WO2017028099A1 - 网站推荐方法和网站推荐系统 - Google Patents

网站推荐方法和网站推荐系统 Download PDF

Info

Publication number
WO2017028099A1
WO2017028099A1 PCT/CN2015/087142 CN2015087142W WO2017028099A1 WO 2017028099 A1 WO2017028099 A1 WO 2017028099A1 CN 2015087142 W CN2015087142 W CN 2015087142W WO 2017028099 A1 WO2017028099 A1 WO 2017028099A1
Authority
WO
WIPO (PCT)
Prior art keywords
website
user
label
time
interest
Prior art date
Application number
PCT/CN2015/087142
Other languages
English (en)
French (fr)
Inventor
常平
Original Assignee
常平
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 常平 filed Critical 常平
Priority to PCT/CN2015/087142 priority Critical patent/WO2017028099A1/zh
Publication of WO2017028099A1 publication Critical patent/WO2017028099A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • the invention belongs to the field of home appliances, and in particular relates to a website recommendation method and a website recommendation system.
  • the user narrows the field of view according to the inertia.
  • the user often knows for a long time before he knows it;
  • the search engine In the second way, although the user can rely on the search engine, it is limited to factors such as keyword ranking and excessive search results. After the user inputs a keyword, the search result is often swayed, so that the website required by the user is drowned in the information. In the stream.
  • the defects of the two methods are based on the user's customization of the information they want, rather than the active recognition of the system. Of course, users will not be actively recommended to sites that users may be interested in but not noticed.
  • the user interest recognition is not active, and the recommendation is not active.
  • a solution is proposed to enable the system to actively recommend websites that may be of interest to the user.
  • An embodiment of the present invention provides a website recommendation method, which aims to In view of the fact that the current technology does not take the initiative to identify user interest, and the recommendation is not active, a solution is proposed to enable the system to actively recommend websites that may be of interest to the user.
  • a website recommendation method includes the following steps:
  • the content corresponding to the specific label is set as the interest of the user
  • An embodiment of the present invention further provides a website recommendation system, including:
  • a recording unit configured to record a corresponding label preset by each website
  • An interest identification unit whose input ends are respectively connected to the output end of the recording unit and the output end of the statistical unit, and is used when the user browses the website with the specific label for more than the time when the user browses the website with other labels.
  • At the threshold setting the content corresponding to the specific tag as the user's interest;
  • a website recommendation unit whose input end is connected to the output end of the interest identification unit, and is used to recommend other websites with the same label to the user according to the specific label.
  • the invention allows the system to automatically recognize the user's interest and push the relevant website by monitoring the user's browsing time on a certain website or a certain type of website and comparing the browsing time of the user with other websites.
  • FIG. 1 is a schematic flowchart of a website recommendation method according to an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of a website recommendation system according to an embodiment of the present invention.
  • FIG. 1 is a diagram of an embodiment of the invention. A schematic diagram of the flow of the website recommendation method, for the convenience of explanation, only the parts related to the embodiment of the present invention are shown.
  • step S101 the corresponding tabs preset by each website are recorded.
  • the 'game' can be preset to its corresponding label on the tgbus.com website.
  • 'literature' is preset as its corresponding label.
  • the nature of the website can be located by setting a label, in order to prepare for subsequent implementations of similar website push, advertisement access and the like.
  • the statistical method can be the absolute time for the user to open the website, but considering the case where the user leaves the computer without closing the website, the absolute time for the user to open the website and the frequency of the user clicking and operating the website can be considered.
  • the number of clicks and operations on the website by the user is greater than a certain threshold, the user is deemed to be browsing the website. time.
  • step S103 The content corresponding to the specific tag is set as the user's interest when the time when the user browses the website with the specific tag is greater than the time when the user browses the website with the other tag exceeds a certain threshold.
  • step S104 According to the specific tag, recommend other websites with the same tags to the user.
  • the invention allows the system to automatically recognize the user's interest and push the relevant website by monitoring the user's browsing time on a certain website or a certain type of website and comparing the browsing time of the user with other websites.
  • FIG. 2 is a schematic structural diagram of a website recommendation system according to an embodiment of the present invention, where the website recommendation system includes:
  • a recording unit 21 configured to record a corresponding label preset by each website
  • the statistical unit 22 is used for counting and recording the time when the user browses the website
  • the interest recognition unit 23 has its input end and the output end of the recording unit 21 and the statistical unit 22, respectively.
  • the output connection is configured to set the content corresponding to the specific label as the user's interest when the time when the user browses the website with the specific label is greater than the time when the user browses the website with the other label exceeds a certain threshold;
  • Website recommendation unit 24 The input end is connected to the output end of the interest identification unit, and is used to recommend other websites with the same label to the user according to the specific label.
  • the working principle is: the recording unit 21 records the corresponding label preset by each website; the statistical unit 22 Count and record the time when users browse the website, interest identification unit 23 When the time when the user browses the website with the specific label is greater than the time when the user browses the website with the other label exceeds a certain threshold, the content corresponding to the specific label is set as the interest of the user; meanwhile, the website recommendation unit 24 Based on the specific tag, other sites with the same tag are recommended to the user.
  • the invention allows the system to automatically recognize the user's interest and push the relevant website by monitoring the user's browsing time on a certain website or a certain type of website and comparing the browsing time of the user with other websites.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种网站推荐方法以及网站推荐系统,所述方法包括:记录各网站预设的对应标签(S101);统计并记录用户浏览网站的时间(S102);当用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣(S103);根据所述特定标签,向用户推荐其他具有相同标签的网站(S104)。该方法以及系统通过监控用户对某一网站或某一类网站的浏览时间,并跟用户对其他网站的浏览时间对比,从而让系统自动识别用户的兴趣,并进行相关网站的推送。

Description

网站推荐方法和网站推荐系统 技术领域
本发明属于家电领域,尤其是涉及一种 网站推荐方法和网站推荐系统 。
背景技术
现有技术中,人们上网查找自己感兴趣的专利完整一般基于两个途径:1、要么根据习惯,浏览其每天上的网站;2、要么利用搜索引擎,通过关键字查找相关的主题网站。
当前的这两种上网方式都有缺陷:
第一种方式中,用户根据惯性,同时也使视野狭窄,当出现了更好的同类专题网站时,用户往往很长一段时间后方才后知后觉;
第二种方式中,用户虽然可以依赖搜索引擎,但限于关键词排名、搜索结果过多等因素,用户输入一个关键词后,搜索结果往往沙石俱下,使得用户所需的网站淹没在信息流中。
统一来看,两种方式的缺陷都是基于用户对自己想要得到的信息的自定义,而不是系统的主动识别。当然,也不会向用户主动推荐用户可能感兴趣而又没有留意到的网站。
综上,根据当前系统对用户兴趣识别不主动,且推荐不主动的缺陷,特提出一个解决方案,以便于系统能够主动推荐用户可能感兴趣的网站。
技术问题
本发明实施例提供了 一种 网站推荐方法 , 目的在于 针对当前技术对用户兴趣识别不主动,且推荐不主动的缺陷,特提出一个解决方案,以便于系统能够主动推荐用户可能感兴趣的网站。
技术解决方案
本发明是这样实现的: 一种 网站推荐方法,包括以下步骤:
记录各网站预设的对应标签;
统计并记录用户浏览网站的时间;
当用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;
根据所述特定标签,向用户推荐其他具有相同标签的网站。
本发明实施例还提供了一种 网站推荐系统 ,包括:
记录单元,用于记录各网站预设的对应标签;
统计单元,用于统计并记录用户浏览网站的时间;
兴趣识别单元,其输入端分别与所述记录单元的输出端以及所述统计单元的输出端连接,用于在用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;
网站推荐单元,其输入端与所述兴趣识别单元的输出端连接,用于根据所述特定标签,向用户推荐其他具有相同标签的网站。
有益效果
该发明通过监控用户对某一网站或某一类网站的浏览时间,并跟用户对其他网站的浏览时间对比,从而让系统自动识别用户的兴趣,并进行相关网站的推送。
附图说明
图 1 是本发明实施例提供的 一种 网站推荐方法 的流程示意图 ;
图 2 是本发明实施例提供的网站推荐系统的结构示意图。
本发明的实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
图 1 是发明实施例提供的 一种 网站推荐方法的流程示意图,为了便于说明,只示出了与本发明实施例相关的部分。
在步骤 S101 中 记录各网站预设的对应标签。
在本实施例中,可在 tgbus.com 网站上,将'游戏'预设为其对应标签,在 tianyaluntan.com 网站上,将'文学'预设为其对应标签。
同时作为一种互联网生态模式,可以通过设置标签的方式定位网站的性质,以为后续的类似网站推送、广告接入等功能的实现做准备。
在步骤 S102 中,统计并记录用户浏览网站的时间。该统计方式可以是用户开启网站的绝对时间,但考虑到用户离开电脑而未关闭网站的情况,可以综合考虑用户开启网站的绝对时间,以及用户对网站进行点击、操作的频率,当在一定时间内用户对网站点击、操作的次数大于一定阈值时,方认定为用户浏览网站 的时间。
在步骤 S103 中,当用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣。
这样就使得系统自动识别了用户上网的关注点和兴趣点。
当识别了用户的关注点和兴趣点后,进入步骤 S104 ,根据所述特定标签,向用户推荐其他具有相同标签的网站。
这样就实现了系统向用户推荐的主动化。
该发明通过监控用户对某一网站或某一类网站的浏览时间,并跟用户对其他网站的浏览时间对比,从而让系统自动识别用户的兴趣,并进行相关网站的推送。
图 2 是本发明实施例提供的一种 网站推荐系统 的结构示意图,该网站推荐系统包括 :
记录单元 21 ,用于记录各网站预设的对应标签;
统计单元 22 ,用于统计并记录用户浏览网站的时间;
兴趣识别单元 23 ,其输入端分别与所述记录单元 21 的输出端以及所述统计单元 22 的输出端连接,用于在用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;
网站推荐单元 24 ,其输入端与所述兴趣识别单元的输出端连接,用于根据所述特定标签,向用户推荐其他具有相同标签的网站。
其工作原理是:记录单元 21 记录各网站预设的对应标签;统计单元 22 统计并记录用户浏览网站的时间,兴趣识别单元 23 在用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;同时,网站推荐单元 24 根据所述特定标签,向用户推荐其他具有相同标签的网站。
该发明通过监控用户对某一网站或某一类网站的浏览时间,并跟用户对其他网站的浏览时间对比,从而让系统自动识别用户的兴趣,并进行相关网站的推送。
以上仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。

Claims (2)

  1. 一种网站推荐方法 ,其特征在于,所述方法包括如下步骤:
    记录各网站预设的对应标签;
    统计并记录用户浏览网站的时间;
    当用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;
    根据所述特定标签,向用户推荐其他具有相同标签的网站。
  2. 一种 网站推荐系统 ,其特征在于,所述 网站推荐系统 包括:
    记录单元,用于记录各网站预设的对应标签;
    统计单元,用于统计并记录用户浏览网站的时间;
    兴趣识别单元,其输入端分别与所述记录单元的输出端以及所述统计单元的输出端连接,用于在用户浏览带特定标签的网站的时间大于用户浏览带其他标签的网站的时间超过一定阈值时,将所述特定标签对应的内容设定为用户的兴趣;
    网站推荐单元,其输入端与所述兴趣识别单元的输出端连接,用于根据所述特定标签,向用户推荐其他具有相同标签的网站。
PCT/CN2015/087142 2015-08-16 2015-08-16 网站推荐方法和网站推荐系统 WO2017028099A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/087142 WO2017028099A1 (zh) 2015-08-16 2015-08-16 网站推荐方法和网站推荐系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/087142 WO2017028099A1 (zh) 2015-08-16 2015-08-16 网站推荐方法和网站推荐系统

Publications (1)

Publication Number Publication Date
WO2017028099A1 true WO2017028099A1 (zh) 2017-02-23

Family

ID=58050701

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/087142 WO2017028099A1 (zh) 2015-08-16 2015-08-16 网站推荐方法和网站推荐系统

Country Status (1)

Country Link
WO (1) WO2017028099A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115878903A (zh) * 2023-02-21 2023-03-31 万链指数(青岛)信息科技有限公司 基于大数据的信息智能推荐方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080040221A1 (en) * 2006-08-08 2008-02-14 Google Inc. Interest Targeting
CN102622445A (zh) * 2012-03-15 2012-08-01 华南理工大学 一种基于用户兴趣感知的网页推送系统及方法
CN102799662A (zh) * 2012-07-10 2012-11-28 北京奇虎科技有限公司 推荐网址的方法、装置及系统
CN103186565A (zh) * 2011-12-28 2013-07-03 中国移动通信集团浙江有限公司 根据用户网页浏览行为判断用户偏好的方法及装置
CN103997507A (zh) * 2013-02-20 2014-08-20 腾讯科技(深圳)有限公司 一种信息的推送方法及装置
CN104199874A (zh) * 2014-08-20 2014-12-10 哈尔滨工程大学 一种基于用户浏览行为的网页推荐方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080040221A1 (en) * 2006-08-08 2008-02-14 Google Inc. Interest Targeting
CN103186565A (zh) * 2011-12-28 2013-07-03 中国移动通信集团浙江有限公司 根据用户网页浏览行为判断用户偏好的方法及装置
CN102622445A (zh) * 2012-03-15 2012-08-01 华南理工大学 一种基于用户兴趣感知的网页推送系统及方法
CN102799662A (zh) * 2012-07-10 2012-11-28 北京奇虎科技有限公司 推荐网址的方法、装置及系统
CN103997507A (zh) * 2013-02-20 2014-08-20 腾讯科技(深圳)有限公司 一种信息的推送方法及装置
CN104199874A (zh) * 2014-08-20 2014-12-10 哈尔滨工程大学 一种基于用户浏览行为的网页推荐方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115878903A (zh) * 2023-02-21 2023-03-31 万链指数(青岛)信息科技有限公司 基于大数据的信息智能推荐方法

Similar Documents

Publication Publication Date Title
WO2020143620A1 (zh) 显示区块链数据的方法、区块链浏览器、用户节点和介质
Dong et al. Time is of the essence: improving recency ranking using twitter data
CN102291251A (zh) 一种用于互联网网站的用户状态跟踪方法及系统
WO2017028099A1 (zh) 网站推荐方法和网站推荐系统
CN104216901B (zh) 信息搜索的方法和系统
WO2017028096A1 (zh) 根据网站浏览时间推荐附近用户的方法和用户推荐系统
WO2017028098A1 (zh) 推荐网站时显示技术信息的方法和网站推荐系统
WO2017028095A1 (zh) 根据网站浏览时间识别用户兴趣的方法和数据处理系统
WO2017028097A1 (zh) 推荐附近用户时的信息提醒方法和用户推荐系统
Peters et al. Social tagging & folksonomies: Indexing, retrieving… and beyond?
WO2017128425A1 (zh) 根据浏览记录推送广告时的信息提示方法以及推送系统
WO2017128057A1 (zh) 视频推送技术的技术使用数据发送方法以及推送系统
WO2017128424A1 (zh) 推送广告技术的数据采集方法以及推送系统
WO2017128146A1 (zh) 根据身份证推荐影视的方法和推荐系统
WO2018023688A1 (zh) 一种网络收音机内容推荐的方法和推荐系统
WO2017128423A1 (zh) 根据浏览记录推送广告的方法以及推送系统
WO2017028092A1 (zh) 投放网页广告时的信息提示方法和广告投放系统
WO2017028094A1 (zh) 识别用户兴趣时的信息提醒方法和数据处理系统
WO2018023649A1 (zh) 根据手机推送视频的方法以及推送系统
WO2018018250A1 (zh) 一种根据年龄推荐节目的数据采集方法以及节目播放系统
Cao et al. Re‐ranking question search results by clustering questions
Jin et al. Extracting Inter-Firm Networks fromWorldWideWeb
WO2017128434A1 (zh) 内容更新时的推送方法以及推送系统
Kopparapu et al. Minimal parsing key concept based question answering system
WO2017128147A1 (zh) 根据身份证推荐影视时的技术信息采集方法和推荐系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15901304

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15901304

Country of ref document: EP

Kind code of ref document: A1