CN109788056A - User's theme message method for pushing and system based on clustering - Google Patents
User's theme message method for pushing and system based on clustering Download PDFInfo
- Publication number
- CN109788056A CN109788056A CN201910025972.9A CN201910025972A CN109788056A CN 109788056 A CN109788056 A CN 109788056A CN 201910025972 A CN201910025972 A CN 201910025972A CN 109788056 A CN109788056 A CN 109788056A
- Authority
- CN
- China
- Prior art keywords
- user
- theme
- information
- clustering
- basic information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a kind of user's theme message method for pushing and system based on clustering, belong to message push technology field, solve app in the prior art, the theme of the mobile form such as H5 is fixed form, in the form of a single, the problems such as user experience is poor, and messaging service face is narrow.The present invention acquires mobile device finger print information and user basic information, user basic information include subject information and user behavior data applied by user;User basic information is clustered by K-Means clustering algorithm, obtains user behavior portrait;It is drawn a portrait according to mobile device finger print information and user and pushes theme message to user.The present invention is pushed for theme message.
Description
Technical field
A kind of user's theme message method for pushing and system based on clustering pushes for theme message, belongs to and disappear
Cease push technology field.
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.
Theme message: the theme background including application, service message push of concern 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.
User be it is diversified, open platform is the channel that user enters certain targeted website, and reasonable analysis is used
User data, the message for pushing different themes to different user groups are just highly desirable.
The theme of the mobile form such as present app, H5 is fixed form, and in the form of a single, it is one that each user, which enters,
The user experience of sample is not classified according to the information of user, and does not carry out user to Users'Data Analysis on backstage
The problem of drawing a portrait, causing poor user experience.
Summary of the invention
Aiming at the problem that the studies above, the purpose of the present invention is to provide user's theme message push based on clustering
Method and system, solve app in the prior art, and the theme of the mobile form such as H5 is fixed form, in the form of a single, cause user
The problem of target app or H5 can not be rapidly entered.
In order to achieve the above object, the present invention adopts the following technical scheme:
A kind of user's theme message method for pushing based on clustering, characterized by the following steps:
Step 1, acquisition mobile device finger print information and user basic information, user basic information include applied by user
Subject information and user behavior data;
Step 2 clusters user basic information by K-Means clustering algorithm, obtains user behavior portrait;
Step 3, being drawn a portrait according to mobile device finger print information and user pushes theme message to user.
Further, user interface is modified by the theme that will be pushed in the step 3, carries out related news push.
A kind of user's theme message supplying system based on clustering characterized by comprising
Data acquisition module: acquiring mobile device finger print information and user basic information, user basic information include user
Applied subject information and user behavior data;
User behavior server: user basic information is clustered by K-Means clustering algorithm, obtains user behavior
Portrait draws a portrait according to mobile device finger print information and user and pushes theme message to user.
Further, the theme of push is modified user interface by the user behavior server, carries out related news push.
The present invention compared with the existing technology, its advantages are shown in:
One, the present invention takes full advantage of the information of user, is reasonably encapsulated to the information of user, then carry out cluster shape
It draws a portrait at user, more effectively can push relevant information to user, dynamic push related subject message is convenient to user in real time
User quickly obtains desired information;
Two, the present invention takes full advantage of artificial intelligence analysis's method, and the focus of user and user is caught to set movement
Standby position concern, can allow user to be more effectively concerned about the message of push.
Detailed description of the invention
Fig. 1 is the prototype figure of clustering in the present invention;
Fig. 2 be the present invention in embodiment in obtain user behavior information schematic diagram;
Fig. 3 is that the K-Means in the present invention clusters schematic diagram.
Specific embodiment
Below in conjunction with the drawings and the specific embodiments, the invention will be further described.
A kind of user's theme message method for pushing based on clustering, includes the following steps:
Step 1, acquisition mobile device finger print information and user basic information, user basic information include applied by user
Subject information and user behavior data;The focus (subject information) paid close attention in user's a cycle (one day) is obtained, and
Source that user behavior data includes user information and user are to the number of clicks of some focus.
Step 2 clusters user basic information by K-Means cluster algorithm, obtains user's portrait;Cluster
Method is K-Means cluster algorithm.
K-Means Clustering specifically:
1, we select several clusters first, and random initializtion their respective central points.In order to calculate need using
Cluster quantity, preferably rapidly browse data and attempting and identify all unique groupings, that is, remove click focus number
After few focus, how remaining focus, the corresponding cluster of each focus are selected.Central point is and data point (i.e. focus)
Vector has the vector of same dimension, such as " X " in figure 3 above.
2, for each data point, by calculating the distance between the point and each cluster central point, according to apart from the smallest
Principle is classified, which is referred in nearest cluster.
3, based on these classification points, the average value of institute's directed quantity in cluster is recalculated, determines new central point.
4, iteration 2-3 several times, or when the central point of each group changes little between iteration twice stops
Iteration, the classification results for then selecting effect best.Also it can choose random initializtion cluster center several times, then select effect
Best classification results.An optimal cluster is selected to be recommended from classification results to get to the focus (theme to be pushed
Message).
Step 3, being drawn a portrait according to mobile device finger print information and user pushes theme message (by user information to user
Source path is pushed).User interface is modified by the theme that will be pushed, carries out related news push.
A kind of user's theme message supplying system based on clustering, comprising:
Data acquisition module: acquiring mobile device finger print information and user basic information, user basic information include user
Applied subject information and user behavior data;Obtain the focus (theme paid close attention in user's a cycle (one day)
Information) and the user behavior data source that includes user information and user to the number of clicks of some focus.
User behavior server: user basic information is clustered by K-Means cluster algorithm, obtains user
Portrait;Clustering method is K-Means cluster algorithm.It is drawn a portrait to push to user according to mobile device finger print information and user and be led
Inscribe message.User interface is modified by the theme that will be pushed, carries out related news push.
Embodiment
It acquires the essential information of device-fingerprint information and user: such as a few services in the new Internetbank row of subject information-, using
In family a cycle (one day), to the click volume of related service, K-Means clustering is carried out to the essential information of user,
Prepare say clustered to a few clothes, number of clicks is most in the corresponding race of division one is selected after cluster, then
In the later period according to device-fingerprint information and user information source, subject information is replaced into the interface that is the theme, realizes final recommendation;
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.It is all using transformation or equivalence replacement and the technical solution that is formed, all fall within rights protection scope of the present invention it
It is interior.
Claims (4)
1. a kind of user's theme message method for pushing based on clustering, characterized by the following steps:
Step 1, acquisition mobile device finger print information and user basic information, user basic information include theme applied by user
Information and user behavior data:
Step 2 clusters user basic information by K-Means clustering algorithm, obtains user behavior portrait;
Step 3, being drawn a portrait according to mobile device finger print information and user pushes theme message to user.
2. a kind of user's theme message method for pushing based on clustering according to claim 1, it is characterised in that: institute
It states in step 3 and user interface is modified by the theme that will be pushed, carry out related news push.
3. a kind of user's theme message supplying system based on clustering characterized by comprising
Data acquisition module: acquiring mobile device finger print information and user basic information, user basic information include that user is answered
Subject information and user behavior data;
User behavior server: clustering user basic information by K-Means clustering algorithm, obtains user behavior picture
Picture draws a portrait according to mobile device finger print information and user and pushes theme message to user.
4. a kind of user's theme message supplying system based on clustering according to claim 3, the user behavior
The theme of push is modified user interface by server, carries out related news push.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025972.9A CN109788056A (en) | 2019-01-10 | 2019-01-10 | User's theme message method for pushing and system based on clustering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910025972.9A CN109788056A (en) | 2019-01-10 | 2019-01-10 | User's theme message method for pushing and system based on clustering |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109788056A true CN109788056A (en) | 2019-05-21 |
Family
ID=66500199
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910025972.9A Pending CN109788056A (en) | 2019-01-10 | 2019-01-10 | User's theme message method for pushing and system based on clustering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109788056A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110807152A (en) * | 2019-10-31 | 2020-02-18 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101819572A (en) * | 2009-09-15 | 2010-09-01 | 电子科技大学 | Method for establishing user interest model |
CN102075851A (en) * | 2009-11-20 | 2011-05-25 | 北京邮电大学 | Method and system for acquiring user preference in mobile network |
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | 中国移动通信集团公司 | Recommending method, system and equipment based on mobile Internet |
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
WO2014040516A1 (en) * | 2012-09-12 | 2014-03-20 | 腾讯科技(深圳)有限公司 | Method and device for sending information |
CN104217352A (en) * | 2014-08-20 | 2014-12-17 | 苏州海云网络科技有限公司 | Accurate push system for mobile advertisements |
CN104281882A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院信息工程研究所 | Method and system for predicting social network information popularity on basis of user characteristics |
CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
CN105490926A (en) * | 2015-12-30 | 2016-04-13 | 哈尔滨工业大学 | User behavior analysis and information push system based on position service |
CN105824912A (en) * | 2016-03-15 | 2016-08-03 | 平安科技(深圳)有限公司 | Personalized recommending method and device based on user portrait |
CN106886597A (en) * | 2017-02-24 | 2017-06-23 | 乐蛙科技(上海)有限公司 | Control system, control method and receiving terminal that a kind of trigger-type is notified |
CN106911806A (en) * | 2017-04-26 | 2017-06-30 | 努比亚技术有限公司 | A kind of method of PUSH message, terminal, server and system |
CN107291755A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信有限公司研究院 | A kind of terminal method for pushing and device |
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
WO2019000852A1 (en) * | 2017-06-28 | 2019-01-03 | Boe Technology Group Co., Ltd. | Apparatus for automatically triaging patient and automatic triage method |
-
2019
- 2019-01-10 CN CN201910025972.9A patent/CN109788056A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101819572A (en) * | 2009-09-15 | 2010-09-01 | 电子科技大学 | Method for establishing user interest model |
CN102075851A (en) * | 2009-11-20 | 2011-05-25 | 北京邮电大学 | Method and system for acquiring user preference in mobile network |
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | 中国移动通信集团公司 | Recommending method, system and equipment based on mobile Internet |
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
WO2014040516A1 (en) * | 2012-09-12 | 2014-03-20 | 腾讯科技(深圳)有限公司 | Method and device for sending information |
CN104217352A (en) * | 2014-08-20 | 2014-12-17 | 苏州海云网络科技有限公司 | Accurate push system for mobile advertisements |
CN104281882A (en) * | 2014-09-16 | 2015-01-14 | 中国科学院信息工程研究所 | Method and system for predicting social network information popularity on basis of user characteristics |
CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
CN105490926A (en) * | 2015-12-30 | 2016-04-13 | 哈尔滨工业大学 | User behavior analysis and information push system based on position service |
CN105824912A (en) * | 2016-03-15 | 2016-08-03 | 平安科技(深圳)有限公司 | Personalized recommending method and device based on user portrait |
CN107291755A (en) * | 2016-04-01 | 2017-10-24 | 中国移动通信有限公司研究院 | A kind of terminal method for pushing and device |
CN106886597A (en) * | 2017-02-24 | 2017-06-23 | 乐蛙科技(上海)有限公司 | Control system, control method and receiving terminal that a kind of trigger-type is notified |
CN106911806A (en) * | 2017-04-26 | 2017-06-30 | 努比亚技术有限公司 | A kind of method of PUSH message, terminal, server and system |
WO2019000852A1 (en) * | 2017-06-28 | 2019-01-03 | Boe Technology Group Co., Ltd. | Apparatus for automatically triaging patient and automatic triage method |
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110807152A (en) * | 2019-10-31 | 2020-02-18 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
CN110807152B (en) * | 2019-10-31 | 2022-06-07 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mehta | Concept drift in streaming data classification: algorithms, platforms and issues | |
CN105095219B (en) | Micro-blog recommendation method and terminal | |
CN103117903B (en) | Surfing flow method for detecting abnormality and device | |
CN106776859A (en) | Mobile solution App commending systems based on user preference | |
Huang et al. | Effective association clusters filtering to cold-start recommendations | |
Zhang et al. | Analysis of power consumer behavior based on the complementation of K-means and DBSCAN | |
Li et al. | Discover and mitigate unknown biases with debiasing alternate networks | |
Zhang et al. | Easy domain adaptation method for filling the species gap in deep learning-based fruit detection | |
CN106846082B (en) | Travel cold start user product recommendation system and method based on hardware information | |
CN111125469B (en) | User clustering method and device of social network and computer equipment | |
CN106951471A (en) | A kind of construction method of the label prediction of the development trend model based on SVM | |
Beal et al. | Billion-scale pretraining with vision transformers for multi-task visual representations | |
CN108399553A (en) | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method | |
CN106649380A (en) | Hot spot recommendation method and system based on tag | |
CN110472016A (en) | Article recommended method, device, electronic equipment and storage medium | |
Ahmed et al. | DGStream: High quality and efficiency stream clustering algorithm | |
Ghane’i-Ostad et al. | Detecting overlapping communities in LBSNs by fuzzy subtractive clustering | |
Zheng et al. | Anomalous telecom customer behavior detection and clustering analysis based on ISP’s operating data | |
CN109788056A (en) | User's theme message method for pushing and system based on clustering | |
Afza et al. | A hybrid classifier using boosting, clustering, and naïve bayesian classifier | |
CN106570174A (en) | Big data analysis method and system running on CMMB super hotspot service platform | |
CN106156256A (en) | A kind of user profile classification transmitting method and system | |
Li et al. | A study on customer churn of commercial banks based on learning from label proportions | |
CN114003803A (en) | Method and system for discovering media account in specific region on social platform | |
Bao et al. | Hot news prediction method based on natural language processing technology and its application |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190521 |
|
RJ01 | Rejection of invention patent application after publication |