CN106407457A - Method for recommending search terms and searching method and device - Google Patents
Method for recommending search terms and searching method and device Download PDFInfo
- Publication number
- CN106407457A CN106407457A CN201610875510.2A CN201610875510A CN106407457A CN 106407457 A CN106407457 A CN 106407457A CN 201610875510 A CN201610875510 A CN 201610875510A CN 106407457 A CN106407457 A CN 106407457A
- Authority
- CN
- China
- Prior art keywords
- search
- search word
- word
- user
- words
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a method for recommending search terms and a searching method and device. The method for recommending the search terms comprises the steps of: receiving a first search term input by a user; carrying out searching on the basis of the first search term, acquiring a search result and outputting the search result; receiving a deletion operation that the user deletes the first search term; according to the first search term, determining one or more second search terms related to the first search terms; and outputting recommending information which represents that the one or more second search terms are recommended to the user. The method for recommending the search terms is used for carrying out personalized search term recommending for different users.
Description
Technical field
The present invention relates to computer realm, more particularly, to a kind of method recommending search word, searching method and device.
Background technology
At present, search engine receives user after the search word that search word input inputs, and is searched based on search word
Rope, and display to the user that Search Results in result of page searching.If user is unsatisfied with to Search Results, Delete Search
Word.Now, in order to improve the search efficiency of user, in correlation technique, the same day or hot news within the next few days can be recommended to user,
Or recommend heat to search word to user.
However, aforesaid way recommend search word hit user expected from probability relatively low it is recommended that accuracy rate is relatively low.
Content of the invention
Embodiments provide a kind of method recommending search word, searching method and device, for using for different
Family carries out personalized recommendation search word.
In a first aspect, the invention provides a kind of recommend search method, including:
First search word of receiving user's input;
Scanned for based on described first search word, obtain Search Results, and export described Search Results;
Receive the deletion action that described user deletes described first search word;
According to described first search word, determine one or more second search words related to described first search word;
Output represents the recommendation information recommending one or more of second search words to described user.
Optionally, according to described first search word, determine that one or more second related to described first search word are searched
Rope word, including:
According to described first search word, obtain the one or more candidate search words related to described first search word;
Judge whether described candidate search word and the degree of association of described first search word reach the default degree of association;
The described candidate search word being up to the described default degree of association is defined as described second search word.
Optionally, according to described first search word, obtain the one or more candidates related to described first search word and search
Rope word, including:
According to the search history of described first search word and described user, determine and associate with described first search word presence
One or more of candidate search words.
Optionally, the search history record according to described first search word and described user, determines and searches with described first
There are one or more of candidate search words of association in rope word, including:
From described Search Results, extract the core word of each page of described Search Results;Described Search Results are institute
State the search history of user;
Described core word is determined described candidate search word.
Optionally, according to described first search word, obtain the one or more candidates related to described first search word and search
Rope word, including:
According to the search of described user custom and described first search word, determine related to described first search word described
One or more candidate search words.
Optionally, the search custom according to described user and described first search word, determine and described first search word phase
One or more of second search words closing, including:
The art determining described first search word is the first field of described user custom search;
The one or more words belonging to described first field are defined as one or more of candidate search words.
Optionally, the content of described second search word does not comprise the content of described first search word.
Second aspect, the invention provides a kind of searching method, including:
First search word of receiving user's input;
Scanned for based on described first search word, obtain the first Search Results, and export described first Search Results;
Receive the deletion action that described user deletes described first search word;
According to described first search word, determine one or more second search words related to described first search word, institute
The content stating the second search word does not comprise the content of described first search word;
Output represents the recommendation information recommending one or more of second search words to described user;
Scanned for based on the second search word that described user confirms, obtain the second Search Results, and export described second
Search Results.
The third aspect, the invention provides a kind of device recommending search word, including:
First receiver module, for the first search word of receiving user's input;
First output module, for being scanned for based on described first search word, is obtained Search Results, and searches described in exporting
Hitch fruit;
Second receiver module, deletes the deletion action of described first search word for receiving described user;
First determining module, for according to described first search word, determine related to described first search word or
Multiple second search words;
Second output module, represents the recommendation recommending one or more of second search words to described user for output
Information.
Optionally, described first determining module is used for, according to described first search word, obtaining and described first search word phase
The one or more candidate search words closing;Judge described candidate search word and described first search word the degree of association whether reach pre-
If the degree of association;The described candidate search word being up to the described default degree of association is defined as described second search word.
Optionally, described first determining module is used for the search history according to described first search word and described user,
Determine the one or more of candidate search words associating with described first search word presence.
Optionally, described first determining module is used for extracting each page of described Search Results from described Search Results
The core word in face;Described Search Results are the search history of described user;Described core word is determined described candidate search word.
Optionally, described first determining module is used for the search custom according to described user and described first search word, really
The fixed one or more of candidate search words related to described first search word.
Optionally, described first determining module is used for determining that the art of described first search word is described user's custom
First field of search;The one or more words belonging to described first field are defined as one or more of candidate search
Word.
Optionally, the content of described second search word does not comprise the content of described first search word.
Fourth aspect, the invention provides a kind of searcher, including:
3rd receiver module, for the first search word of receiving user's input;
3rd output module, for being scanned for based on described first search word, is obtained the first Search Results, and exports institute
State the first Search Results;
4th receiver module, deletes the deletion action of described first search word for receiving described user;
Second determining module, for according to described first search word, determine related to described first search word or
Multiple second search words, the content of described second search word does not comprise the content of described first search word;
4th output module, represents the recommendation recommending one or more of second search words to described user for output
Information;
5th output module, for scanning for based on the second search word that described user confirms, obtains the second search knot
Really, and export described second Search Results.
Said one in the embodiment of the present application or multiple technical scheme, at least have following one or more technology effect
Really:
In embodiments of the present invention, in the first search word of receiving user's input, and scanned for based on the first search word,
Obtain Search Results, and after exporting Search Results, receive user deletes the deletion action of the first search word, then according to first
Search word, determines one or more second search words related to the first search word, and export represent to user's recommendation one or
The recommendation information of multiple second search words.It can be seen that, because the first search word is by user input, the second search word is based on first again
Search word determines, so after user deletes the first search word, the second search word that the present invention is recommended can more conform to
Users ' individualized requirement, and then it is more nearly user's expection, so improve recommendation accuracy rate.
Brief description
Fig. 1 is the method flow diagram recommending search word in the embodiment of the present invention;
Fig. 2-Fig. 7 is the first search word and the second search word schematic diagram in the embodiment of the present invention;
Fig. 8 is the flow chart of searching method in the embodiment of the present invention;
Fig. 9 is the apparatus structure schematic diagram recommending search word in the embodiment of the present invention;
Figure 10 is searcher structural representation in the embodiment of the present invention.
Specific embodiment
Embodiments provide a kind of method recommending search word, searching method and device, for using for different
Family carries out personalized recommendation search word.
In order to solve above-mentioned technical problem, the technical scheme general thought that the present invention provides is as follows:
In embodiments of the present invention, in the first search word of receiving user's input, and scanned for based on the first search word,
Obtain Search Results, and after exporting Search Results, receive user deletes the deletion action of the first search word, then according to first
Search word, determines one or more second search words related to the first search word, and export represent to user's recommendation one or
The recommendation information of multiple second search words.It can be seen that, because the first search word is by user input, the second search word is based on first again
Search word determines, so after user deletes the first search word, the second search word that the present invention is recommended can more conform to
Users ' individualized requirement, and then it is more nearly user's expection, so improve recommendation accuracy rate.
Below by accompanying drawing and technical solution of the present invention is described in detail specific embodiment it should be understood that the application
Specific features in embodiment and embodiment are the detailed description to technical scheme, rather than to present techniques
The restriction of scheme, in the case of not conflicting, the technical characteristic in the embodiment of the present application and embodiment can be mutually combined.
The terms "and/or", only a kind of incidence relation of description affiliated partner, represents there may be three kinds
Relation, for example, A and/or B, can represent:, there are A and B, these three situations of individualism B in individualism A simultaneously.In addition, this
Literary composition in character "/", typically represent forward-backward correlation to as if a kind of relation of "or".
First aspect present invention provides a kind of method recommending search word, refer to Fig. 1, is to push away in the embodiment of the present invention
Recommend the method flow diagram of search.The method includes:
S101:First search word of receiving user's input;
S102:Scanned for based on described first search word, obtain Search Results, and export described Search Results;
S103:Receive the deletion action that described user deletes described first search word;
S104:According to described first search word, determine one or more second search related to described first search word
Word;
S105:Output represents the recommendation information recommending one or more of second search words to described user.
Method in the embodiment of the present invention can be applicable to electronic equipment, for example smart mobile phone, panel computer, intelligent watch or
Notebook computer etc., the present invention is not particularly limited.
First, in S101, by the first search word of input equipment receiving user's input.Specifically, input equipment
For example, touch screen, keyboard or remote control etc..User is according to the needs of oneself, defeated in search word input using input equipment
Enter the first search word.
Then, in S102, search engine is triggered based on the first search word and scans for.Wherein, electronic equipment can be
When thinking that user input finishes, such as no longer receive the input operation of user, automated initiation of search in Preset Time.Can also
The start-up operation that inputs further after receiving user input and completing the first search word and start search.Wherein, startup is searched
Rope is, for example, that user clicks on enter key, or touch-control shows the start button of " search ", and the present invention is not particularly limited.
After starting search, the Search Results of the first search word will be obtained, and then, Search Results are exported, for reference.
If after user observes Search Results, Search Results are unsatisfied with it is desirable alternatively to can re-search for, then can delete
First search word of search word input, then, in S103, user can be received further by input equipment and delete first
The deletion action of search word.
Recommend other search words in order to intelligence to user, in the S104 of the embodiment of the present invention, will search according to first
Rope word, determines one or more second search words related to the first search word.Specifically, can search out from network
The candidate search word related to the first search word, then from all candidate search words arbitrarily determine one or more as
Two search words.Or, because Search Results are searched based on the first search word, so Search Results are searched with first naturally
Rope word is related, then can also extract candidate search word from Search Results, and then using the candidate search extracted word as the
Two search words.Those skilled in the art can scan for according to actual, and the present invention is not particularly limited.
Then, in S105, output represents the recommendation information recommending one or more second search words to user, Jin Eryong
Family directly can select second search word to scan for again from one or more second search words.
As an example it is assumed that user inputs the first search word " iqiyi.com " in search word input, and then search engine base
Scan in the first search word " iqiyi.com ", then export Search Results to user.After user observes Search Results, by the
One search word " iqiyi.com " is deleted.And then, after receiving the deletion action that user deletes the first search word " iqiyi.com ", according to the
One search word " iqiyi.com ", searches out the candidate search word " iqiyi.com net " related to " iqiyi.com ", " dawn Fem 7 from network
Talk ", " famous to trump ", " iqiyi.com vip member shares ", " Ye Zuxin " and " Yuan Hong ", and then by subsequent searches word " iqiyi.com
Net ", " dawn Fem 7 is talked ", " big shot is to trump ", " iqiyi.com vip member shares ", " Ye Zuxin " and " Yuan Hong " search for as second
Word is shown in recommendation region to be recommended to user, as shown in Figure 2.
Or, as shown in Figure 3 it is assumed that user inputs the first search word " Liu Shishi " in search word input, user observes
After Search Results, the first search word " Liu Shishi " is deleted.Then, the second search word " Ye Zuxin " and " Yuan are recommended to user
Great ".
Or, it is assumed that user inputs the first search word " U.S. of mathematics ", Yong Huguan in search word input
After examining Search Results, the first search word " U.S. of mathematics " is deleted.Then, recommend the second search word " U.S. of mathematics to user
Pdf ", " python " and " mountain peak of tide ".
Or, as shown in fig. 5, it is assumed that user inputs the first search word " Wang Shi " in search word input, user observes and searches
After hitch fruit, the first search word " Wang Shi " is deleted.Then, to user recommend the second search word " Wang Shi is unable to escape out destiny ",
" Tian Piao " and " Shi Yuzhu ".
Or, as shown in Figure 6 it is assumed that user inputs the first search word " Qihoo " in search word input, user observes and searches
After hitch fruit, the first search word " Qihoo " is deleted.Then, recommend the second search word " Qihoo 360 " to user, " Baidu refers to
Number ", " China's search " and " Qihoo 360 backdoor object ".
Or, as shown in Figure 7 it is assumed that user inputs the first search word " Semen Sojae Preparatum " in search word input, user observes and searches
After hitch fruit, the first search word " Semen Sojae Preparatum " is deleted.Then, the second search word " Semen Sojae Preparatum film ", " LOFTER " are recommended to user
" Semen Sojae Preparatum is rented a house ".
By foregoing description as can be seen that because the first search word is by user input, the second search word is based on first again
Search word determines, so the second search word that the present invention is recommended is more nearly user's expection, and then is easier to meet user
Individual demand, so improve recommendation accuracy rate.
Further, due to key word related in a large number may be determined according to the first search word, in order to avoid to user
The second excessive search word of quantity is provided to lead to poor user experience, as a kind of optional enforcement, S104 can specifically include:
According to described first search word, obtain the one or more candidate search words related to described first search word;
Judge whether described candidate search word and the degree of association of described first search word reach the default degree of association;
The described candidate search word being up to the described default degree of association is defined as described second search word.
Specifically, first, the one or more candidate search related to the first search word are obtained according to the first search word
Word.In order to avoid exporting the second excessive search word of quantity to user, in embodiments of the present invention, for each candidate search
Word, will determine that whether candidate search word and the degree of association of the first search word reach the default degree of association.If candidate search word and first
The degree of association of search word reaches the default degree of association, then be up to the default degree of association candidate search word be defined as the second search word to
User recommends.If the not up to default degree of association of the degree of association of candidate search word and the first search word, not up to default association
The candidate search word of degree is not the second search word, enters without recommending to user.
Wherein, the degree of association represents the correlation degree of the first search word and candidate search word.In embodiments of the present invention, permissible
Characteristic vector is set up in art based on a word, attribute information and source etc., and then, in calculating the first search word with subsequently
When the degree of association of search word, can specifically calculate between the first search word feature vector and candidate search word feature vector
Distance, and then using the distance between two characteristic vectors as the degree of association.Or, the degree of association can also be specially the first search word
The number of times occurring in the same page with candidate search word represents.Such as first search word is occurred in one of candidate search word
The number of times of the same page is 10, then the degree of association between the first search word and this candidate search word is 10.Or, the degree of association also may be used
To be specially the quantity of the related term of the first search word and the related term identical related term of candidate search word.Such as first search
The related term of word is A, B, C, D, E and F, and the related term of candidate word A is B, C and R, then identical related term has two, is B and C, therefore
First search word is 2 with the degree of association of candidate search word A.Those skilled in the art can be according to actual choosing
Select the method for expressing of the degree of association, the present invention is not particularly limited.
Because the degree of association can have multiple method for expressing, then judge that candidate search word with the degree of association of the first search word is
No reach the default degree of association and can also have multiple methods.Two of which is explained below.
The first, the degree of association is specially the first search word and candidate search word occurs in the number of times of the same page.Then judge
Whether the degree of association of the first search word and candidate search word reaches the default degree of association, particularly as being to judge the first search word and candidate
Whether the number of times that search word occurs in the same page reaches preset times.Wherein, preset times for example, 5,10 or 20 etc., this
Bright those of ordinary skill in the art can be configured according to actual, and the present invention is not particularly limited.
For example, the first search word is " iqiyi.com ", and preset times are 500, candidate search word " dawn Fem 7 talk " and the
One search word degree has 3000 times and occurs in the same page it is determined that " dawn Fem 7 talk " is second search word.Candidate search word
" Apple Seeds " only occur in the same page 302 times with the first search word, then " Apple Seeds " are not the second search words.
Second, the degree of association is specially the related term of the first search word and identical related term in the related term of candidate search word
Quantity, then judge whether the first search word and the degree of association of candidate search word reach the default degree of association, particularly as being judgement
Whether the related term of one search terms reaches predetermined number with the quantity of identical related term in the related term of candidate search word.Its
In, predetermined number for example, 5,10 or 20 etc., those skilled in the art can be configured according to actual,
The present invention is not particularly limited.
For example, the first search word is related term as candidate search word " iqiyi.com net ", " the dawn Fem 7 of " iqiyi.com "
What is said or talked about ", " big shot is to trump ", " iqiyi.com vip member shares ", " Ye Zuxin " and " Yuan Hong ", predetermined number is 2.Candidate search word
The related term of " dawn Fem 7 is talked " is " the Negotiator ", " iqiyi.com vip member shares ", " sunset and rice " and " Gao Xiaosong auto heterodyne ".
The related term of the first search word is " the Negotiator " and " iqiyi.com with the identical related term of candidate search word " dawn Fem 7 is talked "
Vip member shares ", quantity is 2, has reached predetermined number, so candidate word " dawn Fem 7 is talked " is second search word.Candidate
The related term of search word " Apple Seeds " is " Apple Seeds price ", " the Apple Seeds place of production ", " fruit seeds " and " Seed storage
Method ", does not have identical with the related term of the first search word, so quantity is 0, not up to predetermined number, so " Fructus Mali pumilae kind
Son " is not the second search word.
Seen from the above description, the candidate search word degree of association with the first search word being reached the default degree of association is defined as
Second search word recommends user it is ensured that the second search word of output is higher with the first search word degree of correlation, and then makes
Second search word is more nearly user's expection, further increases recommendation accuracy rate, avoids a large amount of second search of output simultaneously
Word and reduce the probability of Consumer's Experience.
In embodiments of the present invention, determine that one or more candidate search words have multiple methods according to the first search word, under
Two of which will be introduced in face.During implementing, including but not limited to following two.
1st kind:
In the 1st kind of mode, according to the first search word, obtain the one or more candidate search related to the first search word
Word is realized by following process:
According to the search history of described first search word and described user, determine and associate with described first search word presence
One or more of candidate search words.
Specifically, the search history in the embodiment of the present invention includes historical search word and Search Results, or acceptable
Including historical search result, or history second search word etc., the present invention is not particularly limited.Therefore, according to the first search word
The mode determining candidate search word with the search history of user just has multiple.It is described below and two of which is introduced, in tool
During body is realized, including but not limited to following two.
1.1st kind:
In 1.1 kinds of modes, search history is specially the Search Results obtaining according to the first search word, and then according to first
Search word determines that one or more candidate search words just specifically include:
From described Search Results, extract the core word of each page of described Search Results;Described Search Results are institute
State the search history of user;
Described core word is determined described candidate search word.
Specifically, the core word in the embodiment of the present invention is, for example, the word of page title, or repeatedly occurs in the page
Word, or and the first search word word arranged side by side etc., the present invention is not particularly limited.
From each page of Search Results, extract the core word of each page.Because Search Results are according to first
Search word and searching for obtains, so each page is all related to the first search word, and then the core word in each page also with
First search word is related.So, each core word extracting is defined as candidate search word.
As an example it is assumed that the first search word is " Liu Shishi ", the one of page in Search Results is included with hereafter
Word:
" the TV play of Liu Shishi and the protagonist such as Yuan Hong, Ye Zuxin and Wu Qilong《Step by step soul-stirring》Very popular.”
Extract core word " Yuan Hong ", " Ye Zuxin ", " Wu Qilong " and " step by step soul-stirring " from the above-mentioned page, and then determine
Candidate search word " Yuan Hong ", " Ye Zuxin ", " Wu Qilong " and " step by step soul-stirring ".Process for remaining page is also similar, because
This just no longer repeats one by one.
1.2nd kind:
In the 1.2nd kind of mode, search history be specially historical search word it is determined that candidate search word be specially determine with
The related historical search word of first search word is candidate search word.
Specifically, filter out the word related to the first search word from multiple historical search words, for example, filter out and first
Search word includes the historical search word of identical content, or filters out and occur in the history in the same page with the first search word and search
Rope word etc., and then the historical search filtering out word is defined as candidate search word.
As an example it is assumed that the first search word is " Liu Shishi ", historical search word is " Wu Qilong ", " Fructus Mali pumilae ", " Liu Shishi
Act the leading role TV play ", " autumn health " and " how cutting Punica granatum L. ", wherein, the historical search related to the first search word " Liu Shishi "
Word is " Wu Qilong " and " Liu Shishi acts the leading role TV play ", so, determine that candidate search word is " Wu Qilong " and " Liu Shishi protagonist electricity
Depending on acute ".
2nd kind:
In the 2nd kind of mode, according to the first search word, obtain the one or more candidate search related to the first search word
Word is realized by following process:
According to the search of described user custom and described first search word, determine related to described first search word described
One or more candidate search words.
Specifically, in the embodiment of the present invention, the search custom of user can be specially the field of user's custom search, or
Person can also be accustomed to the association area of search field for user, and user is accustomed to performer's title of search, movie name etc., this
Invention is not particularly limited.So determine that candidate search word also specifically has various ways according to the search custom of user.Below will
Enumerate two of which to illustrate, during implementing, including but not limited to following two.
2.1st kind:
In the 2.1st kind of mode, the search custom of user is specially the field of user's custom search, then, determine candidate
Search word is just specially:
The art determining described first search word is the first field of described user custom search;
The one or more words belonging to described first field are defined as one or more of candidate search words.
Specifically, first, determine the art of the first search word.Then, judge the art of the first search word
Whether it is the field that user's custom is searched for.If the art of the first search word is the first field of user's custom search,
The one or more words belonging to the first field are defined as a candidate search word.
For example, the such as first search word is " Macaron ", then art is " sweets ".Determine that " sweets " field is
The field of user's custom search, and then, determine that " sandwich biscuit " and " water chestnut cake " that belongs to " sweets " field is candidate search
Word.
2.2nd kind:
In the 2.2nd kind of mode, the search custom of user is specially the association area in the field of user's custom search, that
, determine that candidate search word is just specially:
The art determining described first search word is the first field of described user custom search;
Determine one or more second fields related to described first field;
The one or more words belonging to described second field are defined as one or more of candidate search words.
Specifically, first, determine the art of the first search word.Then, judge the art of the first search word
Whether it is the field that user's custom is searched for.If the art of the first search word is the first field of user's custom search,
Further determine that second field related to the first field, and then the one or more words belonging to the second field are defined as candidate
Search word.
Specifically, the second field can be the field of user's custom search.So, determine the second field it is simply that from
The field related to the first field is determined in the field of family custom search.For continuing to use example above, the first search word
" Macaron " art is " sweets ", and the field of user's custom search includes " sweets ", " baking product ", " Sichuan cuisine " and " footwear
Bag ".Wherein, the first search word " Macaron " art be user custom search field, and " baking product " field with " sweet
Product " field is close, and degree of correlation is high, so determining that the second field is " baking product ".Further, determine and belong to " baking product " field
" chocolate cake " and " rainbow cake " be candidate search word.
Or, the second field can not also be the field of individual habit of user search, but most of user is in search the
The second field searched for is may proceed to after one field.In other words, it can be seen that the second field is pointed in the first field from big data.
For example, the first search word is " Jean short trousers ", then art is " clothes ".Determine that " clothes " field is use
The field of family custom search.Then, according to big data, determine that " shoes and hats " field is pointed in " clothes " field, and then, determine " shoes and hats "
Field is the second field.Then, it is determined that " sandals " and " sunbonnet " that belong to " shoes and hats " field are candidate search word.
Further, as a kind of optional embodiment, the content of the second search word does not comprise the content of the first search word.Change
Yan Zhi, the second search word is entirely different with the content of the first search word.For continuing to use example above, as shown in Fig. 2 first
Search word is " iqiyi.com ", and " the iqiyi.com net " related to " iqiyi.com " is, " dawn Fem 7 is talked ", " big shot is to trump ", " iqiyi.com
Vip member shares ", in " Ye Zuxin " and " Yuan Hong ", due to containing the in " iqiyi.com net " and " iqiyi.com vip member is shared "
The content of one search word " iqiyi.com ", and " dawn Fem 7 is talked ", " big shot is to trump ", " Ye Zuxin " and " Yuan Hong " does not then comprise first
The content of search word " Liu Shishi ", now only to user recommend the second search word only have " dawn Fem 7 talk ", " famous to trump ",
" Ye Zuxin " and " Yuan Hong ".
Based on the inventive concept same with the method for recommendation search word in previous embodiment, second aspect present invention also provides
A kind of searching method, as shown in figure 8, include:
S201:First search word of receiving user's input;
S202:Scanned for based on described first search word, obtain the first Search Results, and export described first search knot
Really;
S203:Receive the deletion action that described user deletes described first search word;
S204:According to described first search word, determine one or more second search related to described first search word
Word;
S205:Output represents the recommendation information recommending one or more of second search words to described user;
S206:Scanned for based on the second search word that described user confirms, obtain the second Search Results, and export described
Second Search Results.
Specifically, the first search word that receive user is inputted by input equipment first in S201, and then in S202
Scanned for based on the first search word, and the first Search Results obtaining are exported.When user is unsatisfied with to the first Search Results
When, in S203, receive user deletes the deletion action of the first search word.In order to improve user's search efficiency, will be according in S204
One search word determines one or more second search words related to the first search word.The second search in the embodiment of the present invention
Word does not comprise the content of the first search word.And then output represents pushing away to user's one or more second search word of recommendation in S205
Recommend information.Finally, scanned for based on the second search word that user confirms in S206, and will be defeated for the second Search Results obtaining
Go out.
The various change mode of method of recommendation search word in earlier figures 1- Fig. 7 embodiment and instantiation are equally applicable
In the searching method of the present embodiment, by the detailed description to the aforementioned method recommending search word, those skilled in the art are permissible
It is apparent from the implementation of searching method in the present embodiment, thus succinct for description, will not be described in detail herein.
Based on the inventive concept same with the method for recommendation search word in previous embodiment, third aspect present invention also provides
A kind of device recommending search word, as shown in figure 9, include:
First receiver module 101, for the first search word of receiving user's input;
First output module 102, for being scanned for based on described first search word, is obtained Search Results, and exports institute
State Search Results;
Second receiver module 103, deletes the deletion action of described first search word for receiving described user;
First determining module 104, for according to described first search word, determining related to described first search word
Or multiple second search word;
Second output module 105, represents for output and recommends one or more of second search words to described user
Recommendation information.
Optionally, the first determining module 104 is used for, according to described first search word, obtaining related to described first search word
One or more candidate search words;Judge described candidate search word and described first search word the degree of association whether reach default
The degree of association;The described candidate search word being up to the described default degree of association is defined as described second search word.
Specifically, the first determining module 104 is used for the search history according to described first search word and described user,
Determine the one or more of candidate search words associating with described first search word presence.
Further, the first determining module 104 is used for extracting each page of described Search Results from described Search Results
Core word;Described Search Results are the search history of described user;Described core word is determined described candidate search word.
Or, specifically, the first determining module 104 is used for search custom and described first search according to described user
Word, determines the one or more of candidate search words related to described first search word.
Further, the first determining module 104 is used for determining that the art of described first search word is described user's custom
First field of search;The one or more words belonging to described first field are defined as one or more of candidate search
Word.
Optionally, the content of described second search word does not comprise the content of described first search word.
The various change mode of method of recommendation search word in earlier figures 1- Fig. 7 embodiment and instantiation are equally applicable
In the device of the recommendation search word of the present embodiment, by the detailed description to the aforementioned method recommending search word, art technology
Personnel are clear that the implementation of the device recommending search word in the present embodiment, thus succinct for description,
Will not be described in detail herein.
Based on the inventive concept same with searching method in previous embodiment, fourth aspect present invention also provides a kind of search
Device, as shown in Figure 10, including:
3rd receiver module 201, for the first search word of receiving user's input;
3rd output module 202, for scanning for based on described first search word, obtains the first Search Results, and defeated
Go out described first Search Results;
4th receiver module 203, deletes the deletion action of described first search word for receiving described user;
Second determining module 204, for according to described first search word, determining related to described first search word
Or multiple second search word, the content of described second search word do not comprise the content of described first search word;
4th output module 205, represents for output and recommends one or more of second search words to described user
Recommendation information;
5th output module 206, for scanning for based on the second search word that described user confirms, obtains the second search
As a result, and export described second Search Results.
The various change mode of method of recommendation search word in aforementioned Fig. 8 embodiment and instantiation are equally applicable to this
The searching method of embodiment, by the detailed description to the aforementioned method recommending search word, those skilled in the art can be clear
The implementation knowing searching method in the present embodiment, so succinct for description, will not be described in detail herein.
Said one in the embodiment of the present application or multiple technical scheme, at least have following one or more technology effect
Really:
In embodiments of the present invention, in the first search word of receiving user's input, and scanned for based on the first search word,
Obtain Search Results, and after exporting Search Results, receive user deletes the deletion action of the first search word, then according to first
Search word, determines one or more second search words related to the first search word, and export represent to user's recommendation one or
The recommendation information of multiple second search words.It can be seen that, because the first search word is by user input, the second search word is based on first again
Search word determines, so after user deletes the first search word, the second search word that the present invention is recommended can more conform to
Users ' individualized requirement, and then it is more nearly user's expection, so improve recommendation accuracy rate.
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 based on teaching in this.As described above, construct required by this kind of system
Structure be obvious.Additionally, the present invention is also not for any certain programmed language.It is understood that, it is possible to use various
Programming language realizes the content of invention described herein, and the description above language-specific done is to disclose this
Bright preferred forms.
In description mentioned herein, illustrate a large amount of details.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of not having these details.In some instances, known method, structure are not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly it will be appreciated that in order to simplify the disclosure and help understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the present invention is grouped together into single enforcement sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:I.e. required guarantor
The application claims of shield more features than the feature being expressly recited in each claim.More precisely, it is such as following
Claims reflected as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
The claims following specific embodiment are thus expressly incorporated in this specific embodiment, wherein each claim itself
All as the separate embodiments of the present invention.
Those skilled in the art are appreciated that and the module in the equipment in embodiment can be carried out adaptively
Change and they are arranged in one or more equipment different from this embodiment.Can the module in embodiment or
Unit or assembly are combined into a module or unit or assembly, and can be divided into multiple submodule or subelement in addition
Or sub-component.In addition to such feature and/or at least some of process or unit exclude each other, can be using appointing
What combination is to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed
All processes of any method or equipment or unit are combined.Unless expressly stated otherwise, this specification (includes adjoint
Claim, summary and accompanying drawing) disclosed in each feature can be come by the alternative features providing identical, equivalent or similar purpose
Replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments in this include institute in other embodiments
Including some features rather than further feature, but the combination of the feature of different embodiment means to be in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment required for protection any it
One can in any combination mode using.
The all parts embodiment of the present invention can be realized with hardware, or to run on one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) come to realize gateway according to embodiments of the present invention, proxy server, in system
Some or all parts some or all functions.The present invention is also implemented as executing side as described herein
Some or all equipment of method or program of device (for example, computer program and computer program).Such
The program realizing the present invention can store on a computer-readable medium, or can have the shape of one or more signal
Formula.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or with any other shape
Formula provides.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference markss between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware including some different elements and by means of properly programmed computer
Existing.If in the unit claim 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 order.These words can be explained and run after fame
Claim.
Obviously, those skilled in the art can carry out the various changes and modification essence without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprise these changes and modification.
Claims (10)
1. a kind of method recommending search word is it is characterised in that include:
First search word of receiving user's input;
Scanned for based on described first search word, obtain Search Results, and export described Search Results;
Receive the deletion action that described user deletes described first search word;
According to described first search word, determine one or more second search words related to described first search word;
Output represents the recommendation information recommending one or more of second search words to described user.
2. the method for claim 1 is it is characterised in that according to described first search word, determine and described first search
Related one or more second search words of word, including:
According to described first search word, obtain the one or more candidate search words related to described first search word;
Judge whether described candidate search word and the degree of association of described first search word reach the default degree of association;
The described candidate search word being up to the described default degree of association is defined as described second search word.
3. method as claimed in claim 1 or 2 is it is characterised in that according to described first search word, obtaining and search with described first
The related one or more candidate search words of rope word, including:
According to the search history of described first search word and described user, determine the institute associating with described first search word presence
State one or more candidate search words.
4. the method as described in any one of claim 1-3 is it is characterised in that according to described first search word and described user
Search history record, determine there are, with described first search word, one or more of candidate search words of associating, including:
From described Search Results, extract the core word of each page of described Search Results;Described Search Results are described use
The search history at family;
Described core word is determined described candidate search word.
5. the method as described in any one of claim 1-4 is it is characterised in that according to described first search word, obtain with described
The related one or more candidate search words of first search word, including:
According to the search of described user custom and described first search word, determine related to described first search word one
Or multiple candidate search word.
6. the method as described in any one of claim 1-5 is it is characterised in that according to the search of described user custom and described the
One search word, determines one or more of second search words related to described first search word, including:
The art determining described first search word is the first field of described user custom search;
The one or more words belonging to described first field are defined as one or more of candidate search words.
7. the method as described in any one of claim 1-6 is not it is characterised in that as described in the content of described second search word comprises
The content of the first search word.
8. a kind of searching method is it is characterised in that include:
First search word of receiving user's input;
Scanned for based on described first search word, obtain the first Search Results, and export described first Search Results;
Receive the deletion action that described user deletes described first search word;
According to described first search word, determine one or more second search words related to described first search word, described the
The content of two search words does not comprise the content of described first search word;
Output represents the recommendation information recommending one or more of second search words to described user;
Scanned for based on the second search word that described user confirms, obtain the second Search Results, and export described second search
Result.
9. a kind of device recommending search word is it is characterised in that include:
First receiver module, for the first search word of receiving user's input;
First output module, for scanning for based on described first search word, obtains Search Results, and exports described search knot
Really;
Second receiver module, deletes the deletion action of described first search word for receiving described user;
First determining module, related to described first search word one or more for according to described first search word, determining
Second search word;
Second output module, represents the recommendation recommending one or more of second search words to described user for output
Breath.
10. a kind of searcher is it is characterised in that include:
3rd receiver module, for the first search word of receiving user's input;
3rd output module, for being scanned for based on described first search word, is obtained the first Search Results, and exports described the
One Search Results;
4th receiver module, deletes the deletion action of described first search word for receiving described user;
Second determining module, related to described first search word one or more for according to described first search word, determining
Second search word, the content of described second search word does not comprise the content of described first search word;
4th output module, represents the recommendation recommending one or more of second search words to described user for output
Breath;
5th output module, for scanning for based on the second search word that described user confirms, obtains the second Search Results, and
Export described second Search Results.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610875510.2A CN106407457A (en) | 2016-09-30 | 2016-09-30 | Method for recommending search terms and searching method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610875510.2A CN106407457A (en) | 2016-09-30 | 2016-09-30 | Method for recommending search terms and searching method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106407457A true CN106407457A (en) | 2017-02-15 |
Family
ID=59228748
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610875510.2A Pending CN106407457A (en) | 2016-09-30 | 2016-09-30 | Method for recommending search terms and searching method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106407457A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107291835A (en) * | 2017-05-31 | 2017-10-24 | 北京京东尚科信息技术有限公司 | A kind of recommendation method and apparatus of search term |
CN109189896A (en) * | 2018-09-28 | 2019-01-11 | 深圳市谷熊网络科技有限公司 | A kind of method, device and equipment of feedback information |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术(北京)有限公司 | Search result recommendation method, system and search engine |
CN104537057A (en) * | 2014-12-26 | 2015-04-22 | 北京奇虎科技有限公司 | Data searching method and client side |
CN105117479A (en) * | 2015-09-11 | 2015-12-02 | 北京金山安全软件有限公司 | Acquisition method and processing method of user search behavior information and electronic equipment |
-
2016
- 2016-09-30 CN CN201610875510.2A patent/CN106407457A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103294814A (en) * | 2013-06-07 | 2013-09-11 | 百度在线网络技术(北京)有限公司 | Search result recommendation method, system and search engine |
CN104537057A (en) * | 2014-12-26 | 2015-04-22 | 北京奇虎科技有限公司 | Data searching method and client side |
CN105117479A (en) * | 2015-09-11 | 2015-12-02 | 北京金山安全软件有限公司 | Acquisition method and processing method of user search behavior information and electronic equipment |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107291835A (en) * | 2017-05-31 | 2017-10-24 | 北京京东尚科信息技术有限公司 | A kind of recommendation method and apparatus of search term |
CN107291835B (en) * | 2017-05-31 | 2020-12-22 | 北京京东尚科信息技术有限公司 | Search term recommendation method and device |
CN109189896A (en) * | 2018-09-28 | 2019-01-11 | 深圳市谷熊网络科技有限公司 | A kind of method, device and equipment of feedback information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103942193B (en) | A kind of method and device of information push | |
CN104216918B (en) | Keyword search methodology and system | |
CN102880654B (en) | Method for dynamically updating favorites of information terminal browser | |
CN105095474B (en) | Establish the method and device of search term and application data recommendation relationship | |
CN104991962B (en) | A kind of method and device generating recommendation information | |
CN102567511A (en) | Method and device for automatically recommending application | |
CN102521257B (en) | Method and device for providing corresponding on-line picture according to thumbnail | |
CN103810198A (en) | Method and device for searching commodity information | |
CN105912680B (en) | Search for recommended method, device and mobile terminal | |
CN102880609A (en) | Equipment and method for providing search results corresponding to query sequences | |
CN106407457A (en) | Method for recommending search terms and searching method and device | |
CN105607830B (en) | A kind of terminal screenshot method, device and terminal | |
CN109543113B (en) | Method and device for determining click recommendation words, storage medium and electronic equipment | |
CN104410563A (en) | Information push method and wireless device | |
CN109388693A (en) | A kind of method and relevant device of determining subregion intention | |
US10055496B2 (en) | Cuisine search device, cuisine search method, program, and computer-readable storage medium | |
CN105630953B (en) | The method and apparatus of mobile search client displaying news | |
CN109726632A (en) | Background recommended method and Related product | |
JP7351782B2 (en) | Information processing system, information processing device, information processing method and program | |
CN107562954A (en) | Recommendation searching method, device and mobile terminal based on mobile terminal | |
CN104765864B (en) | The output intent and client and server of search result | |
CN111488434B (en) | Recommendation method and device for input associative words, storage medium and electronic equipment | |
CN105512341B (en) | Personalized recommendation method and system based on big data search | |
WO2021056829A1 (en) | Menu comparison method and apparatus, and computer storage medium | |
CN105117935B (en) | The implementation method and device of intelligent collocation dress ornament |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |
|
RJ01 | Rejection of invention patent application after publication |