfo
- Publication number
- CN109739603A CN109739603A CN201811619879.2A CN201811619879A CN109739603A CN 109739603 A CN109739603 A CN 109739603A CN 201811619879 A CN201811619879 A CN 201811619879A CN 109739603 A CN109739603 A CN 109739603A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- skin
- mobile device
- clustering
- 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
Landscapes
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of open platform skin layout method and system based on clustering belongs to the technical fields such as cluster, and the skin for solving H5 or app in mobile device in the prior art is all fixed single.The present invention obtains the device-fingerprint information of H5 or app, obtains mobile device information;According to mobile device information, acquires active user's default skin and user data, user data include user basic information and user behavior information of the user in the opereating specification of mobile device screen in a period of time;Based on user basic information and cluster algorithm, to user behavior information cluster analysis, mark off behavioural habits of the user corresponding to user basic information within the scope of the click of screen, affiliated cluster after obtaining user data clustering, i.e. user draws a portrait, and defaulting skin further according to user's portrait and active user, user defaults skin pattern again.It further include system, system includes data acquisition module and user behavior server.The present invention is used for rational deployment skin.
Description
Technical field
A kind of open platform skin layout method and system based on clustering is used for rational deployment skin, belongs to poly-
The technical fields such as class.
Background technique
User's portrait: user's portrait is also known as user role, delineates target user, connection user's demand and design as one kind
The effective tool in direction, user's portrait are widely used in each field.We during practical operation often
The attribute of user, behavior and expectation are tied with the most plain and closeness to life language.As the virtual of actual user
Represent, user's portrait be formed by user role be not be detached from it is constructed except product and market come out, the user of formation
Role needs the main audient and target group of representative energy representative products.
Skin: skin here refers to the theme of corresponding application, color background, interface layout etc..
Clustering: cluster is a kind of machine learning techniques for being related to data point and being grouped.Give one group of data point, Wo Menke
To use clustering algorithm that each data point is categorized into specific group.Theoretically, the data point in same group should have similar
Attribute or feature, and the data point in different group should have the attribute or feature of larger difference.Cluster is unsupervised learning
A kind of method, and the common technology for analysis of statistical data in many fields.It is not have that so-called unsupervised learning, which is exactly data,
There is category label, algorithm will extract certain rule from the exploration to initial data.And clustering be just attempt to by
Sample in data set is divided into several disjoint subsets, and each subset is known as one " cluster ".
Open platform is the channel externally provided, and mobile Internet is the important tool lived close to people, people without when
Without quarter just interactive with internet.
The skin of the operation interface of the mobile form such as present app, H5 is fixed form, in the form of a single, each user
Into user experience is the same, do not classified according to the information of user, user is carried out to Users'Data Analysis from the background
Portrait, classify to user, design and specifically move skin in accordance with particular user, cause all be in all user's operations
The same, such as Fig. 1, user's handedness difference, user's operation range etc. can only all carry out in fixed orientation, some
Behaviour does the function of only needing one-handed performance, and the ability that some clients have to right-hand man completes feature operation etc., some functions
It can be carried out one-handed performance, but the mobile device for having changed a different size of screen cannot carry out corresponding operation, cause
Client bad user experience.
It is for statistical analysis without the function for user behavior on the mobile apparatus in the market at this stage, setting default
To the function of a user-friendly skin, i.e. the skin of app all in mobile device is all fixed single, corresponding
Function menu be laid out and fix, not for behavioural habits carry out reasonable analysis and be laid out, the application can believe according to equipment
Breath, the behavioural habits of user and user information carry out clustering, are reasonably laid out skin.
Summary of the invention
Aiming at the problem that the studies above, the purpose of the present invention is to provide a kind of open platform skin based on clustering
Management method, the skin for solving the app in mobile device in the prior art is all fixed single, can not be according to the row of user
Skin is reasonably laid out for habit and user information.
In order to achieve the above object, the present invention adopts the following technical scheme:
A kind of open platform skin layout method based on clustering, which comprises the steps of:
Step 1, the device-fingerprint information for obtaining H5 or app, obtain mobile device information;
Step 2 includes use according to mobile device information, acquisition active user default skin and user data, user data
Family essential information and user behavior information of the user in the opereating specification of mobile device screen in a period of time;
Step 3 marks off use to user behavior information cluster analysis based on user basic information and cluster algorithm
Behavioural habits of the user corresponding to the essential information of family within the scope of the click of screen, the institute after obtaining user data clustering
Belong to cluster, i.e. user draws a portrait, and is laid out user again further according to user's portrait and active user's default skin and defaults skin pattern.
Further, mobile device information obtained in the step 1 includes the type and screen resolution of mobile device.
Further, the user behavior information in the step 2 is the number that left or right hand clicks H5 or app.
Further, mean shift clustering algorithm is used in the step 3.
A kind of open platform skin layout system based on clustering characterized by comprising
Data acquisition module: the device-fingerprint information of H5 or app is obtained, mobile device information is obtained;According to mobile device
Information, acquires original current user's default skin and user data, user data include user basic information and a period of time
User behavior information of the interior user in the opereating specification of mobile device screen;
User behavior server: for being based on user basic information and cluster algorithm, to user behavior information cluster
Analysis, marks off behavioural habits of the user corresponding to user basic information within the scope of the click of screen, obtains user data
It is silent to be laid out user further according to user's portrait and active user's default skin again for affiliated cluster after clustering, i.e. user portrait
Recognize skin pattern.
Further, mobile device information obtained in the data acquisition module includes the type and screen point of mobile device
Debate rate.
Further, further include user data memory module, obtain the user data that module obtains, user for storing data
Behavior service device called data from user data memory module.
The present invention compared with the existing technology, its advantages are shown in:
One, the present invention can automatically generate reasonable default skin according to the type of equipment, user's portrait and user basic information
Skin promotes user's operation performance, and equipment has changed user, and corresponding default skin can also be updated after data acquisition, is combined conscientiously
Actual life is bonded user experience, is drawn a portrait by artificial intelligence polymerization analysis algorithm to user behavior, life and application
Conscientiously it combines, and takes full advantage of artificial intelligence, the user experience is improved;
Two, adequately the information (i.e. essential information and behavioural information) of user is utilized in the present invention, and closes to information
The class of reason is divided into the cluster divided, and corresponding cluster information needs to carry out clustering according to user behavior information could really
Be set to left or right hand (general early period acquires left area's left hand, and right area's right hand, the number of clicks by which region is most,
Determine left or right hand), only a kind of conventional division, i.e. only one cluster at present;
Three, the skin of the reasonable layout mobile device related development platform of the present invention, enriches the diversification of open platform.
Detailed description of the invention
Fig. 1 is the skin schematic diagram of fixed single in the prior art;
Fig. 2 is the prototype figure of clustering in the present invention;
Fig. 3 be the present invention in embodiment in obtain user behavior information schematic diagram;
Fig. 4 is user's portrait analysis process schematic diagram in the present invention;
Fig. 5 is user behavior information cluster figure.
Specific embodiment
Below in conjunction with the drawings and the specific embodiments, the invention will be further described.
A kind of open platform skin layout method based on clustering, includes the following steps:
Step 1, the device-fingerprint information for obtaining H5 or app, obtain mobile device information;Mobile device information includes movement
The type and screen resolution of equipment.The type of mobile device (refering in particular to touch class equipment), which can correspond to, obtains the type on official website
Device layout, such as whether full frame, information such as key arrangement, in addition the resolution ratio of screen, could uniquely determine in this way
Only available opereating specification after user's mobile device is placed on hand, could adjust in real time skin-like after user's switch mobile phone
Formula.
Step 2 includes use according to mobile device information, acquisition active user default skin and user data, user data
Family essential information and user behavior information of the user in the opereating specification of mobile device screen in a period of time;User believes substantially
Breath is the information such as gender, the age of user.User behavior information is the number etc. that left or right hand clicks H5 or app.
Step 3 marks off use to user behavior information cluster analysis based on user basic information and cluster algorithm
Behavioural habits of the user corresponding to the essential information of family within the scope of the click of screen, the institute after obtaining user data clustering
Belong to cluster, i.e. user draws a portrait, and is laid out user again further according to user's portrait and active user's default skin and defaults skin pattern.
If Fig. 5 shows, specific algorithm is realized: at present using the mean shift clustering algorithm in clustering algorithm.
Mean shift clustering is the algorithm based on sliding window, to find the close quarters of data point.This is one and is based on
The algorithm of mass center is completed by the way that the candidate point of central point is updated to the mean value put in sliding window, to position each group/class
Central point.Then similar window removal is carried out to these candidate windows, ultimately forms center point set and corresponding grouping.
Specific steps:
1., by user behavior information, such as left area's left hand, right area is right in the case where knowing user basic information
Hand obtains the number of clicks in each region, determines that sliding window radius r, sliding radius are 4, screen is divided into upper left, the right side
Upper, lower-left and bottom right, i.e. upper left and lower-left left hand, upper right and bottom right carry out number of clicks acquisition with the right hand, it is also possible to root
It is adjusted according to screen size and user behavior habit, screen is excessive, and region is increased by, the too small just corresponding reduction of screen, increase and decrease
Ratio be at present the corresponding increase and decrease in left and right, for the round sliding window of r start to slide with the central point C, the radius that randomly select.?
Value drift is mobile to the higher region of density in each iteration similar to a kind of hill-climbing algorithm, until convergence.
2. slide into new region each time, the mean value in sliding window is calculated as central point, in sliding window
The quantity of point is the density in window.In moving each time, window can be mobile to the higher region of density, such as upper left, upper right,
Each region in lower-left and bottom right, according to the density being distributed in each region, sliding window lived in each region density it is big move.
3. moving window, the density in central point and window in calculation window makes the direction may not be used in window
The point of receiving is moved to always in circle until density is not further added by.
Retain when the overlapping of multiple sliding windows comprising most multiple spot 4. step 1 to 3 can generate many sliding windows
Then window is laid out according to the sliding window where data point, i.e., should be grasped by left or right hand according to used region
Make to be laid out mobile H5 and app, while can also be automatically adjusted according to user basic information to font.It is corresponding in the present invention
User basic information is clustered, it may also be used for counts the operating habit etc. of each user group.
A kind of open platform skin layout system based on clustering, comprising:
Data acquisition module: the device-fingerprint information of H5 or app is obtained, mobile device information is obtained;According to mobile device
Information, acquires original current user's default skin and user data, user data include user basic information and a period of time
User behavior information of the interior user in the opereating specification of mobile device screen;Mobile device information includes the type of mobile device
With screen resolution.The type of mobile device (refering in particular to touch class equipment) can correspond to the equipment cloth that the type is obtained on official website
Office, such as whether full frame, the information such as key arrangement, in addition the resolution ratio of screen, could uniquely determine that user is mobile in this way
Only available opereating specification after equipment is placed on hand, could adjust in real time skin pattern after user's switch mobile phone.The number
It include the type and screen resolution of mobile device according to mobile device information obtained in acquisition module.User basic information is to use
The information such as gender, the age at family.User behavior information is the number etc. that left or right hand clicks H5 or app.
User behavior server: for being based on user basic information and cluster algorithm, to user behavior information cluster
Analysis, marks off behavioural habits of the user corresponding to user basic information within the scope of the click of screen, obtains user data
It is silent to be laid out user further according to user's portrait and active user's default skin again for affiliated cluster after clustering, i.e. user portrait
Recognize skin pattern.
Further include user data memory module, obtains the user data that module obtains, user behavior clothes for storing data
Business device called data from user data memory module.
Embodiment
One user is loaded with the present invention on mobile phone, to select new to the page layouts such as new Internetbank row H5 or App, this implementation
Internetbank row App, first has to get parms, and Parameter analysis source is that the analysis of backend user data is prepared, and acquisition equipment first refers to
Line information obtains mobile device information;Obtained mobile device information includes the type and screen resolution of mobile device.
According to mobile device information, acquires active user's default skin and user data, user data include that user is basic
The user behavior information of information and user in the opereating specification of mobile device screen;User basic information bank interaction in
It through being acquired, can also be obtained by other APP information exchanges, be for the gender and age, the gender of active user of user
Female, age are 30 years old, can directly be used as a part of data of user's portrait;User behavior information mobile device end into
It is acquired when row operation, obtains behavioural habits (the i.e. user behavior of user in the click location of screen by obtaining user
Information), i.e., the size of the device screen used according to user, collect user operate whithin a period of time new Internetbank row APP or
The position that the H5 page is clicked carries out clustering, and it is for a period of time a cycle (when such as that this implementation, which is to click new Internetbank row app,
Between be one day, the later period is adjusted the period according to user clicks), active user clicks new Internetbank row app in each region of screen
Number, i.e., acquire number of clicks in upper left and lower left region with left hand, the right hand acquires number of clicks in upper right and lower right area,
Then intellectual analysis statistics is carried out, just can know that movable region (wherein just including left or right hand operation etc.), such as Fig. 2 institute
Show.
Based on user basic information and cluster algorithm, i.e., the gender based on user is female, the age is 30 years old to user
Behavioural information is clustered, and behavioural habits of the user corresponding to user basic information within the scope of the click of screen are marked off,
Affiliated cluster after obtaining user data clustering, i.e. user portrait default skin weight further according to user's portrait and active user
New user defaults skin pattern to get corresponding mobile phone screen is arrived, it should be laid out which APP key etc..Rear end (user behavior service
Device) according to cluster algorithm progress user's portrait, it is laid out out default skin corresponding to reasonable user, promotes user behaviour
Make, for example user's habit is left-handed, user is often mobile device lower left in the range of page point solution, and relevant operation key is just
The lower left side in mobile device should be laid out, give left handed user to provide convenient, at the same can also according to user basic information to font into
Row automatic adjustment etc., and so on.
The present invention can carry out brightness processed etc. to skin with acquisition time.
In conclusion the artificial cluster algorithm that the present invention mainly uses, different to user to be carried out with behavioural habits
Classification changes the Traditional skin of former old-fashioned mode, in the internet of new situations, in addition artificial intelligence epoch, greatly
The experience for improving user, be one new promotion such as mobile H5 to mobile device app.
The above is only the representative embodiment in the numerous concrete application ranges of the present invention, to protection scope of the present invention not structure
At any restrictions.All technical solutions formed using transformation or equivalence replacement, are all fallen within rights protection scope of the present invention.
Claims (7)
1. a kind of open platform skin layout method based on clustering, which comprises the steps of:
Step 1, the device-fingerprint information for obtaining H5 or app, obtain mobile device information;
Step 2, according to mobile device information, acquire that active user defaults skin and user data, user data include user's base
This information and user behavior information of the user in the opereating specification of mobile device screen in a period of time;
Step 3 marks off user's base to user behavior information cluster analysis based on user basic information and cluster algorithm
Behavioural habits of the user corresponding to this information within the scope of the click of screen, it is affiliated after obtaining user data clustering
Cluster, i.e. user portrait default skin further according to user's portrait and active user and are laid out user's default skin pattern again.
2. a kind of open platform skin layout method based on clustering according to claim 1, which is characterized in that institute
State the type and screen resolution that mobile device information obtained in step 1 includes mobile device.
3. a kind of open platform skin layout method based on clustering according to claim 1, which is characterized in that institute
Stating the user behavior information in step 2 is the number that left or right hand clicks H5 or app.
4. a kind of open platform skin layout method based on clustering according to claim 1, which is characterized in that institute
It states in step 3 using mean shift clustering algorithm.
5. a kind of open platform skin layout system based on clustering characterized by comprising
Data acquisition module: the device-fingerprint information of H5 or app is obtained, mobile device information is obtained;According to mobile device information,
It acquires original current user's default skin and user data, user data includes user basic information and user in a period of time
User behavior information in the opereating specification of mobile device screen;
User behavior server: for being based on user basic information and cluster algorithm, to user behavior information cluster analysis,
Behavioural habits of the user corresponding to user basic information within the scope of the click of screen are marked off, user data cluster point is obtained
Affiliated cluster after analysis, i.e. user portrait default skin further according to user's portrait and active user and are laid out user's default skin again
Pattern.
6. a kind of open platform skin layout system based on clustering according to claim 5, which is characterized in that institute
State the type and screen resolution that mobile device information obtained in data acquisition module includes mobile device.
7. a kind of open platform skin layout system based on clustering according to claim 5 or 6, feature exist
In, further include user data memory module, for storing data obtain module obtain user data, user behavior server from
Called data in user data memory module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811619879.2A CN109739603A (en) | 2018-12-27 | 2018-12-27 | A kind of open platform skin layout method and system based on clustering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811619879.2A CN109739603A (en) | 2018-12-27 | 2018-12-27 | A kind of open platform skin layout method and system based on clustering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109739603A true CN109739603A (en) | 2019-05-10 |
Family
ID=66361707
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811619879.2A Pending CN109739603A (en) | 2018-12-27 | 2018-12-27 | A kind of open platform skin layout method and system based on clustering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109739603A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114035882A (en) * | 2021-11-26 | 2022-02-11 | 中国银行股份有限公司 | Method and system for setting management end front end interface based on cluster analysis |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103677516A (en) * | 2013-11-27 | 2014-03-26 | 青岛海信电器股份有限公司 | Interface generating method and device of terminal |
CN104765561A (en) * | 2015-03-26 | 2015-07-08 | 深圳市艾优尼科技有限公司 | Terminal |
CN104820490A (en) * | 2015-03-02 | 2015-08-05 | 百度在线网络技术(北京)有限公司 | Feature information acquisition method and system |
CN106297079A (en) * | 2016-08-22 | 2017-01-04 | 浪潮(苏州)金融技术服务有限公司 | A kind of method and device that functional module is provided |
CN108549566A (en) * | 2018-04-16 | 2018-09-18 | 中山大学 | A kind of personal page and client layout generation method based on user characteristics |
CN108549516A (en) * | 2018-04-12 | 2018-09-18 | 北京奇艺世纪科技有限公司 | A kind of interface layout method of adjustment and device |
-
2018
- 2018-12-27 CN CN201811619879.2A patent/CN109739603A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103677516A (en) * | 2013-11-27 | 2014-03-26 | 青岛海信电器股份有限公司 | Interface generating method and device of terminal |
CN104820490A (en) * | 2015-03-02 | 2015-08-05 | 百度在线网络技术(北京)有限公司 | Feature information acquisition method and system |
CN104765561A (en) * | 2015-03-26 | 2015-07-08 | 深圳市艾优尼科技有限公司 | Terminal |
CN106297079A (en) * | 2016-08-22 | 2017-01-04 | 浪潮(苏州)金融技术服务有限公司 | A kind of method and device that functional module is provided |
CN108549516A (en) * | 2018-04-12 | 2018-09-18 | 北京奇艺世纪科技有限公司 | A kind of interface layout method of adjustment and device |
CN108549566A (en) * | 2018-04-16 | 2018-09-18 | 中山大学 | A kind of personal page and client layout generation method based on user characteristics |
Non-Patent Citations (1)
Title |
---|
杨东援: "《透过大数据把脉城市交通》", 31 March 2017 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114035882A (en) * | 2021-11-26 | 2022-02-11 | 中国银行股份有限公司 | Method and system for setting management end front end interface based on cluster analysis |
CN114035882B (en) * | 2021-11-26 | 2024-05-28 | 中国银行股份有限公司 | Method and system for setting front-end interface of management end based on cluster analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
dos Santos et al. | A relevance feedback method based on genetic programming for classification of remote sensing images | |
US7720848B2 (en) | Hierarchical clustering with real-time updating | |
CN102364498B (en) | Multi-label-based image recognition method | |
CN109669759A (en) | Rubbish recovering method, device, equipment and the storage medium of Java Virtual Machine | |
CN105242239A (en) | Indoor subarea positioning method based on crowdsourcing fingerprint clustering and matching | |
CN103399692A (en) | Mobile terminal one-hand operation method and mobile terminal thereof | |
CN102222092A (en) | Massive high-dimension data clustering method for MapReduce platform | |
CN106528804B (en) | A kind of tenant group method based on fuzzy clustering | |
CN110245687A (en) | User classification method and device | |
CN108664651A (en) | A kind of pattern recommends method, apparatus and storage medium | |
CN110287219A (en) | A kind of data processing method and system | |
CN108540988A (en) | A kind of scene partitioning method and device | |
CN112036261A (en) | Gesture recognition method and device, storage medium and electronic device | |
CN108664653A (en) | A kind of Medical Consumption client's automatic classification method based on K-means | |
CN108664515A (en) | A kind of searching method and device, electronic equipment | |
CN108268275A (en) | Software version control method and software version control device | |
Vu | An efficient semi-supervised graph based clustering | |
CN109657705A (en) | A kind of automobile user clustering method and device based on random forests algorithm | |
CN109739603A (en) | A kind of open platform skin layout method and system based on clustering | |
CN109241410A (en) | A kind of article recommended method and device | |
de Pinho et al. | An incremental space to visualize dynamic data sets | |
CN103761503A (en) | Self-adaptive training sample selection method for relevance feedback image retrieval | |
CN107704364B (en) | Background application management-control method, device, storage medium and electronic equipment | |
CN109688217A (en) | A kind of information push method, device and electronic equipment | |
CN107798331A (en) | From zoom image sequence characteristic extracting 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |