CN101169861A - User tendency modeling method based on network browsing behavior - Google Patents

User tendency modeling method based on network browsing behavior Download PDF

Info

Publication number
CN101169861A
CN101169861A CNA2007101949112A CN200710194911A CN101169861A CN 101169861 A CN101169861 A CN 101169861A CN A2007101949112 A CNA2007101949112 A CN A2007101949112A CN 200710194911 A CN200710194911 A CN 200710194911A CN 101169861 A CN101169861 A CN 101169861A
Authority
CN
China
Prior art keywords
user
behavior
keyword
information
browsing
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
Application number
CNA2007101949112A
Other languages
Chinese (zh)
Inventor
刘明晶
刘国越
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BEIJING XINZHI SHIJIE NETWORK TECHNOLOGIES Co Ltd
Original Assignee
BEIJING XINZHI SHIJIE NETWORK TECHNOLOGIES Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BEIJING XINZHI SHIJIE NETWORK TECHNOLOGIES Co Ltd filed Critical BEIJING XINZHI SHIJIE NETWORK TECHNOLOGIES Co Ltd
Priority to CNA2007101949112A priority Critical patent/CN101169861A/en
Publication of CN101169861A publication Critical patent/CN101169861A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A user-orientation modeling method based on website browsing is provided. The invention establishes correlation between keywords of an independent user browsing characteristics and keywords of sales information, sends the correlated correspondent information to the independent user, further determines orientation of the user to the product on sale based on feedback behavior of the independent user, and releases sales information based on characteristics of the oriented requirement of the user.

Description

The user tendency modeling method of browsing behavior Network Based
Technical field
The present invention relates to a kind of user tendency modeling method of browsing behavior Network Based, belong to electric digital data processing field.
Background technology
The application of network browsing behavioral analysis technology aspect trade marketing, deeply develop along direction up to now based on the coupling of the keyword in the search engine database always, typical application is large-scale websites such as http://www.google.com and http://www.baidu.com, its key issue in application technology is the keyword coupling, that is: when user input and search or when clicking the link of a certain keyword, Website server with all information (comprising advertisement, sales promotion information) that comprise this keyword in its data storehouse according to the page quantitatively coupling give this user.This method has improved the accuracy that the web advertisement is thrown in to a great extent for the network marketing that onrelevant is thrown in.Its essential meaning is: the input scope of advertisement or marketing information is dwindled navigating to the page viewers that pay close attention to relevent information from all page viewers, thereby enlarged the possibility of paying close attention to advertisement or relevent information, improved personalized, correlativity and interactive relatively.But from analyzing in logic, this category can not guarantee that it all has real demand to relevant marketing information " to pay close attention to the page viewers of keyword relevant information ", for example the viewer of input inquiry or click " notebook computer " may be the information that needs inquiry associated maintenance, upgrading, do not buy the demand of notebook computer, and said method can pour into the marketing information of a large amount of notebook computers this viewer's webpage.The audient that this input covered, quite a few is arranged is the audient who does not have demand, and especially those do not have to click or search among the viewer of " notebook computer ", and having quite a few has the tendency of buying notebook computer on the contrary, that is to say that the input of this method is still accurate inadequately.Therefore, setting up more accurately, the user tendency model will improve the effective reach of marketing information greatly than present said method.
Publication number is that the patent of invention of CN1700220 is being used following method aspect the keyword coupling transmission advertisement:
A) judge degree of correlation according to title, subtitle, text;
B) according to keyword on same webpage occurrence frequency as the advertisement putting parameter;
C) according to the correlativity of web page interlinkage structure analysis keyword.
These related standards have an obvious characteristics, promptly carry out " machinery " coupling according to the keyword of being set by advertisement publishers in the database fully.This method system will cause its result who analyzes coupling can only be confined to " paying close attention to the page viewers of keyword relevant information " this category, and this category will " quite a few is arranged be the audient who does not have demand ", simultaneously this category also will contain do not pay close attention to keyword that advertisement publishers set but other viewers that buy this advertisement publishers' product tendency are but arranged.Throw in to for the real demander for the information of will marketing, precisely throw in, accurately aspect the location, suitable gap arranged undoubtedly.
Summary of the invention
For than existing key word matching method more accurately consumer positioning to the tendentiousness of certain class marketing product, the invention provides a kind of method of setting up the user tendency model, this method can capture the viewer that a part does not have search or clicks marketing information keyword.
The present invention realizes the user tendency modeling method of browsing behavior Network Based by following steps:
A. obtain marketing information keyword by advertisement publishers or marketing principal's product information;
B. obtain the keyword data of isolated user by the behavior of browsing of website isolated user;
The content of browsing behavior comprises click information, browsing time, inputted search, registers, lands, nullifies and withdraw from.
The keyword data of isolated user is meant the keyword that carries out integrated ordered different weights according to the content of browsing behavior.
C. the keyword that isolated user is browsed is set up related the search with marketing information keyword;
D. the information link of Search Results is thrown in and give this isolated user;
E. according to the feedback behavior of isolated user and browse behavior in conjunction with its all and carry out the tendentiousness grading and set up the user tendency database;
Tendentiousness is meant the tendentiousness of carrying out integrated ordered different weights according to the content of browsing behavior and feeding back behavior.
F. throw in the marketing information according to the tendentiousness of isolated user.
The invention has the beneficial effects as follows to have no the tendentiousness of related viewer with marketing information keyword on the catch surface, use server and data mining technology to carry out data necessary and handle just realization that can be simple and easy to do the marketing product.
The present invention is further described below in conjunction with drawings and Examples.
Fig. 1 is an information flow chart of the present invention.
Fig. 2 is the synoptic diagram of the embodiment of the invention.
Embodiment
In Fig. 1, illustrated that server is 3 information flows that isolated user carries out the tendentiousness modeling of certain website.
1.. server obtains the traffic statistics basic index by Internet from the website;
2.. server obtains the keyword data of isolated user from the behavior of browsing of isolated user by Internet and website;
3.. the information that server is associated with the information keyword of marketing to the keyword of Internet search isolated user;
4.. the information that server obtains isolated user from Internet keyword is associated with marketing information keyword;
5.. server sends to isolated user with the link of the related information that obtains by Internet and website correspondence;
6.. server obtains isolated user to the feedback behavior of related information link and set up the user tendency database from Internet and website;
7.. server is distributed to corresponding isolated user according to the user tendency database information of will marketing.
In embodiment illustrated in fig. 2, illustrated the process of certain isolated user tendentiousness modeling.
1.. server obtains isolated user by Internet and browses essential information from the website;
2.. server obtains first keyword of Liu Xiang for this user by Internet and website from the behavior of browsing of isolated user;
3.. the information that server is associated with Benz to Internet search Liu Xiang;
4.. server obtains the information that Liu Xiang is associated with Benz from Internet;
5.. server sends to isolated user with the link of the related information that obtains by Internet and website correspondence;
6.. server obtains isolated user to the feedback behavior of related information link and set up the user tendency database from Internet and website;
7.. if this user demonstration in the behavior of feedback is paid close attention to some extent to the Benz in the link, when it clicks the keyword relevant with Benz, server sends to this isolated user with the marketing information of Benz automatically, or when this isolated user was visited original web again, server sent to the marketing information of Benz the accession page of this isolated user automatically.
8.. if this user shows the Benz in the link in the behavior of feedback without any concern, 2. server is got back to automatically, carries out the operation of identical flow process with this user's second keyword, if come to the same thing, then move the 3rd keyword equally, until having moved whole keywords.
If at 8. operation result still to Benz without any tendency, 1. the marketing information of then changing another product carries out to similar operation 8., until finding out the tendentiousness of this isolated user to certain series products.

Claims (5)

1. user tendency modeling method of browsing behavior Network Based, it is characterized in that: the keyword of isolated user being browsed behavioural characteristic is set up related with marketing information keyword, relevent information with association sends to this isolated user again, further judge its tendentiousness according to the feedback behavior of this isolated user, throw in the marketing information according to its tendentiousness demand characteristic again this marketing product.
2. the user tendency modeling method of browsing behavior Network Based according to claim 1, it is characterized in that: set up the tendentiousness model of user by the method for association, need not the user and in browsing behavior, the keyword of marketing information is directly searched for or clickthrough the marketing information.
3. the user tendency modeling method of browsing behavior Network Based according to claim 1 is characterized in that: the content of browsing behavior and feedback behavior comprises click information, browsing time, inputted search, registers, lands, nullifies and withdraw from.
4. the user tendency modeling method of browsing behavior Network Based according to claim 1 is characterized in that: the keyword that isolated user is browsed behavioural characteristic is the keyword that behavior and the content of feedback behavior are carried out integrated ordered different weights of browsing according to claim 3.
5. the user tendency modeling method of browsing behavior Network Based according to claim 1 is characterized in that: to the tendentiousness of marketing product is the tendentiousness that the content of browsing behavior and feeding back behavior according to claim 3 is carried out integrated ordered different weights.
CNA2007101949112A 2007-12-06 2007-12-06 User tendency modeling method based on network browsing behavior Pending CN101169861A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNA2007101949112A CN101169861A (en) 2007-12-06 2007-12-06 User tendency modeling method based on network browsing behavior

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNA2007101949112A CN101169861A (en) 2007-12-06 2007-12-06 User tendency modeling method based on network browsing behavior

Publications (1)

Publication Number Publication Date
CN101169861A true CN101169861A (en) 2008-04-30

Family

ID=39390478

Family Applications (1)

Application Number Title Priority Date Filing Date
CNA2007101949112A Pending CN101169861A (en) 2007-12-06 2007-12-06 User tendency modeling method based on network browsing behavior

Country Status (1)

Country Link
CN (1) CN101169861A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968802A (en) * 2010-09-30 2011-02-09 百度在线网络技术(北京)有限公司 Method and equipment for recommending content of Internet based on user browse behavior
CN103970857A (en) * 2014-05-07 2014-08-06 百度在线网络技术(北京)有限公司 Recommended content determining system and method
CN107093102A (en) * 2017-03-31 2017-08-25 柳州译海网络科技有限公司 A kind of packaging system for corporate image

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101968802A (en) * 2010-09-30 2011-02-09 百度在线网络技术(北京)有限公司 Method and equipment for recommending content of Internet based on user browse behavior
CN103970857A (en) * 2014-05-07 2014-08-06 百度在线网络技术(北京)有限公司 Recommended content determining system and method
CN103970857B (en) * 2014-05-07 2017-08-25 百度在线网络技术(北京)有限公司 Content recommendation determines system and method
CN107093102A (en) * 2017-03-31 2017-08-25 柳州译海网络科技有限公司 A kind of packaging system for corporate image

Similar Documents

Publication Publication Date Title
US10789626B2 (en) Deep-linking system, method and computer program product for online advertisement and e-commerce
US9767182B1 (en) Classification of search queries
JP5899275B2 (en) System and method for scoring quality of advertisement and content in online system
US9413834B2 (en) System and method for measuring the virality of internet content using indices
US8799260B2 (en) Method and system for generating web pages for topics unassociated with a dominant URL
US10719836B2 (en) Methods and systems for enhancing web content based on a web search query
US20120259854A1 (en) Conversion Path Based Segmentation
JP2011515731A (en) Hybrid ad campaign
US20130144719A1 (en) Using image match technology to improve image advertisement quality
KR20140038962A (en) Aggregation of conversion paths utilizing user interaction grouping
US20070219955A1 (en) Advertising service based on content and user log mining
WO2012141732A1 (en) Priority dimensional data conversion path reporting
AU2011365446A1 (en) Illustrating cross channel conversion paths
WO2009012466A2 (en) Ad targeting using reference page information
US20120078719A1 (en) Systems and methods for cluster augmentation of search results
US20180096067A1 (en) Creation and optimization of resource contents
CN104572863A (en) Product recommending method and system
CN101188011A (en) Search-based network scenario marketing method
US20170357999A1 (en) Method and system for providing ranking information using effect analysis data of information data
CN101169861A (en) User tendency modeling method based on network browsing behavior
TWI611362B (en) Personalized internet marketing recommendation method
US20180039643A1 (en) Analysis and management of resources in a network
US20150106201A1 (en) Method of delivering a search engine advertisement
CN103377215A (en) Information promotion method and system
US8745504B1 (en) Goal flow visualization

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
DD01 Delivery of document by public notice

Addressee: Intellectual property department head of Beijing new horizon Network Technology Co., Ltd.

Document name: Notification that Application Deemed to be Withdrawn

C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Open date: 20080430