CN105069168A - Search word recommendation method and apparatus - Google Patents
Search word recommendation method and apparatus Download PDFInfo
- Publication number
- CN105069168A CN105069168A CN201510541978.3A CN201510541978A CN105069168A CN 105069168 A CN105069168 A CN 105069168A CN 201510541978 A CN201510541978 A CN 201510541978A CN 105069168 A CN105069168 A CN 105069168A
- Authority
- CN
- China
- Prior art keywords
- word
- search results
- behavioral data
- recommendation
- search
- 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 present invention discloses a search word recommendation method and apparatus. The method at a browser side comprises steps: displaying a search result page acquired according to a current search word; collecting present behavioral data of an operation in the search result page by a user; sending the current search word and the present behavioral data to a web server to request the web server extract a recommended word according to the current search word and the present behavioral data in combination with history behavioral data; and and receiving the recommended word returned from the web server and displaying the recommended word to the user. The method at a web server side comprises steps: receiving a current search word and present behavioral data sent by a browser; according to the current search word and the present behavioral data in combination with history behavioral data, extracting a recommended word by using a data mining technique; and and sending the recommended word to the browser to display on a search results page. According to the method and apparatus disclosed by the present invention, the accuracy and real-time property of recommended words are improved, thereby sufficiently attracting attention of users so as to improve the marketability of recommended words.
Description
Technical field
The embodiment of the present invention relates to search engine technique, particularly relates to a kind of search word recommend method and device.
Background technology
Search engine attracts customer group by providing accurately abundant natural Search Results, promotes flow, then passes through the client payment impression information earning profit that coupling is relevant to search word.Therefore, the search engine recommendation word that some can be provided relevant to impression information for user.
In prior art, word is recommended mainly to utilize the historical behavior data of user and current search word for user provides, extract some relevant with user view and recommend word, word is recommended synchronously to be presented on the impression information position of search results pages these, the defect existed be to recommend the accuracy of word and real-time all lower, fully can not attract the attention of user.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of search word recommend method and device, to improve the accuracy and real-time of recommending word.
First aspect, embodiments provides a kind of search word recommend method, comprising:
Show the search results pages got according to current search word;
Gather this behavioral data that user carries out in described search results pages operating;
Current search word and this behavioral data are sent to the webserver, extract recommendation word according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver;
Receive the recommendation word that the webserver returns, and be shown to described user.
Second aspect, the embodiment of the present invention additionally provides a kind of search word recommendation apparatus, and this application of installation, in browser end, comprising:
Search result display module, for showing the search results pages got according to current search word;
Behavioral data acquisition module, for gathering this behavioral data that user carries out in described search results pages operating;
Sending module, for current search word and this behavioral data are sent to the webserver, extracts recommendation word according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver;
Recommending word display module, for receiving the recommendation word that the webserver returns, and being shown to described user.
The third aspect, the embodiment of the present invention additionally provides a kind of search word recommend method, comprising:
Receive the current search word that sends of browser and this behavioral data, this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word;
According to described current search word and this behavioral data, extract recommendation word in conjunction with historical behavior data separate data mining technology;
Described recommendation word is sent to browser, to show in described search results pages.
Fourth aspect, the embodiment of the present invention additionally provides a kind of search word recommendation apparatus, and this application of installation, in network server end, comprising:
Data reception module, for receiving the current search word and this behavioral data that browser sends, this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word;
Recommend word extraction module, for according to described current search word and this behavioral data, extract recommendation word in conjunction with historical behavior data separate data mining technology;
Recommend word sending module, for described recommendation word is sent to browser, to show in described search results pages.
The search word recommend method that the embodiment of the present invention provides and device, by current search word and this behavioral data, and extract recommendation word in conjunction with historical behavior data, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention one provides;
Fig. 2 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention two provides;
Fig. 3 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention three provides;
Fig. 4 is the structural representation of a kind of search word recommendation apparatus that the embodiment of the present invention four provides;
Fig. 5 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention five provides;
Fig. 6 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention six provides;
Fig. 7 is the structural representation of a kind of search word recommendation apparatus that the embodiment of the present invention seven provides.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not full content.
Embodiment one
Fig. 1 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention one provides, and it is the situation that user recommends search word that the present embodiment is applicable to according to the search word of user and operation behavior, and the method can be performed by browser, specifically comprises as follows:
S110, shows the search results pages got according to current search word.
During the information that user is understood by browser searches oneself needs in mobile terminal or computing machine, need inputted search word in a browser, this search word is called current search word, after browser receives current search word, this current search word is sent to the webserver, the webserver is according to current search word relevant search information in internet, obtain search results pages, and return to browser, browser shows described search results pages after receiving the search results pages that the webserver returns.
S120, gathers this behavioral data that user carries out in described search results pages operating.
In practice, due to the restriction of mobile terminal or computer screen size, browser is when showing Search Results, first screen can only exposition nature Search Results or impression information result, generally need user to carry out some operation behavior (as mouse action or gesture drag screen etc.), just can see the Search Results beyond non-head screen.
After browser display search results pages, user can carry out some operation (as clicked or browsing) in search results pages, when user is interested in a certain Search Results, can clicks this Search Results or browse the simplified summary of this Search Results; When user loses interest in a certain Search Results, can streak this Search Results fast, browser these operation behaviors to user carry out Real-time Collection, obtain this behavioral data that user carries out in described search results pages operating.Wherein, user's navigate search results simplified summary or to streak Search Results be fast judge with the residence time of screen on this Search Results.
S130, is sent to the webserver by current search word and this behavioral data, extracts recommendation word to ask the webserver according to current search word and this behavioral data in conjunction with historical behavior data.
Current search word and this behavioral data collected are sent to the webserver by described browser, extract the recommendation word meeting user view to ask the webserver according to current search word and this behavioral data in conjunction with historical behavior data.Wherein, historical behavior data are user's operation behavior data to the Search Results with a certain search word.
S140, receives the recommendation word that the webserver returns, and is shown to described user.
Described recommendation word is presented in the search results pages of browser after receiving the recommendation word that the webserver returns by described browser, clicks check for user.When showing described recommendation word, the screen position display that may will arrive in the operation of user.In the Search Results of the current display of screen, user may slide downward, also may upward sliding, and word therefore can be recommended to be presented at lower position or the upper position of the Search Results of current display.
The present embodiment is by showing the search results pages got according to current search word, gather this behavioral data that user carries out in described search results pages operating, current term and this behavioral data are sent to the webserver, the webserver has been asked to extract recommendation word according to current term and this behavioral data in conjunction with historical behavior data, receive the recommendation word that the webserver returns, and be shown to described user, owing to combining this behavioral data of user, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user, promote the marketability recommending word.
Embodiment two
Fig. 2 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention two provides, and the present embodiment, on the basis of embodiment one, to receiving the recommendation word that returns of the webserver, and is shown to described user and is optimized, specifically comprise as follows:
S210, shows the search results pages got according to current search word.
S220, gathers this behavioral data that user carries out in described search results pages operating.
S230, is sent to the webserver by current search word and this behavioral data, extracts recommendation word to ask the webserver according to current search word and this behavioral data in conjunction with historical behavior data.
S240, receives the recommendation word that the webserver returns, and described recommendation word packaging is become recommendation card.
After browser receives the recommendation word that the webserver returns, described recommendation word may have a lot of, browser is packed described recommendation word, described recommendation word packaging is become the form of recommending card, thus described recommendation word can be shown to recommend the form of card entirety when showing, in order to avoid omit certain to recommend word when showing.
S250, recommends card described in described search results pages dynamic load.
Described browser loads described recommendation card in described search results pages, during concrete loading, can monitor user ' to the direction of operating of Search Results, be as the criterion with current search result, when user's slide downward, described recommendation card is carried in the lower position of current search result, when user's upward sliding, described recommendation card is carried in the upper position of current search result, makes user can see this recommendation card.
Wherein, described in described search results pages dynamic load, card is recommended to preferably include:
Described recommendation card is carried in the non-head screen impression information position of described search results pages; Or
The head that described recommendation card is carried in described search results pages is shielded impression information position.
Word is recommended generally all to be presented in the impression information position of search results pages, according to the navigation patterns of user to Search Results, user may be shielded with head the slide downward screen that is as the criterion and be arrived non-head screen position, also return again after may skidding off non-head screen and slide to first screen position, therefore, described recommendation card can be carried in the non-head screen impression information position of described search results pages by browser, also the head that described recommendation card is carried in described search results pages can be shielded impression information position.
The present embodiment is by showing the search results pages got according to current search word, gather this behavioral data that user carries out in described search results pages operating, current term and this behavioral data are sent to the webserver, the webserver has been asked to extract recommendation word according to current term and this behavioral data in conjunction with historical behavior data, receive the recommendation word that the webserver returns, and described recommendation word packaging is become recommendation card, card is recommended described in described search results pages dynamic load, owing to combining this behavioral data of user, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user, compared with embodiment one, the present embodiment recommends card to show by recommendation word packaging being become, can avoid omitting and recommend word.
Embodiment three
Fig. 3 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention three provides, and the present embodiment, on the basis of embodiment one, is optimized this behavioral data that collection user operates in described search results pages, specifically comprises as follows:
S310, shows the search results pages got according to current search word.
S320, gathers the click behavioral data of user.
S330, gathers the concern content of user and does not pay close attention to content.
Wherein, Search Results when described concern content refers to that screen residence time on Search Results exceedes setting-up time threshold value, the described Search Results do not paid close attention to when content refers to that screen residence time on Search Results is no more than setting-up time threshold value.
The concern content of above-mentioned click behavioral data and user and do not pay close attention to content as this behavioral data.
Wherein, gather the concern content of user and do not pay close attention to content and preferably include:
Record screen at the starting position of search results pages and end position, and records the residence time;
When the described residence time exceedes setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as concern content;
When the described residence time is no more than setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as not paying close attention to content.
S340, is sent to the webserver by current search word and this behavioral data, extracts recommendation word to ask the webserver according to current search word and this behavioral data in conjunction with historical behavior data.
S350, receives the recommendation word that the webserver returns, and is shown to described user.
The present embodiment is by gathering the click behavioral data of user, the concern content of user and do not pay close attention to content etc. as this behavioral data, current search word and this behavioral data are sent to the webserver, recommendation word is extracted according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver, receive the recommendation word that the webserver returns, and be shown to described user, owing to combining this behavioral data of user, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user, compared with embodiment one, this behavioral data is divided into click behavioral data by the present embodiment, pay close attention to content and do not pay close attention to content, thus the keyword extracted according to this behavioral data is more accurate.
Embodiment four
Fig. 4 is the structural representation of a kind of search word recommendation apparatus that the embodiment of the present invention four provides, search word recommendation apparatus described in the present embodiment is applied to browser end, as shown in Figure 4, this search word recommendation apparatus comprises: search result display module 410, behavioral data acquisition module 420, sending module 430 and recommendation word display module 440.
Wherein, search result display module 410 is for showing the search results pages got according to current search word;
This behavioral data that behavioral data acquisition module 420 carries out in described search results pages operating for gathering user;
Sending module 430, for current search word and this behavioral data are sent to the webserver, extracts recommendation word according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver;
Recommend word display module 440 for receiving the recommendation word that the webserver returns, and be shown to described user.
Preferably, described recommendation word display module comprises:
Recommending card packaging unit, for receiving the recommendation word that the webserver returns, and described recommendation word packaging being become recommendation card;
Recommend card loading unit, for recommending card described in described search results pages dynamic load.
Preferably, described recommendation card loading unit specifically for:
Described recommendation card is carried in the non-head screen impression information position of described search results pages; Or
The head that described recommendation card is carried in described search results pages is shielded impression information position.
Preferably, described behavioral data acquisition module comprises:
First collecting unit, for gathering the click behavioral data of user;
Second collecting unit, for gathering the concern content of user and not paying close attention to content, wherein, Search Results when described concern content refers to that screen residence time on Search Results exceedes setting-up time threshold value, the described Search Results do not paid close attention to when content refers to that screen residence time on Search Results is no more than setting-up time threshold value.
Preferably, described second collecting unit specifically for:
Record screen at the starting position of search results pages and end position, and records the residence time;
When the described residence time exceedes setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as concern content;
When the described residence time is no more than setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as not paying close attention to content.
Above-mentioned search word recommendation apparatus can perform the search word recommend method that the embodiment of the present invention one, embodiment two or embodiment three provide, and possesses the corresponding functional module of manner of execution and beneficial effect.
Embodiment five
Fig. 5 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention five provides, it is the situation that user recommends search word that the present embodiment is applicable to according to the search word of user and operation behavior, the method can be performed by the webserver, specifically comprises as follows:
S510, receives the current search word that sends of browser and this behavioral data, and this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word.
Wherein, this behavioral data described comprise the click behavioral data of user, the concern content of user and user do not pay close attention to content.Search Results when described concern content refers to that screen residence time on Search Results exceedes setting-up time threshold value, the described Search Results do not paid close attention to when content refers to that screen residence time on Search Results is no more than setting-up time threshold value.
S520, according to described current search word and this behavioral data, extracts recommendation word in conjunction with historical behavior data separate data mining technology.
Wherein, data mining generally refers to the process being hidden in wherein information from a large amount of data by algorithm search.Data mining is usually relevant with computer science, and realizes above-mentioned target by all multi-methods such as statistics, Data Environments, information retrieval, machine learning, expert system (relying on thumb rule in the past) and pattern-recognitions.
The webserver, according to described current search word and this behavioral data, utilizes data mining technology in historical behavior data, search for the search word relevant with this behavioral data with described current search word, as recommendation word, and is extracted by described recommendation word.
S530, is sent to browser by described recommendation word, to show in described search results pages.
The recommendation word extracted is sent to browser by the webserver, shows with the search results pages at browser, clicks check for user.
The present embodiment is by receiving the current search word that sends of browser and this behavioral data, recommendation word is extracted in conjunction with historical behavior data separate data mining technology according to described current search word and this behavioral data, and described recommendation word is sent to browser, to show in described search results pages, owing to combining this behavioral data of user when extracting and recommending word, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user, promote the marketability recommending word.
Embodiment six
Fig. 6 is the process flow diagram of a kind of search word recommend method that the embodiment of the present invention six provides, the present embodiment is on the basis of embodiment five, to according to described current search word and this behavioral data, extracting in conjunction with historical behavior data separate data mining technology recommends word to be optimized, and specifically comprises as follows:
S610, receives the current search word that sends of browser and this behavioral data, and this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word.
S620, according to current search word and this behavioral data, historical behavior data corresponding with current search word or this behavioral data in the inquiry table of comparisons, wherein, the described table of comparisons is historical behavior data and the mapping table recommending word.
The a large amount of historical behavior data of described table of comparisons set, and historical behavior data are summed up, according to the rule of historical behavior data, extract corresponding recommendation word, historical behavior data have been constituted the simple directly table of comparisons with recommending word.As long as the webserver is according to current search word and this behavioral data inquiry table of comparisons, historical behavior data corresponding with current search word or this behavioral data in the inquiry table of comparisons, just can fast finding to the recommendation word matched.Wherein, with current search word or historical behavior data corresponding to this behavioral data are corresponding refers to and current search word or the identical or close historical behavior data of this behavioral data.
S630, according to described historical behavior data, extracts recommendation word corresponding with described historical behavior data in the described table of comparisons.
The webserver is according to the historical behavior data corresponding with current search word and this behavioral data, described historical behavior data are inquired about in the table of comparisons, after finding described historical behavior data, extract recommendation word corresponding with described historical behavior data in the table of comparisons.
S640, is sent to browser by described recommendation word, to show in described search results pages.
The present embodiment is by receiving the current search word that sends of browser and this behavioral data, according to current search word and this behavioral data, historical behavior data corresponding with current search word or this behavioral data in the inquiry table of comparisons, according to described historical behavior data, extract recommendation word corresponding with described historical behavior data in the described table of comparisons, described recommendation word is sent to browser by the webserver, to show in described search results pages, owing to combining this behavioral data of user when extracting and recommending word, improve the accuracy and real-time of recommending word, thus fully can attract the attention of user, compared with embodiment five, the present embodiment extracts recommendation word by the inquiry table of comparisons, improve the extraction efficiency of recommending word, save the time.
Embodiment seven
Fig. 7 is the structural representation of a kind of search word recommendation apparatus that the embodiment of the present invention seven provides, search word recommendation apparatus described in the present embodiment is applied to network server end, as shown in Figure 7, this search word recommendation apparatus comprises: data reception module 710, recommendation word extraction module 720 and recommendation word sending module 730.
Wherein, data reception module 710 is for the current search word that receives browser and send and this behavioral data, and this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word;
Recommend word extraction module 720 for according to described current search word and this behavioral data, extract recommendation word in conjunction with historical behavior data separate data mining technology;
Recommend word sending module 730 for described recommendation word is sent to browser, to show in described search results pages.
Preferably, described recommendation word extraction module comprises:
Data query unit, for according to current search word and this behavioral data, inquires about historical behavior data corresponding with current search word or this behavioral data in the table of comparisons, and wherein, the described table of comparisons is historical behavior data and the mapping table recommending word;
Recommend word extraction unit, for according to described historical behavior data, extract recommendation word corresponding with described historical behavior data in the described table of comparisons.
Above-mentioned search word recommendation apparatus can perform the search word recommend method that the embodiment of the present invention five or embodiment six provide, and possesses the corresponding functional module of manner of execution and beneficial effect.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (14)
1. a search word recommend method, is characterized in that, comprising:
Show the search results pages got according to current search word;
Gather this behavioral data that user carries out in described search results pages operating;
Current search word and this behavioral data are sent to the webserver, extract recommendation word according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver;
Receive the recommendation word that the webserver returns, and be shown to described user.
2. method according to claim 1, is characterized in that, receives the recommendation word that returns of the webserver, and is shown to described user and comprises:
Receive the recommendation word that the webserver returns, and described recommendation word packaging is become recommendation card;
Card is recommended described in described search results pages dynamic load.
3. method according to claim 2, is characterized in that, described in described search results pages dynamic load, recommend card to comprise:
Described recommendation card is carried in the non-head screen impression information position of described search results pages; Or
The head that described recommendation card is carried in described search results pages is shielded impression information position.
4., according to the arbitrary described method of claim 1-3, it is characterized in that, this behavioral data that collection user carries out operating in described search results pages comprises:
Gather the click behavioral data of user;
Gather the concern content of user and do not pay close attention to content, wherein, Search Results when described concern content refers to that screen residence time on Search Results exceedes setting-up time threshold value, the described Search Results do not paid close attention to when content refers to that screen residence time on Search Results is no more than setting-up time threshold value.
5. method according to claim 4, is characterized in that, gathers the concern content of user and does not pay close attention to content and comprise:
Record screen at the starting position of search results pages and end position, and records the residence time;
When the described residence time exceedes setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as concern content;
When the described residence time is no more than setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as not paying close attention to content.
6. a search word recommendation apparatus, is characterized in that, comprising:
Search result display module, for showing the search results pages got according to current search word;
Behavioral data acquisition module, for gathering this behavioral data that user carries out in described search results pages operating;
Sending module, for current search word and this behavioral data are sent to the webserver, extracts recommendation word according to current search word and this behavioral data in conjunction with historical behavior data to ask the webserver;
Recommending word display module, for receiving the recommendation word that the webserver returns, and being shown to described user.
7. device according to claim 6, is characterized in that, described recommendation word display module comprises:
Recommending card packaging unit, for receiving the recommendation word that the webserver returns, and described recommendation word packaging being become recommendation card;
Recommend card loading unit, for recommending card described in described search results pages dynamic load.
8. device according to claim 7, is characterized in that, described recommendation card loading unit specifically for:
Described recommendation card is carried in the non-head screen impression information position of described search results pages; Or
The head that described recommendation card is carried in described search results pages is shielded impression information position.
9., according to the arbitrary described device of claim 6-8, it is characterized in that, described behavioral data acquisition module comprises:
First collecting unit, for gathering the click behavioral data of user;
Second collecting unit, for gathering the concern content of user and not paying close attention to content, wherein, Search Results when described concern content refers to that screen residence time on Search Results exceedes setting-up time threshold value, the described Search Results do not paid close attention to when content refers to that screen residence time on Search Results is no more than setting-up time threshold value.
10. device according to claim 9, is characterized in that, described second collecting unit specifically for:
Record screen at the starting position of search results pages and end position, and records the residence time;
When the described residence time exceedes setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as concern content;
When the described residence time is no more than setting-up time threshold value, extract the Search Results between described starting position and end position, this Search Results is as not paying close attention to content.
11. 1 kinds of search word recommend methods, is characterized in that, comprising:
Receive the current search word that sends of browser and this behavioral data, this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word;
According to described current search word and this behavioral data, extract recommendation word in conjunction with historical behavior data separate data mining technology;
Described recommendation word is sent to browser, to show in described search results pages.
12. methods according to claim 11, is characterized in that, according to described current search word and this behavioral data, extract recommend word to comprise in conjunction with historical behavior data separate data mining technology:
According to current search word and this behavioral data, historical behavior data corresponding with current search word or this behavioral data in the inquiry table of comparisons, wherein, the described table of comparisons is historical behavior data and the mapping table recommending word;
According to described historical behavior data, extract recommendation word corresponding with described historical behavior data in the described table of comparisons.
13. 1 kinds of search word recommendation apparatus, is characterized in that, comprising:
Data reception module, for receiving the current search word and this behavioral data that browser sends, this behavioral data described is that described browser collects, user carries out the behavioral data that operates in the search results pages shown according to current search word;
Recommend word extraction module, for according to described current search word and this behavioral data, extract recommendation word in conjunction with historical behavior data separate data mining technology;
Recommend word sending module, for described recommendation word is sent to browser, to show in described search results pages.
14. devices according to claim 13, is characterized in that, described recommendation word extraction module comprises:
Data query unit, for according to current search word and this behavioral data, inquires about historical behavior data corresponding with current search word or this behavioral data in the table of comparisons, and wherein, the described table of comparisons is historical behavior data and the mapping table recommending word;
Recommend word extraction unit, for according to described historical behavior data, extract recommendation word corresponding with described historical behavior data in the described table of comparisons.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510541978.3A CN105069168A (en) | 2015-08-28 | 2015-08-28 | Search word recommendation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510541978.3A CN105069168A (en) | 2015-08-28 | 2015-08-28 | Search word recommendation method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105069168A true CN105069168A (en) | 2015-11-18 |
Family
ID=54498537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510541978.3A Pending CN105069168A (en) | 2015-08-28 | 2015-08-28 | Search word recommendation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105069168A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653588A (en) * | 2015-12-21 | 2016-06-08 | 北京奇虎科技有限公司 | Search history record generation method and device |
| CN106777217A (en) * | 2016-12-23 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of search word recommends method and device |
| CN107015806A (en) * | 2017-03-31 | 2017-08-04 | 北京金山安全软件有限公司 | Video information display method and device and mobile terminal |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107193987A (en) * | 2017-05-27 | 2017-09-22 | 广东神马搜索科技有限公司 | Obtain the methods, devices and systems of the search term related to the page |
| CN107291835A (en) * | 2017-05-31 | 2017-10-24 | 北京京东尚科信息技术有限公司 | A kind of recommendation method and apparatus of search term |
| CN108205545A (en) * | 2016-12-16 | 2018-06-26 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for providing recommendation information to the user |
| CN108737524A (en) * | 2018-05-10 | 2018-11-02 | 佛山欧神诺云商科技有限公司 | A kind of enterprise information push method |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN109491516A (en) * | 2018-11-02 | 2019-03-19 | 北京字节跳动网络技术有限公司 | Input display methods, device, storage medium and the electronic equipment of associational word |
| CN109543113A (en) * | 2018-12-21 | 2019-03-29 | 北京字节跳动网络技术有限公司 | Determine method, apparatus, storage medium and the electronic equipment clicked and recommend word |
| CN111368185A (en) * | 2020-02-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Data display method and device, storage medium and electronic equipment |
| CN111507065A (en) * | 2020-03-10 | 2020-08-07 | 百度在线网络技术（北京）有限公司 | Reading information processing method and device and storage medium |
| CN114756751A (en) * | 2022-04-18 | 2022-07-15 | 北京字节跳动网络技术有限公司 | Recommendation word determination method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130124496A1 (en) * | 2011-11-11 | 2013-05-16 | Microsoft Corporation | Contextual promotion of alternative search results |
| CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Search result recommendation method, system and search engine |
| CN103729351A (en) * | 2012-10-10 | 2014-04-16 | 阿里巴巴集团控股有限公司 | Search term recommendation method and device |
| US20140195348A1 (en) * | 2013-01-09 | 2014-07-10 | Alibaba Group Holding Limited | Method and apparatus for composing search phrases, distributing ads and searching product information |
| CN104143001A (en) * | 2014-08-01 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Search term recommending method and device |
| CN104462364A (en) * | 2014-12-08 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
-
2015
- 2015-08-28 CN CN201510541978.3A patent/CN105069168A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130124496A1 (en) * | 2011-11-11 | 2013-05-16 | Microsoft Corporation | Contextual promotion of alternative search results |
| CN103729351A (en) * | 2012-10-10 | 2014-04-16 | 阿里巴巴集团控股有限公司 | Search term recommendation method and device |
| US20140195348A1 (en) * | 2013-01-09 | 2014-07-10 | Alibaba Group Holding Limited | Method and apparatus for composing search phrases, distributing ads and searching product information |
| CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术（北京）有限公司 | Search result recommendation method, system and search engine |
| CN104143001A (en) * | 2014-08-01 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Search term recommending method and device |
| CN104462364A (en) * | 2014-12-08 | 2015-03-25 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653588B (en) * | 2015-12-21 | 2019-07-02 | 北京奇虎科技有限公司 | Search history records generation method and device |
| CN105653588A (en) * | 2015-12-21 | 2016-06-08 | 北京奇虎科技有限公司 | Search history record generation method and device |
| CN108205545A (en) * | 2016-12-16 | 2018-06-26 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for providing recommendation information to the user |
| CN108205545B (en) * | 2016-12-16 | 2022-06-10 | 百度在线网络技术（北京）有限公司 | Method and equipment for providing recommendation information for user |
| CN106777217A (en) * | 2016-12-23 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of search word recommends method and device |
| WO2018113468A1 (en) * | 2016-12-23 | 2018-06-28 | 北京奇虎科技有限公司 | Search term recommendation method, device, program and medium |
| CN107015806A (en) * | 2017-03-31 | 2017-08-04 | 北京金山安全软件有限公司 | Video information display method and device and mobile terminal |
| CN107172151A (en) * | 2017-05-18 | 2017-09-15 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN107172151B (en) * | 2017-05-18 | 2020-08-07 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
| CN107193987A (en) * | 2017-05-27 | 2017-09-22 | 广东神马搜索科技有限公司 | Obtain the methods, devices and systems of the search term related to the page |
| CN107291835A (en) * | 2017-05-31 | 2017-10-24 | 北京京东尚科信息技术有限公司 | A kind of recommendation method and apparatus of search term |
| CN107291835B (en) * | 2017-05-31 | 2020-12-22 | 北京京东尚科信息技术有限公司 | Search term recommendation method and device |
| CN108737524B (en) * | 2018-05-10 | 2020-11-24 | 佛山欧神诺云商科技有限公司 | Enterprise information pushing method |
| CN108737524A (en) * | 2018-05-10 | 2018-11-02 | 佛山欧神诺云商科技有限公司 | A kind of enterprise information push method |
| CN109491516A (en) * | 2018-11-02 | 2019-03-19 | 北京字节跳动网络技术有限公司 | Input display methods, device, storage medium and the electronic equipment of associational word |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN109543113A (en) * | 2018-12-21 | 2019-03-29 | 北京字节跳动网络技术有限公司 | Determine method, apparatus, storage medium and the electronic equipment clicked and recommend word |
| CN111368185A (en) * | 2020-02-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Data display method and device, storage medium and electronic equipment |
| CN111368185B (en) * | 2020-02-25 | 2023-04-28 | 北京字节跳动网络技术有限公司 | Data display method and device, storage medium and electronic equipment |
| CN111507065A (en) * | 2020-03-10 | 2020-08-07 | 百度在线网络技术（北京）有限公司 | Reading information processing method and device and storage medium |
| CN114756751A (en) * | 2022-04-18 | 2022-07-15 | 北京字节跳动网络技术有限公司 | Recommendation word determination method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105069168A (en) | Search word recommendation method and apparatus | |
| CN103886074B (en) | Commercial product recommending system based on social media | |
| US8886636B2 (en) | Context transfer in search advertising | |
| US20140195893A1 (en) | Method and Apparatus for Generating Webpage Content | |
| US9576251B2 (en) | Method and system for processing web activity data | |
| US8682881B1 (en) | System and method for extracting structured data from classified websites | |
| CN103297469B (en) | The acquisition method of a kind of website data and device | |
| CN105654341A (en) | Aviation product recommendation system and aviation product recommendation method based on cloud service | |
| EP2454690A1 (en) | Systems and methods for providing keyword related search results in augmented content for text on a web page | |
| CN105279224A (en) | Information push method and device | |
| CN109325179A (en) | A kind of method and device that content is promoted | |
| US9672541B2 (en) | Visual tag editor | |
| WO2012100173A1 (en) | Systems and methods for providing a discover prompt to augmented content of a web page | |
| JPWO2014132404A1 (en) | Information processing apparatus, information processing method, information processing program, display control apparatus, and display control program | |
| CN108229991B (en) | Method and device for displaying aggregation promotion information, browser and terminal equipment | |
| CN101145231A (en) | Search engine based directional advertisement sending method | |
| CN102930041A (en) | Retrieval result real-time updating method based on user behavior information and system thereof | |
| JP2011034399A (en) | Method, device and program for extracting relevance of web pages | |
| JP5511782B2 (en) | New advertisement capable URL providing system and new advertisement capable URL providing method | |
| US20140108090A1 (en) | Price mining system and method for mining the price | |
| US20140200996A1 (en) | Information distribution device and information distribution method | |
| KR100869073B1 (en) | A analyzing system for keyword advertisement and analyzing method thereby | |
| JP2017167829A (en) | Detection device, detection method, and detection program | |
| CN105243106A (en) | Method and apparatus used for generating inquiry results | |
| CN104484415A (en) | E-book supplying method and e-book supplying device |
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: 20151118 |
|
| RJ01 | Rejection of invention patent application after publication |