CN108197244A - It is a kind of to search for the method for pushing and device for recommending word - Google Patents
It is a kind of to search for the method for pushing and device for recommending word Download PDFInfo
- Publication number
- CN108197244A CN108197244A CN201711481961.9A CN201711481961A CN108197244A CN 108197244 A CN108197244 A CN 108197244A CN 201711481961 A CN201711481961 A CN 201711481961A CN 108197244 A CN108197244 A CN 108197244A
- Authority
- CN
- China
- Prior art keywords
- search
- word
- webpage
- initial search
- initial
- 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
-
- 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
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90324—Query formulation using system suggestions
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An embodiment of the present invention provides it is a kind of search for recommend word method for pushing and device, the method includes：It scans for obtaining at least one search and webpage using the search term of input；When determining target webpage from described search webpage, obtained from concordance list and recommend word with the matched search of the target webpage；It pushes described search and recommends word.User can be helped to find interested information in the webpage of magnanimity using the embodiment of the present invention, precisely analyze needed for user and recommend the content that user wants.
Description
Technical field
The present invention relates to internet data processing technology field, more particularly to it is a kind of search for recommend word method for pushing and
It is a kind of to search for the pusher for recommending word.
Background technology
At present, most of Internet users have similar behavior in online：From input network address to browsing pages, then
New webpage is constantly opened along page link.Random walk model is established abstract aiming at the user behavior of browsing webpage
Model.This abstract concept model why is established, is many link analysis because including PageRank algorithms
Algorithm is all built upon on the basis of random walk model.In the dynamic evolution of complex network, find for user and preferably search
Hitch fruit provides a shortest path.
The usage scenario of search engine also has similar behavior：It inputs query (query word, search term) and browses search knot
Then fruit clicks search result and opens new webpage, all webpages all have certain correlation with inquiry query, but work as
The webpage newly opened does not meet expection, does not find satisfied answer, needs to rewrite query binary search again and is possible to look for
To satisfied as a result, search process complications are time-consuming.
For this problem, reasonable employment random walk model, it is potential to show user after user clicks search result,
Next may search query, it is possible to reduce the searching cost of user without Manual Override query, helps user quickly just
Search result is found in victory, can effectively promote search experience to a certain extent.
Invention content
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least partly
The search for stating problem recommends the method for pushing of word and corresponding search to recommend the pusher of word.
One side according to the present invention provides a kind of method for pushing searched for and recommend word, including：
It scans for obtaining at least one search and webpage using the search term of input；
When determining target webpage from described search webpage, obtained from concordance list and the target webpage is matched searches
Rope recommends word；
It pushes described search and recommends word.
Optionally, the concordance list generates in the following way：
Obtain the user behaviors log of user；
From the user behaviors log extract initial search word and, scanned for based on the initial search word
At least one initial search webpage；
Determine the transitive relation between the initial search word and the initial search webpage；
Based on the initial search word, the initial search webpage and the initial search word and the initial search
Transitive relation between webpage establishes concordance list.
Optionally, after the transitive relation determined between the initial search word and the initial search webpage,
Including：
Calculate the correlation between the initial search word and corresponding initial search webpage；
Filter out initial search word of the correlation more than predetermined threshold value and corresponding initial search webpage.
Optionally, the correlation includes clicking rate, searching rate and/or view rate.
Optionally, described obtained from concordance list recommends word with the matched search of the target webpage, including：
Search whether exist and the matched initial search webpage of the target webpage in the concordance list；
Recommend word using the corresponding initial search word of the initial search webpage as search.
Optionally, it is obtained from concordance list described with after the matched search recommendation word of the target webpage, further including：
Word is recommended to be disappeared described search to handle again；
Word is recommended to be normalized described search；
Word is recommended to carry out filtering sensitive words processing described search.
According to another aspect of the present invention, a kind of pusher searched for and recommend word is provided, including：
Search and webpage search module scans for obtaining at least one search and webpage suitable for the search term using input；
Word acquisition module is recommended in search, suitable for when determining target webpage from described search webpage, from concordance list
It obtains and recommends word with the matched search of the target webpage；
Word pushing module is recommended in search, recommends word suitable for push described search.
Optionally, described device includes：
User behaviors log acquisition module, suitable for obtaining the user behaviors log of user；
Initial search word extraction module, suitable for from the user behaviors log extract initial search word and, based on described
At least one initial search webpage that initial search word scans for；
Transitive relation determining module, suitable for determining the transmission between the initial search word and the initial search webpage
Relationship；
Concordance list establishes module, suitable for being based on the initial search word, the initial search webpage and described original
Transitive relation between search term and the initial search webpage establishes concordance list.
Optionally, including：
Correlation calculations module is related between the initial search word and corresponding initial search webpage suitable for calculating
Property；
Initial search webpage screening module, suitable for filter out correlation more than predetermined threshold value initial search word with it is corresponding
Initial search webpage.
Optionally, the correlation includes clicking rate, searching rate and/or view rate.
Optionally, described search recommends word acquisition module, including：
Initial search Webpage searching submodule, suitable for searching whether exist and the target webpage the concordance list
Matched initial search webpage；
Word acquisition submodule is recommended in search, suitable for using the corresponding initial search word of the initial search webpage as search
Recommend word.
Optionally, it further includes：
Disappear weight processing module, is handled again suitable for word being recommended to be disappeared described search；
Normalized module, suitable for word being recommended to be normalized described search；
Filter processing module, suitable for word being recommended to carry out filtering sensitive words processing described search.
According to another aspect of the present invention, a kind of terminal device is provided, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, which is characterized in that the processor is realized when performing described program
The step of stating method.
According to another aspect of the present invention, a kind of computer readable storage medium is provided, is stored thereon with computer journey
Sequence, when which is executed by processor the step of the realization above method.
In embodiments of the present invention, when user scans for, obtain search term input by user and based on this search for into
Row search obtains search and webpage, then determines target webpage from these search and webpages again, is finally based on target webpage from pre-
It, can be with using the embodiment of the present invention if obtaining word being recommended to recommend user with search of the search term there are incidence relation in concordance list
Side user finds interested information in the webpage of magnanimity, precisely analyzes needed for user and recommends the content that user wants.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific embodiment for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows a kind of the step of searching for the method for pushing embodiment one for recommending word according to an embodiment of the invention
Flow chart；
Fig. 2 shows a kind of the step of searching for the method for pushing embodiment two for recommending word according to an embodiment of the invention
Flow chart；
Fig. 3 shows a kind of signal of transitive relation between search term and search and webpage according to an embodiment of the invention
Figure；
Fig. 4 shows the schematic diagram of search result in a kind of search engine according to an embodiment of the invention；
Fig. 5 shows the push schematic diagram of search recommendation word in a kind of search engine according to an embodiment of the invention；
Fig. 6 shows a kind of push flow chart of steps for searching for recommendation word according to an embodiment of the invention；
Fig. 7 shows a kind of structural frames for searching for the pusher embodiment for recommending word according to an embodiment of the invention
Figure.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
By background technology it is found that after clicking search result, word is recommended in no any search.If user is to current search knot
Fruit or query result are unsatisfied with, and Manual Override search term is needed to re-search for, and improve the searching cost of user.
The embodiment of the present invention is in view of the above-mentioned problems, propose a kind of push strategy searched for and recommend word, based on user complete
The user behaviors log of net establishes concordance list, when the webpage that search term of the displaying based on input of user's click search engine inquires
Afterwards, show and recommend word with the relevant search of web page contents, user is helped to find interested information in the webpage of magnanimity, is precisely divided
Needed for analysis user and recommend the content that user wants.It is introduced below for the embodiment of the present invention.
With reference to Fig. 1, a kind of method for pushing embodiment one for searching for recommendation word according to an embodiment of the invention is shown
Step flow chart, specifically may include steps of：
Step 101, it scans for obtaining at least one search and webpage using the search term of input.
In the concrete realization, user can input one or more search term and scan on a search engine, search
Index is held up, and will be scanned for obtaining search result, i.e. search and webpage according to search term.
Step 102, it when determining target webpage from described search webpage, is obtained and the target webpage from concordance list
Word is recommended in matched search.
In actual search scene, the quantity for the search and webpage searched for is usually multiple, these will on the client
User is showed to select, if user determines a target webpage from numerous search and webpages, the embodiment of the present invention will also
It further goes to find corresponding search recommendation word based on target webpage from preset concordance list.
Step 103, push described search recommends word.
After search recommendation word is obtained, search recommendation word is pushed to user.Preferably, search recommends word can be with searching
Rope word is presented along to user.
In embodiments of the present invention, when user scans for, obtain search term input by user and based on this search for into
Row search obtains search and webpage, then determines target webpage from these search and webpages again, is finally based on target webpage from pre-
It, can be with using the embodiment of the present invention if obtaining word being recommended to recommend user with search of the search term there are incidence relation in concordance list
Side user finds interested information in the webpage of magnanimity, precisely analyzes needed for user and recommends the content that user wants.
With reference to Fig. 2, a kind of method for pushing embodiment two for searching for recommendation word according to an embodiment of the invention is shown
Step flow chart, specifically may include steps of：
Step 201, the user behaviors log of user is obtained.
In embodiments of the present invention, the user behaviors log of the whole network search user is excavated, the data in user behaviors log include useful
The behavioral datas such as family search, click, browsing are analyzed.
Step 202, from the user behaviors log extract initial search word and, searched based on the initial search word
At least one initial search webpage that rope obtains.
The behavioral datas such as search, click, browsing in subordinate act daily record extract initial search word and based on initial search
The initial search webpage that word scans for.
Step 203, the transitive relation between the initial search word and the initial search webpage is determined；
After initial search word and initial search webpage are obtained in subordinate act daily record, based on whole initial search word and original
Beginning search and webpage goes to analyze the transitive relation between these data.
Specifically, the transitive relation between initial search word and initial search webpage is established, that is, is established<Search term, url>
Index relative, i.e., jumping to another url from a search term, (i.e. search and webpage, each file is uniquely fixed on internet
Position symbol) probability distribution.
Step 204, based on the initial search word, the initial search webpage and the initial search word with it is described
Transitive relation between initial search webpage establishes concordance list.
In embodiments of the present invention, the transitive relation between initial search word and search and webpage is established, transitive relation is built
It is vertical to be realized based on random walk model.
Random walk brief introduction：In the initial period, user opens browser and browses the 1st webpage, it is assumed that there are one empty for we
Intend clock and be used for timing, at this time can be using setting time as 1, user is directed toward some link (url) in webpage after webpage is finished watching
The page it is interested, then click the link, into the 2nd page, at this time dummy clock timing again, clock moves towards word 2, such as
Fruit webpage contains k link, then the probability that user jumps to the page pointed by any one link from current page is equal
's.User constantly repeats above procedure, is redirected between the page being directed toward in the link of phase mutual.If some page is included
All-links, user is not interested to continue to browse, then may input another network address in a browser, directly reach
The webpage, this behavior referred to as remotely redirect.Assuming that sharing the m page in internet, then user remotely jumps to any one
The probability of the page is also equal, as 1/m.Random walk model is exactly one to directly redirecting and remotely redirecting two kinds of users
Navigation patterns carry out abstract concept model.
With reference to Fig. 3, q1/q2/q3 represents different search terms, and u1/u2/u3/u4 represents different search and webpages, between the two
Line show the access behavior of user.The transmission of transitive relation means that perhaps u3 with q1 there is the transmission not being expressed also to close
System, i.e., the content that next user probably searches for.
In embodiments of the present invention, between the initial search word and initial search webpage that analyze and they
Transitive relation is saved backup being saved in concordance list.
In one preferred embodiment of the invention, the initial search word and the initial search webpage are determined described
Between transitive relation after, including：
Calculate the correlation between the initial search word and corresponding initial search webpage；
Filter out initial search word of the correlation more than predetermined threshold value and corresponding initial search webpage.
In practice, since the data volume of User action log in the whole network is huge, if by all search terms and
Search and webpage be just saved in simply by the presence of transitive relation it is in concordance list and unrealistic, therefore in embodiments of the present invention will also be into one
Step considers the correlation between search term and search and webpage, just protects search term and search and webpage when correlation is more than predetermined threshold value
It is stored in concordance list.
The probability that correlation is clicked for search metric word with search and webpage, specifically, can refer to such as click
Rate, searching rate and/or view rate etc..
Step 205, it scans for obtaining at least one search and webpage using the search term of input.
The embodiment of the present invention is suitable for the scene that user uses search engine, can be while user searches for and accesses webpage
Search, which is pushed, for user recommends word.For this functionality there are many realization means, one kind is to automatically turn on search to recommend word in practice
Function, one kind is manually opened or word function is recommended in closing search.
Step 206, it when determining target webpage from described search webpage, is obtained and the target webpage from concordance list
Word is recommended in matched search.
It in practical applications, will be from concordance list if user determines target webpage from numerous search and webpages
It goes to search whether that being present in the matched search of the target webpage recommends word, looks for that user is potential, it next may search
Query (word is recommended in search).
In one preferred embodiment of the invention, the step 206 can include following sub-step：
Search whether exist and the matched initial search webpage of the target webpage in the concordance list；
Recommend word using the corresponding initial search word of the initial search webpage as search.
Specifically, the identical webpage of the target webpage selected there are user can be directly searched whether in concordance list, such as
Fruit exists, then obtains the corresponding search term of the target webpage in concordance list, and recommend word using the search term as search.
Step 207, push described search recommends word.
After getting search recommendation word, it is possible to word be recommended to be pushed to user search.With reference to Fig. 4, user draws in search
It holds up input " names of the people ", shows encyclopaedia entry after clicking search, after user clicks encyclopaedia entry this search result,
Show " recommending for you " result in bottom (i.e. word is recommended in search)：Such as TV play, novel, story introduction information, to currently searching
The supplement of hitch fruit, so as to user's quadratic search, as shown in Figure 5.
Before pushing search recommendation word for user, word can also be recommended to handle search so that word is recommended in search
It is more accurate, and it is more in line with user demand.
In one preferred embodiment of the invention, the method can also include the following steps：
To described search recommend word disappeared handle again and/or, to described search recommend word be normalized and/
Or, word is recommended to carry out filtering sensitive words processing described search.
Preferably, the embodiment of the present invention recommends word to handle obtained search so that search recommends word more to accord with
Close user demand.Specifically, it can carry out at the service logics such as weight, normalization, filtering sensitive words that disappear of recommending data
Reason finally shows click with reference to user behavior and recommends word.
In order to which those skilled in the art is made to more fully understand the embodiment of the present invention, illustrated below using an example.
With reference to Fig. 6, a kind of search for showing the embodiment of the present invention recommends the push flow chart of steps of word, has specifically included following step
Suddenly：
1) user behaviors log of the whole network search user is excavated, includes but not limited in user behaviors log to search for, clicks, browse etc. and is capable
For data；
2) the transmission analysis of word relationship, the transitive relation based on the whole network search term query, webpage url are recommended in search；
3) it establishes<Query, url>Index relative, i.e., the probability distribution of another url is jumped to from a query, is built
Vertical concordance list；
4) based on the processing for recommending guide service logic：The weight that disappears, normalization, the filtering sensitive words of such as recommending data,
Finally show search with reference to user behavior and recommend word.
The usage scenario of combination search engine user of the embodiment of the present invention, is rationally utilized random walk model, works as user
Show potentially, next keyword (search recommendation word) that user may search for after clicking search result, in current web page
Hold closely related search term.The searching cost of user can be reduced：Without Manual Override search term, user's rapid and convenient is helped
Search result is found, can effectively promote the experience of search to a certain extent, while improve the flow of search engine.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but this field
Technical staff should know that the embodiment of the present invention is not limited by described sequence of movement, because implementing according to the present invention
Example, certain steps may be used other sequences or are carried out at the same time.Secondly, those skilled in the art should also know, specification
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
With reference to Fig. 7, a kind of pusher embodiment for searching for recommendation word according to an embodiment of the invention is shown
Structure diagram can specifically include following module：
Search and webpage search module 301 scans for obtaining at least one dragnet suitable for the search term using input
Page；
Word acquisition module 302 is recommended in search, suitable for when determining target webpage from described search webpage, from concordance list
Middle acquisition recommends word with the matched search of the target webpage；
Word pushing module 303 is recommended in search, recommends word suitable for push described search.
In one preferred embodiment of the invention, described device can also include：
User behaviors log acquisition module, suitable for obtaining the user behaviors log of user；
Initial search word extraction module, suitable for from the user behaviors log extract initial search word and, based on described
At least one initial search webpage that initial search word scans for；
Transitive relation determining module, suitable for determining the transmission between the initial search word and the initial search webpage
Relationship；
Concordance list establishes module, suitable for being based on the initial search word, the initial search webpage and described original
Transitive relation between search term and the initial search webpage establishes concordance list.
In one preferred embodiment of the invention, can include：
Correlation calculations module is related between the initial search word and corresponding initial search webpage suitable for calculating
Property；
Initial search webpage screening module, suitable for filter out correlation more than predetermined threshold value initial search word with it is corresponding
Initial search webpage.
In one preferred embodiment of the invention, the correlation includes clicking rate, searching rate and/or view rate.
In one preferred embodiment of the invention, described search recommends word acquisition module, including：
Initial search Webpage searching submodule, suitable for searching whether exist and the target webpage the concordance list
Matched initial search webpage；
Word acquisition submodule is recommended in search, suitable for using the corresponding initial search word of the initial search webpage as search
Recommend word.
In one preferred embodiment of the invention, described device can also include：
Disappear weight processing module, is handled again suitable for word being recommended to be disappeared described search；
Normalized module, suitable for word being recommended to be normalized described search；
Filter processing module, suitable for word being recommended to carry out filtering sensitive words processing described search.
For device embodiment, since it is basicly similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
The embodiment of the invention also discloses a kind of terminal devices, including memory, processor and store on a memory simultaneously
The computer program that can be run on a processor, the processor realize the step of the above method embodiment when performing described program
Suddenly.
The embodiment of the invention also discloses a kind of computer readable storage mediums, are stored thereon with computer program, the journey
The step of above method embodiment is realized when sequence is executed by processor.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification provided in this place, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Profit requirement, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization or to be run on one or more processor
Software module realize or realized with combination thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize that search according to embodiments of the present invention is recommended in the pushing equipment of word
Some or all components some or all functions.The present invention is also implemented as performing side as described herein
The some or all equipment or program of device (for example, computer program and computer program product) of method.It is such
Realizing the program of the present invention can may be stored on the computer-readable medium or can have the shape of one or more signal
Formula.Such signal can be downloaded from internet website to be obtained either providing or with any other shape on carrier signal
Formula provides.
It should be noted that the present invention will be described rather than limits the invention, and ability for above-described embodiment
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and run after fame
Claim.
The embodiment of the invention discloses A1, it is a kind of search for recommend word method for pushing, including：
It scans for obtaining at least one search and webpage using the search term of input；
When determining target webpage from described search webpage, obtained from concordance list and the target webpage is matched searches
Rope recommends word；
It pushes described search and recommends word.
A2, the method as described in claim A1, which is characterized in that the concordance list generates in the following way：
Obtain the user behaviors log of user；
From the user behaviors log extract initial search word and, scanned for based on the initial search word
At least one initial search webpage；
Determine the transitive relation between the initial search word and the initial search webpage；
Based on the initial search word, the initial search webpage and the initial search word and the initial search
Transitive relation between webpage establishes concordance list.
A3, the method as described in claim A1 or A2, which is characterized in that it is described extracted from the user behaviors log it is defeated
The initial search word that enters and, after at least one initial search webpage scanned for based on the initial search word,
Including：
Calculate the correlation between the initial search word and corresponding initial search webpage；
Filter out initial search word of the correlation more than predetermined threshold value and corresponding initial search webpage.
A4, the method as described in claim A1 or A2 or A3, which is characterized in that the correlation includes clicking rate, searches
Rope rate and/or view rate.
A5, the method as described in claim A1 or A2 or A3 or A4, which is characterized in that it is described from concordance list obtain with
Word is recommended in the matched search of target webpage, including：
Search whether exist and the matched initial search webpage of the target webpage in the concordance list；
Recommend word using the corresponding initial search word of the initial search webpage as search.
A6, the method as described in claim A1 or A2 or A3 or A4 or A5, which is characterized in that described from concordance list
It obtains after recommending word with the matched search of the target webpage, further includes：
Word is recommended to be disappeared described search to handle again；
Word is recommended to be normalized described search；
Word is recommended to carry out filtering sensitive words processing described search.
The embodiment of the invention also discloses B7, it is a kind of search for recommend word pusher, including：
Search and webpage search module scans for obtaining at least one search and webpage suitable for the search term using input；
Word acquisition module is recommended in search, suitable for when determining target webpage from described search webpage, from concordance list
It obtains and recommends word with the matched search of the target webpage；
Word pushing module is recommended in search, recommends word suitable for push described search.
B8, the device as described in claim B7, which is characterized in that described device includes：
User behaviors log acquisition module, suitable for obtaining the user behaviors log of user；
Initial search word extraction module, suitable for from the user behaviors log extract initial search word and, based on described
At least one initial search webpage that initial search word scans for；
Transitive relation determining module, suitable for determining the transmission between the initial search word and the initial search webpage
Relationship；
Concordance list establishes module, suitable for being based on the initial search word, the initial search webpage and described original
Transitive relation between search term and the initial search webpage establishes concordance list.
B9, the device as described in claim B7 or B8, which is characterized in that including：
Correlation calculations module is related between the initial search word and corresponding initial search webpage suitable for calculating
Property；
Initial search webpage screening module, suitable for filter out correlation more than predetermined threshold value initial search word with it is corresponding
Initial search webpage.
B10, the device as described in claim B7 or B8 or B9, which is characterized in that the correlation includes clicking rate, searches
Rope rate and/or view rate.
B11, the device as described in claim B7 or B8 or B9 or B10, which is characterized in that described search recommends word to obtain
Module, including：
Initial search Webpage searching submodule, suitable for searching whether exist and the target webpage the concordance list
Matched initial search webpage；
Word acquisition submodule is recommended in search, suitable for using the corresponding initial search word of the initial search webpage as search
Recommend word.
B12, the device as described in claim B7 or B8 or B9 or B10 or B11, which is characterized in that further include：
Disappear weight processing module, is handled again suitable for word being recommended to be disappeared described search；
Normalized module, suitable for word being recommended to be normalized described search；
Filter processing module, suitable for word being recommended to carry out filtering sensitive words processing described search.
The embodiment of the invention also discloses C13, a kind of terminal devices, including memory, processor and are stored in memory
Computer program that is upper and can running on a processor, which is characterized in that the processor realizes right when performing described program
It is required that the step of any one of A1-A6 the methods.
The embodiment of the invention also discloses D14, a kind of computer readable storage mediums, are stored thereon with computer program,
It is characterized in that, the step of any one of claim A1-A6 the methods are realized when the program is executed by processor.
Claims (10)
1. a kind of search for the method for pushing for recommending word, including：
It scans for obtaining at least one search and webpage using the search term of input；
When determining target webpage from described search webpage, obtain from concordance list and pushed away with the matched search of the target webpage
Recommend word；
It pushes described search and recommends word.
2. the method as described in claim 1, which is characterized in that the concordance list generates in the following way：
Obtain the user behaviors log of user；
From the user behaviors log extract initial search word and, scanned at least based on the initial search word
One initial search webpage；
Determine the transitive relation between the initial search word and the initial search webpage；
Based on the initial search word, the initial search webpage and the initial search word and the initial search webpage
Between transitive relation establish concordance list.
3. method as claimed in claim 1 or 2, which is characterized in that it is described determine the initial search word with it is described original
After transitive relation between search and webpage, including：
Calculate the correlation between the initial search word and corresponding initial search webpage；
Filter out initial search word of the correlation more than predetermined threshold value and corresponding initial search webpage.
4. the method as described in claims 1 or 2 or 3, which is characterized in that the correlation include clicking rate, searching rate and/or
View rate.
5. method as claimed in claim 1 or 2 or 3 or 4, which is characterized in that described to be obtained and the target from concordance list
Word is recommended in the matched search of webpage, including：
Search whether exist and the matched initial search webpage of the target webpage in the concordance list；
Recommend word using the corresponding initial search word of the initial search webpage as search.
6. the method as described in claims 1 or 2 or 3 or 4 or 5, which is characterized in that it is described from concordance list obtain with it is described
After word is recommended in the matched search of target webpage, further include：
Word is recommended to be disappeared described search to handle again；
Word is recommended to be normalized described search；
Word is recommended to carry out filtering sensitive words processing described search.
7. a kind of search for the pusher for recommending word, including：
Search and webpage search module scans for obtaining at least one search and webpage suitable for the search term using input；
Word acquisition module is recommended in search, suitable for when determining target webpage from described search webpage, being obtained from concordance list
Recommend word with the matched search of the target webpage；
Word pushing module is recommended in search, recommends word suitable for push described search.
8. device as claimed in claim 7, which is characterized in that described device includes：
User behaviors log acquisition module, suitable for obtaining the user behaviors log of user；
Initial search word extraction module, suitable for from the user behaviors log extract initial search word and, based on described original
At least one initial search webpage that search term scans for；
Transitive relation determining module is closed suitable for the transmission determined between the initial search word and the initial search webpage
System；
Concordance list establishes module, suitable for being based on the initial search word, the initial search webpage and the initial search
Transitive relation between word and the initial search webpage establishes concordance list.
9. a kind of terminal device including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the step of any one of claim 1-6 the methods when performing described program
Suddenly.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of any one of claim 1-6 the methods are realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711481961.9A CN108197244A (en) | 2017-12-29 | 2017-12-29 | It is a kind of to search for the method for pushing and device for recommending word |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711481961.9A CN108197244A (en) | 2017-12-29 | 2017-12-29 | It is a kind of to search for the method for pushing and device for recommending word |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108197244A true CN108197244A (en) | 2018-06-22 |
Family
ID=62586810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711481961.9A Pending CN108197244A (en) | 2017-12-29 | 2017-12-29 | It is a kind of to search for the method for pushing and device for recommending word |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108197244A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109213848A (en) * | 2018-11-23 | 2019-01-15 | 北京字节跳动网络技术有限公司 | Determination method, apparatus, storage medium and the electronic equipment of relevant search word |
| CN109587527A (en) * | 2018-11-09 | 2019-04-05 | 青岛聚看云科技有限公司 | A kind of method and device that individualized video is recommended |
| CN110532454A (en) * | 2019-08-28 | 2019-12-03 | 北京奇艺世纪科技有限公司 | A kind of search words recommending method and device |
| CN110619076A (en) * | 2018-12-25 | 2019-12-27 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN110990696A (en) * | 2019-11-25 | 2020-04-10 | 三角兽（北京）科技有限公司 | Method and device for recommending search intention |
| CN112115389A (en) * | 2019-06-21 | 2020-12-22 | 北京字节跳动网络技术有限公司 | Information processing method and device, storage medium and electronic equipment |
| CN115203599A (en) * | 2022-09-13 | 2022-10-18 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100892990B1 (en) * | 2008-09-19 | 2009-04-10 | 김수현 | Auto comparison searching system and method of search site |
| KR20090105715A (en) * | 2008-04-03 | 2009-10-07 | 주식회사 인텔렉추얼애드 | Method for Providing Expert's Recommendation Search Result and Recording Medium |
| CN103186574A (en) * | 2011-12-29 | 2013-07-03 | 北京百度网讯科技有限公司 | Method and device for generating searching result |
| CN104346396A (en) * | 2013-08-05 | 2015-02-11 | 腾讯科技（深圳）有限公司 | Data processing method, device, terminal and system of instant messaging client |
| CN105045901A (en) * | 2015-08-05 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Search keyword push method and device |
| CN105138614A (en) * | 2015-08-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for information display in search result page |
-
2017
- 2017-12-29 CN CN201711481961.9A patent/CN108197244A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090105715A (en) * | 2008-04-03 | 2009-10-07 | 주식회사 인텔렉추얼애드 | Method for Providing Expert's Recommendation Search Result and Recording Medium |
| KR100892990B1 (en) * | 2008-09-19 | 2009-04-10 | 김수현 | Auto comparison searching system and method of search site |
| CN103186574A (en) * | 2011-12-29 | 2013-07-03 | 北京百度网讯科技有限公司 | Method and device for generating searching result |
| CN104346396A (en) * | 2013-08-05 | 2015-02-11 | 腾讯科技（深圳）有限公司 | Data processing method, device, terminal and system of instant messaging client |
| CN105045901A (en) * | 2015-08-05 | 2015-11-11 | 百度在线网络技术（北京）有限公司 | Search keyword push method and device |
| CN105138614A (en) * | 2015-08-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for information display in search result page |
Non-Patent Citations (1)
| Title |
|---|
| 郭世龙等: "基于随机游走模型的关键词推荐算法", 《产业与科技论坛》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109587527A (en) * | 2018-11-09 | 2019-04-05 | 青岛聚看云科技有限公司 | A kind of method and device that individualized video is recommended |
| CN109587527B (en) * | 2018-11-09 | 2021-06-04 | 青岛聚看云科技有限公司 | Personalized video recommendation method and device |
| CN109213848A (en) * | 2018-11-23 | 2019-01-15 | 北京字节跳动网络技术有限公司 | Determination method, apparatus, storage medium and the electronic equipment of relevant search word |
| CN110619076A (en) * | 2018-12-25 | 2019-12-27 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN110619076B (en) * | 2018-12-25 | 2023-04-07 | 北京时光荏苒科技有限公司 | Search term recommendation method and device, computer and storage medium |
| CN112115389A (en) * | 2019-06-21 | 2020-12-22 | 北京字节跳动网络技术有限公司 | Information processing method and device, storage medium and electronic equipment |
| CN110532454A (en) * | 2019-08-28 | 2019-12-03 | 北京奇艺世纪科技有限公司 | A kind of search words recommending method and device |
| CN110532454B (en) * | 2019-08-28 | 2022-04-22 | 北京奇艺世纪科技有限公司 | Search term recommendation method and device |
| CN110990696A (en) * | 2019-11-25 | 2020-04-10 | 三角兽（北京）科技有限公司 | Method and device for recommending search intention |
| CN110990696B (en) * | 2019-11-25 | 2023-04-14 | 腾讯科技（深圳）有限公司 | Method and device for recommending search intention |
| CN115203599A (en) * | 2022-09-13 | 2022-10-18 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197244A (en) | It is a kind of to search for the method for pushing and device for recommending word | |
| US20180239781A1 (en) | Automatically obtaining real-time, geographically-relevant product information from heterogeneus sources | |
| US10146887B2 (en) | Providing separate views for items | |
| EP2946316B1 (en) | Indexing application pages of native applications | |
| CN105956161B (en) | A kind of information recommendation method and device | |
| US9069843B2 (en) | Iterative refinement of search results based on user feedback | |
| CN103577597B (en) | Keyword search system based on current browse webpage | |
| CN103488781B (en) | Method, the search engine server of information search are provided | |
| CN103699669B (en) | The method of message push and a kind of browser terminal is carried out in a kind of browser | |
| US20140279048A1 (en) | Systems and methods for providing relevant pathways through linked information | |
| CN103577596B (en) | Keyword search methodology and device based on current browse webpage | |
| US20130290319A1 (en) | Performing application searches | |
| CN104602042A (en) | User behavior based label setting method | |
| CN102930058B (en) | A kind of method and apparatus realizing searching in the address field of browser | |
| US20080282186A1 (en) | Keyword generation system and method for online activity | |
| CN103530414B (en) | Web Page Key Words open up word method and apparatus | |
| CN105224554A (en) | Search word is recommended to carry out method, system, server and the intelligent terminal searched for | |
| US9830304B1 (en) | Systems and methods for integrating dynamic content into electronic media | |
| CN107562966B (en) | Intelligent learning-based optimization system and method for webpage link retrieval sequencing | |
| CN107832332A (en) | The method, apparatus and electronic equipment for recommending word are generated in navigating search frame | |
| US11500952B1 (en) | Indexing access limited native applications | |
| CN102521257A (en) | Method and device for providing corresponding on-line picture according to thumbnail | |
| CN106471497A (en) | Auxiliary using context browses | |
| CN103226574A (en) | Information search method and information search device | |
| CN105183888A (en) | Data processing method based on browser and browser |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |
|
| RJ01 | Rejection of invention patent application after publication |