CN108073719A - A kind of content recommendation method and device - Google Patents
A kind of content recommendation method and device Download PDFInfo
- Publication number
- CN108073719A CN108073719A CN201711483914.8A CN201711483914A CN108073719A CN 108073719 A CN108073719 A CN 108073719A CN 201711483914 A CN201711483914 A CN 201711483914A CN 108073719 A CN108073719 A CN 108073719A
- Authority
- CN
- China
- Prior art keywords
- keyword
- topic
- topic keyword
- recommendation
- recommended
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of content recommendation method, device, electronic equipment and computer readable storage mediums.This method includes：Corresponding topic keyword is generated for the content to be recommended in content library to be recommended, and correspondence is saved in recommendation storehouse；It determines and the matched target topic keyword of designated user；According to target topic keyword, corresponding recommendation is chosen from commending contents storehouse；Selected recommendation is recommended into designated user.As it can be seen that by the technical program, acquisition and the matched recommendation of designated user achieve the purpose that commending contents, can also promote the usage experience of user, avoid the dislike mood of user, prevent customer loss.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of content recommendation method, device, electronic equipment and calculating
Machine readable storage medium storing program for executing.
Background technology
In order to enable when people carry out various operations in internet, more content informations can be obtained, such as
News information, more and more websites or application program all possess commending contents function.But carry out commending contents when
Wait, if content recommended to the user is that user is uninterested, can not realize commending contents purpose or recommend
Content is precisely what user did not liked, then can not only realize the purpose of commending contents, also result in user lose using should
Website or the interest of application program reduce the usage experience of user, the loss of user can be caused under serious situation.
The content of the invention
In view of the above problems, it is proposed that the present invention overcomes the above problem in order to provide one kind or solves at least partly
State content recommendation method, device, electronic equipment and the computer readable storage medium of problem.One side according to the invention,
A kind of content recommendation method is provided, wherein, this method includes：
Corresponding topic keyword is generated for the content to be recommended in content library to be recommended, and correspondence is saved in recommendation
In content library；
It determines and the matched target topic keyword of designated user；
According to the target topic keyword, corresponding recommendation is chosen from the commending contents storehouse；
Selected recommendation is recommended into the designated user.
Optionally, this method further comprises：
Obtain the hierarchy information of topic keyword；
From the hierarchy information of the topic keyword, find out and be in same layer with the target topic keyword
Secondary fraternal topic keyword；
According to the fraternal topic keyword found out, corresponding recommendation is chosen from the commending contents storehouse, and will
Selected recommendation recommends the designated user.
Optionally, the content to be recommended in content library to be recommended generates corresponding topic keyword and includes：
For a content to be recommended, keyword is extracted from the content to be recommended, by each keyword and topic of extraction
Key word library is matched, and if there is occurrence, then the matched keyword is that the corresponding topic of the recommendation is crucial
Word is known as the first topic keyword.
Optionally, it is further to generate corresponding topic keyword for the content to be recommended in content library to be recommended
Including：
Obtain the hierarchy information of topic keyword；
From the hierarchy information of the topic keyword, find out and be in same layer with the first topic keyword
Secondary fraternal topic keyword, using fraternal topic keyword as the corresponding topic keyword of the recommendation；And/or from institute
In the hierarchy information for stating topic keyword, the father's topic for finding out the last layer in the first topic keyword time closes
Key word, using father's topic keyword as the corresponding topic keyword of the recommendation.
Optionally, it is described to determine to include with the matched target topic keyword of designated user：
Keyword is extracted in the content browsed from the designated user, each keyword of extraction and topic key word library are carried out
Matching, if there is occurrence, then the matched keyword is and the matched target topic keyword of the designated user.
According to another aspect of the present invention, a kind of content recommendation device is provided, wherein, which includes：
Storage unit, suitable for preserving recommendation storehouse；
Topic determination unit, the content to be recommended being suitable in content library to be recommended determine corresponding topic keyword
And correspondence is saved in recommendation storehouse；And it is adapted to determine that and the matched target topic keyword of designated user；
Commending contents unit, suitable for according to the target topic keyword, being chosen from the commending contents storehouse corresponding
Selected recommendation is recommended the designated user by recommendation.
Optionally,
The storage unit is further adapted for preserving the hierarchy information of topic keyword；
The topic determination unit is further adapted for from the hierarchy information of the topic keyword, find out with
The target topic keyword is in the fraternal topic keyword of same level；
The commending contents unit is further adapted for according to the fraternal topic keyword found out, from the commending contents
Corresponding recommendation is chosen in storehouse, and selected recommendation is recommended into the designated user.
Optionally,
The storage unit is further adapted for preserving topic key word library；
The topic determination unit, suitable for a content to be recommended, extracting keyword from the content to be recommended, carrying
Each keyword taken is matched with topic key word library, and if there is occurrence, then the matched keyword is the recommendation
The corresponding topic keyword of content is known as the first topic keyword.
Optionally,
The storage unit is further adapted for preserving the hierarchy information of topic keyword；
The topic determination unit is further adapted for from the hierarchy information of the topic keyword, find out with
The first topic keyword is in the fraternal topic keyword of same level, using fraternal topic keyword as the recommendation
Corresponding topic keyword；And/or from the hierarchy information of the topic keyword, find out in the described first words
Father's topic keyword of the last layer time of keyword is inscribed, father's topic keyword is crucial as the corresponding topic of the recommendation
Word.
Optionally,
The topic determination unit, suitable for extracting keyword from the content that the designated user browses, by each pass of extraction
Key word is matched with topic key word library, and if there is occurrence, then the matched keyword is and the designated user
The target topic keyword matched somebody with somebody.
According to another aspect of the invention, a kind of electronic equipment is provided, wherein, which includes：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the place when executed
Device is managed to perform according to foregoing method.
In accordance with a further aspect of the present invention, a kind of computer readable storage medium is provided, wherein, it is described computer-readable
The one or more programs of storage medium storage, one or more of programs when being executed by a processor, realize foregoing method.
Technique according to the invention scheme is that the content to be recommended in content library to be recommended generates corresponding topic pass
Key word, and correspondence is saved in recommendation storehouse；It determines and the matched target topic keyword of designated user；According to target topic
Keyword chooses corresponding recommendation from commending contents storehouse；Selected recommendation is recommended into designated user.It can
See, by the technical program, acquisition and the matched recommendation of designated user achieve the purpose that commending contents, can also be promoted
The usage experience of user avoids the dislike mood of user, prevents customer loss.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific embodiment for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will be apparent understanding.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows the flow diagram of content recommendation method according to an embodiment of the invention；
Fig. 2 shows the structure diagram of content recommendation device according to an embodiment of the invention；
Fig. 3 shows the structure diagram of electronic equipment according to an embodiment of the invention；
Fig. 4 shows the structure diagram of computer readable storage medium according to an embodiment of the invention；
Fig. 5 shows the schematic diagram of the hierarchy information of topic keyword according to an embodiment of the invention.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Fig. 1 shows the flow diagram of content recommendation method according to an embodiment of the invention.It as shown in Figure 1, should
Method includes：
Step S110 is that the content to be recommended in content library to be recommended generates corresponding topic keyword, and corresponding
It is saved in recommendation storehouse.
Step S120 is determined and the matched target topic keyword of designated user.
Step S130 according to target topic keyword, chooses corresponding recommendation from commending contents storehouse.
Selected recommendation is recommended designated user by step S140.
In the present embodiment, content to be recommended is typically more specific, when carrying out the recommendation of content, can not say by
Content to be recommended goes to be recommended one by one, so correspond to it is for the operation of recommendation and infeasible, so in the present embodiment
In, it is to generate corresponding topic keyword for the content to be recommended in content library to be recommended first, and corresponding be saved in pushes away
It recommends in content library.Here same topic keyword can correspond to multiple contents to be recommended, and a content to be recommended may also
Corresponding multiple topic keywords, can be according only to topic keyword so when being recommended, will be with topic keyword pair
The recommendation answered is recommended together, meets the actual requirement of recommendation operation.
Meanwhile in the present embodiment, when to designated user's recommendation, the matched target topic of designated user is first obtained
Keyword is recommended according to target topic keyword, then the content recommended can meet the demand of designated user, be unlikely to allow
Designated user generates the mood of dislike, avoids customer loss.Table 1 lists recommendation storehouse and corresponds to the recommendation and right preserved
The topic keyword answered.
Table 1
As shown in table 1, the topic generated according to content to be recommended " the live song and dance skewered of girlhood superfinishing coloured silk " is crucial
Word is " South Korea's pop music, girlhood and pop music group of South Korea ", then just by the recommendation and the topic of generation
Keyword, which corresponds to, to be preserved；According to content to be recommended, " why cat, which eats fish, to snap into throat by thornFinish watching the knowledge that rises at last "
The topic keyword of generation is " cold knowledge and existence general knowledge ", then just that the recommendation is corresponding with the topic keyword of generation
It preserves.
In one example, if it is " girlhood " to obtain with the matched target topic keyword of designated user, from
The recommendation " the live song and dance skewered of girlhood superfinishing coloured silk " that corresponding " girlhood " is chosen in the commending contents storehouse pushes away
It recommends and gives the designated user.
As it can be seen that by the technical program, acquisition and the matched recommendation of designated user achieve the purpose that commending contents,
The usage experience of user can also be promoted, the dislike mood of user is avoided, prevents customer loss.
In one embodiment of the invention, method shown in FIG. 1 further comprises：Obtain the level knot of topic keyword
Structure information；From the hierarchy information of topic keyword, the brother that same level is in target topic keyword is found out
Topic keyword；According to the fraternal topic keyword found out, corresponding recommendation is chosen from commending contents storehouse, and by institute
The recommendation of selection recommends designated user.
In the present embodiment, the hierarchy information of the topic keyword of acquisition be think it is default and/or, according to god
Data result through network training, the hierarchy information of the topic keyword of generation, for example, topic keyword " girlhood "
As a node in the hierarchy information of topic keyword, the fraternal topic keyword in same level is " T-
Ara ", " EXO ", " SJM " etc.；The last layer node of " girlhood ", i.e. father's topic keyword are " pop music groups of South Korea ",
Father's topic keyword of " pop music group of South Korea " is " South Korea's pop music "；Next node layer of " girlhood ", i.e., it is sub
Topic keyword has " world met again again ", " Jin Taiyan " etc..That is, in the hierarchy information of topic keyword
In, a topic keyword is corresponding with fraternal topic keyword, father's topic keyword and sub-topic keyword.
In the present embodiment, in order to obtain specified use is recommended with the matched more recommendations of designated user
Family, obtain with after the matched target topic keyword of designated user, from the hierarchy information of the topic keyword of acquisition
In, find out the fraternal topic keyword that same level is in target topic keyword；It is closed according to the fraternal topic found out
Key word chooses corresponding recommendation from commending contents storehouse, and selected recommendation is recommended designated user.
For example, after the matched target topic keyword " girlhood " of designated user obtained, find out and " during maiden
The fraternal topic keyword of generation " same level is " T-ara ", then recommendation corresponding with " T-ara " is also recommended this refers to
Determine user.
In one embodiment of the invention, method shown in FIG. 1 further comprises：Obtain the level knot of topic keyword
Structure information；From the hierarchy information of topic keyword, father's words of the last layer in target topic keyword time are found out
Inscribe keyword；According to the father's topic keyword found out, corresponding recommendation is chosen from commending contents storehouse, and by selected by
Recommendation recommend designated user.
For example, after the matched target topic keyword " girlhood " of designated user obtained, find out and " during maiden
Generation " father's topic keyword of last layer time is " pop music group of South Korea ", then will be corresponding with " pop music group of South Korea "
Recommendation also recommends the designated user.
In a specific example, Fig. 5 shows the level knot of topic keyword according to an embodiment of the invention
The schematic diagram of structure information.Based on the hierarchy information of the topic keyword shown in Fig. 5, if designated user is interested
Topic keyword for "《Flirting Scholar》", then according to the hierarchy information of Fig. 5 topic keywords shown, to topic
Father's topic keyword (father node) extension of keyword, topic keyword "《Flirting Scholar》" father's topic keyword be
" Hong Kong film ", " Zhou Xing speed film " then can recommend the content that include this father's topic keyword to designated user；And/or to
Fraternal topic keyword (brotgher of node) extension of topic keyword, topic keyword "《Flirting Scholar》" fraternal topic
Keyword have "《Talk on the journey to west》”、“《Shaolin Soccer》" etc., then it can recommend to designated user crucial comprising these fraternal topics
The content of word.
By the above embodiments, in commending contents, user is recommended in real time according to the navigation patterns of user interested
Content, not only need to recommend and user watch the similar content of history, it is also necessary to the interest of user is further expanded, it is anti-
Only user interest is restrained, and causes customer loss.
Further, on the basis of above-described embodiment, the method described in Fig. 1 further comprises：From topic keyword
In hierarchy information, father's topic keyword in father's topic keyword is found out；According to father's topic of father's topic keyword
Keyword chooses corresponding recommendation from commending contents storehouse, and selected recommendation is recommended designated user；With/
Or, from the hierarchy information of topic keyword, the fraternal topic keyword of father's topic keyword is found out, according to father's topic
The fraternal topic keyword of keyword chooses corresponding recommendation from commending contents storehouse, and selected recommendation is pushed away
It recommends to designated user.
For example, the interested target topic keyword of designated user for "《Flirting Scholar》", then it is closed according to topic
The hierarchy information of key word extends, target topic keyword to father's topic keyword of father's topic of target topic keyword
“《Flirting Scholar》" father's topic for " Hong Kong film ", and father's topic keyword of father's topic keyword is " comedy electricity
Shadow " then can recommend the content for including topic keyword " comedy movie " to designated user；And/or to target topic keyword
Father's topic keyword fraternal topic keyword extension, target topic keyword "《Flirting Scholar》" father's topic be
" Hong Kong film ", and brother's topic keyword of father's topic keyword is " continent film ", then can recommend to include as designated user
The content of topic keyword " continent film ".
It needs to do the interest of user and further extend, user experience can be further improved.
In one embodiment of the invention, method shown in FIG. 1 further comprises：Obtain the level knot of topic keyword
Structure information；From the hierarchy information of topic keyword, the son words of next level in target topic keyword are found out
Inscribe keyword；According to the sub-topic keyword found out, corresponding recommendation is chosen from commending contents storehouse, and by selected by
Recommendation recommend designated user；Alternatively, according to the sub-topic keyword found out and the brother of the sub-topic keyword
Younger brother's topic keyword chooses corresponding recommendation from commending contents storehouse, and selected recommendation is recommended specified
User.
For example, the interested target topic keyword of designated user for "《Flirting Scholar》", then it is closed according to topic
The hierarchy information of key word is extended to the sub-topic of target topic keyword, target topic keyword "《The Tang Baihu point autumns
It is fragrant》" sub-topic is " Zhou Xing speeds version《Flirting Scholar》", then it can recommend to designated user comprising topic keyword " week
Star is speeded version《Flirting Scholar》" content.
In one embodiment of the invention, it is that content to be recommended generation in content library to be recommended is each in step S110
Self-corresponding topic keyword includes：For a content to be recommended, keyword is extracted from the content to be recommended, by extraction
Each keyword is matched with topic key word library, and if there is occurrence, then the matched keyword is the recommendation
Corresponding topic keyword is known as the first topic keyword.
Here topic key word library be an artificially generated and/or, from Neural Network Data storehouse choose generation.
For example, content to be recommended is " the live song and dance skewered of girlhood superfinishing coloured silk ", the keyword therefrom extracted is " few
Female's epoch ", " song skewered ", " scene ", according to topic key word library, the topic keyword to match is " girlhood ", then
By the topic keyword of " girlhood " as the content to be recommended, as the first topic keyword.
Further, it is that content to be recommended in content library to be recommended generates corresponding topic and closes in step S110
Key word further comprises：Obtain the hierarchy information of topic keyword；From the hierarchy information of topic keyword, search
Go out to be in the fraternal topic keyword of same level with the first topic keyword, using fraternal topic keyword as the recommendation
Corresponding topic keyword；And/or from the hierarchy information of topic keyword, find out in the first topic keyword
Last layer time father's topic keyword, using father's topic keyword as the corresponding topic keyword of the recommendation；And/or
From the hierarchy information of topic keyword, the sub-topic for finding out next level in the first topic keyword is crucial
Word, using sub-topic keyword as the corresponding topic keyword of the recommendation.
The hierarchy information of topic keyword in the present embodiment is the same as the level knot of the topic keyword in above description
Structure information is not repeating herein.
In the present embodiment, if only will determine that topic keyword can be so that the recommendation loses very from recommendation
Mostly recommended chance, in order to increase its recommended chance, when getting the first topic keyword, will close with the first topic
Key word be in same level fraternal topic keyword also serve as the corresponding topic keyword of the recommendation and/or, will be in
Father's topic keyword of the last layer time of first topic keyword is as the corresponding topic keyword of the recommendation.
For example, in previous example, by " girlhood " as the first topic of content keyword to be recommended, according to topic
The hierarchy information of keyword, it is " T-ara " to find out and be in the fraternal topic keyword of same level with " girlhood ",
" T-ara " is used as the corresponding topic keyword of the recommendation；And/or it from the hierarchy information of topic keyword, looks into
Father's topic keyword " pop music group of South Korea " of the last layer time in " girlhood " is found out, by " South Korea's pop music
Group " is used as the corresponding topic keyword of the recommendation.In this way, content " the color scene song of girlhood superfinishing to be recommended
The topic keyword of dance skewered " is then " girlhood ", " T-ara " and " pop music group of South Korea ".
When carrying out commending contents, hit that the topic keyword of the content to be recommended is more, then the content to be recommended is pushed away
The chance recommended is bigger, meets the requirement of recommendation operation.
In one embodiment of the invention, determined and the matched target topic keyword of designated user in step S120
Including：Keyword is extracted in the content browsed from the designated user, by each keyword of extraction and the progress of topic key word library
Match somebody with somebody, if there is occurrence, then the matched keyword is and the matched target topic keyword of the designated user.
In the present embodiment, according to the browsing history of user, it is possible to determine that the designated user is more interested
Topic, and then the usage experience of user can be further enhanced by the interested commending contents of user to user.
For example, the keyword of the browsing content of definite designated user is " existence general knowledge ", then by the keyword, " life is normal
Know " it can will then be somebody's turn to do the target of " existence general knowledge " as the designated user from the topic keyword match in topic key word library
Topic keyword.In commending contents, according to " existence general knowledge " by corresponding recommendation in recommendation storehouse, such as " for
What cat, which eats fish, to snap into throat by thornFinish watching the knowledge that rises at last " recommend user.
Fig. 2 shows the structure diagram of content recommendation device according to an embodiment of the invention.It as shown in Fig. 2, should
Content recommendation device 200 includes：
Storage unit 210, suitable for preserving recommendation storehouse.
Topic determination unit 220, the content to be recommended being suitable in content library to be recommended determine that corresponding topic closes
Key word and correspondence be saved in recommendation storehouse；And it is adapted to determine that and the matched target topic keyword of designated user.
Commending contents unit 230, suitable for according to target topic keyword, being chosen from commending contents storehouse in corresponding recommendation
Hold, selected recommendation is recommended into designated user.
In the present embodiment, content to be recommended is typically more specific, when carrying out the recommendation of content, can not say by
Content to be recommended goes to be recommended one by one, so correspond to it is for the operation of recommendation and infeasible, so in the present embodiment
In, it is to generate corresponding topic keyword for the content to be recommended in content library to be recommended first, and corresponding be saved in pushes away
It recommends in content library.Here same topic keyword can correspond to multiple contents to be recommended, and a content to be recommended may also
Corresponding multiple topic keywords, can be according only to topic keyword so when being recommended, will be with topic keyword pair
The recommendation answered is recommended together, meets the actual requirement of recommendation operation.
Meanwhile in the present embodiment, when to designated user's recommendation, the matched target topic of designated user is first obtained
Keyword is recommended according to target topic keyword, then the content recommended can meet the demand of designated user, be unlikely to allow
Designated user generates the mood of dislike, avoids customer loss.Table 1 lists recommendation storehouse and corresponds to the recommendation and right preserved
The topic keyword answered.
Table 1
As shown in table 1, the topic generated according to content to be recommended " the live song and dance skewered of girlhood superfinishing coloured silk " is crucial
Word is " South Korea's pop music, girlhood and pop music group of South Korea ", then just by the recommendation and the topic of generation
Keyword, which corresponds to, to be preserved；According to content to be recommended, " why cat, which eats fish, to snap into throat by thornFinish watching the knowledge that rises at last "
The topic keyword of generation is " cold knowledge and existence general knowledge ", then just that the recommendation is corresponding with the topic keyword of generation
It preserves.
In one example, if it is " girlhood " to obtain with the matched target topic keyword of designated user, from
The recommendation " the live song and dance skewered of girlhood superfinishing coloured silk " that corresponding " girlhood " is chosen in the commending contents storehouse pushes away
It recommends and gives the designated user.
As it can be seen that by the technical program, acquisition and the matched recommendation of designated user achieve the purpose that commending contents,
The usage experience of user can also be promoted, the dislike mood of user is avoided, prevents customer loss.
In one embodiment of the invention,
Storage unit 210 is further adapted for preserving the hierarchy information of topic keyword.
Topic determination unit 220 is further adapted for from the hierarchy information of topic keyword, is found out and is talked about with target
Topic keyword is in the fraternal topic keyword of same level.
230 yuan of commending contents list is further adapted for, according to the fraternal topic keyword found out, selecting from commending contents storehouse
Corresponding recommendation is taken, and selected recommendation is recommended into designated user.
In the present embodiment, the hierarchy information of the topic keyword of acquisition be think it is default and/or, according to god
Data result through network training, the hierarchy information of the topic keyword of generation, for example, topic keyword " girlhood "
As a node in the hierarchy information of topic keyword, the fraternal topic keyword in same level is " T-
Ara ", " EXO ", " SJM " etc.；The last layer node of " girlhood ", i.e. father's topic keyword are " pop music groups of South Korea ",
Father's topic keyword of " pop music group of South Korea " is " South Korea's pop music "；Next node layer of " girlhood ", i.e., it is sub
Topic keyword has " world met again again ", " Jin Taiyan " etc..That is, in the hierarchy information of topic keyword
In, a topic keyword is corresponding with fraternal topic keyword, father's topic keyword and sub-topic keyword.
In the present embodiment, in order to obtain specified use is recommended with the matched more recommendations of designated user
Family, obtain with after the matched target topic keyword of designated user, from the hierarchy information of the topic keyword of acquisition
In, find out the fraternal topic keyword that same level is in target topic keyword；It is closed according to the fraternal topic found out
Key word chooses corresponding recommendation from commending contents storehouse, and selected recommendation is recommended designated user.
For example, after the matched target topic keyword " girlhood " of designated user obtained, find out and " during maiden
The fraternal topic keyword of generation " same level is " T-ara ", then recommendation corresponding with " T-ara " is also recommended this and specified
User.
In one embodiment of the invention,
Storage unit 210 is further adapted for preserving the hierarchy information of topic keyword.
Topic determination unit 220 is further adapted for from the hierarchy information of topic keyword, finds out in target
Father's topic keyword of the last layer time of topic keyword.
Commending contents unit 230 is further adapted for, according to the father's topic keyword found out, choosing from commending contents storehouse
Corresponding recommendation, and selected recommendation is recommended into designated user.
For example, after the matched target topic keyword " girlhood " of designated user obtained, find out and " during maiden
Generation " father's topic keyword of last layer time is " pop music group of South Korea ", then will be corresponding with " pop music group of South Korea "
Recommendation also recommends the designated user.
In a specific example, Fig. 5 shows the level knot of topic keyword according to an embodiment of the invention
The schematic diagram of structure information.Based on the hierarchy information of the topic keyword shown in Fig. 5, if designated user is interested
Topic keyword for "《Flirting Scholar》", then according to the hierarchy information of Fig. 5 topic keywords shown, to topic
Father's topic keyword (father node) extension of keyword, topic keyword "《Flirting Scholar》" father's topic keyword be
" Hong Kong film ", " Zhou Xing speed film " then can recommend the content that include this father's topic keyword to designated user；And/or to
Fraternal topic keyword (brotgher of node) extension of topic keyword, topic keyword "《Flirting Scholar》" fraternal topic
Keyword have "《Talk on the journey to west》”、“《Shaolin Soccer》" etc., then it can recommend to designated user crucial comprising these fraternal topics
The content of word.
By the above embodiments, in commending contents, user is recommended in real time according to the navigation patterns of user interested
Content, not only need to recommend and user watch the similar content of history, it is also necessary to the interest of user is further expanded, it is anti-
Only user interest is restrained, and causes customer loss.
Further, on the basis of above-described embodiment, topic determination unit 220, suitable for from the level of topic keyword
In structural information, father's topic keyword in father's topic keyword is found out；And/or the hierarchical structure from topic keyword
In information, the fraternal topic keyword of father's topic keyword is found out.
Commending contents unit 230, suitable for being chosen according to father's topic keyword of father's topic keyword from commending contents storehouse
Corresponding recommendation, and selected recommendation is recommended into designated user；And/or the brother according to father's topic keyword
Younger brother's topic keyword chooses corresponding recommendation from commending contents storehouse, and selected recommendation is recommended specified use
Family.
For example, the interested target topic keyword of designated user for "《Flirting Scholar》", then it is closed according to topic
The hierarchy information of key word extends, target topic keyword to father's topic keyword of father's topic of target topic keyword
“《Flirting Scholar》" father's topic for " Hong Kong film ", and father's topic keyword of father's topic keyword is " comedy electricity
Shadow " then can recommend the content for including topic keyword " comedy movie " to designated user；And/or to target topic keyword
Father's topic keyword fraternal topic keyword extension, target topic keyword "《Flirting Scholar》" father's topic be
" Hong Kong film ", and brother's topic keyword of father's topic keyword is " continent film ", then can recommend to include as designated user
The content of topic keyword " continent film ".
It needs to do the interest of user and further extend, user experience can be further improved.
In one embodiment of the invention,
Storage unit 210 is further adapted for obtaining the hierarchy information of topic keyword.
Topic determination unit 220 is further adapted for from the hierarchy information of topic keyword, finds out in target
The sub-topic keyword of next level of topic keyword.
Commending contents unit 230 is further adapted for, according to the sub-topic keyword found out, choosing from commending contents storehouse
Corresponding recommendation, and selected recommendation is recommended into designated user；It is alternatively, crucial according to the sub-topic found out
The fraternal topic keyword of word and the sub-topic keyword, chooses corresponding recommendation from commending contents storehouse, and by institute
The recommendation of selection recommends designated user.
For example, the interested target topic keyword of designated user for "《Flirting Scholar》", then it is closed according to topic
The hierarchy information of key word is extended to the sub-topic of target topic keyword, target topic keyword "《The Tang Baihu point autumns
It is fragrant》" sub-topic is " Zhou Xing speeds version《Flirting Scholar》", then it can recommend to designated user comprising topic keyword " week
Star is speeded version《Flirting Scholar》" content.
In one embodiment of the invention, storage unit 210 are further adapted for preserving topic key word library.
Topic determination unit 220, suitable for a content to be recommended, extracting keyword from the content to be recommended, carrying
Each keyword taken is matched with topic key word library, and if there is occurrence, then the matched keyword is the recommendation
The corresponding topic keyword of content is known as the first topic keyword.
Here topic key word library be an artificially generated and/or, from Neural Network Data storehouse choose generation.
For example, content to be recommended is " the live song and dance skewered of girlhood superfinishing coloured silk ", the keyword therefrom extracted is " few
Female's epoch ", " song skewered ", " scene ", according to topic key word library, the topic keyword to match is " girlhood ", then
By the topic keyword of " girlhood " as the content to be recommended, as the first topic keyword.
Further, storage unit 210 are further adapted for preserving the hierarchy information of topic keyword；
Topic determination unit 220 is further adapted for from the hierarchy information of topic keyword, is found out and the first words
Topic keyword is in the fraternal topic keyword of same level, using fraternal topic keyword as the corresponding topic of the recommendation
Keyword；And/or from the hierarchy information of topic keyword, the last layer in the first topic keyword is found out
Father's topic keyword, using father's topic keyword as the corresponding topic keyword of the recommendation；It is and/or crucial from topic
In the hierarchy information of word, the sub-topic keyword of next level in the first topic keyword is found out, by sub-topic
Keyword is as the corresponding topic keyword of the recommendation.
The hierarchy information of topic keyword in the present embodiment is the same as the level knot of the topic keyword in above description
Structure information is not repeating herein.
In the present embodiment, if only will determine that topic keyword can be so that the recommendation loses very from recommendation
Mostly recommended chance, in order to increase its recommended chance, when getting the first topic keyword, will close with the first topic
Key word be in same level fraternal topic keyword also serve as the corresponding topic keyword of the recommendation and/or, will be in
Father's topic keyword of the last layer time of first topic keyword is as the corresponding topic keyword of the recommendation.
For example, in previous example, by " girlhood " as the first topic of content keyword to be recommended, according to topic
The hierarchy information of keyword, it is " T-ara " to find out and be in the fraternal topic keyword of same level with " girlhood ",
" T-ara " is used as the corresponding topic keyword of the recommendation；And/or it from the hierarchy information of topic keyword, looks into
Father's topic keyword " pop music group of South Korea " of the last layer time in " girlhood " is found out, by " South Korea's pop music
Group " is used as the corresponding topic keyword of the recommendation.In this way, content " the color scene song of girlhood superfinishing to be recommended
The topic keyword of dance skewered " is then " girlhood ", " T-ara " and " pop music group of South Korea ".
When carrying out commending contents, hit that the topic keyword of the content to be recommended is more, then the content to be recommended is pushed away
The chance recommended is bigger, meets the requirement of recommendation operation.
In one embodiment of the invention, topic determination unit 220, suitable for being carried from the content that the designated user browses
Keyword is taken, each keyword of extraction is matched with topic key word library, if there is occurrence, then the matched key
Word be and the matched target topic keyword of the designated user.
In the present embodiment, according to the browsing history of user, it is possible to determine that the designated user is more interested
Topic, and then the usage experience of user can be further enhanced by the interested commending contents of user to user.
For example, the keyword of the browsing content of definite designated user is " existence general knowledge ", then by the keyword, " life is normal
Know " it can will then be somebody's turn to do the target of " existence general knowledge " as the designated user from the topic keyword match in topic key word library
Topic keyword.In commending contents, according to " existence general knowledge " by corresponding recommendation in recommendation storehouse, such as " for
What cat, which eats fish, to snap into throat by thornFinish watching the knowledge that rises at last " recommend user.
The present invention also provides a kind of electronic equipment, wherein, which includes：
Processor；And
The memory of storage computer executable instructions is arranged to, executable instruction performs processor when executed
Content recommendation method according to figure 1 and its each embodiment.
Fig. 3 shows the structure diagram of electronic equipment according to an embodiment of the invention.As shown in figure 3, the electronics
Equipment 300 includes：
Processor 310；And the memory 320 of storage computer executable instructions (program code) is arranged to, it is depositing
In reservoir 320, there is the memory space 330 of storage program code, for performing the program code of steps of a method in accordance with the invention
340 are stored in memory space 330, and it is according to figure 1 and its each which when executed perform processor 310
Content recommendation method in embodiment.
Fig. 4 shows a kind of structure diagram of computer readable storage medium according to an embodiment of the invention.Such as
Shown in Fig. 4, which stores one or more programs (program code) 410, one or more programs
(program code) 410 when being executed by a processor, realizes the content recommendation method in shown in FIG. 1 and its each embodiment.
It should be noted that each embodiment of electronic equipment shown in Fig. 3 and computer readable storage medium shown in Fig. 4
It is corresponding identical with each embodiment of method shown in FIG. 1, it has been described in detail above, details are not described herein.
In conclusion technique according to the invention scheme, is that the content to be recommended generation in content library to be recommended is each right
The topic keyword answered, and correspondence is saved in recommendation storehouse；It determines and the matched target topic keyword of designated user；Root
According to target topic keyword, corresponding recommendation is chosen from commending contents storehouse；Selected recommendation is recommended into finger
Determine user.As it can be seen that by the technical program, acquisition and the matched recommendation of designated user achieve the purpose that commending contents, also
The usage experience of user can be promoted, the dislike mood of user is avoided, prevents customer loss.
It should be noted that：
Algorithm and display be not inherently related to any certain computer, virtual bench or miscellaneous equipment provided herein.
Various fexible units can also be used together with teaching based on this.As described above, required by constructing this kind of device
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification provided in this place, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
Shield the present invention claims the more features of feature than being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it may be employed any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Profit requirement, summary and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization or to be run on one or more processor
Software module realize or realized with combination thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize content recommendation device according to embodiments of the present invention, electronic equipment
With some or all functions of some or all components in computer readable storage medium.The present invention is also implemented as
For perform some or all equipment of method as described herein or program of device (for example, computer program and
Computer program product).Such program for realizing the present invention can may be stored on the computer-readable medium or can have
The form of one or more signal.Such signal can be downloaded from internet website and obtained or on carrier signal
It provides or is provided in the form of any other.
For example, Fig. 3 shows the structure diagram of electronic equipment according to an embodiment of the invention.The electronic equipment
300 conventionally comprise processor 310 and are arranged to the memory 320 of storage computer executable instructions (program code).It deposits
Reservoir 320 can be such as flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk or ROM etc
Electronic memory.Memory 320 has storage for performing any method and step in shown in FIG. 1 and each embodiment
The memory space 330 of program code 340.For example, it can include being respectively used to realization for the memory space 330 of program code
Each program code 340 of various steps in the method in face.These program codes can be from one or more computer journey
It reads or is written in sequence product in this one or more computer program product.These computer program products include all
Such as hard disk, the program code carrier of compact-disc (CD), storage card or floppy disk etc.Such computer program product is usually
Such as the computer readable storage medium 400 described in Fig. 4.The computer readable storage medium 400 can have the electronics with Fig. 3
Memory paragraph, memory space of 320 similar arrangement of memory in equipment etc..Program code can be pressed for example in a suitable form
Contracting.In general, storage unit is stored with to perform the program code 410 of steps of a method in accordance with the invention, you can with by such as
The program code that 310 etc processor is read, when these program codes are run by electronic equipment, causes the electronic equipment to be held
Each step in row method described above.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
1. a kind of content recommendation method, wherein, this method includes：
Corresponding topic keyword is generated for the content to be recommended in content library to be recommended, and correspondence is saved in recommendation
In storehouse；
It determines and the matched target topic keyword of designated user；
According to the target topic keyword, corresponding recommendation is chosen from the commending contents storehouse；
Selected recommendation is recommended into the designated user.
2. the method for claim 1, wherein this method further comprises：
Obtain the hierarchy information of topic keyword；
From the hierarchy information of the topic keyword, find out and be in same level with the target topic keyword
Fraternal topic keyword；
According to the fraternal topic keyword found out, corresponding recommendation is chosen from the commending contents storehouse, and by selected by
The recommendation taken recommends the designated user.
3. method as claimed in claim 1 or 2, wherein, the content to be recommended generation in content library to be recommended is each
Corresponding topic keyword includes：
For a content to be recommended, keyword is extracted from the content to be recommended, each keyword of extraction and topic is crucial
Character library is matched, and if there is occurrence, then the matched keyword is the corresponding topic keyword of the recommendation, is claimed
For the first topic keyword.
4. such as the method any one of claim 1-3, wherein, the content to be recommended life in content library to be recommended
Further comprise into corresponding topic keyword：
Obtain the hierarchy information of topic keyword；
From the hierarchy information of the topic keyword, find out and be in same level with the first topic keyword
Fraternal topic keyword, using fraternal topic keyword as the corresponding topic keyword of the recommendation；And/or from the words
In the hierarchy information for inscribing keyword, the father's topic for finding out the last layer in the first topic keyword time is crucial
Word, using father's topic keyword as the corresponding topic keyword of the recommendation.
5. such as the method any one of claim 1-4, wherein, it is described to determine to close with the matched target topic of designated user
Key word includes：
Keyword is extracted in the content browsed from the designated user, by each keyword of extraction and the progress of topic key word library
Match somebody with somebody, if there is occurrence, then the matched keyword is and the matched target topic keyword of the designated user.
6. a kind of content recommendation device, wherein, which includes：
Storage unit, suitable for preserving recommendation storehouse；
Topic determination unit, the content to be recommended being suitable in content library to be recommended determine corresponding topic keyword and right
It should be saved in recommendation storehouse；And it is adapted to determine that and the matched target topic keyword of designated user；
Commending contents unit, suitable for according to the target topic keyword, corresponding recommendation is chosen from the commending contents storehouse
Selected recommendation is recommended the designated user by content.
7. device as claimed in claim 6, wherein,
The storage unit is further adapted for preserving the hierarchy information of topic keyword；
The topic determination unit is further adapted for from the hierarchy information of the topic keyword, find out with it is described
Target topic keyword is in the fraternal topic keyword of same level；
The commending contents unit is further adapted for according to the fraternal topic keyword found out, from the commending contents storehouse
Corresponding recommendation is chosen, and selected recommendation is recommended into the designated user.
8. device as claimed in claims 6 or 7, wherein,
The storage unit is further adapted for preserving topic key word library；
The topic determination unit, suitable for a content to be recommended, keyword being extracted from the content to be recommended, by extraction
Each keyword is matched with topic key word library, and if there is occurrence, then the matched keyword is the recommendation
Corresponding topic keyword is known as the first topic keyword.
9. a kind of electronic equipment, wherein, which includes：
Processor；And
The memory of storage computer executable instructions is arranged to, the executable instruction makes the processor when executed
It performs according to method according to any one of claims 1 to 5.
10. a kind of computer readable storage medium, wherein, the computer-readable recording medium storage one or more program,
One or more of programs when being executed by a processor, realize method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711483914.8A CN108073719A (en) | 2017-12-29 | 2017-12-29 | A kind of content recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711483914.8A CN108073719A (en) | 2017-12-29 | 2017-12-29 | A kind of content recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108073719A true CN108073719A (en) | 2018-05-25 |
Family
ID=62156012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711483914.8A Pending CN108073719A (en) | 2017-12-29 | 2017-12-29 | A kind of content recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073719A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207917A (en) * | 2013-04-25 | 2013-07-17 | 百度在线网络技术（北京）有限公司 | Method for marking multimedia content and method and system for generating recommended content |
| CN104537115A (en) * | 2015-01-21 | 2015-04-22 | 北京字节跳动科技有限公司 | Method and device for exploring user interests |
| CN105975522A (en) * | 2016-04-29 | 2016-09-28 | 清华大学深圳研究生院 | Multi-field content recommendation method and server |
-
2017
- 2017-12-29 CN CN201711483914.8A patent/CN108073719A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207917A (en) * | 2013-04-25 | 2013-07-17 | 百度在线网络技术（北京）有限公司 | Method for marking multimedia content and method and system for generating recommended content |
| CN104537115A (en) * | 2015-01-21 | 2015-04-22 | 北京字节跳动科技有限公司 | Method and device for exploring user interests |
| CN105975522A (en) * | 2016-04-29 | 2016-09-28 | 清华大学深圳研究生院 | Multi-field content recommendation method and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103440335B (en) | Video recommendation method and device | |
| CN102946566B (en) | Video recommending method and device based on historical information | |
| CN107730313A (en) | Recommend method and device in shop based on rationale for the recommendation | |
| US20190147003A1 (en) | Dynamic search set creation in a search engine | |
| CN109271594B (en) | Recommendation method of electronic book, electronic equipment and computer storage medium | |
| WO2018121700A1 (en) | Method and device for recommending application information based on installed application, terminal device, and storage medium | |
| CA3153598A1 (en) | Method of and device for predicting video playback integrity | |
| CN106462801A (en) | Training neural networks on partitioned training data | |
| WO2015183720A1 (en) | Personalized search results | |
| CN106294830A (en) | The recommendation method and device of multimedia resource | |
| CN106528894B (en) | The method and device of label information is set | |
| JP2018518726A (en) | Information retrieval navigation method and apparatus | |
| CN111639255B (en) | Recommendation method and device for search keywords, storage medium and electronic equipment | |
| CN108307239A (en) | A kind of video content recommendation method and apparatus | |
| CN104537057A (en) | Data searching method and client side | |
| US10956470B2 (en) | Facet-based query refinement based on multiple query interpretations | |
| US20140280240A1 (en) | Similarity Engine for Facilitating Re-Creation of an Application Collection of a Source Computing Device on a Destination Computing Device | |
| CN107341181A (en) | Method, apparatus, computer-readable recording medium and computer equipment are recommended in search | |
| CN109117442A (en) | A kind of application recommended method and device | |
| CN107391540A (en) | A kind of small routine methods of exhibiting, device and grader | |
| CN108052666A (en) | A kind of content recommendation method and device | |
| CN112733024A (en) | Information recommendation method and device | |
| Radlinski et al. | On natural language user profiles for transparent and scrutable recommendation | |
| CN109597934B (en) | Method and device for determining click recommendation words, storage medium and electronic equipment | |
| CN109543113B (en) | Method and device for determining click recommendation words, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180525 |
|
| RJ01 | Rejection of invention patent application after publication |