CN105607756A - Information recommendation method and device - Google Patents

Information recommendation method and device Download PDF

Info

Publication number
CN105607756A
CN105607756A CN201510984623.1A CN201510984623A CN105607756A CN 105607756 A CN105607756 A CN 105607756A CN 201510984623 A CN201510984623 A CN 201510984623A CN 105607756 A CN105607756 A CN 105607756A
Authority
CN
China
Prior art keywords
recommendation
content
information
input
content recommendation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510984623.1A
Other languages
Chinese (zh)
Other versions
CN105607756B (en
Inventor
刘明骏
查婷婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201510984623.1A priority Critical patent/CN105607756B/en
Publication of CN105607756A publication Critical patent/CN105607756A/en
Application granted granted Critical
Publication of CN105607756B publication Critical patent/CN105607756B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023Arrangements 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
    • G06F3/0233Character input methods
    • G06F3/0236Character input methods using selection techniques to select from displayed items
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023Arrangements 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
    • G06F3/0233Character input methods
    • G06F3/0237Character input methods using prediction or retrieval techniques

Abstract

The invention discloses an information recommendation method and device. The information recommendation method comprises the steps that at least one candidate determined according to the input performed by a user on an input method interface; the at least one candidate is compared with a marked key word set, and obtaining recommendation contents corresponding to the target marked key word if the candidate hits a target marked key word; the recommendation contents are displayed within a set display area; the recommendation contents serve as input results of the input method interface according to the selection of the user, and meanwhile relevant information of the recommendation contents is sent when the user sends user input information including the recommendation contents. By the adoption of the technical scheme, the operation of performing service information communication of the user is simplified, the time is saved, and the information recommendation method is quick and convenient.

Description

Information recommendation method and device
Technical field
The present invention relates to the information processing technology, relate in particular to a kind of information recommendation method and device.
Background technology
Along with the development of Internet technology, all kinds of chat application have become the very important one of userSocial instrument. Wherein, input method, as important instrumental application program, is between chat application and userImportant interactive tool.
Described input method, refers to as various symbol input computers or other equipment (as mobile phone) are adoptedCoding method. Wherein, in order to facilitate user's content such as input characters on the equipment such as computer, mobile phone, oneAs input method the association's vocabulary based on regular collocation of some is all provided, in prior art, input methodIn the associational word of shown regular collocation, the normally character string based on user's input (typical, phonetic),Obtain the multiple candidate word corresponding with character string, and the frequency that occurs according to candidate word is at interface of input methodCandidate word shows in viewing area.
The progress of technology makes people also improve constantly the requirement of input method, and existing input method cannot expireThe data input demand of the growing personalization of foot people, high efficiency.
Summary of the invention
The invention provides a kind of information recommendation method and device, simplified user and carried out information on services interchangeOperation, saves time and convenient and swift.
On the one hand, the embodiment of the present invention provides a kind of information recommendation method. Described information recommendation method, bagDraw together:
Obtain at least one candidate word that user determines in the input of interface of input method;
Described at least one candidate word and mark keyword set are compared, if described candidate word is hit orderMark mark keyword, obtains the content recommendation corresponding with described target label keyword;
Described content recommendation is shown in setting display area;
Select according to user, the input results using described content recommendation as described interface of input method, and usingFamily sends while comprising the user's input information of described content recommendation, sends the association letter of described content recommendation simultaneouslyBreath.
On the other hand, the embodiment of the present invention also provides a kind of information recommending apparatus. Described information recommending apparatus,Comprise:
Candidate word acquisition module, at least one candidate who determines in the input of interface of input method for obtaining userWord;
Content recommendation acquisition module, for comparing described at least one candidate word and mark keyword setRight, if described candidate word hit mark keyword obtains corresponding with described target label keywordContent recommendation;
Content recommendation display module, for showing described content recommendation in setting display area;
Input results determination module, for selecting according to user, using described content recommendation as described input methodThe input results at interface, and in the time that user's transmission comprises the user's input information of described content recommendation, send out simultaneouslySend the related information of described content recommendation.
The technical scheme that the embodiment of the present invention provides, determines extremely in the input of interface of input method by obtaining userA few candidate word, compares at least one candidate word and mark keyword set, if candidate word lifeMiddle target label keyword, obtains the content recommendation corresponding with target label keyword, and content recommendation is existedSet in display area and show, and select according to user, defeated using content recommendation as interface of input methodEnter result, and send while comprising the user's input information of content recommendation user, send content recommendation simultaneouslyRelated information directly obtains recommendation information under the scene at input method place, has simplified user and has served letterThe operation that breath exchanges, has avoided user manually to input information on services and the switching of terminal between different application,Save time and convenient and swift.
Brief description of the drawings
Fig. 1 is the flow chart of a kind of information recommendation method of providing of the embodiment of the present invention one;
Fig. 2 is the flow chart of a kind of information recommendation method of providing of the embodiment of the present invention two;
Fig. 3 A is the schematic diagram of the applicable a kind of information recommendation method of the embodiment of the present invention three;
Fig. 3 B is the schematic diagram of the applicable a kind of information recommendation method of the embodiment of the present invention three;
Fig. 3 C is the schematic diagram of the applicable a kind of information recommendation method of the embodiment of the present invention three;
Fig. 3 D is the schematic diagram of the applicable a kind of information recommendation method of the embodiment of the present invention three;
Fig. 3 E is the schematic diagram of the applicable a kind of information recommendation method of the embodiment of the present invention three;
Fig. 4 is the structural representation of a kind of information recommending apparatus of providing of the embodiment of the present invention four.
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described in further detail. Be understandable that, thisLocate described specific embodiment only for explaining the present invention, but not limitation of the invention. Also need in additionBe noted that for convenience of description, in accompanying drawing, only show part related to the present invention but not all knotStructure.
Before in further detail exemplary embodiment being discussed, it should be mentioned that some exemplary embodiment quiltsBe described as processing or the method described as flow chart. Although flow chart is described operations (or step)The processing of one-tenth order, but many operations wherein can be implemented concurrently, concomitantly or simultaneously. ThisOutward, the order of operations can be rearranged. In the time that its operation completes, process and can be terminated, stillCan also there is the additional step not comprising in the accompanying drawings. This processing can corresponding to method, function, code,Subroutine, subprogram etc.
Embodiment mono-
Fig. 1 is the flow chart of a kind of information recommendation method of providing of the embodiment of the present invention one. The method can be by believingBreath recommendation apparatus is carried out, and this device can be realized by the mode of hardware and/or software, and this device configures conventionallyIn the input method system of terminal, and be applicable in information interaction scene, described terminal comprises mobile phone, flat boardComputer and PC etc., described information interaction scene specifically can comprise: instant messaging scene (for example,QQ or micro-letter chat scenario), short message sends scene or mail and sends scene etc. and have clear and definite information and connectDebit's information interaction scene. Referring to Fig. 1, the information recommendation method that the present embodiment provides specifically comprises:
S110, obtain at least one candidate word that user determines in the input of interface of input method.
Described user can comprise in the input of interface of input method: user is defeated in interface of input method by keyboardThe character string entering, or the voice of the speech input interface input of user by embedding in interface of input method.
Receive user after the input of interface of input method, input method system is resolved user's input, resolvesResult is afterwards to input corresponding candidate word with user, and the quantity of candidate word can be one or more.Wherein, candidate word can be the information off-line that terminal is downloaded at set intervals, can be also that real-time online obtainsThe information of getting.
For example, user has inputted character string " baidu " by interface of input method, by the character of settingAfter string parse operation, obtain the candidate word such as " Baidu ", " ferry-boat " and " having the honour to read ".
S120, described at least one candidate word and mark keyword set are compared, if described candidateWord hit mark keyword, obtains the content recommendation corresponding with described target label keyword.
Wherein, mark keyword set can be the set that input method system arranges for candidate word, mark keyEach mark keyword in set of words is to there being certain content recommendation. By at least one candidate word and markEach mark keyword in note keyword set is compared, if existed and candidate in mark keyword setThe mark keyword that word is identical, determines that this mark keyword is target label keyword, and and then obtains orderContent recommendation corresponding to mark mark keyword.
Typically, user can be information on services (for example: " chafing dish ") in the input of interface of input method, correspondingGround, described content recommendation be the service recommendation content that is associated with this information on services (for example: " chafing dish is dragged in seabedShop in address, the on-site shop of user, this shop corresponding purchase by group webpage and consumption evaluate etc. ").
Further, obtaining the content recommendation corresponding with described target label keyword can comprise: according to establishingDetermine relating attribute, determine the content recommendation corresponding with described mark keyword, wherein, described relating attribute canTo comprise content recommendation provider value of bidding to described mark keyword, and/or described content recommendation with described inThe degree of association of mark keyword. Mark keyword can determine by the mode of bidding, can be by the value of biddingHigh provider's service content is as the content recommendation corresponding with target label keyword, and by this providerAs content recommendation provider. In addition, can also determine by the degree of association of content recommendation and mark keywordRelating attribute, exemplarily, the degree of association of content recommendation and mark keyword is higher, and relating attribute is larger.
Preferably, can be simultaneously according to the degree of association and the content recommendation of content recommendation and described mark keywordThe content recommendation that provider is corresponding with mark keyword to the competing pricing of described mark keyword.
For example, setting a mark keyword is " chafing dish ", and the content recommendation associated with this mark keyword canTo comprise: the information of chafing dish designer-label store such as " chafing dish are dragged in seabed " and " little fertile sheep chafing dish ", according to different firePot designer-label store value of bidding to this mark keyword " chafing dish ", can finally determine corresponding with " chafing dish "Content recommendation.
Further, described content recommendation can be visiting card type composite content, wherein, and described composite content bagDraw together word content and/or image content. Picture can with the form of footmark be presented at word content the upper left corner orThe person upper right corner.
S130, described content recommendation is shown setting in display area.
The content recommendation obtaining may be displayed in the display area of setting of interface of input method, for example, and inputCandidate word display area, user's input frame display area or the input method function menu display area at method interfaceDeng, the present embodiment does not limit this.
Preferably, consider user's sight line focal position, can be by described content recommendation at interface of input methodCandidate word display area in set and display position show, wherein said set and display position is positioned at lifeAfter the display position of the candidate word of middle target label keyword.
S140, according to user select, the input results using described content recommendation as described interface of input method,And send while comprising the user's input information of described content recommendation user, send described content recommendation simultaneouslyRelated information.
If user selects content recommendation, the input results using described content recommendation as described interface of input method,And content recommendation can be presented in the input frame of interface of input method. In the time that user clicks transmission, will recommendWhen content sends in the application at input method place, send the related information of described content recommendation.
Further, the related information of described content recommendation can comprise described visiting card type composite content, recommendationService hyperlink and recommendation descriptor, wherein, described recommendation service hyperlink receives for guidance informationSide opens the service associated with content recommendation and lands page. Described service land page be described recommendation service hyperlinkCorresponding webpage.
Further, the word content in described visiting card type composite content can be shop name, described recommendation clothesBusiness hyperlink can purchase by group for the shop that popularization business in setting shop provides the hyperlink of the page; Or
Word content in described visiting card type composite content can be brand name or trade name, described recommendation serviceHyperlink can be the hyperlink of brand or commodity provider website homepage; Or
Word content in described visiting card type composite content can be Brand Service name, the super chain of described recommendation serviceConnecing can be the hyperlink of brand loose-leaf.
The technical scheme that the embodiment of the present invention provides, determines extremely in the input of interface of input method by obtaining userA few candidate word, compares at least one candidate word and mark keyword set, if candidate word lifeMiddle target label keyword, obtains the content recommendation corresponding with target label keyword, and content recommendation is existedSet in display area and show, and select according to user, defeated using content recommendation as interface of input methodEnter result, and send while comprising the user's input information of content recommendation user, send content recommendation simultaneouslyRelated information directly obtains recommendation information under the scene at input method place, has simplified user and has served letterThe operation that breath exchanges, has avoided user manually to input information on services and the switching of terminal between different application,Save time and convenient and swift.
Embodiment bis-
Fig. 2 is the flow chart of a kind of information recommendation method of providing of the embodiment of the present invention two. The present embodiment is in realityExecute on the basis of example one, S120, S130 are further optimized, described information recommendation method specifically comprises:
S210, obtain at least one candidate word that user determines in the input of interface of input method.
S220, described at least one candidate word and mark keyword set are compared, if described candidateWord hit mark keyword, obtains the content recommendation corresponding with described target label keyword.
Further, described at least one candidate word and mark keyword set are compared and can be comprised:Each mark keyword in the mark keyword set that described at least one candidate word and this locality are stored comparesRight; And/or
Described at least one candidate word is sent to remote server, with indicate described remote server will described inEach mark keyword in the mark keyword set of at least one candidate word and remote storage is compared, andReturn to comparison result.
Wherein, when candidate word is compared with the each mark keyword in local mark keyword set of storing,Input method system can directly obtain comparison result; Each in the mark keyword set of candidate word and remote storageWhen mark keyword is compared, comparison process is carried out in remote server, after comparison process finishes. RatioResult is sent to the input method system of user terminal by remote server.
If the corresponding multinomial content recommendation of the described target label keyword of S230, in described multinomial recommendationRong Zhong, according to set screening rule, filter out optimum Match recommendation items as with described target label keywordCorresponding content recommendation.
Further, in described multinomial content recommendation, according to setting screening rule, filter out optimum MatchRecommendation items, as the content recommendation corresponding with described target label keyword, specifically can comprise: according to temperatureDescribed multinomial content recommendation is sorted, obtain content recommendation that temperature is the highest as optimum Match recommendation items;Or obtain terminal positional information, the associated letter according to described terminal positional information with described multinomial content recommendationBreath mates, and obtains content recommendation that matching degree is the highest as optimum Match recommendation items; Or described in obtainingThe chat contextual information of interface of input method instant messaging scene of living in, according to described chat contextual information withThe related information of described multinomial content recommendation mates, and obtains content recommendation that matching degree is the highest as the bestCoupling recommendation items; Or obtain terminal use's attribute information, according to described terminal use's attribute information with described inThe related information of multinomial content recommendation mates, and obtains content recommendation that matching degree is the highest as optimum MatchRecommendation items.
Wherein, temperature can be the attention rate of on-line customer to a certain content, and Internet user's attention rate moreHeight, the temperature of this content is higher. Temperature can quantize with certain numerical value, correspondingly, and multinomial recommendationContent correspondence different temperatures, can sort to multinomial content recommendation according to the numerical value of temperature, and thenObtain content recommendation that temperature is the highest as optimum Match recommendation items. Described terminal use's attribute information can beThe information such as age of user, personal preference, habits and customs, terminal use's attribute information can be by inputIn method system, user's input record analysis is obtained, also terminal use's attribute information can be uploaded to long-rangeServer also records and analyzes user's input, and analysis result is returned to user in remote serverThe input method system of terminal, as terminal use's attribute information.
S240, described content recommendation is shown setting in display area.
S250, according to user select, the input results using described content recommendation as described interface of input method,And send while comprising the user's input information of described content recommendation user, send described content recommendation simultaneouslyRelated information.
Further, in the time that user's transmission comprises the user's input information of described content recommendation, send institute simultaneouslyState the related information of content recommendation, can comprise:
In the time detecting that user sends the user's input information that comprises described content recommendation, by described user's inputDescribed combined type content recommendation in information replaces with after the word content in described compound content recommendation, sendsUser's input information after renewal. The benefit arranging is like this: ensureing to send on the basis of information completely degree,Reduce the transmission of redundancy, reduced to send the data traffic that described content recommendation consumes.
The technical scheme that the embodiment of the present invention provides, according to setting screening rule, filters out optimum Match and recommendsItem, as the content recommendation corresponding with described target label keyword, obtains content recommendation rapidly, has improvedThe hit rate of content recommendation to user's actual need, has promoted user effectively in interchange information on services processUser experience.
Embodiment tri-
The embodiment of the present invention provides a kind of detailed description of the invention of information recommendation method. Described information recommendation sideMethod specifically comprises following content:
Referring to Fig. 3 A, under the chat scenario of group chat pattern, input method system obtains a group chat user defeatedEnter input " xiaofeiyang " in method interface, and determine at least one candidate word " little fertile sheep " and " shallow coffeeNet " etc., wherein, " the little fertile sheep " in candidate word, the target label having hit in mark keyword set closesKeyword " little fertile sheep ".
If the value of bidding according to content recommendation provider to mark keyword, pre-determines little fertile sheep Hui Nan shopThe value of bidding in shop is the highest, the content recommendation corresponding with target label keyword " little fertile sheep " is defined as" little fertile sheep (Hui Nan shop) ", this content recommendation is presented at the demonstration position of candidate word with the form of word and pictureAfter putting, referring to Fig. 3 A, in content recommendation, word content is " little fertile sheep (Hui Nan shop) ", image contentFor example, for promoting business's's (, purchasing by group class application program) icon, figure in the setting shop that little fertile sheep Hui Nan shop is correspondingIn 3A, this icon is the footmark that purchases by group application Baidu glutinous rice, and this footmark is presented at the upper right corner of word content.
After input method system detects that user clicks content recommendation, content recommendation is presented in input frame,Referring to Fig. 3 B, now, content recommendation is correspondingly transformed to image content front, and word content is rear, pictureContent is the mark of Baidu's glutinous rice.
Input results using content recommendation as interface of input method, and send the use that comprises content recommendation userWhen family input message, send the related information of content recommendation simultaneously. Referring to Fig. 3 C, the pass of above-mentioned content recommendationConnection information comprises recommendation service hyperlink, this shop in Baidu's glutinous rice application of little fertile sheep (Nan Hui shop)The related information of the corresponding content recommendation such as per capita consuming level and consumer's overall merit.
Other group chats user, after receiving the chat message that comprises content recommendation, clicks under chat backgroundThe related information of content recommendation, page is landed in the service that the page jump under chat scenario provides to Baidu's glutinous rice,Referring to Fig. 3 D and 3E, this service land page can comprise the evaluation of shop name, solid shop picture, user,The activity that purchases by group, recommendation dish and coupons etc. that pre-capita consumption, contact method, address, this shop provide.
Meanwhile, the transmit leg user of content recommendation can obtain the related information of content recommendation equally. RespectivelyUser can land page by service and directly return to the chat scenario of group chat.
The technical scheme that the embodiment of the present invention provides, user can be under current scene without manual input andApplication is switched can obtain information on services, and information on services is extended to chatting object.
Embodiment tetra-
Fig. 4 is the structural representation of a kind of information recommending apparatus of providing of the embodiment of the present invention four. Referring to Fig. 4,Described information recommending apparatus comprises that candidate word acquisition module 40, content recommendation acquisition module 41, content recommendation showShow module 42 and input results determination module 43.
Wherein, candidate word acquisition module 40 is for obtaining at least one that user determines in the input of interface of input methodIndividual candidate word; Content recommendation acquisition module 41 is for by described at least one candidate word and mark keyword setCompare, if described candidate word hit mark keyword obtains and described target label keyThe content recommendation that word is corresponding; Content recommendation display module 42 is for setting display area by described content recommendationInside show; Input results determination module 43 is for selecting according to user, using described content recommendation as instituteState the input results of interface of input method, and in the time that user's transmission comprises the user's input information of described content recommendation,Send the related information of described content recommendation simultaneously.
The technical scheme that the embodiment of the present invention provides, determines extremely in the input of interface of input method by obtaining userA few candidate word, compares at least one candidate word and mark keyword set, if candidate word lifeMiddle target label keyword, obtains the content recommendation corresponding with target label keyword, and content recommendation is existedSet in display area and show, and select according to user, defeated using content recommendation as interface of input methodEnter result, and send while comprising the user's input information of content recommendation user, send content recommendation simultaneouslyRelated information directly obtains recommendation information under the scene at input method place, has simplified user and has served letterThe operation that breath exchanges, has avoided user manually to input information on services and the switching of terminal between different application,Save time and convenient and swift.
Further, content recommendation acquisition module 41 can comprise local comparing unit and/or long-range comparing listUnit.
Wherein, local comparing unit is for the mark keyword with local storage by described at least one candidate wordEach mark keyword in set is compared; Long-range comparing unit is for sending out described at least one candidate wordDeliver to remote server, to indicate described remote server by described at least one candidate word and remote storageEach mark keyword in mark keyword set is compared, and returns to comparison result.
Further, content recommendation acquisition module 41 can comprise content recommendation determining unit. Wherein, recommendContent determining unit, for according to setting relating attribute, is determined the content recommendation corresponding with described mark keyword,Wherein, described relating attribute comprises content recommendation provider value of bidding to described mark keyword, and/or instituteState the degree of association of content recommendation and described mark keyword.
Further, content recommendation can be visiting card type composite content, and wherein, described composite content can wrapDraw together word content and/or image content.
Further, the related information of content recommendation can comprise described visiting card type composite content, recommendation serviceHyperlink and recommendation descriptor, wherein, described recommendation service hyperlink is beaten for guidance information recipientOpen the service associated with content recommendation and land page.
Further, the word content in described visiting card type composite content is shop name, and described recommendation service is superThe shop that being linked as setting shop popularization business provides purchases by group the hyperlink of the page; Or
Word content in described visiting card type composite content is brand name or trade name, the super chain of described recommendation serviceConnect the hyperlink for brand or commodity provider website homepage; Or
Word content in described visiting card type composite content is Brand Service name, and described recommendation service hyperlink isThe hyperlink of brand loose-leaf.
Further, content recommendation acquisition module 41 can comprise content recommendation screening unit. Content recommendation sieveIf menu unit is for the corresponding multinomial content recommendation of described target label keyword, in described multinomial recommendationRong Zhong, according to set screening rule, filter out optimum Match recommendation items as with described target label keywordCorresponding content recommendation.
Further, content recommendation screening unit, specifically can be for:
According to temperature, described multinomial content recommendation is sorted, obtain content recommendation that temperature is the highest asGood coupling recommendation items; Or
Obtain terminal positional information, the associated letter according to described terminal positional information with described multinomial content recommendationBreath mates, and obtains content recommendation that matching degree is the highest as optimum Match recommendation items; Or
Obtain the chat contextual information of described interface of input method instant messaging scene of living in, according to described chatContextual information mates with the related information of described multinomial content recommendation, obtains the recommendation that matching degree is the highestContent is as optimum Match recommendation items; Or
Obtain terminal use's attribute information, according to described terminal use's attribute information and described multinomial content recommendationRelated information mate, obtain content recommendation that matching degree is the highest as optimum Match recommendation items.
Further, content recommendation display module 42 specifically can be for: by described content recommendation in input methodSet and display position in the candidate word display area at interface shows, wherein, and described set and display positionAfter being positioned at the display position of candidate word of hit mark keyword.
Further, input results determination module 43 can comprise: replacement unit. Wherein, replacement unit is usedIn in the time detecting that user sends the user's input information that comprises described content recommendation, described user is inputted to letterDescribed combined type content recommendation in breath replaces with after the word content in described compound content recommendation, sends moreUser's input information after new.
The information recommending apparatus that the present embodiment provides, the information recommendation side providing with any embodiment of the present inventionOwned by France in same inventive concept, can carry out the information recommendation method that any embodiment of the present invention provides, possessCarry out the corresponding functional module of information recommendation method and beneficial effect. The not skill of detailed description in the present embodimentArt details, the information recommendation method that can provide referring to any embodiment of the present invention.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, any familiarProfessional and technical personnel, is not departing within the scope of technical solution of the present invention, when utilizing the skill of above-mentioned announcementArt content is made a little change or modification etc., all any amendments of doing within the spirit and principles in the present invention,Protection scope of the present invention is equal to replacement or improvement etc., within all should be included in.

Claims (20)

1. an information recommendation method, is characterized in that, comprising:
Obtain at least one candidate word that user determines in the input of interface of input method;
Described at least one candidate word and mark keyword set are compared, if described candidate word is hit orderMark mark keyword, obtains the content recommendation corresponding with described target label keyword;
Described content recommendation is shown in setting display area;
Select according to user, the input results using described content recommendation as described interface of input method, and usingFamily sends while comprising the user's input information of described content recommendation, sends the association letter of described content recommendation simultaneouslyBreath.
2. information recommendation method according to claim 1, is characterized in that, by described at least one timeSelecting word and mark keyword set to compare comprises:
Described at least one candidate word and the each mark keyword in local mark keyword set of storing are enteredRow comparison; And/or
Described at least one candidate word is sent to remote server, with indicate described remote server will described inEach mark keyword in the mark keyword set of at least one candidate word and remote storage is compared, andReturn to comparison result.
3. information recommendation method according to claim 1, is characterized in that, obtains and described target markContent recommendation corresponding to note keyword comprises:
According to setting relating attribute, determine the content recommendation corresponding with described mark keyword, wherein, described inRelating attribute comprises content recommendation provider value of bidding to described mark keyword, and/or described content recommendationThe degree of association with described mark keyword.
4. information recommendation method according to claim 1, is characterized in that, described content recommendation is run after fameChip composite content, wherein, described composite content comprises word content and/or image content.
5. information recommendation method according to claim 4, is characterized in that, the pass of described content recommendationConnection information comprises described visiting card type composite content, recommendation service hyperlink and recommendation descriptor, wherein,Described recommendation service hyperlink is opened the service associated with content recommendation for guidance information recipient and is landed page.
6. information recommendation method according to claim 5, is characterized in that, in described visiting card type is compoundWord content in appearance is shop name, and described recommendation service hyperlink promotes for setting shop the shop that business providesPurchase by group the hyperlink of the page; Or
Word content in described visiting card type composite content is brand name or trade name, the super chain of described recommendation serviceConnect the hyperlink for brand or commodity provider website homepage; Or
Word content in described visiting card type composite content is Brand Service name, and described recommendation service hyperlink isThe hyperlink of brand loose-leaf.
7. information recommendation method according to claim 1, is characterized in that, by described at least one timeSelect word and mark keyword set to compare, if described candidate word hit mark keyword obtainsGet the content recommendation corresponding with described target label keyword, comprising:
If the corresponding multinomial content recommendation of described target label keyword, in described multinomial content recommendation,According to setting screening rule, filter out optimum Match recommendation items as corresponding with described target label keywordContent recommendation.
8. information recommendation method according to claim 7, is characterized in that, in described multinomial recommendationRong Zhong, according to set screening rule, filter out optimum Match recommendation items as with described target label keywordCorresponding content recommendation, specifically comprises:
According to temperature, described multinomial content recommendation is sorted, obtain content recommendation that temperature is the highest asGood coupling recommendation items; Or
Obtain terminal positional information, the associated letter according to described terminal positional information with described multinomial content recommendationBreath mates, and obtains content recommendation that matching degree is the highest as optimum Match recommendation items; Or
Obtain the chat contextual information of described interface of input method instant messaging scene of living in, according to described chatContextual information mates with the related information of described multinomial content recommendation, obtains the recommendation that matching degree is the highestContent is as optimum Match recommendation items; Or
Obtain terminal use's attribute information, according to described terminal use's attribute information and described multinomial content recommendationRelated information mate, obtain content recommendation that matching degree is the highest as optimum Match recommendation items.
9. information recommendation method according to claim 1, is characterized in that, described content recommendation is existedSet in display area and show, comprising:
Set and display position by described content recommendation in the candidate word display area of interface of input method showsShow, wherein, described set and display position be positioned at hit mark keyword candidate word display position itAfter.
10. information recommendation method according to claim 4, is characterized in that, sends and comprises userWhen the user's input information of described content recommendation, send the related information of described content recommendation simultaneously, comprising:
In the time detecting that user sends the user's input information that comprises described content recommendation, by described user's inputDescribed combined type content recommendation in information replaces with after the word content in described compound content recommendation, sendsUser's input information after renewal.
11. 1 kinds of information recommending apparatus, is characterized in that, comprising:
Candidate word acquisition module, at least one candidate who determines in the input of interface of input method for obtaining userWord;
Content recommendation acquisition module, for comparing described at least one candidate word and mark keyword setRight, if described candidate word hit mark keyword obtains corresponding with described target label keywordContent recommendation;
Content recommendation display module, for showing described content recommendation in setting display area;
Input results determination module, for selecting according to user, using described content recommendation as described input methodThe input results at interface, and in the time that user's transmission comprises the user's input information of described content recommendation, send out simultaneouslySend the related information of described content recommendation.
12. information recommending apparatus according to claim 11, is characterized in that, described content recommendation obtainsDelivery piece, comprising:
Local comparing unit, for the mark keyword set with local storage by described at least one candidate wordIn each mark keyword compare; And/or
Long-range comparing unit, for described at least one candidate word is sent to remote server, to indicateState remote server by the each mark in the mark keyword set of described at least one candidate word and remote storageKeyword is compared, and returns to comparison result.
13. information recommending apparatus according to claim 11, is characterized in that, described content recommendation obtainsDelivery piece, comprising:
Content recommendation determining unit, for according to setting relating attribute, determines corresponding with described mark keywordContent recommendation, wherein, described relating attribute comprises competing to described mark keyword of content recommendation providerBe worth, and/or the degree of association of described content recommendation and described mark keyword.
14. information recommending apparatus according to claim 11, is characterized in that, described content recommendation isVisiting card type composite content, wherein, described composite content comprises word content and/or image content.
15. information recommending apparatus according to claim 14, is characterized in that, described content recommendationRelated information comprises described visiting card type composite content, recommendation service hyperlink and recommendation descriptor, wherein,Described recommendation service hyperlink is opened the service associated with content recommendation for guidance information recipient and is landed page.
16. information recommending apparatus according to claim 15, is characterized in that, described visiting card type is compoundWord content in content is shop name, and described recommendation service hyperlink promotes for setting shop the shop that business providesPaving purchases by group the hyperlink of the page; Or
Word content in described visiting card type composite content is brand name or trade name, the super chain of described recommendation serviceConnect the hyperlink for brand or commodity provider website homepage; Or
Word content in described visiting card type composite content is Brand Service name, and described recommendation service hyperlink isThe hyperlink of brand loose-leaf.
17. information recommending apparatus according to claim 11, is characterized in that, content recommendation obtains mouldPiece, comprising:
Content recommendation screening unit, if for the corresponding multinomial content recommendation of described target label keyword,In described multinomial content recommendation, according to set screening rule, filter out optimum Match recommendation items as with instituteState the content recommendation that target label keyword is corresponding.
18. information recommending apparatus according to claim 17, is characterized in that, content recommendation screening is singleUnit, specifically for:
According to temperature, described multinomial content recommendation is sorted, obtain content recommendation that temperature is the highest asGood coupling recommendation items; Or
Obtain terminal positional information, the associated letter according to described terminal positional information with described multinomial content recommendationBreath mates, and obtains content recommendation that matching degree is the highest as optimum Match recommendation items; Or
Obtain the chat contextual information of described interface of input method instant messaging scene of living in, according to described chatContextual information mates with the related information of described multinomial content recommendation, obtains the recommendation that matching degree is the highestContent is as optimum Match recommendation items; Or
Obtain terminal use's attribute information, according to described terminal use's attribute information and described multinomial content recommendationRelated information mate, obtain content recommendation that matching degree is the highest as optimum Match recommendation items.
19. information recommending apparatus according to claim 11, is characterized in that, described content recommendation is aobviousShow module, specifically for:
Set and display position by described content recommendation in the candidate word display area of interface of input method showsShow, wherein, described set and display position be positioned at hit mark keyword candidate word display position itAfter.
20. information recommending apparatus according to claim 14, is characterized in that, described input results is trueCover half piece, comprising:
Replacement unit, in the time detecting that user sends the user's input information that comprises described content recommendation,Described combined type content recommendation in described user's input information is replaced with to the literary composition in described compound content recommendationAfter word content, send the user's input information after upgrading.
CN201510984623.1A 2015-12-24 2015-12-24 Information recommendation method and device Active CN105607756B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510984623.1A CN105607756B (en) 2015-12-24 2015-12-24 Information recommendation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510984623.1A CN105607756B (en) 2015-12-24 2015-12-24 Information recommendation method and device

Publications (2)

Publication Number Publication Date
CN105607756A true CN105607756A (en) 2016-05-25
CN105607756B CN105607756B (en) 2019-05-10

Family

ID=55987740

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510984623.1A Active CN105607756B (en) 2015-12-24 2015-12-24 Information recommendation method and device

Country Status (1)

Country Link
CN (1) CN105607756B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106227871A (en) * 2016-07-29 2016-12-14 百度在线网络技术(北京)有限公司 A kind of for providing the method and apparatus of association service information in input method
CN106293119A (en) * 2016-07-29 2017-01-04 百度在线网络技术(北京)有限公司 A kind of method and apparatus carrying out information recommendation in input method
CN106371625A (en) * 2016-09-29 2017-02-01 北京小米移动软件有限公司 Associated word display method and device
CN107179838A (en) * 2017-05-25 2017-09-19 维沃移动通信有限公司 The display methods and mobile terminal of a kind of candidate word
CN107526828A (en) * 2017-09-01 2017-12-29 广东神马搜索科技有限公司 Page info recommends method and apparatus
CN107621890A (en) * 2017-09-27 2018-01-23 珠海市魅族科技有限公司 Information displaying method and device, computer installation and readable storage medium storing program for executing
CN107678610A (en) * 2016-08-02 2018-02-09 财团法人资讯工业策进会 Network equipment and messaging providers method
CN107844203A (en) * 2017-11-29 2018-03-27 维沃移动通信有限公司 A kind of input method candidate words recommending method and mobile terminal
CN107894852A (en) * 2017-11-13 2018-04-10 珠海市魅族科技有限公司 A kind of keyboard shift method and electronic equipment
CN108257037A (en) * 2018-01-18 2018-07-06 封玉涛 It is a kind of with social scene turn to point of penetration apply fusion method and device
CN108376162A (en) * 2018-02-22 2018-08-07 北京百度网讯科技有限公司 Method and apparatus for pushed information
CN109003170A (en) * 2018-08-31 2018-12-14 浙江口碑网络技术有限公司 Acquisition methods and device for the shop material shown in the page
CN109101505A (en) * 2017-06-20 2018-12-28 北京搜狗科技发展有限公司 A kind of recommended method, recommendation apparatus and the device for recommendation
WO2019029409A1 (en) * 2017-08-11 2019-02-14 腾讯科技(深圳)有限公司 Instant messaging-based information pushing method and apparatus, terminal and storage medium
CN109446311A (en) * 2018-10-30 2019-03-08 五八有限公司 A kind of chat Enhancement Method, device, storage medium and terminal
CN110020106A (en) * 2017-09-08 2019-07-16 北京搜狗科技发展有限公司 A kind of recommended method, recommendation apparatus and the device for recommendation
CN110222256A (en) * 2019-05-06 2019-09-10 北京搜狗科技发展有限公司 A kind of information recommendation method, device and the device for information recommendation
CN112383662A (en) * 2020-11-09 2021-02-19 维沃移动通信有限公司 Information display method and device and electronic equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104035947A (en) * 2013-09-16 2014-09-10 腾讯科技(深圳)有限公司 Method and device for recommending interest points, and method and device for obtaining recommended interest points
CN104298429A (en) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 Information presentation method based on input and input method system
CN104765791A (en) * 2015-03-24 2015-07-08 北京搜狗科技发展有限公司 Information inputting method and device
CN104794246A (en) * 2015-05-15 2015-07-22 百度在线网络技术(北京)有限公司 Information search method and information search device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104035947A (en) * 2013-09-16 2014-09-10 腾讯科技(深圳)有限公司 Method and device for recommending interest points, and method and device for obtaining recommended interest points
CN104298429A (en) * 2014-09-25 2015-01-21 北京搜狗科技发展有限公司 Information presentation method based on input and input method system
CN104765791A (en) * 2015-03-24 2015-07-08 北京搜狗科技发展有限公司 Information inputting method and device
CN105183787A (en) * 2015-03-24 2015-12-23 北京搜狗科技发展有限公司 Information input method and apparatus
CN104794246A (en) * 2015-05-15 2015-07-22 百度在线网络技术(北京)有限公司 Information search method and information search device

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106227871A (en) * 2016-07-29 2016-12-14 百度在线网络技术(北京)有限公司 A kind of for providing the method and apparatus of association service information in input method
CN106293119A (en) * 2016-07-29 2017-01-04 百度在线网络技术(北京)有限公司 A kind of method and apparatus carrying out information recommendation in input method
CN107678610A (en) * 2016-08-02 2018-02-09 财团法人资讯工业策进会 Network equipment and messaging providers method
CN106371625A (en) * 2016-09-29 2017-02-01 北京小米移动软件有限公司 Associated word display method and device
CN107179838A (en) * 2017-05-25 2017-09-19 维沃移动通信有限公司 The display methods and mobile terminal of a kind of candidate word
CN107179838B (en) * 2017-05-25 2019-07-26 维沃移动通信有限公司 A kind of display methods and mobile terminal of candidate word
CN109101505A (en) * 2017-06-20 2018-12-28 北京搜狗科技发展有限公司 A kind of recommended method, recommendation apparatus and the device for recommendation
WO2019029409A1 (en) * 2017-08-11 2019-02-14 腾讯科技(深圳)有限公司 Instant messaging-based information pushing method and apparatus, terminal and storage medium
CN107526828A (en) * 2017-09-01 2017-12-29 广东神马搜索科技有限公司 Page info recommends method and apparatus
CN107526828B (en) * 2017-09-01 2020-10-16 阿里巴巴(中国)有限公司 Page information recommendation method and device
CN110020106A (en) * 2017-09-08 2019-07-16 北京搜狗科技发展有限公司 A kind of recommended method, recommendation apparatus and the device for recommendation
CN107621890A (en) * 2017-09-27 2018-01-23 珠海市魅族科技有限公司 Information displaying method and device, computer installation and readable storage medium storing program for executing
CN107894852A (en) * 2017-11-13 2018-04-10 珠海市魅族科技有限公司 A kind of keyboard shift method and electronic equipment
CN107844203A (en) * 2017-11-29 2018-03-27 维沃移动通信有限公司 A kind of input method candidate words recommending method and mobile terminal
CN107844203B (en) * 2017-11-29 2021-02-19 维沃移动通信有限公司 Input method candidate word recommendation method and mobile terminal
CN108257037A (en) * 2018-01-18 2018-07-06 封玉涛 It is a kind of with social scene turn to point of penetration apply fusion method and device
CN108376162A (en) * 2018-02-22 2018-08-07 北京百度网讯科技有限公司 Method and apparatus for pushed information
CN109003170A (en) * 2018-08-31 2018-12-14 浙江口碑网络技术有限公司 Acquisition methods and device for the shop material shown in the page
CN109446311A (en) * 2018-10-30 2019-03-08 五八有限公司 A kind of chat Enhancement Method, device, storage medium and terminal
CN110222256A (en) * 2019-05-06 2019-09-10 北京搜狗科技发展有限公司 A kind of information recommendation method, device and the device for information recommendation
CN112383662A (en) * 2020-11-09 2021-02-19 维沃移动通信有限公司 Information display method and device and electronic equipment

Also Published As

Publication number Publication date
CN105607756B (en) 2019-05-10

Similar Documents

Publication Publication Date Title
CN105607756A (en) Information recommendation method and device
US10180979B2 (en) System and method for generating suggestions by a search engine in response to search queries
AU2017210638A1 (en) Social match platform apparatuses, methods and systems
US8769417B1 (en) Identifying an answer to a question in an electronic forum
CN107580704A (en) Context personage recommends
US8844800B2 (en) Ratings using machine-readable representations
CN104657879A (en) User engagement-based contextually-dependent automated pricing for non-guaranteed delivery
KR20190057408A (en) Optimized item attribute comparison
CN103150352A (en) System to generate related search queries
CN106682169B (en) Application label mining method and device, application searching method and server
US20190332633A1 (en) Generating feedback for a target content item based on published content items
CN106796583A (en) System and method for recognizing and advising emoticon
Chen et al. Social opinion mining for supporting buyers’ complex decision making: exploratory user study and algorithm comparison
EP3117339A1 (en) Systems and methods for keyword suggestion
US20140129634A1 (en) Social media-based content recommendation apparatus
KR101345119B1 (en) System and method for generating and diagonizing image concept identity code, and system for providing information and method for providing services thereof
KR102132931B1 (en) System and method for customized value information retrieval and social network configuration
CN110827063A (en) Multi-strategy fused commodity recommendation method, device, terminal and storage medium
KR20100037711A (en) Method for collecting, providing goods information service and system thereof
CN109155041A (en) The recommendation based on travelling or promotion associated with socialgram is provided
KR20090049464A (en) System for acquiring and providing wisdom using real time feedback information from wisdom sharers connected via online and the method therefor
KR101952408B1 (en) Apparatus for providing user with rewards using skin image of virtual keyboard and method thereof
KR20200030252A (en) Apparatus and method for providing artwork
US20180218084A1 (en) Systems and methods for enhanced online research
US10445793B2 (en) Review text output system and review text output method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant