CN105607756B - Information recommendation method and device - Google Patents
Information recommendation method and device Download PDFInfo
- Publication number
- CN105607756B CN105607756B CN201510984623.1A CN201510984623A CN105607756B CN 105607756 B CN105607756 B CN 105607756B CN 201510984623 A CN201510984623 A CN 201510984623A CN 105607756 B CN105607756 B CN 105607756B
- Authority
- CN
- China
- Prior art keywords
- recommendation
- information
- user
- label keyword
- candidate word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- 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
Abstract
The invention discloses a kind of information recommendation method and devices.The information recommendation method, comprising: obtain user's at least one candidate word determining in the input of interface of input method;At least one described candidate word is compared with label keyword set, if the candidate word hits target label keyword, obtains recommendation corresponding with the target label keyword;The recommendation is shown in setting display area;It is selected according to user, using the recommendation as the input results of the interface of input method, and when it includes user's input information of the recommendation that user, which sends, while sending the related information of the recommendation.Technical solution provided by the invention simplifies the operation that user carries out information on services exchange, saves time and convenient and efficient.
Description
Technical field
The present invention relates to the information processing technology more particularly to a kind of information recommendation methods and device.
Background technique
With the continuous development of Internet technology, all kinds of chat applications have become a kind of very important social work of user
Tool.Wherein, input method is the important interactive tool between chat application and user as important instrumental application program.
The input method refers to the coding staff used for various symbols are inputted computer or other equipment (such as mobile phone)
Method.Wherein, the contents such as text are inputted in the equipment such as computer, mobile phone in order to facilitate user, the method for typically entering is each provided with centainly
Association's vocabulary based on regular collocation of quantity, in the prior art, the associational word of shown regular collocation in input method, usually
It is the character string (typical, phonetic) based on user's input, obtains multiple candidate words corresponding with character string, and according to candidate
The frequency that word occurs is shown in the candidate word display area of interface of input method.
So that requirement of the people to input method is also being continuously improved, existing input method is unable to satisfy people for the progress of technology
Growing personalization, efficient data input demand.
Summary of the invention
The present invention provides a kind of information recommendation method and devices, simplify the operation that user carries out information on services exchange,
Save time and convenient and efficient.
On the one hand, the embodiment of the invention provides a kind of information recommendation methods.The information recommendation method, comprising:
Obtain user's at least one candidate word determining in the input of interface of input method;
At least one described candidate word is compared with label keyword set, if the candidate word hits target mark
Remember keyword, then obtains recommendation corresponding with the target label keyword;
The recommendation is shown in setting display area;
It is selected according to user, using the recommendation as the input results of the interface of input method, and is sent in user
When user including the recommendation inputs information, while sending the related information of the recommendation.
On the other hand, the embodiment of the invention also provides a kind of information recommending apparatus.The information recommending apparatus, comprising:
Candidate word obtains module, for obtaining user's at least one candidate word determining in the input of interface of input method;
Recommendation obtains module, at least one described candidate word to be compared with label keyword set, such as
Candidate word described in fruit hits target label keyword, then obtains recommendation corresponding with the target label keyword;
Recommendation display module, for showing the recommendation in setting display area;
Input results determining module, for being selected according to user, using the recommendation as the interface of input method
Input results, and when it includes user's input information of the recommendation that user, which sends, while sending the recommendation
Related information.
Technical solution provided in an embodiment of the present invention, by obtain input determination of the user in interface of input method at least one
A candidate word at least one candidate word is compared with label keyword set, if candidate word hits target label key
Word then obtains recommendation corresponding with target label keyword, and recommendation is shown in setting display area, and
It is selected according to user, using recommendation as the input results of interface of input method, and sends the use including recommendation in user
When family inputs information, while the related information of recommendation is sent, directly acquires recommendation information under the scene where input method,
The operation that user carries out information on services exchange is simplified, user is avoided and is manually entered information on services and terminal in different application
Between switching, save time and convenient and efficient.
Detailed description of the invention
Fig. 1 is a kind of flow chart for information recommendation method that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow chart of information recommendation method provided by Embodiment 2 of the present invention;
Fig. 3 A is a kind of schematic diagram of the applicable information recommendation method of the embodiment of the present invention three;
Fig. 3 B is a kind of schematic diagram of the applicable information recommendation method of the embodiment of the present invention three;
Fig. 3 C is a kind of schematic diagram of the applicable information recommendation method of the embodiment of the present invention three;
Fig. 3 D is a kind of schematic diagram of the applicable information recommendation method of the embodiment of the present invention three;
Fig. 3 E is a kind of schematic diagram of the applicable information recommendation method of the embodiment of the present invention three;
Fig. 4 is a kind of structural schematic diagram for information recommending apparatus that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing or method described as flow chart.Although operations (or step) are described as the processing of sequence by flow chart,
Many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be pacified again
Row.Processing can be terminated when its operations are completed, it is also possible to have the additional step being not included in attached drawing.The processing
It can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 is a kind of flow chart for information recommendation method that the embodiment of the present invention one provides.This method can be by information recommendation
Device executes, which can be realized by way of hardware and/or software, which is typically configured in the input genealogy of law of terminal
In system, and suitable for information exchange scene, the terminal includes mobile phone, tablet computer and PC etc., the information
Interaction scenarios can specifically include: instant messaging scene (for example, QQ or wechat chat scenario), short message send scene or
Mail sends the information exchange scene with clear receiving party such as scene.Referring to Fig. 1, information recommendation provided in this embodiment
Method specifically includes:
S110, user's at least one candidate word determining in the input of interface of input method is obtained.
The user is in the word that the input of interface of input method may include: that user passes through that keyboard inputs in interface of input method
The voice that symbol string or user pass through the speech input interface input being embedded in interface of input method.
User is received after the input of interface of input method, input method system parses user's input, after parsing
It as a result is candidate word corresponding with user's input, the quantity of candidate word can be one or more.Wherein, candidate word can be
The information off-line that terminal is downloaded at regular intervals is also possible to the information of real-time online acquisition.
For example, user has input character string " baidu " by interface of input method, is grasped by the character string parsing of setting
After work, candidate words such as " Baidu ", " ferry-boat " and " having the honour to read " are obtained.
S120, at least one described candidate word is compared with label keyword set, if the candidate word is hit
Target label keyword then obtains recommendation corresponding with the target label keyword.
Wherein, label keyword set can be the set that input method system is directed to candidate word setting, mark keyword set
Each label keyword in conjunction is corresponding with certain recommendation.It will be at least one candidate word and label keyword set
Each label keyword be compared, if label keyword set in exist label keyword identical with candidate word, really
The fixed label keyword is target label keyword, and obtains the corresponding recommendation of target label keyword in turn.
Typically, user can be information on services (such as: " chafing dish ") in the input of interface of input method, correspondingly, described
Recommendation be service recommendation content associated with the information on services (such as: " and seabed fish out chafing dish restaurant user location shop
Floor file location, the shop are corresponding to purchase by group webpage and consumption evaluation etc. ").
Further, obtaining recommendation corresponding with the target label keyword may include: to be associated with according to setting
Attribute determines recommendation corresponding with the label keyword, wherein the relating attribute may include that recommendation provides
The degree of association of the side to bid value and/or the recommendation and the label keyword of the label keyword.Label is crucial
Word can determine that the service content for being worth highest provider that can will bid is as crucial with target label by way of bidding
The corresponding recommendation of word, and using the provider as recommendation provider.Furthermore it is also possible to pass through recommendation and label
The degree of association of keyword determines relating attribute, and illustratively, the degree of association of recommendation and label keyword is higher, relating attribute
It is bigger.
It preferably, can be simultaneously according to the degree of association and recommendation provider of recommendation and the label keyword
Determining recommendation corresponding with label keyword is worth to bidding for the label keyword.
For example, setting a label keyword as " chafing dish ", may include: with the associated recommendation of label keyword
The information of the chafing dishes designer-label store such as " seabed fishing chafing dish " and " small fertilizer sheep chafing dish ", according to different chafing dish designer-label store to label key
The value of bidding of word " chafing dish " can finally determine recommendation corresponding with " chafing dish ".
Further, the recommendation can be visiting card type composite content, wherein the composite content includes in text
Appearance and/or image content.Picture can be shown in the upper left corner or the upper right corner of word content in the form of footmark.
S130, the recommendation is shown in setting display area.
The recommendation of acquisition may be displayed in the display area of the setting of interface of input method, for example, interface of input method
Candidate word display area, user's input frame display area or input method function menu display area etc., the present embodiment is to this
And it is not limited.
Preferably, it is contemplated that the sight focal position of user, can by the recommendation interface of input method candidate
Setting display position in word display area is shown, wherein the setting display position, which is located at, hits target label keyword
Candidate word display position after.
S140, it is selected according to user, using the recommendation as the input results of the interface of input method, and in user
When sending user's input information including the recommendation, while sending the related information of the recommendation.
If user selects recommendation, using the recommendation as the input results of the interface of input method, and can
Showing recommendation in the input frame of interface of input method.When user clicks and sends, input is sent by recommendation
While in application where method, the related information of the recommendation is sent.
Further, the related information of the recommendation may include that the visiting card type composite content, recommendation service are super
Link and recommendation description information, wherein the recommendation service hyperlink is opened for guidance information recipient and recommendation
Page is landed in associated service.The service landing page is the corresponding webpage of the recommendation service hyperlink.
Further, the word content in the visiting card type composite content can be store name, the recommendation service hyperlink
The hyperlink that the shop that quotient provides purchases by group the page can be promoted for setting shop by connecing;Or
Word content in the visiting card type composite content can be brand name or trade name, the recommendation service hyperlink
It can be brand or the hyperlink of commodity provider website homepage;Or
Word content in the visiting card type composite content can be Brand Service name, and the recommendation service hyperlink can be with
For the hyperlink of the brand campaigns page.
Technical solution provided in an embodiment of the present invention, by obtain input determination of the user in interface of input method at least one
A candidate word at least one candidate word is compared with label keyword set, if candidate word hits target label key
Word then obtains recommendation corresponding with target label keyword, and recommendation is shown in setting display area, and
It is selected according to user, using recommendation as the input results of interface of input method, and sends the use including recommendation in user
When family inputs information, while the related information of recommendation is sent, directly acquires recommendation information under the scene where input method,
The operation that user carries out information on services exchange is simplified, user is avoided and is manually entered information on services and terminal in different application
Between switching, save time and convenient and efficient.
Embodiment two
Fig. 2 is a kind of flow chart of information recommendation method provided by Embodiment 2 of the present invention.The present embodiment is in embodiment one
On the basis of, S120, S130 are advanced optimized, the information recommendation method specifically includes:
S210, user's at least one candidate word determining in the input of interface of input method is obtained.
S220, at least one described candidate word is compared with label keyword set, if the candidate word is hit
Target label keyword then obtains recommendation corresponding with the target label keyword.
Further, by least one described candidate word with label keyword set be compared may include: will be described
At least one candidate word is compared with each label keyword in the label keyword set being locally stored;And/or
At least one described candidate word is sent to remote server, to indicate the remote server by described at least one
A candidate word is compared with each label keyword in the label keyword set remotely stored, and returns to comparison result.
Wherein, when candidate word is compared with each label keyword in the label keyword set being locally stored, input
Method system can directly acquire comparison result;Each label keyword in candidate word and the label keyword set remotely stored carries out
When comparison, comparison process carries out in remote server, after comparison process.Comparison result is sent to use by remote server
The input method system of family terminal.
If S230, the target label keyword correspond to multinomial recommendation, in the multinomial recommendation, press
According to setting screening rule, best match recommendation items are filtered out as recommendation corresponding with the target label keyword.
Further, in the multinomial recommendation, according to setting screening rule, best match recommendation items work is filtered out
It for recommendation corresponding with the target label keyword, can specifically include: according to temperature to the multinomial recommendation
It is ranked up, obtains the highest recommendation of temperature as best match recommendation items;Or terminal positional information is obtained, according to institute
It states terminal positional information to be matched with the related information of the multinomial recommendation, obtains the highest recommendation of matching degree and make
For best match recommendation items;Or the chat contextual information of instant messaging scene locating for the interface of input method is obtained, according to
The chat contextual information is matched with the related information of the multinomial recommendation, is obtained in the highest recommendation of matching degree
Hold and is used as best match recommendation items;Or obtain terminal user's attribute information, according to terminal user's attribute information with it is described
The related information of multinomial recommendation is matched, and obtains the highest recommendation of matching degree as best match recommendation items.
Wherein, temperature can be on-line customer to the attention rate of a certain content, and the attention rate of Internet user is higher, this is interior
The temperature of appearance is higher.Temperature can be quantified with certain numerical value, and correspondingly, multinomial recommendation corresponds to different heat
Degree, can be ranked up multinomial recommendation according to the numerical value of temperature, and then obtain the highest recommendation of temperature as most
Good matching recommendation items.Terminal user's attribute information can be the information such as age, personal preference, the living habit of user, eventually
End subscriber attribute information can be obtained by analyzing in input method system the input record of user, can also be by terminal user
Attribute information is uploaded to remote server and analyzes in remote server the input record of user, and will analyze result
The input method system for returning to user terminal, as terminal user's attribute information.
S240, the recommendation is shown in setting display area.
S250, it is selected according to user, using the recommendation as the input results of the interface of input method, and in user
When sending user's input information including the recommendation, while sending the related information of the recommendation.
Further, when it includes user's input information of the recommendation that user, which sends, while the recommendation is sent
The related information of content may include:
When detecting that user sends user's input information including the recommendation, the user is inputted in information
The combined type recommendation replace with the word content in the compound recommendation after, send updated user input
Information.The benefit being arranged in this way is: on the basis of guaranteeing to send information integrity, reducing the transmission of redundancy, reduces
Data traffic consumed by the transmission recommendation.
Technical solution provided in an embodiment of the present invention filters out best match recommendation items conduct according to setting screening rule
Recommendation corresponding with the target label keyword, rapidly obtains recommendation, improves recommendation to user's reality
User experience of the user in exchange service information process is effectively promoted in the hit rate of border demand.
Embodiment three
The embodiment of the invention provides a kind of specific embodiments of information recommendation method.The information recommendation method is specific
Including following content:
Referring to Fig. 3 A, under the chat scenario of group chat mode, input method system obtains a group chat user in input method circle
Input " xiaofeiyang " in face, and determine at least one candidate word " small fertilizer sheep " and " Emperador Light " etc., wherein candidate word
In " small fertilizer sheep ", hit the target label keyword " small fertilizer sheep " in label keyword set.
If predefining the small fertile shop sheep Hui Nan shop to the value of bidding of label keyword according to recommendation provider
It bids and is worth highest, then recommendation corresponding with target label keyword " small fertilizer sheep " is determined as " small fertilizer sheep (shop Hui Nan) ",
After the recommendation is shown in the display position of candidate word in the form of text and picture, referring to Fig. 3 A, in recommendation, text
Word content is " small fertilizer sheep (shop Hui Nan) ", and image content is that quotient is promoted (for example, purchasing by group in the corresponding setting shop in the small fertilizer shop sheep Hui Nan
Class application program) icon, the icon is the footmark purchased by group using Baidu's glutinous rice in Fig. 3 A, which is shown in word content
The upper right corner.
After input method system detects that user clicks recommendation, recommendation is shown in input frame, referring to figure
3B, at this point, recommendation is correspondingly transformed to image content preceding, for word content rear, image content is the mark of Baidu's glutinous rice
Know.
Using recommendation as the input results of interface of input method, and the user including recommendation is sent in user and is inputted
When information, while sending the related information of recommendation.Referring to Fig. 3 C, the related information of above-mentioned recommendation includes small fertile sheep
The recommendation service hyperlink in the application of Baidu's glutinous rice in (shop Nan Hui), the corresponding per capita consuming level in the shop and consumer
The related information of the recommendations such as overall merit.
User is after receiving including the chat message of recommendation for other group chats, clicks in the recommendation under chat background
The related information of appearance, the service landing page that page jump to Baidu's glutinous rice under chat scenario provides, referring to Fig. 3 D and 3E, the clothes
Business landing page may include that store name, solid shop picture, user's evaluation, pre-capita consumption, contact method, address, the shop mention
What is supplied purchases by group activity, recommends dish and coupons etc..
At the same time, the related information of the equally available recommendation of the sender user of recommendation.Each user can
Directly to return to the chat scenario of group chat by service landing page.
Technical solution provided in an embodiment of the present invention, user can be under current scenes without being manually entered and using cutting
Information on services can be obtained by changing, and information on services is extended to chatting object.
Example IV
Fig. 4 is a kind of structural schematic diagram for information recommending apparatus that the embodiment of the present invention four provides.Referring to fig. 4, the letter
Breath recommendation apparatus includes that candidate word obtains module 40, recommendation obtains module 41, recommendation display module 42 and input are tied
Fruit determining module 43.
Wherein, candidate word obtains module 40 and is used to obtain user at least one candidate determining in the input of interface of input method
Word;Recommendation obtains module 41 and is used at least one described candidate word being compared with label keyword set, if institute
It states candidate word and hits target label keyword, then obtain recommendation corresponding with the target label keyword;Recommendation
Display module 42 is used to show the recommendation in setting display area;Input results determining module 43 is used for root
It is selected according to user, using the recommendation as the input results of the interface of input method, and sending in user includes described push away
When recommending user's input information of content, while sending the related information of the recommendation.
Technical solution provided in an embodiment of the present invention, by obtain input determination of the user in interface of input method at least one
A candidate word at least one candidate word is compared with label keyword set, if candidate word hits target label key
Word then obtains recommendation corresponding with target label keyword, and recommendation is shown in setting display area, and
It is selected according to user, using recommendation as the input results of interface of input method, and sends the use including recommendation in user
When family inputs information, while the related information of recommendation is sent, directly acquires recommendation information under the scene where input method,
The operation that user carries out information on services exchange is simplified, user is avoided and is manually entered information on services and terminal in different application
Between switching, save time and convenient and efficient.
Further, it may include local comparing unit and/or long-range comparing unit that recommendation, which obtains module 41,.
Wherein, local comparing unit for will at least one described candidate word in the label keyword set that is locally stored
Each label keyword be compared;Long-range comparing unit is used at least one described candidate word being sent to remote server,
To indicate the remote server by least one described candidate word and each label in the label keyword set that remotely stores
Keyword is compared, and returns to comparison result.
Further, it may include recommendation determination unit that recommendation, which obtains module 41,.Wherein, recommendation determines
Unit is used to determine recommendation corresponding with the label keyword, wherein the relating attribute according to setting relating attribute
Including recommendation provider to bid value and/or the recommendation and the label keyword of the label keyword
The degree of association.
Further, recommendation can be visiting card type composite content, wherein the composite content may include in text
Appearance and/or image content.
Further, the related information of recommendation may include the visiting card type composite content, recommendation service hyperlink
And recommend description information, wherein the recommendation service hyperlink is opened for guidance information recipient and is associated with recommendation
Service land page.
Further, the word content in the visiting card type composite content is store name, and the recommendation service hyperlink is connected in
Promote the hyperlink that the shop that quotient provides purchases by group the page in setting shop;Or
Word content in the visiting card type composite content is brand name or trade name, and the recommendation service hyperlink is connected in product
The hyperlink of board or commodity provider website homepage;Or
Word content in the visiting card type composite content is Brand Service name, and it is living that the recommendation service hyperlink is connected in brand
The hyperlink of the dynamic page.
Further, it may include recommendation screening unit that recommendation, which obtains module 41,.Recommendation screening unit
If corresponding to multinomial recommendation for the target label keyword, in the multinomial recommendation, sieved according to setting
Choosing rule, filters out best match recommendation items as recommendation corresponding with the target label keyword.
Further, recommendation screening unit specifically can be used for:
The multinomial recommendation is ranked up according to temperature, obtains the highest recommendation of temperature as best match
Recommendation items;Or
Terminal positional information is obtained, is carried out according to the related information of the terminal positional information and the multinomial recommendation
Matching obtains the highest recommendation of matching degree as best match recommendation items;Or
The chat contextual information for obtaining instant messaging scene locating for the interface of input method, according to the chat context
Information is matched with the related information of the multinomial recommendation, obtains the highest recommendation of matching degree as best match
Recommendation items;Or
Terminal user's attribute information is obtained, according to being associated with for terminal user's attribute information and the multinomial recommendation
Information is matched, and obtains the highest recommendation of matching degree as best match recommendation items.
Further, recommendation display module 42 specifically can be used for: by the recommendation in interface of input method
Setting display position in candidate word display area is shown, wherein the setting display position, which is located at, hits target label
After the display position of the candidate word of keyword.
Further, input results determining module 43 may include: replacement unit.Wherein, replacement unit is for detecting
When sending user's input information including the recommendation to user, the combined type that the user inputs in information is pushed away
After recommending the word content that content replaces in the compound recommendation, sends updated user and input information.
Information recommending apparatus provided in this embodiment belongs to information recommendation method provided by any embodiment of the invention
Information recommendation method provided by any embodiment of the invention can be performed in same inventive concept, has execution information recommended method
Corresponding functional module and beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is arbitrarily real
The information recommendation method of example offer is provided.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, any to be familiar with this profession
Technical staff, without departing from the scope of the present invention, when the technology contents using the disclosure above make a little change
More or modify etc., any modification, equivalent replacement or improvement done within the spirit and principles of the present invention etc. should all include
Within protection scope of the present invention.
Claims (16)
1. a kind of information recommendation method characterized by comprising
Obtain user's at least one candidate word determining in the input of interface of input method;
At least one described candidate word is compared with label keyword set, is closed if the candidate word hits target label
Keyword then obtains recommendation corresponding with the target label keyword, wherein the label keyword set is input method
System is directed to the set of candidate word setting;
The recommendation is shown in setting display area;
It is selected according to user, using the recommendation as the input results of the interface of input method, and is sent in user and include
When the user of the recommendation inputs information, while sending the related information of the recommendation;
Wherein, the recommendation is visiting card type composite content, and the visiting card type composite content includes word content and/or picture
Content;The related information of the recommendation includes the visiting card type composite content, recommendation service hyperlink and recommends to describe
Information, the recommendation service hyperlink is opened for guidance information recipient lands page with the associated service of recommendation.
2. information recommendation method according to claim 1, which is characterized in that will at least one described candidate word and label pass
Keyword set, which is compared, includes:
At least one described candidate word is compared with each label keyword in the label keyword set being locally stored;
And/or
At least one described candidate word is sent to remote server, to indicate that the remote server will at least one described time
It selects word to be compared with each label keyword in the label keyword set remotely stored, and returns to comparison result.
3. information recommendation method according to claim 1, which is characterized in that obtain corresponding with the target label keyword
Recommendation include:
According to setting relating attribute, corresponding with label keyword recommendation is determined, wherein the relating attribute includes
Pass of the recommendation provider to bid value and/or the recommendation and the label keyword of the label keyword
Connection degree.
4. information recommendation method according to claim 1, which is characterized in that in the text in the visiting card type composite content
Holding is store name, and the recommendation service hyperlink is connected in setting shop and promotes the hyperlink that the shop that quotient provides purchases by group the page;Or
Word content in the visiting card type composite content is brand name or trade name, the recommendation service hyperlink be connected in brand or
The hyperlink of commodity provider website homepage;Or
Word content in the visiting card type composite content is Brand Service name, and the recommendation service hyperlink is connected in brand campaigns page
The hyperlink in face.
5. information recommendation method according to claim 1, which is characterized in that will at least one described candidate word and label pass
Keyword set is compared, if the candidate word hits target label keyword, obtains and the target label keyword
Corresponding recommendation, comprising:
If the target label keyword corresponds to multinomial recommendation, in the multinomial recommendation, sieved according to setting
Choosing rule, filters out best match recommendation items as recommendation corresponding with the target label keyword.
6. information recommendation method according to claim 5, which is characterized in that in the multinomial recommendation, according to setting
Determine screening rule, filters out best match recommendation items as recommendation corresponding with the target label keyword, specific packet
It includes:
The multinomial recommendation is ranked up according to temperature, the highest recommendation of temperature is obtained and recommends as best match
?;Or
Terminal positional information is obtained, according to the progress of the related information of the terminal positional information and the multinomial recommendation
Match, obtains the highest recommendation of matching degree as best match recommendation items;Or
The chat contextual information for obtaining instant messaging scene locating for the interface of input method, according to the chat contextual information
It is matched with the related information of the multinomial recommendation, obtains the highest recommendation of matching degree and recommend as best match
?;Or
Terminal user's attribute information is obtained, according to the related information of terminal user's attribute information and the multinomial recommendation
It is matched, obtains the highest recommendation of matching degree as best match recommendation items.
7. information recommendation method according to claim 1, which is characterized in that by the recommendation in setting display area
Inside shown, comprising:
Setting display position of the recommendation in the candidate word display area of interface of input method is shown, wherein
The setting display position is located at after the display position for the candidate word for hitting target label keyword.
8. information recommendation method according to claim 1, which is characterized in that sending in user includes the recommendation
When user inputs information, while sending the related information of the recommendation, comprising:
When detecting that user sends user's input information including the recommendation, the user is inputted into the institute in information
After stating the word content that recommendation replaces in the visiting card type composite content, sends updated user and input information.
9. a kind of information recommending apparatus characterized by comprising
Candidate word obtains module, for obtaining user's at least one candidate word determining in the input of interface of input method;
Recommendation obtains module, at least one described candidate word to be compared with label keyword set, if institute
It states candidate word and hits target label keyword, then obtain recommendation corresponding with the target label keyword, wherein described
Label keyword set is the set that input method system is directed to candidate word setting;
Recommendation display module, for showing the recommendation in setting display area;
Input results determining module, for being selected according to user, using the recommendation as the input of the interface of input method
As a result, and when it includes that the user of the recommendation inputs information that user, which sends, while sending the association of the recommendation
Information;
Wherein, the recommendation is visiting card type composite content, and the visiting card type composite content includes word content and/or picture
Content;The related information of the recommendation includes the visiting card type composite content, recommendation service hyperlink and recommends to describe
Information, the recommendation service hyperlink is opened for guidance information recipient lands page with the associated service of recommendation.
10. information recommending apparatus according to claim 9, which is characterized in that the recommendation obtains module, comprising:
Local comparing unit, for by least one described candidate word and each label in the label keyword set that is locally stored
Keyword is compared;And/or
Long-range comparing unit, at least one described candidate word to be sent to remote server, to indicate the remote service
At least one described candidate word is compared device with each label keyword in the label keyword set remotely stored, and returns
Return comparison result.
11. information recommending apparatus according to claim 9, which is characterized in that the recommendation obtains module, comprising:
Recommendation determination unit, for determining recommendation corresponding with the label keyword according to setting relating attribute,
Wherein, the relating attribute includes bid value and/or the recommendation of the recommendation provider to the label keyword
With the degree of association of the label keyword.
12. information recommending apparatus according to claim 9, which is characterized in that the text in the visiting card type composite content
Content is store name, and the recommendation service hyperlink is connected in setting shop and promotes the hyperlink that the shop that quotient provides purchases by group the page;Or
Person
Word content in the visiting card type composite content is brand name or trade name, the recommendation service hyperlink be connected in brand or
The hyperlink of commodity provider website homepage;Or
Word content in the visiting card type composite content is Brand Service name, and the recommendation service hyperlink is connected in brand campaigns page
The hyperlink in face.
13. information recommending apparatus according to claim 9, which is characterized in that recommendation obtains module, comprising:
Recommendation screening unit, if multinomial recommendation is corresponded to for the target label keyword, described multinomial
In recommendation, according to setting screening rule, best match recommendation items are filtered out as corresponding with the target label keyword
Recommendation.
14. information recommending apparatus according to claim 13, which is characterized in that recommendation screening unit is specifically used for:
The multinomial recommendation is ranked up according to temperature, the highest recommendation of temperature is obtained and recommends as best match
?;Or
Terminal positional information is obtained, according to the progress of the related information of the terminal positional information and the multinomial recommendation
Match, obtains the highest recommendation of matching degree as best match recommendation items;Or
The chat contextual information for obtaining instant messaging scene locating for the interface of input method, according to the chat contextual information
It is matched with the related information of the multinomial recommendation, obtains the highest recommendation of matching degree and recommend as best match
?;Or
Terminal user's attribute information is obtained, according to the related information of terminal user's attribute information and the multinomial recommendation
It is matched, obtains the highest recommendation of matching degree as best match recommendation items.
15. information recommending apparatus according to claim 9, which is characterized in that the recommendation display module, it is specific to use
In:
Setting display position of the recommendation in the candidate word display area of interface of input method is shown, wherein
The setting display position is located at after the display position for the candidate word for hitting target label keyword.
16. information recommending apparatus according to claim 9, which is characterized in that the input results determining module, comprising:
Replacement unit, for detect user send include the recommendation user input information when, by the user
After the recommendation in input information replaces with the word content in the visiting card type composite content, updated use is sent
Family inputs information.
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 CN105607756A (en) | 2016-05-25 |
CN105607756B true 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) |
Families Citing this family (30)
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 |
TWI654529B (en) * | 2016-08-02 | 2019-03-21 | 財團法人資訊工業策進會 | Network device and message providing 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 |
CN108664336A (en) * | 2017-04-01 | 2018-10-16 | 北京搜狗科技发展有限公司 | Recommend method and apparatus, the device for recommendation |
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 |
CN109101505B (en) * | 2017-06-20 | 2021-09-03 | 北京搜狗科技发展有限公司 | Recommendation method, recommendation device and device for recommendation |
CN108306814B (en) * | 2017-08-11 | 2020-07-28 | 腾讯科技(深圳)有限公司 | Information pushing method, device, terminal and storage medium based on instant messaging |
CN107526828B (en) * | 2017-09-01 | 2020-10-16 | 阿里巴巴(中国)有限公司 | Page information recommendation method and device |
CN110020106B (en) * | 2017-09-08 | 2021-11-19 | 北京搜狗科技发展有限公司 | Recommendation method, recommendation device and 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 |
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 |
CN110033338A (en) * | 2018-01-11 | 2019-07-19 | 北京搜狗科技发展有限公司 | Recommended method and device, the device for recommendation |
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 |
CN110096165A (en) * | 2018-01-31 | 2019-08-06 | 北京搜狗科技发展有限公司 | A kind of association method, device and electronic equipment |
CN108376162B (en) * | 2018-02-22 | 2019-10-18 | 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 |
CN109446311B (en) * | 2018-10-30 | 2022-04-05 | 五八有限公司 | Chat enhancement method, device, storage medium and terminal |
CN109725863B (en) * | 2018-11-14 | 2022-04-19 | 北京风行在线技术有限公司 | Method, device, equipment and system for screen projection |
CN110222256B (en) * | 2019-05-06 | 2021-10-22 | 北京搜狗科技发展有限公司 | Information recommendation method and device and information recommendation device |
CN110162710B (en) * | 2019-05-28 | 2022-06-21 | 北京搜狗科技发展有限公司 | Information recommendation method and device under input scene |
CN112118169B (en) * | 2019-06-21 | 2023-04-18 | 腾讯科技(深圳)有限公司 | Message reply method, device, terminal and storage medium |
CN112118168B (en) * | 2019-06-21 | 2022-07-22 | 腾讯科技(深圳)有限公司 | Message sending method, device, terminal and storage medium |
CN110989847B (en) * | 2019-11-22 | 2024-03-29 | 维沃移动通信有限公司 | Information recommendation method, device, terminal equipment and storage medium |
CN112988031B (en) * | 2019-12-18 | 2023-06-27 | 北京搜狗科技发展有限公司 | Position input method and device and electronic equipment |
CN112383662B (en) * | 2020-11-09 | 2022-03-25 | 维沃移动通信有限公司 | Information display method and device and electronic equipment |
CN115080833B (en) * | 2021-03-10 | 2024-02-27 | 阿里巴巴新加坡控股有限公司 | Information flow recommendation method, equipment, system and storage medium |
CN112883279A (en) * | 2021-03-24 | 2021-06-01 | 杭州太火鸟科技有限公司 | Intelligent recommendation method, device and equipment based on big data and readable storage medium |
CN115686337A (en) * | 2022-06-06 | 2023-02-03 | 北京百度网讯科技有限公司 | Information processing method, information processing device, electronic equipment and computer readable storage medium |
Citations (4)
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 |
-
2015
- 2015-12-24 CN CN201510984623.1A patent/CN105607756B/en active Active
Patent Citations (5)
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 |
Also Published As
Publication number | Publication date |
---|---|
CN105607756A (en) | 2016-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105607756B (en) | Information recommendation method and device | |
US10805252B2 (en) | Prioritizing messages within a message network | |
US9830313B2 (en) | Identifying expanding hashtags in a message | |
US11061990B2 (en) | Generating feedback for a target content item based on published content items | |
CN110046299B (en) | Computerized system and method for automatically performing an implicit message search | |
US10845949B2 (en) | Continuity of experience card for index | |
CN107580704A (en) | Context personage recommends | |
US20150254714A1 (en) | Systems and methods for keyword suggestion | |
KR20140105841A (en) | Systems and methods for identifying and suggesting emoticons | |
CN106682170B (en) | Application search method and device | |
US10269048B2 (en) | Xpath related and other techniques for use in native advertisement placement | |
US20160098416A1 (en) | Auto complete search box based on the user's context to reduce user's input | |
CN104731870A (en) | Method and device for providing recommendation information | |
CN105389361A (en) | Search recommendation method and apparatus | |
US10990620B2 (en) | Aiding composition of themed articles about popular and novel topics and offering users a navigable experience of associated content | |
CN110459211A (en) | Interactive method, client, electronic equipment and storage medium | |
CN104063799A (en) | Promotion message pushing method and device | |
CN108269196A (en) | Add in the method, apparatus and computer equipment of network social association | |
CN113590851A (en) | Suggesting entities in an online system to create content and add tags to the content | |
CN113434755A (en) | Page generation method and device, electronic equipment and storage medium | |
CN111563198A (en) | Material recall method, device, equipment and storage medium | |
US10922722B2 (en) | System and method for contextual video advertisement serving in guaranteed display advertising | |
US20150293977A1 (en) | Interactive search results | |
US20180032907A1 (en) | Detecting abusive language using character n-gram features | |
CN108920125B (en) | It is a kind of for determining the method and apparatus of speech recognition result |
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 |