CN105243144A - Method and device for recommending interesting labels - Google Patents
Method and device for recommending interesting labels Download PDFInfo
- Publication number
- CN105243144A CN105243144A CN201510670272.7A CN201510670272A CN105243144A CN 105243144 A CN105243144 A CN 105243144A CN 201510670272 A CN201510670272 A CN 201510670272A CN 105243144 A CN105243144 A CN 105243144A
- Authority
- CN
- China
- Prior art keywords
- interest tags
- site information
- website
- clicks
- client
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a method for recommending interesting labels. The method comprises the following steps: creating a plurality of interesting labels; collecting website information of a website clicked by a user; carrying out matching on the plurality of interesting labels and the website information of the website clicked by the user, and screening out the interesting label corresponding to the website information; and recommending the interesting label corresponding to the website information to a client. Through the method and the device, the interested content can be accurately recommended to the user.
Description
Technical field
The present invention relates to internet arena, in particular to a kind of recommend method and device of interest tags.
Background technology
, people are when browsing video, news, shopping, and client may receive some content recommendations, and these content recommendations are that the web page contents browsed to user is relevant mostly.Such as, when user is when the news browsing today's tops is interested in a certain bar headline, this title will be clicked and enter content part, now the content of backstage, website meeting default user to this part is interested, relevant content is recommended to it, but the content not under the title clicked of representative of consumer is exactly the interested content of user, so just causes the inaccurate problem of content of recommending to user.
Summary of the invention
Technical matters to be solved by this invention is for the deficiencies in the prior art, provides a kind of recommend method and device of interest tags, can recommend its interested content exactly to user.
According to the aspect that the present invention solves the problems of the technologies described above, provide a kind of recommend method of interest tags, the method comprises: create multiple interest tags; Gather user click the site information of website; By described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information; The interest tags corresponding with described site information is recommended to client.
The invention has the beneficial effects as follows: the site information can clicked according to user recommends its interested content exactly.
On the basis of technique scheme, the present invention can also do following improvement.
Further, described site information comprises page info and the website domain name that described user browses described website.
Further, by described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information to comprise: mate with described multiple interest tags according to the page info of described website and website domain name, and form corresponding relation; Filter out the interest tags of described corresponding relation.
Further, interest tags corresponding for described site information is recommended to comprise before client: the recommendation request receiving described user; According to described recommendation request, the history obtaining the described site information that described user clicked clicks record; Click record according to described history and generate the interest tags corresponding with described site information.
Further, described history is clicked and is recorded as the number of clicks of described multiple interest tags respectively in described client in preset time period, it is characterized in that, click the record generation interest tags corresponding with described site information according to described history and comprise: judge in described preset time period, whether described multiple interest tags point other number of clicks in described client is greater than preset times; If judge that in described preset time period, described multiple interest tags point other number of clicks in described client is greater than described preset times, then filter out the interest tags that number of clicks is greater than described preset times.
According to another aspect that the present invention solves the problems of the technologies described above, provide a kind of recommendation apparatus of interest tags, this device comprises: creation module, for creating multiple interest tags; Acquisition module, for gather user click the site information of website; Matching module, for by described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information; Recommending module, for recommending the interest tags corresponding with described site information to client.
Further, described site information comprises page info and the website domain name that described user browses described website.
Further, described matching module comprises: matching unit, for mating with described multiple interest tags according to the page info of described website and website domain name, and forms corresponding relation; First screening unit, for filtering out the interest tags of described corresponding relation.
Further, described recommendation apparatus also comprises: receiver module, for by before interest tags corresponding for described site information recommendation to client, receives the recommendation request of described user; Acquisition module, clicks record for the history obtaining the described site information that described user clicked according to described recommendation request; Generation module, generates the interest tags corresponding with described site information for clicking record according to described history.
Further, described history is clicked and is recorded as the number of clicks of described multiple interest tags respectively in described client in preset time period, described generation module comprises: judging unit, for judging in described preset time period, whether described multiple interest tags point other number of clicks in described client is greater than preset times; Second screening unit, if for judging that in described preset time period, described multiple interest tags point other number of clicks in described client is greater than described preset times, then filter out the interest tags that number of clicks is greater than described preset times.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the recommend method of interest tags according to the embodiment of the present invention;
Fig. 2 is the structural representation of the recommendation apparatus of interest tags according to the embodiment of the present invention;
In accompanying drawing, the list of parts representated by each label is as follows:
1, creation module, 2, acquisition module, 3, matching module, 4, recommending module.
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
Fig. 1 is the process flow diagram of the recommend method of interest tags according to the embodiment of the present invention.As shown in Figure 1, the method comprises the steps:
Step 1: create multiple interest tags;
Step 2: gather user click the site information of website;
Step 3: by multiple interest tags and user click website site information mate, filter out the interest tags corresponding with site information;
Step 4: the interest tags corresponding with site information is recommended to client.
Preferably, site information comprises the page info and website domain name that user browses web sites.
Preferably, by multiple interest tags and user click website site information mate, filter out the interest tags corresponding with site information and comprise: mate with multiple interest tags according to the page info of website and website domain name, and form corresponding relation; Filter out the interest tags of corresponding relation.
Preferably, interest tags corresponding for site information is recommended to comprise before client: the recommendation request receiving user; According to recommendation request, the history obtaining the site information that user clicked clicks record; Click record according to history and generate the interest tags corresponding with site information.
Preferably, history is clicked and is recorded as multiple interest tags difference number of clicks on the client in preset time period, clicks the record generation interest tags corresponding with site information and comprises: judge that in preset time period, multiple interest tags divides other number of clicks whether to be greater than preset times on the client according to history; If judge that in preset time period, multiple interest tags divides other number of clicks to be greater than preset times on the client, then filter out the interest tags that number of clicks is greater than preset times.
Fig. 2 is the structural representation of the recommendation apparatus of interest tags according to the embodiment of the present invention.As shown in Figure 2, this device comprises: creation module 1, acquisition module 2, matching module 3 and recommending module 4.
Creation module 1 is for creating multiple interest tags;
Acquisition module 2 for gather user click the site information of website;
Matching module 3 for by multiple interest tags and user click website site information mate, filter out the interest tags corresponding with site information;
Recommending module 4 is for recommending the interest tags corresponding with site information to client.
Preferably, site information comprises the page info and website domain name that user browses web sites.
Preferably, matching module comprises: matching unit and the first screening unit.Matching unit is used for mating with multiple interest tags according to the page info of website and website domain name, and forms corresponding relation; First screening unit is for filtering out the interest tags of corresponding relation.
Preferably, recommendation apparatus also comprises: receiver module, acquisition module and generation module.
Receiver module is used for, by before interest tags corresponding for site information recommendation to client, receiving the recommendation request of user; The history that acquisition module is used for obtaining according to recommendation request the site information that user clicked clicks record; Generation module is used for clicking record according to history and generates the interest tags corresponding with site information.
Preferably, history is clicked and is recorded as multiple interest tags difference number of clicks on the client in preset time period, and generation module comprises: judging unit and the second screening unit.
Judging unit is for judging that in preset time period, multiple interest tags divides other number of clicks whether to be greater than preset times on the client; If the second screening unit is used for judging that in preset time period, multiple interest tags divides other number of clicks to be greater than preset times on the client, then filter out the interest tags that number of clicks is greater than preset times.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a recommend method for interest tags, is characterized in that, comprising:
Create multiple interest tags;
Gather user click the site information of website;
By described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information;
The interest tags corresponding with described site information is recommended to client.
2. the recommend method of interest tags according to claim 1, is characterized in that, described site information comprises page info and the website domain name that described user browses described website.
3. the recommend method of interest tags according to claim 2, is characterized in that, by described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information and comprise:
Mate with described multiple interest tags according to the page info of described website and website domain name, and form corresponding relation;
Filter out the interest tags of described corresponding relation.
4. the recommend method of interest tags according to claim 1, is characterized in that, is recommended to comprise before client by interest tags corresponding for described site information:
Receive the recommendation request of described user;
According to described recommendation request, the history obtaining the described site information that described user clicked clicks record;
Click record according to described history and generate the interest tags corresponding with described site information.
5. the recommend method of the interest tags described in 4 is wanted according to right, described history is clicked and is recorded as the number of clicks of described multiple interest tags respectively in described client in preset time period, it is characterized in that, click the record generation interest tags corresponding with described site information according to described history and comprise:
Judge in described preset time period, whether described multiple interest tags point other number of clicks in described client is greater than preset times;
If judge that in described preset time period, described multiple interest tags point other number of clicks in described client is greater than described preset times, then filter out the interest tags that number of clicks is greater than described preset times.
6. a recommendation apparatus for interest tags, is characterized in that, comprising:
Creation module, for creating multiple interest tags;
Acquisition module, for gather user click the site information of website;
Matching module, for by described multiple interest tags and described user click website site information mate, filter out the interest tags corresponding with described site information;
Recommending module, for recommending the interest tags corresponding with described site information to client.
7. the recommendation apparatus of interest tags according to claim 6, is characterized in that, described site information comprises page info and the website domain name that described user browses described website.
8. the recommendation apparatus of interest tags according to claim 7, is characterized in that, described matching module comprises:
Matching unit, for mating with described multiple interest tags according to the page info of described website and website domain name, and forms corresponding relation;
First screening unit, for filtering out the interest tags of described corresponding relation.
9. the recommendation apparatus of interest tags according to claim 6, is characterized in that, described recommendation apparatus also comprises:
Receiver module, for by before interest tags corresponding for described site information recommendation to client, receives the recommendation request of described user;
Acquisition module, clicks record for the history obtaining the described site information that described user clicked according to described recommendation request;
Generation module, generates the interest tags corresponding with described site information for clicking record according to described history.
10. want the recommendation apparatus of the interest tags described in 9 according to right, described history is clicked and is recorded as the number of clicks of described multiple interest tags respectively in described client in preset time period, and it is characterized in that, described generation module comprises:
Judging unit, for judging in described preset time period, whether described multiple interest tags point other number of clicks in described client is greater than preset times;
Second screening unit, if for judging that in described preset time period, described multiple interest tags point other number of clicks in described client is greater than described preset times, then filter out the interest tags that number of clicks is greater than described preset times.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510670272.7A CN105243144A (en) | 2015-10-15 | 2015-10-15 | Method and device for recommending interesting labels |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510670272.7A CN105243144A (en) | 2015-10-15 | 2015-10-15 | Method and device for recommending interesting labels |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105243144A true CN105243144A (en) | 2016-01-13 |
Family
ID=55040792
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510670272.7A Pending CN105243144A (en) | 2015-10-15 | 2015-10-15 | Method and device for recommending interesting labels |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105243144A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109561162A (en) * | 2017-09-26 | 2019-04-02 | 北京国双科技有限公司 | Excavate the method and device that user accesses hobby |
CN110580317A (en) * | 2019-08-29 | 2019-12-17 | 武汉赛可锐信息技术有限公司 | social information analysis method and device, terminal equipment and storage medium |
CN110968780A (en) * | 2018-09-30 | 2020-04-07 | 腾讯科技(深圳)有限公司 | Page content recommendation method and device, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090265350A1 (en) * | 2007-06-20 | 2009-10-22 | Huawei Technologies Co., Ltd. | Method, system and key extractor for correlating advertisements in a vertical search engine |
CN102799662A (en) * | 2012-07-10 | 2012-11-28 | 北京奇虎科技有限公司 | Method, device and system for recommending website |
CN102929964A (en) * | 2012-10-11 | 2013-02-13 | 北京百度网讯科技有限公司 | Website push method and website push system |
CN103870512A (en) * | 2012-12-18 | 2014-06-18 | 腾讯科技(深圳)有限公司 | Method and device for generating user interest label |
-
2015
- 2015-10-15 CN CN201510670272.7A patent/CN105243144A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090265350A1 (en) * | 2007-06-20 | 2009-10-22 | Huawei Technologies Co., Ltd. | Method, system and key extractor for correlating advertisements in a vertical search engine |
CN102799662A (en) * | 2012-07-10 | 2012-11-28 | 北京奇虎科技有限公司 | Method, device and system for recommending website |
CN102929964A (en) * | 2012-10-11 | 2013-02-13 | 北京百度网讯科技有限公司 | Website push method and website push system |
CN103870512A (en) * | 2012-12-18 | 2014-06-18 | 腾讯科技(深圳)有限公司 | Method and device for generating user interest label |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109561162A (en) * | 2017-09-26 | 2019-04-02 | 北京国双科技有限公司 | Excavate the method and device that user accesses hobby |
CN110968780A (en) * | 2018-09-30 | 2020-04-07 | 腾讯科技(深圳)有限公司 | Page content recommendation method and device, computer equipment and storage medium |
CN110580317A (en) * | 2019-08-29 | 2019-12-17 | 武汉赛可锐信息技术有限公司 | social information analysis method and device, terminal equipment and storage medium |
CN110580317B (en) * | 2019-08-29 | 2022-02-22 | 武汉赛可锐信息技术有限公司 | Social information analysis method and device, terminal equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103164427B (en) | News Aggreagation method and device | |
CN104699704B (en) | Content pushing and receiving method, device and system | |
CN104133820A (en) | Content recommending method and content recommending device | |
CN108229810B (en) | Industry analysis system and method based on network information resources | |
CN102693271A (en) | Network information recommending method and system | |
CN101409690A (en) | Method and system for obtaining internet user behaviors | |
CN102129632A (en) | Method, device and system for capturing webpage information | |
CN103744856A (en) | Method, device and system for linkage extended search | |
CN104778208A (en) | Method and system for optimally grasping search engine SEO (search engine optimization) website data | |
CN105162822A (en) | Website log data processing method and device | |
CN105117434A (en) | Webpage classification method and webpage classification system | |
CN101980529A (en) | Video service system supporting integration of three networks | |
CN105243144A (en) | Method and device for recommending interesting labels | |
CN105450677A (en) | Data processing method, device and system | |
CN103870452A (en) | Method and method for recommending data | |
CN105808642B (en) | Recommendation method and device | |
CN101894109A (en) | Database building method and device | |
CN104391936A (en) | Method and device for processing tags in browser favorite | |
CN104753979A (en) | Method, server, terminal and system for displaying website information | |
US20130232139A1 (en) | Electronic device and method for generating recommendation content | |
CN101807187A (en) | Browsing information-based instant search method | |
CN104835052A (en) | Method and system for improving network advertisement delivery precision | |
CN103605742A (en) | Method and device for recognizing network resource entity content page | |
CN103227791B (en) | A kind of method of data acquisition and device | |
CN101576933A (en) | Fully-automatic grouping method of WEB pages based on title separator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160113 |
|
RJ01 | Rejection of invention patent application after publication |