CN105989120A - Personalized content recommendation method and personalized content recommendation system - Google Patents
Personalized content recommendation method and personalized content recommendation system Download PDFInfo
- Publication number
- CN105989120A CN105989120A CN201510080720.8A CN201510080720A CN105989120A CN 105989120 A CN105989120 A CN 105989120A CN 201510080720 A CN201510080720 A CN 201510080720A CN 105989120 A CN105989120 A CN 105989120A
- Authority
- CN
- China
- Prior art keywords
- user
- key word
- content
- relevant
- terminal
- 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
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a personalized content recommendation method and a personalized content recommendation system. The method comprises the following steps: analyzing the current interface of a terminal, and extracting at least one keyword from the interface; outputting a dialog box, wherein the dialog box comprises prompt information, and the prompt information is used for prompting a user to check contents associated with the keyword or not; detecting whether a confirmation instruction input by the user by aiming at the prompt information is received or not within preset time, wherein the confirmation instruction is used for indicating the terminal to output the contents associated with the keyword; and when the confirmation instruction input by the user by aiming at the prompt information is received within preset time, recommending the contents associated with the keyword to the user. The embodiment of the invention can be implemented to recommend associated contents to the user according to the requirements of the user, and lowers the dislike degree of the user.
Description
Technical field
The present invention relates to communication technical field, particularly relate in a kind of personalization content recommendation method and personalization
Hold commending system.
Background technology
Along with developing rapidly of mobile communication technology, many operators provide the user by offering software store
Various application softwaries and service.Currently, operator is in order to promote the product of oneself newly research and development, it will usually with
After family enters software store, pop-up dialogue box recommends the product of these new research and development to user, and user is due to this
The product of new research and development does not has any understanding, or does not need the product of these new research and development, and user would generally be straight
Connect close box.Visible, this way of recommendation easily causes the dislike of user, is difficult to meet user personality
The requirement changed.
Summary of the invention
The embodiment of the present invention provides a kind of personalization content recommendation method and individualized content commending system, permissible
Demand according to user recommends related content to user, reduces the dislike degree of user.
Embodiment of the present invention first aspect provides a kind of personalization content recommendation method, including:
The interface that analysing terminal is current, and from described interface, extract at least one key word;
Output dialog box, described dialog box includes that information, described information are used for prompting the user whether
Check the content relevant to described key word;
Whether detection receives the confirmation instruction that user inputs for described information, institute in Preset Time
State and confirm that instruction is for indicating the content that the output of described terminal is relevant to described key word;
When receiving the confirmation instruction that user inputs for described information in described Preset Time, to
User recommends the content relevant to described key word.
In the first possible implementation of first aspect, receive in Preset Time in step detection
After user instructs for the confirmation that described information inputs, and recommend and described pass to user in step
Before the content that keyword is relevant, described method also includes:
The historical record that user is relevant to described key word is obtained according to described key word;
Resolve described historical record, the preference type relevant to described key word to determine user;
The described content relevant to described key word to user's recommendation, including:
According to described preference type, recommend the content relevant to described key word to user.
In conjunction with the first possible implementation of first aspect, the realization that the second in first aspect is possible
In mode, resolve described historical record, the preference type relevant to described key word to determine user in step
Afterwards, and in step according to described preference type, to user recommend the content relevant to described key word it
Before, described method also includes:
Obtain described terminal residual internal memory;
Described according to described preference type, recommend the content relevant to described key word to user, including:
According to described preference type and described terminal residual internal memory, recommend relevant to described key word to user
Content.
In conjunction with the implementation that the second of first aspect is possible, in the third possible realization of first aspect
In mode, described according to described preference type with described terminal residual internal memory, recommend and described key to user
The content that word is relevant, including:
According to described preference type and described terminal residual internal memory, search matches with described preference type and accounts for
The content of described free memory it is less than with internal memory;
The content relevant to described key word searched is recommended to user.
In conjunction with first aspect, in the 4th kind of possible implementation of first aspect, described method also includes:
When detection does not receives the confirmation instruction that user inputs for described information in Preset Time,
Close described dialog box.
Embodiment of the present invention second aspect provides a kind of individualized content commending system, including:
Analyzing module, for the interface that analysing terminal is current, and it is crucial to extract at least one from described interface
Word;
Output module, is used for exporting dialog box, and described dialog box includes information, and described information is used
Check the content relevant to described key word in prompting the user whether;
Whether detection module, receive user in Preset Time for detection and input for described information
Confirmation instruction, described confirm that instruction is for indicating the described terminal output content relevant to described key word;
Recommending module, for carrying for described when described detection module receives user in described Preset Time
When showing the confirmation instruction that information inputs, recommend the content relevant to described key word to user.
In conjunction with second aspect, in the first possible implementation of second aspect, described system also includes:
Type acquisition module, for receiving user for institute at described detection module in described Preset Time
After stating the confirmation instruction of information input, and described recommending module is recommended and described key word to user
Before relevant content, obtain, according to described key word, the historical record that user is relevant to described key word;
Parsing module, is used for resolving described historical record, the hobby relevant to described key word to determine user
Type;
Described recommending module, specifically for according to described preference type, recommending and described key word phase to user
The content closed.
In conjunction with the first possible implementation of second aspect, the realization that the second in second aspect is possible
In mode, described system also includes:
Internal memory acquisition module, for resolving described historical record at described parsing module, to determine user and institute
After stating the preference type that key word is relevant, and described recommending module is according to described preference type and described end
End free memory, before user recommends the content relevant to described key word, obtains in described terminal residual
Deposit;
Described recommending module, specifically for according to described preference type and described terminal residual internal memory, to user
Recommend the content relevant to described key word.
In conjunction with the implementation that the second of second aspect is possible, in the third possible realization of second aspect
In mode, described recommending module includes:
Search subelement, for according to described preference type and described terminal residual internal memory, search and described happiness
Good type matching and committed memory are less than the content of described free memory;
Recommend subelement, for recommending the content relevant to described key word searched to user.
In conjunction with second aspect, in the 4th kind of possible implementation of second aspect, described system also includes:
Close module, for not receiving user in Preset Time for described in the detection of described detection module
When the confirmation of information input instructs, close described dialog box.
Compared to prior art, a kind of personalization content recommendation method of embodiment of the present invention offer and personalization
Commending contents terminal, by the interface that analysing terminal is current, and it is crucial to extract at least one from described interface
Word, exports dialog box further, receives what user included for this dialog box in detection in Preset Time
After the confirmation instruction of information input, recommend the content relevant to this key word to user, such that it is able to
Demand according to user recommends related content to user, reduces the dislike degree of user.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, institute in embodiment being described below
The accompanying drawing used is needed to be briefly described, it should be apparent that, the accompanying drawing in describing below is only the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work,
Other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of a kind of personalization content recommendation method disclosed in the embodiment of the present invention;
Fig. 2 is the schematic flow sheet of another kind of personalization content recommendation method disclosed in the embodiment of the present invention;
Fig. 3 is the structural representation of a kind of individualized content commending system disclosed in the embodiment of the present invention;
Fig. 4 is the structural representation of another kind of individualized content commending system disclosed in the embodiment of the present invention;
Fig. 5 is the structural representation of another kind of individualized content commending system disclosed in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
The every other embodiment obtained under property work premise, broadly falls into the scope of protection of the invention.
The embodiment of the invention discloses a kind of personalization content recommendation method and individualized content commending system, can
To improve the convenience of user's downloaded software.It is described in detail individually below.
In the embodiment of the present invention, terminal can include any device that network can be utilized to carry out content recommendation;It addition,
Terminal can also include smart machine, such as smart mobile phone, panel computer, personal computer (Personal
Computer, PC), the smart machine such as notebook computer.Wherein, this content can include but not limited to application
Program (such as various APP), theme, the tinkle of bells, wallpaper, webpage, evaluation and test, activity, special topic, classification and
Consumer products advertisements etc., the embodiment of the present invention is not construed as limiting.
Referring to Fig. 1, Fig. 1 is that disclosed in the embodiment of the present invention, the flow process of a kind of personalization content recommendation method is shown
It is intended to.As it is shown in figure 1, the method may comprise steps of:
The interface that S101, analysing terminal are current, and from interface, extract at least one key word.
In the embodiment of the present invention, the current interface of terminal can include but not limited to Application Program Interface, theme
Browser interface, the tinkle of bells browser interface, wallpaper browser interface, web page browsing interface, evaluation and test interface, movable boundary
Face, special topic interface, classification interface and consumer products advertisement interface etc., the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, terminal can analyze the interface currently browsed, and from the interface currently browsed
Extract a key word, it is also possible to from the interface currently browsed, extract multiple key word.
As an example it is assumed that terminal is currently at wallpaper browser interface, after this wallpaper browser interface of terminal analysis,
A key word can be extracted from current wallpaper browser interface, such as " wallpaper ", it is also possible to extract multiple key word,
Such as " wallpaper " " dynamically ", the embodiment of the present invention is not construed as limiting.
S102, output dialog box.
In the embodiment of the present invention, above-mentioned dialog box includes information, and this information is used for pointing out the user be
No check the content relevant to key word.
In the embodiment of the present invention, terminal output dialog box is not in the output of any interface in terminal, but
During certain module interfaces (such as wallpaper module interfaces) in terminal enters application market or software store
Output.
Whether S103, detection receive the confirmation instruction that user inputs for information in Preset Time,
If so, step S104 is performed, if it is not, process ends.
In the embodiment of the present invention, above-mentioned Preset Time can be terminal system time of acquiescence when dispatching from the factory, it is possible to
Thinking the Preset Time that user is arranged in advance, the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, above-mentioned confirmation instruction be by user click or double-click in dialog box virtual really
Recognize button and trigger.
In one embodiment, in Preset Time, do not receive what user inputted for information when detection
When confirming instruction, terminal can be automatically switched off dialog box, in order to avoid causing the dislike of user.
As the optional embodiment of one, when detection does not receives user for prompting letter in Preset Time
When the confirmation of breath input instructs, terminal can export above-mentioned dialog box again, checks this dialogue when user cancels
When the number of times of frame reaches predetermined threshold value (such as 3 times), terminal no longer can export this dialog box to this user.
S104, recommend the content relevant to key word to user.
In the embodiment of the present invention, in Preset Time, receive user for prompting in the detection of step S103 terminal
After the confirmation instruction of information input, show that user agrees to check the content relevant to key word, now, terminal
Can send searching request to server, this searching request includes the key word of said extracted, so that service
Device, according to this key word, searches for the content relevant to this key word from data base, and wherein, this server can
To search for the content relevant to this key word in the application market belonging to the interface at this terminal present analysis, also
The content relevant to this key word can be searched for outside application market, then send in the content that will search
To terminal, this content is being shown on terminal interface to recommend the content relevant to key word to user by terminal.
It should be noted that above-mentioned terminal necessarily be in network service state could receive server send with
The content that key word is relevant, namely above-mentioned terminal necessarily be in network service state and could recommend to user and close
The content that keyword is relevant.
As an example it is assumed that terminal is currently at wallpaper browser interface, the key word that terminal is extracted is " wallpaper "
" dynamically ", terminal after receiving the confirmation instruction that user inputs for information, will carry wallpaper with
The searching request of dynamic two key words is sent to server, after server receives this searching request, is counting
According to storehouse is searched for the content relevant to " wallpaper " " dynamically ", then the various dynamic wallpapers searched are sent
To terminal, this dynamic wallpaper is being recommended user by terminal.
As a kind of optional embodiment, in Preset Time, receive user for institute in the detection of step S103
After stating the confirmation instruction of information input, and recommend and described key word phase to user in step S104
Before the content closed, described method also includes:
The historical record that user is relevant to described key word is obtained according to described key word;
Resolve described historical record, the preference type relevant to described key word to determine user;
The described content relevant to described key word to user's recommendation, including:
According to described preference type, recommend the content relevant to described key word to user.
In this embodiment, terminal can determine the preference type of user according to the historical record of user, enters
And to recommend the content consistent with described preference type to user according to this preference type, use such that it is able to improve
The satisfaction of family individual demand.
In one embodiment, terminal can also obtain the internal memory of terminal current residual, in conjunction with the hobby of user
Type and terminal residual internal memory, recommend the content relevant to key word to user, so can search server
Rope to the content relevant to key word screen further, select with general and meet in user preferences and terminal residual
Depositing the content that can accommodate, this way of recommendation is possible not only to the content committed memory nothing too greatly avoiding recommending
The problem that method is installed, can also meet the requirement of user individual simultaneously.
In the embodiment depicted in figure 1, by the interface that analysing terminal is current, and extract from interface to
A few key word, exports dialog box further, receives user in detection right for this in Preset Time
After the confirmation instruction of the information input that words frame includes, recommend the content relevant to this key word to user,
Such that it is able to recommend related content according to the demand of user to user, reduce the dislike degree of user.
Referring to Fig. 2, Fig. 2 is the flow process of another kind of personalization content recommendation method disclosed in the embodiment of the present invention
Schematic diagram.As in figure 2 it is shown, the method may comprise steps of:
The interface that S201, analysing terminal are current, and from interface, extract at least one key word.
In the embodiment of the present invention, the current interface of terminal can include but not limited to Application Program Interface, theme
Browser interface, the tinkle of bells browser interface, wallpaper browser interface, web page browsing interface, evaluation and test interface, movable boundary
Face, special topic interface, classification interface and consumer products advertisement interface etc., the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, terminal can analyze the interface currently browsed, and from the interface currently browsed
Extract a key word, it is also possible to from the interface currently browsed, extract multiple key word.
As an example it is assumed that terminal is currently at wallpaper browser interface, after this wallpaper browser interface of terminal analysis,
A key word can be extracted from current wallpaper browser interface, such as " wallpaper ", it is also possible to extract multiple key word,
Such as " wallpaper " " dynamically ", the embodiment of the present invention is not construed as limiting.
S202, output dialog box.
In the embodiment of the present invention, above-mentioned dialog box includes information, and this information is used for pointing out the user be
No check the content relevant to key word.
In the embodiment of the present invention, terminal output dialog box is not in the output of any interface in terminal, but
During certain module interfaces (such as wallpaper module interfaces) in terminal enters application market or software store
Output.
Whether S203, detection receive the confirmation instruction that user inputs for information in Preset Time,
If so, step S204 is performed, if it is not, perform step S208.
In the embodiment of the present invention, above-mentioned Preset Time can be terminal system time of acquiescence when dispatching from the factory, it is possible to
Thinking the Preset Time that user is arranged in advance, the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, above-mentioned confirmation instruction be by user click or double-click in dialog box virtual really
Recognize button and trigger.
S204, according to key word, obtain the historical record that user is relevant to key word.
In the embodiment of the present invention, this historical record can be some contents of terminal storage, it is also possible to is user
Content browsed under network state, the embodiment of the present invention is not construed as limiting.
As an example it is assumed that this key word is the tinkle of bells, terminal just can obtain the historical record being correlated with the tinkle of bells,
This historical record can be the music of storage in terminal music player list, it is also possible to be that user watched
Song in Internet video, it is also possible to be the background music of certain webpage, and for example assumes that this key word is wallpaper,
Terminal just can obtain the historical record being correlated with wallpaper, and this historical record can be storage in terminal photograph album
Picture, it is also possible to for the picture in the video that user watched, it is also possible to for the picture in certain interface.
S205, parsing historical record, the preference type relevant to key word to determine user.
In the embodiment of the present invention, terminal get user with the relevant historical record of key word after, one can be entered
Step analyzes this historical record, obtains the preference type that user is relevant to key word from historical record.Such as,
This key word is the tinkle of bells, and terminal obtains the music stored in terminal music player list and user watched
Video in music, extract the beat of these music and title of the song or the lyrics, analyze and determine that user likes
Type.Such as, these music beats are relatively slower, all with " love " word in title of the song or the lyrics, then
Terminal may determine that the ringing-type that user likes be rhythm slowly and in title of the song or the lyrics all with " love " word
Type.
S206, acquisition terminal residual internal memory.
In the embodiment of the present invention, terminal need obtain terminal residual internal memory, i.e. terminal can also store new
Internal memory shared by content, with the problem avoiding the content recommended to occur installing.For example, it is assumed that terminal
Free memory is 2G, then the internal memory shared by content recommended not can exceed that 2G.
S207, according to preference type and terminal residual internal memory, recommend the content relevant to key word to user.
In the embodiment of the present invention, step S207 according to preference type and terminal residual internal memory, to user recommend with
The specific implementation of the content that key word is relevant may comprise steps of:
11) according to described preference type and described terminal residual internal memory, search matches with described preference type
And committed memory is less than the content of described free memory;
12) content relevant to described key word searched is recommended to user.
In the embodiment of the present invention, after the preference type determining user, in combining terminal current residual
Deposit, the content relevant to key word searched made screening further, select with general meet user preferences and
The content that terminal residual internal memory can accommodate, by this way of recommendation, is possible not only to the content avoiding recommending
The problem that committed memory is too big and cannot install, can also meet the requirement of user individual simultaneously.
S208, close box.
In the embodiment of the present invention, when detection does not receives what user inputted for information in Preset Time
When confirming instruction, terminal can be automatically switched off dialog box, in order to avoid causing the dislike of user.
In the embodiment depicted in fig. 2, at the interface that analysing terminal is current, and extract at least from interface
One key word, and detection receives the confirmation that user input for information in Preset Time and instructs
Afterwards, preference type and terminal residual internal memory further combined with user to recommend and this key word to user
Relevant content, such that it is able to recommend related content according to the demand of user to user, reduces the dislike of user
Degree.
Being apparatus of the present invention embodiment below, apparatus of the present invention embodiment is used for performing the inventive method embodiment
One to two method realized, for convenience of description, illustrate only the part relevant to the embodiment of the present invention, tool
Body technique details does not discloses, and refer to the embodiment of the present invention one and embodiment two.
Referring to Fig. 3, Fig. 3 is that disclosed in the embodiment of the present invention, the structure of a kind of individualized content commending system is shown
It is intended to;As it is shown on figure 3, this individualized content commending system 300 may include that analysis module 301, output
Module 302, detection module 303 and recommending module 304, wherein:
Analyze module 301, for the interface that analysing terminal is current, and from described interface, extract at least one pass
Keyword.
In the embodiment of the present invention, the current interface of terminal 300 can include but not limited to Application Program Interface,
Theme browser interface, the tinkle of bells browser interface, wallpaper browser interface, web page browsing interface, evaluation and test interface, work
Arena face, special topic interface, classification interface and consumer products advertisement interface etc., the embodiment of the present invention does not limits
Fixed.
In the embodiment of the present invention, terminal 300 can analyze the interface currently browsed, and from the boundary currently browsed
Face is extracted a key word, it is also possible to from the interface currently browsed, extract multiple key word.
As an example it is assumed that terminal 300 is currently at wallpaper browser interface, it is clear that terminal 300 analyzes this wallpaper
Look at behind interface, a key word can be extracted from current wallpaper browser interface, such as " wallpaper ", it is also possible to extract
Multiple key words, such as " wallpaper " " dynamically ", the embodiment of the present invention is not construed as limiting.
Output module 302, is used for exporting dialog box, and described dialog box includes information, described information
Check the content relevant to described key word for prompting the user whether.
In the embodiment of the present invention, above-mentioned dialog box includes information, and this information is used for pointing out the user be
No check the content relevant to key word.
In the embodiment of the present invention, it is not to be in any interface in terminal 300 that output module 302 exports dialog box
Output, but certain module interfaces (the such as wall in terminal 300 enters application market or software store
Paper module interfaces) time just output.
Whether detection module 303, receive user for detection defeated for described information in Preset Time
The confirmation instruction entered, described confirmation instruction is for indicating the content that the output of described terminal is relevant to described key word.
In the embodiment of the present invention, above-mentioned Preset Time can be terminal system time of acquiescence when dispatching from the factory, it is possible to
Thinking the Preset Time that user is arranged in advance, the embodiment of the present invention is not construed as limiting.
In the embodiment of the present invention, above-mentioned confirmation instruction be by user click or double-click in dialog box virtual really
Recognize button and trigger.
In one embodiment, in Preset Time, user is not received for carrying when detection module 303 detects
When showing the confirmation instruction that information inputs, terminal 300 can be automatically switched off dialog box, in order to avoid causing, user's is anti-
Sense.
As the optional embodiment of one, in Preset Time, do not receive use when detection module 303 detects
During the confirmation instruction that family inputs for information, output module 302 can export above-mentioned dialog box again,
When user cancels and checks that the number of times of this dialog box reaches predetermined threshold value (such as 3 times), output module 302
No longer can export this dialog box to this user.
Recommending module 304, for receiving user for described when described detection module in described Preset Time
When the confirmation of information input instructs, recommend the content relevant to described key word to user.
In the embodiment of the present invention, detect at detection module 303 and in Preset Time, receive user for prompting
After the confirmation instruction of information input, show that user agrees to check the content relevant to key word, now, terminal
Can send searching request to server, this searching request includes the key word of said extracted, so that service
Device, according to this key word, searches for the content relevant to this key word from data base, and wherein, this server can
To search for the content relevant to this key word in the application market belonging to the interface at this terminal present analysis, also
The content relevant to this key word can be searched for outside application market, then send in the content that will search
To terminal, this content is being shown on terminal interface to recommend the content relevant to key word to user by terminal.
It should be noted that above-mentioned terminal 300 necessarily be in network service state could receive server transmission
The content relevant with key word, namely above-mentioned terminal necessarily be in network service state and could recommend to user
The content relevant to key word.
As an example it is assumed that terminal is currently at wallpaper browser interface, the key word that terminal is extracted is " wallpaper "
" dynamically ", terminal after receiving the confirmation instruction that user inputs for information, will carry wallpaper with
The searching request of dynamic two key words is sent to server, after server receives this searching request, is counting
According to storehouse is searched for the content relevant to " wallpaper " " dynamically ", then the various dynamic wallpapers searched are sent
To terminal, this dynamic wallpaper is being recommended user by terminal.
As the optional embodiment of one, please also refer to Fig. 4, Fig. 4 be disclosed in the embodiment of the present invention another
A kind of structural representation of individualized content commending system;Wherein, the system shown in Fig. 4 is shown in Fig. 3
System on the basis of further optimize and to obtain, as shown in Figure 4, this individualized content commending system 300
Can also include: record acquisition module 305 and parsing module 306, wherein:
Record acquisition module 305, for receiving user at above-mentioned detection module 303 in above-mentioned Preset Time
After the confirmation instruction inputted for above-mentioned information, and above-mentioned recommending module 304 to user recommend with
Before the content that above-mentioned key word is relevant, obtain go through relevant to above-mentioned key word of user according to above-mentioned key word
The Records of the Historian is recorded.
In the embodiment of the present invention, this historical record can be some contents of terminal storage, it is also possible to is user
Content browsed under network state, the embodiment of the present invention is not construed as limiting.
As an example it is assumed that this key word is the tinkle of bells, record acquisition module 305 just can obtain with the tinkle of bells phase
The historical record closed, this historical record can be the music of storage in terminal music player list, it is also possible to
It is the song in the Internet video watched of user, it is also possible to be the background music of certain webpage, and for example assume
This key word is wallpaper, and terminal just can obtain the historical record being correlated with wallpaper, and this historical record can be
The picture of storage in terminal photograph album, it is also possible to for the picture in the video that user watched, it is also possible to for certain
Picture in interface.
Parsing module 306, is used for resolving described historical record, the happiness relevant to described key word to determine user
Good type;
In the embodiment of the present invention, record acquisition module 305 gets the historical record that user is correlated with key word
After, this historical record can be analyzed by parsing module 306 further, from historical record, obtain user and pass
The preference type that keyword is relevant.Such as, this key word is the tinkle of bells, and terminal obtains terminal music player list
Music in the video that the music of middle storage and user watched, extracts beat and the title of the song of these music
Or the lyrics, analyze and determine the type that user likes.Such as, these music beats are relatively slow, title of the song or
All with " love " word in the lyrics, then terminal may determine that the ringing-type that user likes be rhythm slowly and
All with the type of " love " word in title of the song or the lyrics.
Above-mentioned recommending module 304, specifically for according to described preference type, recommending relevant to key word to user
Content.
As the optional embodiment of one, please also refer to Fig. 5, Fig. 5 be disclosed in the embodiment of the present invention another
A kind of structural representation of individualized content commending system;Wherein, the system shown in Fig. 5 is shown in Fig. 4
System on the basis of further optimize and to obtain, as it is shown in figure 5, this individualized content commending system 300
Internal memory acquisition module 307 can also be included, wherein:
Internal memory acquisition module 307, for described parsing module resolve described historical record, with determine user with
After the preference type that described key word is relevant, and described recommending module is according to described preference type and described
Terminal residual internal memory, before user recommends the content relevant to described key word, obtains described terminal residual
Internal memory.
In the embodiment of the present invention, internal memory acquisition module 307 needs to obtain terminal residual internal memory, i.e. terminal and also may be used
With the internal memory shared by the new content of storage, with the problem avoiding the content recommended to occur installing.Example
As, it is assumed that save as 2G in terminal residual, then the internal memory shared by content recommended not can exceed that 2G.
Described recommending module, specifically for according to described preference type and described terminal residual internal memory, to user
Recommend the content relevant to described key word.
As the optional embodiment of one, described recommending module 304 may include that
Search subelement 3041, for according to described preference type and described terminal residual internal memory, search and institute
State preference type to match and committed memory is less than the content of described free memory;
Recommend subelement 3042, for recommending the content relevant to described key word searched to user.
In this inventive embodiments, after the preference type determining user, combining terminal current residual
Internal memory, makees screening further to the content relevant to key word searched, selects with general and meet user preferences
And the content that terminal residual internal memory can accommodate, by this way of recommendation, it is possible not only to avoid the interior of recommendation
The problem holding committed memory too big and cannot install, can also meet the requirement of user individual simultaneously.
As the optional embodiment of another kind, the personalization system shown in Fig. 5 can also include:
Close module 308, in Preset Time, do not receive user for carrying for detecting at detection module 303
When showing the confirmation instruction that information inputs, close box.
In the embodiment of the present invention, in Preset Time, do not receive user for carrying when detection module 303 detects
When showing the confirmation instruction that information inputs, close module 308 and can be automatically switched off dialog box, in order to avoid causing user
Dislike.
In the individualized content commending system described by Fig. 3~Fig. 5, work as analyzing module 301 analysing terminal
Front interface, and from interface, extract at least one key word, and detection module 303 detects when default
In receive the confirmation instruction that user inputs for information after, further according to the hobby class of user
Type and/or terminal residual internal memory cause recommending module 304 recommend the content relevant to this key word to user, from
And related content can be recommended according to the demand of user to user, reduce the dislike degree of user.
It should be noted that for each embodiment of the method aforesaid, in order to be briefly described, therefore by its all table
Stating as a series of combination of actions, but those skilled in the art should know, the application is not by described
The restriction of sequence of movement because according to the application, certain some step can use other orders or simultaneously
Carry out.Secondly, those skilled in the art also should know, embodiment described in this description belongs to excellent
Select embodiment, necessary to involved action and unit not necessarily the application.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, in certain embodiment the most in detail
The thin part described, may refer to the associated description of other embodiments.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method,
Can be by computer program and complete to instruct relevant hardware, described program can be stored in computer
In read/write memory medium, this program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each method.
Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory,
Or random store-memory body (Random Access Memory, RAM) etc. ROM).
Above disclosed be only present pre-ferred embodiments, certainly can not with this limit the present invention it
Interest field, the equivalent variations therefore made according to the claims in the present invention, still belong to the scope that the present invention is contained.
Claims (10)
1. a personalization content recommendation method, is applied to terminal, it is characterised in that including:
The interface that analysing terminal is current, and from described interface, extract at least one key word;
Output dialog box, described dialog box includes that information, described information are used for prompting the user whether
Check the content relevant to described key word;
Whether detection receives the confirmation instruction that user inputs for described information, institute in Preset Time
State and confirm that instruction is for indicating the content that the output of described terminal is relevant to described key word;
When receiving the confirmation instruction that user inputs for described information in described Preset Time, to
User recommends the content relevant to described key word.
Method the most according to claim 1, it is characterised in that connect in Preset Time in step detection
After receiving the confirmation instruction that user inputs for described information, and recommend and institute to user in step
Before stating the content that key word is relevant, described method also includes:
The historical record that user is relevant to described key word is obtained according to described key word;
Resolve described historical record, the preference type relevant to described key word to determine user;
The described content relevant to described key word to user's recommendation, including:
According to described preference type, recommend the content relevant to described key word to user.
Method the most according to claim 2, it is characterised in that resolve described historical record in step,
After the preference type relevant to described key word to determine user, and in step according to described preference type,
Before user recommends the content relevant to described key word, described method also includes:
Obtain described terminal residual internal memory;
Described according to described preference type, recommend the content relevant to described key word to user, including:
According to described preference type and described terminal residual internal memory, recommend relevant to described key word to user
Content.
Method the most according to claim 3, it is characterised in that described according to described preference type with institute
State terminal residual internal memory, recommend the content relevant to described key word to user, including:
According to described preference type and described terminal residual internal memory, search matches with described preference type and accounts for
The content of described free memory it is less than with internal memory;
The content relevant to described key word searched is recommended to user.
Method the most according to claim 1, it is characterised in that described method also includes:
When detection does not receives the confirmation instruction that user inputs for described information in Preset Time,
Close described dialog box.
6. an individualized content commending system, is applied to terminal, it is characterised in that including:
Analyzing module, for the interface that analysing terminal is current, and it is crucial to extract at least one from described interface
Word;
Output module, is used for exporting dialog box, and described dialog box includes information, and described information is used
Check the content relevant to described key word in prompting the user whether;
Whether detection module, receive user in Preset Time for detection and input for described information
Confirmation instruction, described confirm that instruction is for indicating the described terminal output content relevant to described key word;
Recommending module, for carrying for described when described detection module receives user in described Preset Time
When showing the confirmation instruction that information inputs, recommend the content relevant to described key word to user.
System the most according to claim 6, it is characterised in that described system also includes:
Record acquisition module, for receiving user for institute at described detection module in described Preset Time
After stating the confirmation instruction of information input, and described recommending module is recommended and described key word to user
Before relevant content, obtain, according to described key word, the historical record that user is relevant to described key word;
Parsing module, is used for resolving described historical record, the hobby relevant to described key word to determine user
Type;
Described recommending module, specifically for according to described preference type, recommending and described key word phase to user
The content closed.
System the most according to claim 7, it is characterised in that described system also includes:
Internal memory acquisition module, for resolving described historical record at described parsing module, to determine user and institute
After stating the preference type that key word is relevant, and described recommending module is according to described preference type and described end
End free memory, before user recommends the content relevant to described key word, obtains in described terminal residual
Deposit;
Described recommending module, specifically for according to described preference type and described terminal residual internal memory, to user
Recommend the content relevant to described key word.
System the most according to claim 8, it is characterised in that described recommending module includes:
Search subelement, for according to described preference type and described terminal residual internal memory, search and described happiness
Good type matching and committed memory are less than the content of described free memory;
Recommend subelement, for recommending the content relevant to described key word searched to user.
System the most according to claim 6, it is characterised in that described system also includes:
Close module, for not receiving user in Preset Time for described in the detection of described detection module
When the confirmation of information input instructs, close described dialog box.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510080720.8A CN105989120B (en) | 2015-02-12 | 2015-02-12 | A kind of personalization content recommendation method and individualized content recommender system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510080720.8A CN105989120B (en) | 2015-02-12 | 2015-02-12 | A kind of personalization content recommendation method and individualized content recommender system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105989120A true CN105989120A (en) | 2016-10-05 |
CN105989120B CN105989120B (en) | 2019-08-13 |
Family
ID=57042506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510080720.8A Active CN105989120B (en) | 2015-02-12 | 2015-02-12 | A kind of personalization content recommendation method and individualized content recommender system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105989120B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529993A (en) * | 2016-10-20 | 2017-03-22 | 天脉聚源(北京)科技有限公司 | Intelligent advertisement delivery method and device |
CN106776774A (en) * | 2016-11-11 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal chooses picture device and method |
CN107967352A (en) * | 2017-12-15 | 2018-04-27 | 四川汉科计算机信息技术有限公司 | Information knowledge wisdom recommends method |
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 |
CN109241399A (en) * | 2018-07-11 | 2019-01-18 | 杭州电子科技大学 | A kind of personalized recommendation method combined based on trust and influence power |
CN110989847A (en) * | 2019-11-22 | 2020-04-10 | 维沃移动通信有限公司 | Information recommendation method and device, terminal equipment and storage medium |
WO2020073528A1 (en) * | 2018-10-12 | 2020-04-16 | 平安科技(深圳)有限公司 | Session-based information push method and apparatus, computer device, and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102509233A (en) * | 2011-11-29 | 2012-06-20 | 汕头大学 | User online action information-based recommendation method |
CN102622390A (en) * | 2011-10-11 | 2012-08-01 | 北京掌汇天下科技有限公司 | Application recommending method and application recommending server in mobile terminal |
CN102693271A (en) * | 2012-03-06 | 2012-09-26 | 奇智软件(北京)有限公司 | Network information recommending method and system |
CN102982156A (en) * | 2012-11-30 | 2013-03-20 | 北京奇虎科技有限公司 | System and method for realizing searching in mobile terminal |
CN103955465A (en) * | 2014-03-28 | 2014-07-30 | 百度在线网络技术(北京)有限公司 | Method and device for generating recommended page |
CN104050163A (en) * | 2013-03-11 | 2014-09-17 | 捷达世软件(深圳)有限公司 | Content recommendation system and method |
CN104112213A (en) * | 2013-04-19 | 2014-10-22 | 腾讯科技(深圳)有限公司 | Method and apparatus of recommendation information |
CN104123360A (en) * | 2014-07-18 | 2014-10-29 | 腾讯科技(深圳)有限公司 | Application recommendation data acquisition method, device and system and electronic device |
CN104133820A (en) * | 2013-05-06 | 2014-11-05 | 腾讯科技(深圳)有限公司 | Content recommending method and content recommending device |
CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
CN104216881A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技(深圳)有限公司 | Method and device for recommending individual labels |
CN104268176A (en) * | 2012-06-26 | 2015-01-07 | 北京奇虎科技有限公司 | Recommendation method and system based on search keyword |
-
2015
- 2015-02-12 CN CN201510080720.8A patent/CN105989120B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622390A (en) * | 2011-10-11 | 2012-08-01 | 北京掌汇天下科技有限公司 | Application recommending method and application recommending server in mobile terminal |
CN102509233A (en) * | 2011-11-29 | 2012-06-20 | 汕头大学 | User online action information-based recommendation method |
CN102693271A (en) * | 2012-03-06 | 2012-09-26 | 奇智软件(北京)有限公司 | Network information recommending method and system |
CN104268176A (en) * | 2012-06-26 | 2015-01-07 | 北京奇虎科技有限公司 | Recommendation method and system based on search keyword |
CN102982156A (en) * | 2012-11-30 | 2013-03-20 | 北京奇虎科技有限公司 | System and method for realizing searching in mobile terminal |
CN104050163A (en) * | 2013-03-11 | 2014-09-17 | 捷达世软件(深圳)有限公司 | Content recommendation system and method |
CN104112213A (en) * | 2013-04-19 | 2014-10-22 | 腾讯科技(深圳)有限公司 | Method and apparatus of recommendation information |
CN104133820A (en) * | 2013-05-06 | 2014-11-05 | 腾讯科技(深圳)有限公司 | Content recommending method and content recommending device |
CN104216881A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技(深圳)有限公司 | Method and device for recommending individual labels |
CN103955465A (en) * | 2014-03-28 | 2014-07-30 | 百度在线网络技术(北京)有限公司 | Method and device for generating recommended page |
CN104123360A (en) * | 2014-07-18 | 2014-10-29 | 腾讯科技(深圳)有限公司 | Application recommendation data acquisition method, device and system and electronic device |
CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106529993A (en) * | 2016-10-20 | 2017-03-22 | 天脉聚源(北京)科技有限公司 | Intelligent advertisement delivery method and device |
CN106776774A (en) * | 2016-11-11 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal chooses picture device and method |
CN107967352A (en) * | 2017-12-15 | 2018-04-27 | 四川汉科计算机信息技术有限公司 | Information knowledge wisdom recommends method |
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 |
CN109241399A (en) * | 2018-07-11 | 2019-01-18 | 杭州电子科技大学 | A kind of personalized recommendation method combined based on trust and influence power |
WO2020073528A1 (en) * | 2018-10-12 | 2020-04-16 | 平安科技(深圳)有限公司 | Session-based information push method and apparatus, computer device, and storage medium |
CN110989847A (en) * | 2019-11-22 | 2020-04-10 | 维沃移动通信有限公司 | Information recommendation method and device, terminal equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105989120B (en) | 2019-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105989120A (en) | Personalized content recommendation method and personalized content recommendation system | |
US10055783B1 (en) | Identifying objects in video | |
CN107783705A (en) | Show method, apparatus, computer installation and the storage medium of application program | |
US20190155846A1 (en) | Search result displaying method and apparatus | |
CN106874467A (en) | Method and apparatus for providing Search Results | |
CN105719646A (en) | Voice control music playing method and voice control music playing apparatus | |
CN101636735A (en) | The equipment of integration search of web site and method | |
CN106896932A (en) | A kind of candidate word recommends method and device | |
CN103620588A (en) | Identifying matching applications based on browsing activity | |
CN108763579A (en) | Search for content recommendation method, device, terminal device and storage medium | |
CN105243058A (en) | Webpage content translation method and electronic apparatus | |
CN102984050A (en) | Method, client and system for searching voices in instant messaging | |
CN104809224A (en) | Method and device for presenting application information | |
CN106227873A (en) | Searching method and device | |
US20170228378A1 (en) | Extracting topics from customer review search queries | |
CN105677815A (en) | Webpage bookmark addition method and terminal | |
Lavid Ben Lulu et al. | Functionality-based clustering using short textual description: Helping users to find apps installed on their mobile device | |
CN103020128A (en) | Method and device for data interaction with terminal device | |
CN110032616A (en) | A kind of acquisition method and device of document reading conditions | |
TW201717067A (en) | System, method and computer readable recording media for issue display | |
CN104598571A (en) | Method and device for playing multimedia resource | |
CN107045527A (en) | A kind of application content collecting method and device | |
CN103914519A (en) | Recommendation method and device | |
KR101542417B1 (en) | Method and apparatus for learning user preference | |
US11695810B2 (en) | Enhanced content sharing platform |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |