Method and device for forecasting whether user is off network

A user and off-grid technology, applied in the Internet field, can solve problems such as lack of interest, user dislike, and leaving

Active Publication Date: 2012-07-25
ALIBABA (CHINA) CO LTD
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this method has a disadvantage. First, although it can be basically judged that the user has left the network, we cannot predict other behaviors of the user. For example, the user may have gone to other websites; It is no longer interested in the original browsing content; or the user leaves because he does not like a certain function of the website, these are also impossible to count
[0004] The chain-type mining method commonly used in the existing telecommunications industry to mine users' online behavior is only suitable for flat business structures and cannot satisfy the multi-dimensional operation methods of users of social networking sites

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for forecasting whether user is off network
  • Method and device for forecasting whether user is off network
  • Method and device for forecasting whether user is off network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Example 1, see figure 1 , the invention discloses a method for predicting users leaving the network, including:

[0037] S1. Distribute the matrix site element table to the registered user who logs in, and set the initial value of each element;

[0038] The matrix site element table of the present embodiment includes horizontal column and vertical column, and horizontal column is user behavior classification, and user behavior classification includes: browse, publish, comment, share, delete, and vertical column is at least one site function set classification, site function Collection categories include: news, photo albums, logs, friends, BLOG.

[0039] The specific implementation method first sets all the operations of a social networking site as a user behavior matrix, and the vertical column is classified by user behavior (browsing, posting, updating), and the horizontal column is based on the set of functions of one or more sites with the same nature (new things) ...

Embodiment 2

[0049] like Figure 4 As shown, the difference between this embodiment and embodiment 1 also includes

[0050] S31: Reset the initial value of the element value in the site element table. It can be reset in the early morning of every day, or it can be reset at other times.

[0051]Set up a website element configuration table in the background, and each element can set horizontal classification and vertical classification. When users log in to the foreground every day, a temporary site element table is automatically assigned to them, which is recorded in an array. The initial value of each element is 0. It is cached on the server, and each user has one and only one element array every day. For each operation performed by the user, the value of the element is updated, and the data of all users of the day is uniformly saved every morning, and the cache is cleared. Multi-cluster The server is distributed, and the data needs to be aggregated first, and then calculated. Set a fix...

Embodiment 4

[0058] Example 4, see Figure 5 , one A device for predicting users leaving the network is used to implement the above method, including:

[0059] An element table allocation unit 10, a user operation recording unit 20, an average active value calculation unit 30, a downward trend judgment unit 40, and an element value reset unit.

[0060] The element table allocation unit 10 is used to distribute the matrix type site element table to the registered user who logs in, and the initial value of each element is set;

[0061] The matrix site element table of the present embodiment includes horizontal column and vertical column, and horizontal column is user behavior classification, and user behavior classification includes: browse, publish, comment, share, delete, and vertical column is at least one site function set classification, site function Collection categories include: news, photo albums, logs, friends, BLOG.

[0062] The specific implementation method first sets all th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for forecasting whether a user is off network, which comprises the following steps: distributing matrix-type site elements to a registered user who logs in; setting the initial value of each element; recording all the operations of the registered user; summarizing the operations of the registered user; calculating an average active value of the user; judging whether the average active values of different users in the preset time present descending trend or not, if so, determining the user to be an off-network user; otherwise, returning to the step of distributing matrix-type site elements to the registered user who logs in, and setting the initial value of each element. The invention also discloses a device for forecasting whether the user is off network. The invention provides a user behavior excavation manner, which can be used for calculating the standard active value by matching with a certain algorithm, thereby forecasting the possibility of the user off network in advance from the trend of the active degree of the user, so that operators can take corresponding remedial measures.

Description

technical field [0001] The present invention relates to the technical field of the Internet, and more specifically, to a method and device for predicting users leaving the network. Background technique [0002] With the informatization of society and the continuous development of the Internet, website operators often need to understand the behaviors of users in the process of interacting with the website. [0003] The current off-network analysis of social networking sites generally uses the user's login time for judgment. For example, if a user has not logged in for more than three months, it can be judged that the user has left the network. But this method has a disadvantage. First, although it can be basically judged that the user has left the network, we cannot predict other behaviors of the user. For example, the user may have gone to other websites; He is no longer interested in the original browsing content; or the user leaves because he does not like a certain funct...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06F17/30
Inventor 梁捷黄耀悦
Owner ALIBABA (CHINA) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap