CN109190049A - Keyword recommendation method, system, electronic equipment and computer-readable medium - Google Patents
Keyword recommendation method, system, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109190049A CN109190049A CN201811299050.9A CN201811299050A CN109190049A CN 109190049 A CN109190049 A CN 109190049A CN 201811299050 A CN201811299050 A CN 201811299050A CN 109190049 A CN109190049 A CN 109190049A
- Authority
- CN
- China
- Prior art keywords
- keyword
- user
- search
- browsing
- word
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a kind of keyword recommendation method, system, electronic equipment and computer-readable medium, the keyword recommendation method, comprising: obtains the incidence relation between search key according to historical search data；Keyword corresponding with the browsing behavior is extracted according to user browsing behavior；Association search word is generated according to keyword incidence relation and the corresponding keyword of extracted user browsing behavior, and is shown the association search word as recommendation word in the search box of browsing pages.It realizes and improves browse efficiency, at least one of carry out browsing guidance, accurate information push in conjunction with the navigation interest of user, increase multiple purposes such as user experience.
Description
Technical field
This disclosure relates to the technical fields such as computer, internet, big data, and in particular to a kind of keyword recommendation method,
System, electronic equipment and computer-readable medium.
Background technique
Currently, user is in browse network content, browsing demand be usually it is changeable, in order to improve the efficiency and essence of browsing
Quasi- degree devises search box in some Web content pages, so that user searches for the content that expectation obtains, but existing skill
Search is not usually presented in search empty frames in the search box of Web content Pages Design in art and recommends word, it usually needs uses
Family is manually entered search term and scans for, and user is manually entered keyword and has problems in that sometimes user may not can select
Select accurate keyword, it is understood that there may be the browse efficiency for seriously affecting user to content is manually entered in the situation that the language fails to express the meaning,
Reduce user experience；In addition in most cases user's browsing content when its browsing demand be changeable, sometimes even not
Determining, the mode that keyword is manually entered is unfavorable for guidance to user's browsing content.
Summary of the invention
In view of problems of the prior art, the first purpose of the disclosure be to provide a kind of keyword recommendation method,
System, device and computer-readable medium, can be realized improve browse efficiency, in conjunction with user navigation interest carry out browsing draw
It leads, accurate information push, at least one of increase multiple purposes such as user experience.
For this purpose, the disclosure uses following technical scheme:
As the disclosure in a first aspect, providing a kind of keyword recommendation method, comprising:
The incidence relation between search key is obtained according to historical search data；
Keyword corresponding with the browsing behavior is extracted according to user browsing behavior；
Association search word is generated according to keyword incidence relation and the corresponding keyword of extracted user browsing behavior, and
It is shown the association search word as recommendation word in the search box of browsing pages.
As the second aspect of the disclosure, a kind of keyword recommender system is provided, comprising:
Keyword extraction analysis module, for obtaining the incidence relation between search key according to historical search data；
User browsing behavior keyword extracting module, it is corresponding with the browsing behavior for being extracted according to user browsing behavior
Keyword；
Search term recommending module, the keyword incidence relation and user for being provided according to keyword extraction analysis module are clear
The corresponding keyword of user browsing behavior that behavior keyword extracting module of looking at is extracted generates association search word, and by the association
Search term is shown in the search box of browsing pages as recommendation word.
As the third aspect of the disclosure, a kind of electronic equipment is provided, comprising: processor and memory, the memory
With the medium for being stored with program code, when the processor reads the program code of the media storage, the electronics is set
It is standby to be able to carry out method described in the embodiment of the present disclosure.
As the fourth aspect of the disclosure, a kind of computer-readable medium is provided, the media storage has computer-readable
Instruction, the computer-readable instruction can be executed by processor to realize method described in the embodiment of the present disclosure.
Compared with prior art, the disclosure is at least had the advantages that
The disclosure establishes keyword incidence relation by searching for data according to user's history, is extracted by user browsing behavior
Keyword corresponding with browsing behavior, and the association search word of keyword corresponding with extracted user browsing behavior is shown
In the search box of browsing pages, to realize user when browsing some page, presented automatically in the search box in the page
User uses the maximum search key of possibility, saves the step of search key is manually entered in user, reduces user
The keyword situation that may be present that the language fails to express the meaning is voluntarily selected, it in some specific cases can also browsing row to user
To guide, browse efficiency is improved, the user experience is improved.
Detailed description of the invention
Fig. 1 is the flow diagram of method described in the embodiment of the present disclosure；
Fig. 2 is the structural schematic diagram of keyword recommender system described in the embodiment of the present disclosure；
Fig. 3 is the schematic diagram of computer readable storage medium according to an embodiment of the present disclosure；
Fig. 4 is electronic devices structure schematic diagram described in the embodiment of the present disclosure.
The disclosure is further described below.But following examples is only the simple example of the disclosure, not generation
Table or the rights protection scope for limiting the disclosure, the protection scope of the disclosure are subject to claims.
Specific embodiment
Further illustrate the technical solution of the disclosure below with reference to the accompanying drawings and specific embodiments.
For the disclosure is better described, be easy to understand the technical solution of the disclosure, the disclosure it is typical but non-limiting
Embodiment is as follows: it is necessary to be noted that embodiment listed by present disclosure specification is merely to describe the problem conveniently
And the illustrative embodiment provided, it must not be not understood as the disclosure uniquely correct embodiment, must not be more not understood as
To the restricted explanation of disclosure protection scope.
Fig. 1 is the flow diagram of keyword recommendation method described in the embodiment of the present disclosure, the keyword recommendation method
Include: S1: the incidence relation between search key is obtained according to historical search data；
S2: keyword corresponding with the browsing behavior is extracted according to user browsing behavior；
S3: association search is generated according to keyword incidence relation and the corresponding keyword of extracted user browsing behavior
Word, and shown the association search word as recommendation word in the search box of browsing pages.
The history according to the incidence relation that historical search data obtains between search key described in the disclosure is searched
Rope data are not limited to the historical data of active user, can be the historical search data of all search users, or
The historical search data of part specific user group can also expire for what is extracted from the historical search data of all search users
The historical search data of sufficient special characteristic.
As a preferred embodiment, the step of incidence relation obtained according to historical search data between search key
Include: according to user access webpage, the content of click, the search term used, user access webpage, click content and/
Or at least one of sequencing of search term used obtains the incidence relation between search key.
Such as: user has accessed " defective product " related web page first, has further clicked on " the defective product in the webpage
User's accounting of whereabouts " is 85%, user's accounting of " Product Safety problem " is 80%, " XXX responsible person introduces XXXX correlation
User's accounting of situation " is 60%, user's accounting of " product supervisory system " is 40%, while also making in browsed web content
User's accounting with search key " AA product " is 95%, user's accounting of " BB product " is 90%, " adverse reaction+production
User's accounting that user's accounting of product " is 96%, user's accounting of " crime of production and sales low-quality goods " is 30%, " reparation " is
20%, then it can be known according to historical datas such as the access data of above-mentioned user, search data, " defective product ", " defective product
Whereabouts ", " Product Safety problem ", " correlation circumstance ", " product supervisory system ", " AA product ", " BB product ", " adverse reaction+
Incidence relation between the keywords such as product ", " crime of production and sales low-quality goods ", " reparation ", above-mentioned incidence relation refer to one
The degree of correlation of specific keyword and other keywords, for example, the user 90% of access " defective product " related web page
Above user further has accessed the related web pages such as " AA product ", " BB product ", " adverse reaction+product ", then can recognize
There is extremely strong incidence relation for " defective product " and the keywords such as " AA product ", " BB product ", " adverse reaction+product ",
Incidence relation described in some preferred embodiments can be marked using grade mark or explicitly quantitative digitlization, such as will
Incidence relation between " defective product " and " AA product ", " BB product ", " adverse reaction+product " is labeled as " extremely strong ", " A
Grade ", " level-one " or other any characters that can be identified can also by the incidence relation in the case where meeting specified conditions
Quantitative notation methods are digitized to use, such as the degree of association of " defective product " and " AA product " is labeled as 95%, " problem
The degree of association of product " and " BB product " is labeled as 90%, is labeled as " defective product " and the degree of association of " adverse reaction+product "
96%.Still further in some preferred embodiments, " AA product ", " BB production can be calculated by specific association algorithm
The incidence relation of keywords arbitrarily between the two such as product ", " adverse reaction+product ".Additionally need special instruction is some
In preferred embodiment, the incidence relation is directive, it may be assumed that the degree of association of " defective product " and " AA product " is 95%
The degree of association for not indicating " AA product " and " defective product " is 95%, that is to say, that 95% user of access " defective product "
" AA product " related web page can be accessed, it is not intended that the meeting access of the user 95% of access " AA product " related web page " is asked
Inscribe product " related web page.Above-mentioned directionality index can be by the content of the webpage, click that user accesses and/or what is used search
The relevant historical datas such as the sequencing of rope word obtain.
It is mentioned above that incidence relation between keyword can be obtained by historical search data, still, it is related to calculate institute
The calculation amount that the incidence relation of keyword between the two needs is excessive, expends resource, influences efficiency, in some historical datas missing
In the case of, certain difficulty may be had by calculating the incidence relation between all keywords.As a preferred embodiment, Ke Yigen
According to user access webpage, click content and/or the search term used and user access webpage, click content and/or
The search term sequencing used determines core word first；It still can be true by " defective product " for the example being previously mentioned
Be set to core word, then only calculated according to historical data " defective product " and " defective product whereabouts ", " Product Safety problem ",
" correlation circumstance ", " product supervisory system ", " AA product ", " BB product ", " adverse reaction+product ", " production and sales low-quality goods
Then the incidence relation is generated incidence relation list to facilitate system by the incidence relation between the keywords such as crime ", " reparation "
It calls.
In order to improve the utilization efficiency of the list for some lower data of duplicate, redundancy the and/or degree of correlation
It can be removed by the way of data cleansing, duplicate removal, filtering.
Embodiment as a further preference extracts keyword corresponding with the browsing behavior according to user browsing behavior
The search term that step uses when including: particular content, the browsing duration, browsing according to the browsing of user is extracted goes with the browsing
For corresponding keyword.Such as: user has browsed the related web page contents of " defective product ", mentioned in article " AA product ",
" BB product ", " adverse reaction ", " safety ", " listed company ", user further use keyword or click link " AA production
Product ", " BB product ", " adverse reaction " related web page, and longer time has been used to browse related pages content, then it is assumed that it " asks
Inscribe product " with " AA product ", " BB product ", between " adverse reaction " with stronger relevance.
As a preferred embodiment, above-mentioned incidence relation can be marked using qualitative and quantitative notation methods, qualitative
It can be relevance grades, such as: extremely strong, stronger, general, poor, weak rigidity etc., the certainly pass in the specific use process
Other any suitable characters, such as A, B, C, D ... can be used by joining grade, and 1,2,3,4 ... wait any recognizable character.For
Quantitative notation methods can be obtained by correlation data calculations such as the browsing durations of specific user's access probability, specific webpage
?.
In step S2: extracting keyword corresponding with the browsing behavior according to user browsing behavior；Here user refers to
Active user, such as active user have browsed the content of " the unqualified XXX product flow direction of XXX biology " related web page, it is assumed that according to
The keyword corresponding with the browsing behavior that the browsing behavior extracts is " defective product ".Then, in step s3 according to key
Word association relationship and the corresponding keyword of extracted user browsing behavior generate association search word, such as: " AA product ", " BB
Product ", " adverse reaction ", " safety "；The search in browsing pages is shown using the association search word as recommendation word simultaneously
In frame, in this case, does not need further to be manually entered keyword for most users, click directly on relevant pass
The purpose further browsed can be realized in keyword search.
As a preferred embodiment, the step of extracting keyword corresponding with the browsing behavior according to user browsing behavior is logical
The mode for crossing the specific content of pages semantic analysis to user's browsing extracts the corresponding keyword.The semantic analysis refers to
Computer extracts relevant keyword according to the core meaning analysis to be expressed of entire article content, specifically can be according to entire
Word frequency, position and spaced relationship of certain particular words of specific term used in article etc. extract keyword.Further lift
For example, such as the number that " product " occurs in certain article is most, and " unqualified " term is had also appeared in title, then can be with
It is " defective product " by keyword extraction corresponding with the browsing behavior.It certainly is only particularization explanation above, for a certain clear
The keyword that behavior of looking at is extracted is not limited to one, can according to need selection or the multiple corresponding keywords of setting.
When the user of reality browses search, its usual browsing demand be it is uncertain, search need be also it is changeable, can
Replacement, which can be needed frequently to rewrite, needs keyword to be used.In some preferred embodiments, recommend in the browsing pages
Search box in keyword be and the key recommended according to the variation real-time update of browsing behavior and content in real time
Word.It is advantageous that the real-time dynamic change of the browsing behavior according to user in described search frame, real-time recommendation and user interest
The keyword that point is closely related, facilitates the search need of user, while can play and purposefully draw in time to the utmost
Lead the effect that user browses specific content.Referred to herein as the design of guidance user browsing behavior, setting can be passed through in disclosure
Specific key conjunctive word is achieved, that is, according to the needs of guidance browsing behavior, is purposefully rewritten opposite with browsing behavior
The association keyword for the keyword answered, and opportunity in the search box is shown by adjusting correlation degree control associative key.
As another aspect of the disclosure, the disclosure also provides a kind of system corresponding with aforementioned method steps, right
It is also included in system corresponding with the method in many technical details for describing to submit in the method in front, for section
About length be not unfolded one by one in the description to system.
System described in the disclosure can for entity hardware system, software function module constitute virtual system or hardware and
The system that software be combined with each other, but those skilled in the art should understand that any software function module constitute virtual system its
The realization of function all be unable to do without the support of entity hardware device.
Fig. 2 is the structural schematic diagram of keyword recommender system described in the disclosure, the keyword recommender system 100, packet
It includes:
Keyword extraction analysis module 101, the association for being obtained between search key according to historical search data are closed
System；
User browsing behavior keyword extracting module 102, for being extracted and the browsing behavior pair according to user browsing behavior
The keyword answered；
Search term recommending module 103, keyword incidence relation and use for being provided according to keyword extraction analysis module
The corresponding keyword of the user browsing behavior that family browsing behavior keyword extracting module is extracted generates association search word, and will be described
Association search word is shown in the search box of browsing pages as recommendation word.
As a preferred embodiment, the keyword extraction analysis module 101 can according to user access webpage, click
Content, the search term used and user access webpage, click content and/or the search term used sequencing at least
One incidence relation obtained between search key.
Embodiment more preferably, the keyword extraction analysis module 101 include: core word extracting sub-module, are used
In the content of the webpage, click that are accessed according to user, the search term used, user access webpage, click content and/or make
At least one of search term sequencing determines core word；
Incidence relation extracting sub-module, for extracting the conspiracy relation between the core word and other keywords；
Incidence relation list generates submodule, for generating the column of the incidence relation between the core word and other keywords
Table.
Embodiment as a further preference, the incidence relation list generate submodule, comprising: data cleansing is gone
Weight, filter element, for being removed some duplicate, redundancy and/or phases by the way of data cleansing, duplicate removal, filtering
The lower data of Guan Du are to improve the utilization efficiency of the list.
As preferred embodiment, the keyword extraction analysis module 101 can also be according to the tool of the browsing of user
The search term used when holding in vivo, browsing duration, browsing extracts keyword corresponding with the browsing behavior.Further, root
Extracting keyword corresponding with the browsing behavior according to user browsing behavior includes: the mark according to the specific content of pages of user's browsing
Topic, content word frequency extract corresponding keyword.
As preferred embodiment, user browsing behavior keyword extracting module 102 includes semantic analysis submodule, is led to
The mode for crossing the specific content of pages semantic analysis to user's browsing extracts keyword corresponding with user browsing behavior.Institute's predicate
Justice analysis refers to that computer extracts relevant keyword according to the core meaning analysis to be expressed of entire article content, specifically may be used
Spaced relationship with the word frequency of the specific term according to used in entire article, position and certain particular words etc. extracts crucial
Word.Further for example, the number that " product " occurs such as in certain article is most, and " unqualified " is had also appeared in title
Keyword extraction corresponding with the browsing behavior can be then " defective product " by term.It certainly is only particularization explanation above,
The keyword extracted for a certain browsing behavior is not limited to one, can according to need selection or the multiple corresponding keys of setting
Word.
When the user of reality browses search, its usual browsing demand be it is uncertain, search need be also it is changeable, can
Replacement, which can be needed frequently to rewrite, needs keyword to be used.As a preferred embodiment, described search word recommending module 103 can be real
When by recommend word show in the search box of browsing pages, furthermore, can according to user's subsequent web pages access behavior into
Recommendation word in Mobile state real-time update search box.It is advantageous that real-time according to the browsing behavior of user in described search frame
The keyword that dynamic change, real-time recommendation and user interest point are closely related, facilitates the search need of user to the utmost,
It can play the role of purposefully user being guided to browse specific content in time simultaneously.Referred to herein as guidance user browsing behavior
Design can be achieved in disclosure by setting specific crucial conjunctive word, that is, according to the needs of guidance browsing behavior,
The association keyword of keyword corresponding with browsing behavior is purposefully rewritten, and controls related close by adjusting correlation degree
Keyword shows opportunity in the search box.
As another aspect of the disclosure, also offer a kind of electronic equipment, comprising: processor and memory, it is described to deposit
Reservoir has the medium (computer readable storage medium) for being stored with program code, when the processor reads the media storage
Program code when, the electronic equipment is able to carry out following method and step: according to historical search data obtain search key
Between incidence relation；Keyword corresponding with the browsing behavior is extracted according to user browsing behavior；It is closed according to crucial word association
It is keyword generation association search word corresponding with extracted user browsing behavior, and using the association search word as recommendation
Word is shown in the search box of browsing pages.
Further: when the processor reads the program code of the media storage, the electronic equipment can also
Execute other any methods described in the disclosure.
Fig. 4 is the schematic diagram for illustrating computer readable storage medium according to an embodiment of the present disclosure.As shown in figure 4, root
According to the computer readable storage medium 300 of the embodiment of the present disclosure, it is stored thereon with non-transitory computer-readable instruction 301.When
When the non-transitory computer-readable instruction 301 is run by processor, the keyword for executing each embodiment of the disclosure above-mentioned is pushed away
Recommend all or part of the steps of method.
Fig. 3 is the hardware structural diagram for illustrating the electronic equipment according to the embodiment of the present disclosure.Electronic equipment can be with each
Kind of form is implemented, and the electronic equipment in the disclosure can include but is not limited to such as mobile phone, smart phone, notebook electricity
Brain, PDA (personal digital assistant), PAD (tablet computer), PMP (portable media player), is led at digit broadcasting receiver
The mobile terminal device of boat device, vehicle-mounted terminal equipment, vehicle-mounted display terminal, vehicle electronics rearview mirror etc. and such as number
The fixed equipment of TV, desktop computer etc..
As shown in figure 3, electronic equipment 1100 may include processor 1120, input unit 1130, memory 1140, output
Unit 1150 etc..Fig. 3 shows the electronic equipment with various assemblies, it should be understood that being not required for implementing all show
Component out.More or fewer components can alternatively be implemented.
Wherein, for processor 1120 for executing method disclosed in the disclosure, input unit 1130 can be defeated according to user
The order entered generates key input data with the various operations of controlling electronic devices, and output unit 1150 provides output signal.Storage
Device 1140 can store the software program etc. of the processing and control operation that are executed by processor 1120, or can temporarily deposit
Store up oneself data through exporting or will export.Memory 1140 may include the storage medium of at least one type.Moreover, electronics
Equipment 1100 can cooperate with the network storage device for the store function for executing memory 1140 by network connection.Processor
The overall operation of 1120 usual controlling electronic devicess.
The various embodiments for the keyword recommendation method that the disclosure proposes can be to use such as computer software, hardware
Or any combination thereof computer-readable medium implement.
Hardware is implemented, the various embodiments for the keyword recommendation method that the disclosure proposes can be by using specific
Purposes integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device
(PLD), field programmable gate array (FPGA), processor, controller, microprocessor, microcontroller are designed to execute here
At least one of electronic unit of function of description is implemented, in some cases, the keyword recommendation side that the disclosure proposes
The various embodiments of method can be implemented in processor 1120.The keyword recommendation side proposed for software implementation, the disclosure
The various embodiments of method can be implemented with the individual software module that allows to execute at least one functions or operations.Software generation
Code can be implemented by the software application (or program) write with any programming language appropriate, and software code can store
It is executed in memory 1140 and by processor 1120.
The Applicant declares that the disclosure illustrates the detailed construction feature of the disclosure through the foregoing embodiment, but the disclosure is simultaneously
It is not limited to above-mentioned detailed construction feature, that is, does not mean that the disclosure must rely on above-mentioned detailed construction feature and could implement.Institute
Belong to those skilled in the art it will be clearly understood that any improvement to the disclosure, to the equivalence replacement of component selected by the disclosure
And increase, selection of concrete mode of accessory etc., it all falls within the protection scope and the open scope of the disclosure.
The preferred embodiment of the disclosure is described in detail above, still, during the disclosure is not limited to the above embodiment
Detail a variety of simple variants can be carried out to the technical solution of the disclosure in the range of the technology design of the disclosure, this
A little simple variants belong to the protection scope of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the disclosure to it is various can
No further explanation will be given for the combination of energy.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (12)
1. a kind of keyword recommendation method, comprising:
The incidence relation between search key is obtained according to historical search data；
Keyword corresponding with the browsing behavior is extracted according to user browsing behavior；
Association search word is generated according to keyword incidence relation and the corresponding keyword of extracted user browsing behavior, and by institute
Association search word is stated to show in the search box of browsing pages as recommendation word.
2. the method as described in claim 1 obtains the step of the incidence relation between search key according to historical search data
Suddenly include:
According to the webpage of user's access, the content of click, the search term used, the sequencing relationship of the access, the point
At least one of the sequencing relationship hit, described sequencing relationship used obtain the association between search key and close
System.
3. the method as described in claim 1 obtains the step of the incidence relation between search key according to historical search data
Suddenly include:
According to the webpage of user's access, the content of click, the search term used, the sequencing relationship of the access, the point
At least one of the sequencing relationship hit, described sequencing relationship used determine core word；
Extract the conspiracy relation between the core word and other keywords；
Generate the incidence relation list between the core word and other keywords.
4. method as claimed in claim 3 generates the step of the incidence relation list between the core word and other keywords
Suddenly the step of including: data cleansing, duplicate removal, filtering.
5. the method as described in claim 1 extracts the step of keyword corresponding with the browsing behavior according to user browsing behavior
The search term used when suddenly including: particular content, the browsing duration, browsing according to the browsing of user extracts and the browsing behavior
Corresponding keyword.
6. the method as described in claim 1 extracts the step of keyword corresponding with the browsing behavior according to user browsing behavior
Suddenly include:
Corresponding keyword is extracted according to the title of the specific content of pages of user's browsing, content word frequency.
7. the method as described in claim 1 extracts the step of keyword corresponding with the browsing behavior according to user browsing behavior
Suddenly include:
The corresponding keyword is extracted by way of the specific content of pages semantic analysis browsed to user.
8. the method as described in claim 1, the recommendation word real-time exhibition is in the search box of browsing pages.
9. the method as described in claim 1 further comprises: accessing behavior according to user's subsequent web pages and carry out dynamic realtime more
Recommendation word in new search frame.
10. a kind of keyword recommender system, comprising:
Keyword extraction analysis module, for obtaining the incidence relation between search key according to historical search data；
User browsing behavior keyword extracting module, for extracting key corresponding with the browsing behavior according to user browsing behavior
Word；
Search term recommending module, keyword incidence relation and user for being provided according to keyword extraction analysis module browse row
Association search word is generated for the corresponding keyword of user browsing behavior that keyword extracting module is extracted, and by the association search
Word is shown in the search box of browsing pages as recommendation word.
11. a kind of electronic equipment, comprising: processor and memory, the memory have the medium for being stored with program code, when
When the processor reads the program code of the media storage, the electronic equipment is able to carry out any one of claim 1-9
The method.
12. a kind of computer-readable medium, the media storage has computer-readable instruction, and the computer-readable instruction can quilt
Processor is executed to realize method as claimed in any one of claims 1-9 wherein.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811299050.9A CN109190049B (en) | 2018-11-02 | 2018-11-02 | Keyword recommendation method, system, electronic device and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811299050.9A CN109190049B (en) | 2018-11-02 | 2018-11-02 | Keyword recommendation method, system, electronic device and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109190049A true CN109190049A (en) | 2019-01-11 |
| CN109190049B CN109190049B (en) | 2021-11-23 |
Family
ID=64941487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811299050.9A Active CN109190049B (en) | 2018-11-02 | 2018-11-02 | Keyword recommendation method, system, electronic device and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190049B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110795627A (en) * | 2019-10-28 | 2020-02-14 | 苏州跃盟信息科技有限公司 | Information recommendation method and device and electronic equipment |
| CN111324804A (en) * | 2020-02-21 | 2020-06-23 | 北京字节跳动网络技术有限公司 | Search keyword recommendation model generation method, keyword recommendation method and device |
| 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 |
| CN111428120A (en) * | 2020-03-17 | 2020-07-17 | 北京字节跳动网络技术有限公司 | Information determination method and device, electronic equipment and storage medium |
| CN111488434A (en) * | 2019-01-25 | 2020-08-04 | 北京字节跳动网络技术有限公司 | Recommendation method and device for input associative words, storage medium and electronic equipment |
| CN112417299A (en) * | 2020-12-08 | 2021-02-26 | 西安联乘智能科技有限公司 | Webpage recommendation method, computer storage medium and computing device |
| CN112445968A (en) * | 2019-09-03 | 2021-03-05 | 百度(中国)有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN112783295A (en) * | 2021-02-18 | 2021-05-11 | 北京泽桥传媒科技股份有限公司 | Automatic content recommendation method and terminal based on user behaviors |
| CN113111286A (en) * | 2021-05-12 | 2021-07-13 | 北京字节跳动网络技术有限公司 | Information display method and device and computer storage medium |
| CN113360779A (en) * | 2021-08-09 | 2021-09-07 | 智者四海（北京）技术有限公司 | Content recommendation method and device, computer equipment and readable medium |
| CN114596138A (en) * | 2022-03-07 | 2022-06-07 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN117688243A (en) * | 2023-12-19 | 2024-03-12 | 广州无限可能数字科技有限公司 | Keyword screening recommendation method and system based on big data |
Citations (9)
| 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 |
| WO2013143429A1 (en) * | 2012-03-26 | 2013-10-03 | 腾讯科技（深圳）有限公司 | Recommendation search method for search engine, device and computer readable storage medium |
| CN103577392A (en) * | 2013-11-15 | 2014-02-12 | 北京奇虎科技有限公司 | Keyword pushing method and device based on current browse webpage |
| CN105069168A (en) * | 2015-08-28 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Search word recommendation method and apparatus |
| CN105893493A (en) * | 2016-03-29 | 2016-08-24 | 北京小米移动软件有限公司 | Searching method and device |
| CN107832332A (en) * | 2017-09-29 | 2018-03-23 | 北京奇虎科技有限公司 | The method, apparatus and electronic equipment for recommending word are generated in navigating search frame |
| CN108197242A (en) * | 2017-12-29 | 2018-06-22 | 北京奇虎科技有限公司 | Method for pushing, device and the server of word are recommended in search |
| CN108197244A (en) * | 2017-12-29 | 2018-06-22 | 北京奇虎科技有限公司 | It is a kind of to search for the method for pushing and device for recommending word |
| CN108664513A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method, apparatus and equipment for pushing keyword |
-
2018
- 2018-11-02 CN CN201811299050.9A patent/CN109190049B/en active Active
Patent Citations (9)
| 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 |
| WO2013143429A1 (en) * | 2012-03-26 | 2013-10-03 | 腾讯科技（深圳）有限公司 | Recommendation search method for search engine, device and computer readable storage medium |
| CN103577392A (en) * | 2013-11-15 | 2014-02-12 | 北京奇虎科技有限公司 | Keyword pushing method and device based on current browse webpage |
| CN105069168A (en) * | 2015-08-28 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Search word recommendation method and apparatus |
| CN105893493A (en) * | 2016-03-29 | 2016-08-24 | 北京小米移动软件有限公司 | Searching method and device |
| CN108664513A (en) * | 2017-03-31 | 2018-10-16 | 北京京东尚科信息技术有限公司 | Method, apparatus and equipment for pushing keyword |
| CN107832332A (en) * | 2017-09-29 | 2018-03-23 | 北京奇虎科技有限公司 | The method, apparatus and electronic equipment for recommending word are generated in navigating search frame |
| CN108197242A (en) * | 2017-12-29 | 2018-06-22 | 北京奇虎科技有限公司 | Method for pushing, device and the server of word are recommended in search |
| CN108197244A (en) * | 2017-12-29 | 2018-06-22 | 北京奇虎科技有限公司 | It is a kind of to search for the method for pushing and device for recommending word |
Non-Patent Citations (2)
| Title |
|---|
| 温有奎: ""信息检索系统的关联关键词推荐研究"", 《数字图书馆论坛》 * |
| 马超 等: ""面向探索式搜索过程的查询推荐"", 《东北大学学报(自然科学版)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488434A (en) * | 2019-01-25 | 2020-08-04 | 北京字节跳动网络技术有限公司 | Recommendation method and device for input associative words, storage medium and electronic equipment |
| CN112445968B (en) * | 2019-09-03 | 2023-04-21 | 百度(中国)有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN112445968A (en) * | 2019-09-03 | 2021-03-05 | 百度(中国)有限公司 | Information pushing method, device, equipment and computer readable storage medium |
| CN110795627B (en) * | 2019-10-28 | 2022-08-19 | 苏州跃盟信息科技有限公司 | Information recommendation method and device and electronic equipment |
| CN110795627A (en) * | 2019-10-28 | 2020-02-14 | 苏州跃盟信息科技有限公司 | Information recommendation method and device and electronic equipment |
| CN111324804A (en) * | 2020-02-21 | 2020-06-23 | 北京字节跳动网络技术有限公司 | Search keyword recommendation model generation method, keyword recommendation method and device |
| CN111324804B (en) * | 2020-02-21 | 2023-09-22 | 抖音视界有限公司 | Search keyword recommendation model generation method, keyword recommendation method and device |
| 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 |
| CN111428120A (en) * | 2020-03-17 | 2020-07-17 | 北京字节跳动网络技术有限公司 | Information determination method and device, electronic equipment and storage medium |
| CN112417299A (en) * | 2020-12-08 | 2021-02-26 | 西安联乘智能科技有限公司 | Webpage recommendation method, computer storage medium and computing device |
| CN112783295A (en) * | 2021-02-18 | 2021-05-11 | 北京泽桥传媒科技股份有限公司 | Automatic content recommendation method and terminal based on user behaviors |
| CN113111286A (en) * | 2021-05-12 | 2021-07-13 | 北京字节跳动网络技术有限公司 | Information display method and device and computer storage medium |
| CN113360779A (en) * | 2021-08-09 | 2021-09-07 | 智者四海（北京）技术有限公司 | Content recommendation method and device, computer equipment and readable medium |
| CN114596138A (en) * | 2022-03-07 | 2022-06-07 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN117688243A (en) * | 2023-12-19 | 2024-03-12 | 广州无限可能数字科技有限公司 | Keyword screening recommendation method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109190049B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190049A (en) | Keyword recommendation method, system, electronic equipment and computer-readable medium | |
| US11314823B2 (en) | Method and apparatus for expanding query | |
| US20190018900A1 (en) | Method and Apparatus for Displaying Search Results | |
| JP5721818B2 (en) | Use of model information group in search | |
| JP6346218B2 (en) | Search method, apparatus and server for online trading platform | |
| US20130290319A1 (en) | Performing application searches | |
| US9990442B2 (en) | Method for determining relevant search results | |
| US20120150861A1 (en) | Highlighting known answers in search results | |
| CN112632359B (en) | Information recommendation method, device, electronic equipment and storage medium | |
| CN111639255B (en) | Recommendation method and device for search keywords, storage medium and electronic equipment | |
| CN103870461A (en) | Topic recommendation method, device and server | |
| US20140379719A1 (en) | System and method for tagging and searching documents | |
| KR101925950B1 (en) | Method and device for recommending contents based on inflow keyword and relevant keyword for contents | |
| JP6728178B2 (en) | Method and apparatus for processing search data | |
| US20140365868A1 (en) | Method, server, browser, and system for recommending text information | |
| CN104035972A (en) | Knowledge recommending method and system based on micro blogs | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN112579854A (en) | Information processing method, device, equipment and storage medium | |
| CN106777173A (en) | Information flow methods of exhibiting, system and user terminal | |
| CN112307365A (en) | Information display method and device, electronic equipment and storage medium | |
| CN104933099B (en) | Method and device for providing target search result for user | |
| CN107315735B (en) | Method and equipment for note arrangement | |
| CN107368525B (en) | Method and device for searching related words, storage medium and terminal equipment | |
| JP5777663B2 (en) | Search support device and search support program | |
| JP2012043290A (en) | Information providing device, information providing method, program, and information recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |