CN108170293A - Input the personalized recommendation method and device of association - Google Patents
Input the personalized recommendation method and device of association Download PDFInfo
- Publication number
- CN108170293A CN108170293A CN201711489711.XA CN201711489711A CN108170293A CN 108170293 A CN108170293 A CN 108170293A CN 201711489711 A CN201711489711 A CN 201711489711A CN 108170293 A CN108170293 A CN 108170293A
- Authority
- CN
- China
- Prior art keywords
- input
- user
- search
- association
- input association
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
-
- 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)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of personalized recommendation method and device for inputting association, this method includes：By receiving search query input by user, identify the type of current search query, when analyzing the Pinyin information in the part or all of phonetic hit input association Candidate Set of current search query, associate candidate word using the historical search word corresponding to the Pinyin information of hit as input, the personalized recommendation of input association is carried out, improves the efficiency of the personalized recommendation method of input association.User does not need to Manual Override search term and is re-searched for can accurately expecting suitable search term to express search intention yet, and then can improve the accuracy of the personalized recommendation method of input association.Further combined with existing input association model, the searching cost of user can be reduced, user is helped quickly and easily to find search result, the export effect of entire search box is improved, can further promote search experience.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of personalized recommendation method and dress for inputting association
It puts.
Background technology
With the rapid development of network, nowadays people increasingly like by search engine come search for some for learn or
Oneself interested data.During existing search engine is used, when user is when being manually entered, such as input Pinyin mistake
When, after search result is clicked, any recommendation word is shown on the page, at this point, user needs Manual Override search term to carry out again
Search if user has the query that high frequency needs repeat search, such as official website addressing, audio-visual video, is required for Xu such as complete every time
Phonetic byte, user can not accurately expect suitable search term to express search intention, and existing input association is caused to push away
Recommending method, there are the defects of efficiency is low, accuracy is low and input is of high cost.
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
State the personalized recommendation method and device of the input association of problem.
One side according to the present invention provides a kind of personalized recommendation method for inputting association, including：
Receive search query input by user, the type of identification current search query；
If identification obtains current search query as phonetic type, preset input association Candidate Set is obtained, wherein, it is described
Input association Candidate Set includes user's history search term and corresponding Pinyin information；
Analyze the Pinyin information in the part or all of phonetic hit input association Candidate Set of current search query
When, associate candidate word using the historical search word corresponding to the Pinyin information of hit as input, carry out the personalization of input association
Recommend.
Optionally, the historical search word corresponding to the Pinyin information using hit associates candidate word as input, carries out
The personalized recommendation of association is inputted, including：
According to described search query, the preset quantity of described search query is obtained from existing input association recommended models
Input association candidate word；
The historical search word corresponding to the Pinyin information of candidate word and hit is associated in the input of preset quantity to getting
Unified sequence is carried out, ranking results as input are associated and carry out personalized recommendation.
Optionally, the input of the described pair of preset quantity got is associated corresponding to the Pinyin information of candidate word and hit
Historical search word carries out unified sequence, including：
According to the priority level of the historical search word corresponding to the Pinyin information of the hit higher than the preset quantity
The sequence of the priority level of input association candidate word carries out unified sequence.
Optionally, the method further includes：
User's search behavior daily record in network is excavated, hot spot candidate word is extracted from user's search behavior daily record,
Generate existing input association candidate family.
Optionally, the method further includes：
User's history search record is obtained, user's history search term is extracted from user's history search record；
The user's history search term of extraction is translated, obtains the corresponding Pinyin information of user's history search term；
According to the correspondence between the user's history search term and the Pinyin information translated to it, establish
Input association Candidate Set.
Optionally, if this method is applied to browser, the acquisition user's history search records, including：
The user's history search record of its record is obtained from the Local Storage of browser.
Optionally, the method further includes：The input association Candidate Set of foundation is stored in browser local.
Optionally, the Pinyin information in the part phonetic hit of the analysis current search query input association Candidate Set,
Including：
The prefix of current search query is obtained, wherein, the prefix includes at least one since phonetic initial position
Complete Pinyin field, a complete Pinyin field correspond to a Chinese character；
By the spelling corresponding with each user's history search term inputted in association's Candidate Set of the phonetic prefix of the query
The prefix of message breath carries out prefix matching；
If there are the consistent Pinyin information of prefix matching in input association Candidate Set, the current search query's
Pinyin information in the part phonetic hit input association Candidate Set.
Optionally, the Pinyin information in the part phonetic hit of the analysis current search query input association Candidate Set,
Including：
Multiple complete Pinyin fields in the phonetic of described search query are obtained, wherein, a complete Pinyin field corresponds to
One Chinese character；
Multiple complete Pinyin fields of acquisition are corresponding with each user's history search term that the input is associated in Candidate Set
Pinyin information matched；
If there is the specified quantity with described search query in the corresponding Pinyin information of at least one user's history search term
The phonetic field that matches of complete Pinyin field, the part phonetic hit input association of the current search query waits
Pinyin information in selected works.
Optionally, the Pinyin information in whole phonetics hit of analysis current search query input association Candidate Set,
Including：
By the spelling corresponding with each user's history search term inputted in association's Candidate Set of the phonetic of described search query
Message breath is matched；
If whole phonetics of described search query Pinyin information phase corresponding at least one user's history search term
Match, the Pinyin information in whole phonetics hit input association Candidate Set of the current search query.
Optionally, the method further includes：
If it is not phonetic type that identification, which obtains current search query, preset input association Candidate Set is obtained；
Whether the part or all of keyword of analysis current search query hits the history in input association Candidate Set
Search term if so, associating candidate word using the historical search word of hit as input, carries out the personalized recommendation of input association.
Another aspect according to the present invention provides a kind of personalized recommendation device for inputting association, including：
Identification module, suitable for receiving search query input by user, the type of identification current search query；
If obtaining current search query as phonetic type suitable for identification, it is candidate to obtain preset input association for acquisition module
Collection, wherein, input association Candidate Set includes user's history search term and corresponding Pinyin information；
Recommending module, suitable for analyzing the part or all of phonetic of the current search query hit input association Candidate Set
In Pinyin information when, using the historical search word corresponding to the Pinyin information of hit as input associate candidate word, inputted
The personalized recommendation of association.
Optionally, the recommending module is further adapted for：
According to described search query, the preset quantity of described search query is obtained from existing input association recommended models
Input association candidate word；
The historical search word corresponding to the Pinyin information of candidate word and hit is associated in the input of preset quantity to getting
Unified sequence is carried out, ranking results as input are associated and carry out personalized recommendation.
Optionally, the recommending module is further adapted for：
According to the priority level of the historical search word corresponding to the Pinyin information of the hit, higher than the preset quantity
The sequence of the priority level of input association candidate word carries out unified sequence.
Optionally, described device further includes：
Generation module suitable for excavating user's search behavior daily record in network, is carried from user's search behavior daily record
Hot spot candidate word is taken, generates existing input association candidate family.
Optionally, described device, which further includes, establishes module, is suitable for：
User's history search record is obtained, user's history search term is extracted from user's history search record；
The user's history search term of extraction is translated, obtains the corresponding Pinyin information of user's history search term；
According to the correspondence between the user's history search term and the Pinyin information translated to it, establish
Input association Candidate Set.
Optionally, if the device is applied to browser, the module of establishing is further adapted for：
The user's history search record of its record is obtained from the Local Storage of browser.
Optionally, memory module is further included, is suitable for：
The input association Candidate Set of foundation is stored in browser local.
Optionally, the recommending module is further adapted for：
The prefix of current search query is obtained, wherein, the prefix includes at least one since phonetic initial position
Complete Pinyin field, a complete Pinyin field correspond to a Chinese character；
By the spelling corresponding with each user's history search term inputted in association's Candidate Set of the phonetic prefix of the query
The prefix of message breath carries out prefix matching；
If there are the consistent Pinyin information of prefix matching in input association Candidate Set, the current search query's
Pinyin information in the part phonetic hit input association Candidate Set.
Optionally, the recommending module is further adapted for：
Multiple complete Pinyin fields in the phonetic of described search query are obtained, wherein, a complete Pinyin field corresponds to
One Chinese character；
Multiple complete Pinyin fields of acquisition are corresponding with each user's history search term that the input is associated in Candidate Set
Pinyin information matched；
If there is the specified quantity with described search query in the corresponding Pinyin information of at least one user's history search term
The phonetic field that matches of complete Pinyin field, the part phonetic hit input association of the current search query waits
Pinyin information in selected works.
Optionally, the recommending module is further adapted for：
By the spelling corresponding with each user's history search term inputted in association's Candidate Set of the phonetic of described search query
Message breath is matched；
If whole phonetics of described search query Pinyin information phase corresponding at least one user's history search term
Match, the Pinyin information in whole phonetics hit input association Candidate Set of the current search query.
Optionally, the acquisition module is further adapted for：If it is not phonetic type that identification, which obtains current search query, obtain pre-
The input association Candidate Set put；
The recommending module is further adapted for：It is described defeated whether the part or all of keyword of analysis current search query hits
Enter the historical search word in association's Candidate Set, if so, associating candidate word using the historical search word of hit as input, inputted
The personalized recommendation of association.
According to the present invention in another aspect, a kind of computer program is additionally provided, including computer-readable code, when described
When computer-readable code is run on the computing device, the computing device is caused to perform the input described in any embodiment above
Associate personalized recommendation method.
Another aspect according to the present invention, additionally provides a kind of computer-readable medium, wherein storing as described above
Computer program.
In embodiments of the present invention, first, by receiving search query input by user, identification current search query's
Type, then, the Pinyin information in the part or all of phonetic hit input association Candidate Set of analysis current search query
When, associate candidate word using the historical search word corresponding to the Pinyin information of hit as input, carry out the personalization of input association
Recommend, improve the efficiency of the personalized recommendation method of input association.User does not need to Manual Override search term and is searched again
Rope also can accurately expect suitable search term to express search intention, and then can improve the personalized recommendation of input association
The accuracy of method.Further combined with existing input association model, the searching cost of user can be reduced, helps user quick
Search result is easily found, improves the export effect of entire search box to a certain extent, can further promote search
Experience.
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.
According to the accompanying drawings to the detailed description of the specific embodiment of the invention, those skilled in the art will be brighter
The above and other objects, advantages and features of 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 the flow diagram of the personalized recommendation method of input association according to an embodiment of the invention；
Fig. 2 shows user's histories in the personalized recommendation method of input association according to an embodiment of the invention to search for
In the corresponding Pinyin information of word with the part phonetic hit situation schematic diagram of current search query；
Fig. 3 a show that the input of the recommendation method using existing input association thinks that Candidate Set exports schematic diagram；
Fig. 3 b show that candidate is thought in the input of the personalized recommendation method of input association according to an embodiment of the invention
Collection export schematic diagram；
Fig. 4 shows the structure diagram of the personalized recommendation device of input association according to an embodiment of the invention；
Fig. 5 shows that the structure of the personalized recommendation device of another input association according to an embodiment of the invention is shown
It is intended to；
Fig. 6 shows to perform the frame of the computing device of personalized recommendation method that input according to the present invention is associated
Figure；And
Fig. 7 shows the journey for keeping or carrying the personalized recommendation method for realizing input association according to the present invention
The storage unit of sequence code.
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.
In order to solve the above technical problems, an embodiment of the present invention provides a kind of personalized recommendation methods for inputting association.Fig. 1
Show the flow diagram of the personalized recommendation method of input association according to an embodiment of the invention.Referring to Fig. 1, the party
Method includes at least step S102 to step S106.
Step S102 receives search query input by user, the type of identification current search query.
In this step, the type for searching for query can be phonetic, or Chinese character.
Wherein, search query can be partial or complete phonetic field or partial or complete Chinese Character
Section.Such as：" qinghuadaxue "/" qinghua ", " Tsinghua University "/" Tsing-Hua University " etc..In this embodiment, it is cited not
The search query of same type is only schematical, and search query types mentioned in this article can also be other search
Query types, the embodiment of the present invention are not specifically limited this.
Step S104 if identification obtains current search query as phonetic type, obtains preset input association Candidate Set,
Wherein, input association Candidate Set includes user's history search term and corresponding Pinyin information.
In this step, it has pre-defined by user's history search term and there is one-to-one correspondence with the user's history search term
The input association Candidate Set that the pinyin combinations of relationship form.Wherein, input association Candidate Set is shown by way of Chinese character.
Phonetic in the part or all of phonetic hit input association Candidate Set of step S106, analysis current search query
During information, candidate word is associated using the historical search word corresponding to the Pinyin information of hit as input, carry out of input association
Propertyization is recommended.
Such as：When current search query is " qinghuadaxue " or " qinghua ", all by " qinghuadaxue " or
As input association candidate word, the personalization for carrying out input association pushes away " qinghua " corresponding historical search word " Tsinghua University "
It recommends.Therefore, the embodiment of the present invention is by receiving search query input by user, the type of identification current search query, analysis
When the Pinyin information in Candidate Set is associated in the part or all of phonetic hit input of current search query, by the spelling of hit
The corresponding historical search word of message breath carries out the personalized recommendation of input association, improves defeated as input association candidate word
Enter the efficiency of the personalized recommendation method of association.User does not need to that Manual Override search term re-searched for also can be accurately
Suitable search term is expected to express search intention, so as to improve the accuracy of the personalized recommendation method of input association.
The embodiment of the present invention can reduce the searching cost of user, help further combined with existing input association model
User quickly and easily finds search result, can promote the export effect of entire search box, further improve search experience.
Step S102 is seen above, in an embodiment of the present invention, is receiving search query input by user, identification is worked as
Before the type of preceding search query, preset input association Candidate Set is had built up.Wherein, preset input association Candidate Set
It can establish in the following way：
First, user's history search record is obtained, user's history search term is extracted from user's history search record；
Secondly, the user's history search term of extraction is translated, obtains the corresponding Pinyin information of user's history search term；
Finally, it according to the correspondence between user's history search term and the Pinyin information translated to it, builds
Vertical input association Candidate Set.
Wherein, if this method is applied to browser, the user that its record is obtained from the Local Storage of browser goes through
The input association Candidate Set of foundation is simultaneously stored in browser local by history search record.
Step S104 is seen above, is not phonetic class when identification obtains current search query in an embodiment of the present invention
During type, preset input association Candidate Set is also obtained.
Step S106 is seen above, in an embodiment of the present invention, following manner analysis current search query may be used
Part phonetic hit input association Candidate Set in Pinyin information：
First, the prefix of current search query is obtained, wherein, prefix includes at least one since phonetic initial position
A complete Pinyin field, a complete Pinyin field correspond to a Chinese character；
Then, by the phonetic prefix of query phonetic corresponding with inputting each user's history search term in association's Candidate Set
The prefix of information carries out prefix matching；
Finally, if there are the consistent Pinyin information of prefix matching, the parts of current search query in input association Candidate Set
Pinyin information in phonetic hit input association Candidate Set.
In an embodiment of the present invention, in the part phonetic hit input association Candidate Set of analysis current search query
Pinyin information further comprises following steps：
Multiple complete Pinyin fields in the phonetic of search query are obtained, wherein, a complete Pinyin field corresponds to one
Chinese character；
By the spelling corresponding with inputting each user's history search term in association's Candidate Set of multiple complete Pinyin fields of acquisition
Message breath is matched；
If exist in the corresponding Pinyin information of at least one user's history search term with searching for the complete of the specified quantity of query
The phonetic in Candidate Set is associated in the phonetic field that whole phonetic field matches, the part phonetic hit input of current search query
Information.
In a specific embodiment, exist with reference to figure 2, in the corresponding Pinyin information of user's history search term and " Tsing-Hua University
The corresponding phonetic of university " " qinghuadaxue " when it is " qinghua " to search for query, then represents current search query's
Pinyin information in part phonetic hit input association Candidate Set.
Step S106 is seen above, in an embodiment of the present invention, following manner analysis current search query may be used
Whole phonetics hit input association Candidate Set in Pinyin information：
The phonetic of query will be searched for input and associated the corresponding Pinyin information of each user's history search term in Candidate Set into
Row matching；
If whole phonetics Pinyin information corresponding at least one user's history search term of search query matches, when
Pinyin information in whole phonetics hit input association Candidate Set of preceding search query.
In a specific embodiment, exist in the corresponding Pinyin information of user's history search term corresponding with " charger baby "
Phonetic " chongdianbao ", when it is " chongdianbao " to search for query, then the part for representing current search query is spelled
Pinyin information in sound hit input association Candidate Set.
Step S106 is seen above, in an embodiment of the present invention, that following manner carries out input association may be used
Propertyization is recommended：
First, according to search query, the preset quantity of search query is obtained from existing input association recommended models
Input association candidate word；
Then, input association's candidate word of the preset quantity to getting is searched with the history corresponding to the Pinyin information of hit
Rope word carries out unified sequence, and ranking results as input are associated and carry out personalized recommendation.
In an embodiment of the present invention, following manner may be used, candidate word is associated to the input of preset quantity got
Unified sequence is carried out with the historical search word corresponding to the Pinyin information of hit：
Associate according to the priority level of the historical search word corresponding to the Pinyin information of hit, the input higher than preset quantity
The sequence of the priority level of candidate word carries out unified sequence.
In an embodiment of the present invention, according to the priority level of the historical search word corresponding to the Pinyin information of hit, height
Unified sort is carried out in the sequence of the priority level of the input association candidate word of preset quantity, and following manner realization may be used：
It is excellent higher than the input association candidate word of preset quantity according to the priority level of user's history search term got
The sequence of first rank carries out the first minor sort；
For first time ranking results, the sequence of positions of the input association candidate word of wherein preset quantity is remained unchanged,
And the second minor sort is carried out according to the sequence that historical search number successively decreases to user's history search term therein, by the second minor sort
As a result recommended as input association.
Wherein, the height of user's history search term priority level is related to the number of its searching times, and searching times are more,
Its priority is higher.
In a specific embodiment, the input association that preset quantity is preserved in the Local Storage of browser waits
Select word：" lover's prattle ", " Tsinghua University ", " Tsing-Hua University ", " blue and white porcelain " and " the blue and white porcelain lyrics " etc., user pass through input for the first time
" qinghua " after preset input association's candidate word " Tsing-Hua University " is selected to scan for, passes twice through input " qinghua " respectively,
Preset input association's candidate word " Tsinghua University " is selected to scan for, at this point, candidate word " Tsing-Hua University " is associated in input and " Tsing-Hua University is big
Learn " become user's history search term.With reference to figure 3a, wherein, Fig. 3 a are the input using the recommendation method of existing input association
Think that Candidate Set exports schematic diagram.Wherein, to the row of " lover's prattle ", " Tsinghua University ", " Tsing-Hua University ", " blue and white porcelain " and " the blue and white porcelain lyrics "
Program process is as follows：
First, " lover's prattle ", " Tsinghua University ", " Tsing-Hua University ", " blue and white porcelain " and " the blue and white porcelain lyrics " is integrally ranked up, by
Belong to user's history search term in " lover's prattle ", " Tsinghua University ", priority level is higher than " lover's prattle ", " blue and white porcelain " and " blue and white porcelain
Candidate word is associated in the inputs such as the lyrics ", so " Tsing-Hua University " and " Tsinghua University " comes " lover's prattle ", " blue and white porcelain " and " the blue and white porcelain lyrics "
It waits before inputs association candidate word；
Then, then to user's history search term " Tsing-Hua University " and " Tsinghua University " it is ranked up by searching times, due to " Tsing-Hua University
The searching times of university " are more than " Tsing-Hua University ", so " Tsinghua University " is come before " Tsing-Hua University ".
So by two minor sorts, final ranking results are " Tsinghua University ", " Tsing-Hua University ", lover's prattle ", it is " blue and white porcelain " and " green
The flower porcelain lyrics ".Wherein, specific ranking results can refer to Fig. 3 b, wherein, Fig. 3 b are to be joined according to the input of one embodiment of the invention
The input for the personalized recommendation method thought thinks that Candidate Set exports schematic diagram.
In an embodiment of the present invention, this method further includes：User's search behavior daily record in network is excavated, is searched from user
Hot spot candidate word is extracted in rope user behaviors log, generates existing input association candidate family.
In a specific embodiment, when many network users search for film popular in the recent period by search engine《Fragrant China》
When, user's search behavior daily record " film virtue China " is excavated, when other network users input search query by search engine
When " fanghua ", " virtue China " shows as hot spot candidate word, and as input association candidate word " virtue China film ".
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of personalized recommendation device for inputting association, Fig. 4
Show the structure diagram of the personalized recommendation device of input association according to an embodiment of the invention.Referring to Fig. 4, input
The personalized recommendation device 400 of association can at least include identification module 410, acquisition module 420 and recommending module 430.
Now introduce each composition of the personalized recommendation device 400 of the input association of the embodiment of the present invention or the function of device with
And the connection relation between each section：
Identification module 410, suitable for receiving search query input by user, the type of identification current search query；
Acquisition module 420 is coupled with identification module 410, if obtaining current search query as phonetic type suitable for identification,
Preset input association Candidate Set is obtained, wherein, input association Candidate Set includes user's history search term and corresponding phonetic is believed
Breath；
Recommending module 430 is coupled with acquisition module 420, suitable for analyzing the part or all of phonetic of current search query life
When the Pinyin information in Candidate Set is associated in middle input, associate the historical search word corresponding to the Pinyin information of hit as input
Candidate word carries out the personalized recommendation of input association.
In an embodiment of the present invention, recommending module 430 is further adapted for, and according to search query, recommends from existing input association
The input association candidate word of the preset quantity of search query is obtained in model.
In an embodiment of the present invention, recommending module 430 is further adapted for, and is searched according to the history corresponding to the Pinyin information of hit
The priority level of rope word, the sequence higher than the priority level of the input association candidate word of preset quantity carry out unified sequence.
The embodiment of the present invention additionally provides the personalized recommendation device of another input association, and Fig. 5 is shown according to this hair
Another structure diagram of the personalized recommendation device of the input association of bright one embodiment.Referring to Fig. 5, of association is inputted
Property recommendation apparatus 400 further includes generation module 440, establishes module 450 and memory module other than comprising above-mentioned module
460.Wherein,
Generation module 440 is coupled with recommending module 430, suitable for excavating user's search behavior daily record in network, from user
Hot spot candidate word is extracted in search behavior daily record, generates existing input association candidate family.
Module 450 is established, is coupled with generation module 440, suitable for obtaining user's history search record, is searched for from user's history
User's history search term is extracted in record, the user's history search term of extraction is translated, obtains user's history search term pair
The Pinyin information answered according to the correspondence between user's history search term and the Pinyin information translated to it, is built
Vertical input association Candidate Set.
In an embodiment of the present invention, if the device is applied to browser, module 450 is established, is further adapted for from browser
The user's history search record of its record is obtained in Local Storage.
Memory module 460 is coupled with establishing module 450, and the input association Candidate Set of foundation is stored in browser local.
In an embodiment of the invention, recommending module 430 is further adapted for, and obtains the prefix of current search query, wherein,
Prefix includes at least one complete Pinyin field since phonetic initial position, and a complete Pinyin field corresponds to a Chinese
Word, by the prefix of the phonetic prefix of query Pinyin information corresponding with inputting each user's history search term in association's Candidate Set
Prefix matching is carried out, if there are the consistent Pinyin information of prefix matching, the parts of current search query in input association Candidate Set
Pinyin information in phonetic hit input association Candidate Set.
In an embodiment of the invention, recommending module 430 is further adapted for, and obtains multiple complete in the phonetic of search query
Whole phonetic field, wherein, a complete Pinyin field corresponds to a Chinese character, and multiple complete Pinyin fields of acquisition and input are joined
Think that the corresponding Pinyin information of each user's history search term in Candidate Set is matched, if at least one user's history search term pair
There is the phonetic field to match with searching for the complete Pinyin field of the specified quantity of query in the Pinyin information answered, currently search
Pinyin information in the part phonetic hit input association Candidate Set of rope query.
In an embodiment of the invention, recommending module 430 is further adapted for, and the phonetic for searching for query and input association are waited
The corresponding Pinyin information of each user's history search term in selected works is matched, if whole phonetics and at least one of search query
The corresponding Pinyin information of a user's history search term matches, and whole phonetics hit input association of current search query is candidate
The Pinyin information of concentration.
In an embodiment of the invention, acquisition module 420 are further adapted for, if it is not to spell that identification, which obtains current search query,
Sound type obtains preset input association Candidate Set.
In an embodiment of the invention, recommending module 430 are further adapted for, and analysis current search query's is part or all of
Whether keyword hits the historical search word in input association Candidate Set, if so, joining the historical search word of hit as input
Think candidate word, carry out the personalized recommendation of input association.
The embodiment of the present invention additionally provides a kind of computer program, including computer-readable code, when computer-readable generation
When code is run on the computing device, computing device is caused to perform the personalized recommendation side of the input association of any embodiment above
Method.
The embodiment of the present invention additionally provides a kind of computer-readable medium, wherein storing computer journey as mentioned in the above
Sequence.
According to the combination of any one above-mentioned preferred embodiment or multiple preferred embodiments, the embodiment of the present invention can reach
Following advantageous effect：
In embodiments of the present invention, by receiving search query input by user, the type of identification current search query,
Then, associate candidate word using the historical search word corresponding to the Pinyin information of hit as input, carry out the individual character of input association
Change and recommend, improve the efficiency of the personalized recommendation method of input association.User does not need to Manual Override search term and carries out again
Search also can accurately expect suitable search term to express search intention, so as to improve the personalized recommendation of input association
The accuracy of method.Further combined with existing input association model, the searching cost of user can be reduced, helps user quick
Search result is easily found, the export effect of entire search box can be promoted, further improve search experience.
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 detail in the claims, embodiment claimed it is one of arbitrary
It 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 the personalized recommendation dress of input association according to embodiments of the present invention
The some or all functions of some or all components in putting.The present invention is also implemented as described here for performing
Some or all equipment of method or program of device (for example, computer program and computer program product).This
The program of the realization present invention of sample can may be stored on the computer-readable medium or can have one or more signal
Form.Such signal can be downloaded from internet website to be obtained either providing or with any other on carrier signal
Form provides.
For example, Fig. 6 shows the block diagram of the computing device for the personalized recommendation method that can realize input association.The calculating
Equipment conventionally comprises the computer program product or computer-readable medium of 620 form of processor 610 and memory.Storage
Device 620 can be such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or ROM etc
Electronic memory.Memory 620 has storage for performing depositing for the program code 631 of any method and step in the above method
Storage sky 630.For example, the memory space 630 of storage program code can be various in above method including being respectively used to realize
Each program code 631 of step.These program codes can be read from one or more computer program product or
It is written in this one or more computer program product.These computer program products include such as hard disk, compact-disc
(CD), the program code carrier of storage card or floppy disk etc.Such computer program product is usually for example shown in Fig. 7
Portable or static memory cell.The storage unit can have and 620 similar arrangement of memory in the computing device of Fig. 6
Memory paragraph, memory space etc..Program code can for example be compressed in a suitable form.In general, storage unit includes being used for
Perform the computer-readable code 631 ' of the method and step of the present invention, you can with the generation read by such as 610 etc processor
Code when these codes are run by computing device, causes the computing device to perform each step in method described above.
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.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of personalized recommendation method for inputting association, including：
Receive search query input by user, the type of identification current search query；
If identification obtains current search query as phonetic type, preset input association Candidate Set is obtained, wherein, the input
Associate Candidate Set and include user's history search term and corresponding Pinyin information；
It, will when analyzing the Pinyin information in the part or all of phonetic hit input association Candidate Set of current search query
Historical search word corresponding to the Pinyin information of hit carries out the personalized recommendation of input association as input association candidate word.
2. according to the method described in claim 1, wherein, historical search word corresponding to the Pinyin information using hit as
Input association candidate word carries out the personalized recommendation of input association, including：
According to described search query, the preset quantity of acquisition described search query is defeated from existing input association recommended models
Enter association's candidate word；
Input association's candidate word of preset quantity to getting is carried out with the historical search word corresponding to the Pinyin information of hit
Unified sequence, ranking results as input are associated and carry out personalized recommendation.
3. method according to claim 1 or 2, wherein, the input association candidate word of the described pair of preset quantity got
Unified sequence is carried out with the historical search word corresponding to the Pinyin information of hit, including：
It is higher than the input of the preset quantity according to the priority level of the historical search word corresponding to the Pinyin information of the hit
The sequence for associating the priority level of candidate word carries out unified sequence.
4. according to claim 1-3 any one of them methods, wherein, it further includes：
User's search behavior daily record in network is excavated, hot spot candidate word, generation are extracted from user's search behavior daily record
Existing input association candidate family.
5. according to claim 1-4 any one of them methods, wherein, it further includes：
User's history search record is obtained, user's history search term is extracted from user's history search record；
The user's history search term of extraction is translated, obtains the corresponding Pinyin information of user's history search term；
According to the correspondence between the user's history search term and the Pinyin information translated to it, described in foundation
Input association Candidate Set.
6. according to claim 1-5 any one of them methods, wherein, if this method is applied to browser, the acquisition user
Historical search records, including：
The user's history search record of its record is obtained from the Local Storage of browser.
7. according to claim 1-6 any one of them methods, wherein, it further includes：Candidate Set is associated into the input of foundation
It is stored in browser local.
8. a kind of personalized recommendation device for inputting association, including：
Identification module, suitable for receiving search query input by user, the type of identification current search query；
Acquisition module if obtaining current search query as phonetic type suitable for identification, obtains preset input association Candidate Set,
Wherein, input association Candidate Set includes user's history search term and corresponding Pinyin information；
Recommending module, suitable for analyzing in the part or all of phonetic of the current search query hit input association Candidate Set
During Pinyin information, associate candidate word using the historical search word corresponding to the Pinyin information of hit as input, carry out input association
Personalized recommendation.
9. a kind of electronic equipment, including：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the processor when executed
Perform the personalized recommendation method according to claim 1-7 any one of them input association.
10. a kind of computer storage media, wherein, the one or more programs of computer storage media storage are one
Or multiple programs by the electronic equipment including multiple application programs when being performed so that the electronic equipment is performed will according to right
Seek the personalized recommendation method of 1-7 any one of them input association.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711489711.XA CN108170293A (en) | 2017-12-29 | 2017-12-29 | Input the personalized recommendation method and device of association |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711489711.XA CN108170293A (en) | 2017-12-29 | 2017-12-29 | Input the personalized recommendation method and device of association |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108170293A true CN108170293A (en) | 2018-06-15 |
Family
ID=62516728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711489711.XA Pending CN108170293A (en) | 2017-12-29 | 2017-12-29 | Input the personalized recommendation method and device of association |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108170293A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108983995A (en) * | 2018-06-19 | 2018-12-11 | 深圳市元征科技股份有限公司 | Information association method, device, terminal and medium |
| CN109446407A (en) * | 2018-09-18 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Correlation recommendation method, apparatus, computer equipment and storage medium |
| CN109491516A (en) * | 2018-11-02 | 2019-03-19 | 北京字节跳动网络技术有限公司 | Input display methods, device, storage medium and the electronic equipment of associational word |
| CN109582847A (en) * | 2018-11-23 | 2019-04-05 | 咪咕视讯科技有限公司 | A kind of information processing method and device, storage medium |
| CN109582155A (en) * | 2018-11-23 | 2019-04-05 | 北京字节跳动网络技术有限公司 | Input recommended method, device, storage medium and the electronic equipment of associational word |
| CN111274502A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Search ranking method and device, computer equipment and storage medium |
| CN112307183A (en) * | 2020-10-30 | 2021-02-02 | 北京金堤征信服务有限公司 | Search data identification method and device, electronic equipment and computer storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100088303A1 (en) * | 2008-10-03 | 2010-04-08 | Microsoft Corporation | Mining new words from a query log for input method editors |
| CN102681987A (en) * | 2011-03-07 | 2012-09-19 | 北京无限讯奇信息技术有限公司 | Convenient index solution for mobile phone search |
| CN103186615A (en) * | 2011-12-30 | 2013-07-03 | 北大方正集团有限公司 | Search prompting method and system |
| CN103365833A (en) * | 2012-03-28 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Context scene based candidate word input prompt method and system for implementing same |
| CN103678675A (en) * | 2013-12-25 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Method, server and system for achieving searching through Pinyin |
| CN104143001A (en) * | 2014-08-01 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Search term recommending method and device |
| CN104199954A (en) * | 2012-06-26 | 2014-12-10 | 北京奇虎科技有限公司 | Recommendation system and method for search input |
| CN105824833A (en) * | 2015-01-07 | 2016-08-03 | 苏宁云商集团股份有限公司 | Keyword recommendation method and system based on user behavior feedback |
| CN106919703A (en) * | 2017-03-09 | 2017-07-04 | 北京微影时代科技有限公司 | Film information searching method and device |
| CN107273537A (en) * | 2017-06-30 | 2017-10-20 | 深圳创维数字技术有限公司 | One kind search words recommending method, set top box and storage medium |
| CN107273457A (en) * | 2017-06-01 | 2017-10-20 | 珠海市魅族科技有限公司 | A kind of searching method and device, computer installation and computer-readable recording medium |
-
2017
- 2017-12-29 CN CN201711489711.XA patent/CN108170293A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100088303A1 (en) * | 2008-10-03 | 2010-04-08 | Microsoft Corporation | Mining new words from a query log for input method editors |
| CN102681987A (en) * | 2011-03-07 | 2012-09-19 | 北京无限讯奇信息技术有限公司 | Convenient index solution for mobile phone search |
| CN103186615A (en) * | 2011-12-30 | 2013-07-03 | 北大方正集团有限公司 | Search prompting method and system |
| CN103365833A (en) * | 2012-03-28 | 2013-10-23 | 百度在线网络技术（北京）有限公司 | Context scene based candidate word input prompt method and system for implementing same |
| CN104199954A (en) * | 2012-06-26 | 2014-12-10 | 北京奇虎科技有限公司 | Recommendation system and method for search input |
| CN103678675A (en) * | 2013-12-25 | 2014-03-26 | 乐视网信息技术（北京）股份有限公司 | Method, server and system for achieving searching through Pinyin |
| CN104143001A (en) * | 2014-08-01 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Search term recommending method and device |
| CN105824833A (en) * | 2015-01-07 | 2016-08-03 | 苏宁云商集团股份有限公司 | Keyword recommendation method and system based on user behavior feedback |
| CN106919703A (en) * | 2017-03-09 | 2017-07-04 | 北京微影时代科技有限公司 | Film information searching method and device |
| CN107273457A (en) * | 2017-06-01 | 2017-10-20 | 珠海市魅族科技有限公司 | A kind of searching method and device, computer installation and computer-readable recording medium |
| CN107273537A (en) * | 2017-06-30 | 2017-10-20 | 深圳创维数字技术有限公司 | One kind search words recommending method, set top box and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 刘佳奇: "酒店订购平台搜索***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108983995A (en) * | 2018-06-19 | 2018-12-11 | 深圳市元征科技股份有限公司 | Information association method, device, terminal and medium |
| CN108983995B (en) * | 2018-06-19 | 2022-05-13 | 深圳市元征科技股份有限公司 | Information association method, device, terminal and medium |
| CN109446407A (en) * | 2018-09-18 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Correlation recommendation method, apparatus, computer equipment and storage medium |
| CN109491516A (en) * | 2018-11-02 | 2019-03-19 | 北京字节跳动网络技术有限公司 | Input display methods, device, storage medium and the electronic equipment of associational word |
| CN109582847A (en) * | 2018-11-23 | 2019-04-05 | 咪咕视讯科技有限公司 | A kind of information processing method and device, storage medium |
| CN109582155A (en) * | 2018-11-23 | 2019-04-05 | 北京字节跳动网络技术有限公司 | Input recommended method, device, storage medium and the electronic equipment of associational word |
| CN109582847B (en) * | 2018-11-23 | 2021-08-24 | 咪咕视讯科技有限公司 | Information processing method and device and storage medium |
| CN111274502A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Search ranking method and device, computer equipment and storage medium |
| CN112307183A (en) * | 2020-10-30 | 2021-02-02 | 北京金堤征信服务有限公司 | Search data identification method and device, electronic equipment and computer storage medium |
| CN112307183B (en) * | 2020-10-30 | 2024-04-19 | 北京金堤征信服务有限公司 | Search data identification method, apparatus, electronic device and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108227955A (en) | It is a kind of that the method and device for recommending input association is searched for based on user's history | |
| CN108170293A (en) | Input the personalized recommendation method and device of association | |
| US10051030B2 (en) | Interactive searching and recommanding method and apparatus | |
| CN103514299B (en) | Information search method and device | |
| CN106815192B (en) | Model training method and device and sentence emotion recognition method and device | |
| CN104050286B (en) | Method and device for providing search result integration | |
| CN110019616B (en) | POI (Point of interest) situation acquisition method and equipment, storage medium and server thereof | |
| CN108227954A (en) | A kind of method, apparatus and electronic equipment that search input associational word is provided | |
| CN109300059B (en) | Dish recommending method and device | |
| CN104077388A (en) | Summary information extraction method and device based on search engine and search engine | |
| CN106021449A (en) | Searching method and device for mobile terminal and mobile terminal | |
| CN104537057B (en) | Data search method and client | |
| CN105786875B (en) | Question and answer are provided to the method and apparatus of data search result | |
| CN108255999A (en) | Content recommendation method and device | |
| CN104699845B (en) | Method and device is provided based on the Search Results puing question to class search word | |
| CN111291210A (en) | Image material library generation method, image material recommendation method and related device | |
| CN104063476A (en) | Social network-based content recommending method and system | |
| CN110968998B (en) | Intelligent prediction input method and system | |
| CN107807957A (en) | entity library generating method and device | |
| CN103488787B (en) | A kind of method for pushing and device of the online broadcasting entrance object based on video search | |
| CN103559313B (en) | Searching method and device | |
| CN105224614A (en) | Application program classification display method and device | |
| CN108108465A (en) | A kind of method and apparatus for pushing recommendation | |
| CN108197243A (en) | Method and device is recommended in a kind of input association based on user identity | |
| CN104462504A (en) | Method and device for providing reasoning process data in search |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |