CN110472145A - A kind of content recommendation method and electronic equipment - Google Patents
A kind of content recommendation method and electronic equipment Download PDFInfo
- Publication number
- CN110472145A CN110472145A CN201910677414.0A CN201910677414A CN110472145A CN 110472145 A CN110472145 A CN 110472145A CN 201910677414 A CN201910677414 A CN 201910677414A CN 110472145 A CN110472145 A CN 110472145A
- Authority
- CN
- China
- Prior art keywords
- portrait
- target
- target user
- user
- content
- 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
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 present invention provides a kind of content recommendation method and electronic equipments, are related to Internet technical field.Wherein, this method comprises: obtaining content to be recommended and the corresponding at least two target users portrait of target user;The matching factor between the target weight coefficient and each target user portrait and content to be recommended of each target user's portrait is determined respectively;According to the corresponding matching factor of each target user portrait and target weight coefficient, the corresponding recommendation index of target user is determined;When recommending index to meet default recommendation condition, content to be recommended is pushed to target user.In the present invention, it can determine that target user draws a portrait in the target user of different field, and the target weight coefficient based on different target user portrait, and the matching degree of each target user portrait and content to be recommended, determine whether that target user pushes content to be recommended cross-cutting but relevant to each target user portrait field, so as to carry out personalized commending contents to target user in frontier.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of content recommendation methods and electronic equipment.
Background technique
With the rapid development of Internet technology, the demand that user obtains content from internet also increasingly tends to field
Extensiveization, this also just promotes many software products using original particular area product as core, extends the production in a large amount of periphery fields
Product obtain demand to meet the cross-cutting content of user.
However, in practical applications, for user when obtaining content, there is typically further personalized commending contents demands, and
Many software products can not carry out respectively personalized commending contents to different user in newly-increased field.
Summary of the invention
The present invention provides a kind of content recommendation method and electronic equipment, is unable to satisfy use with the recommendation for solving cross-cutting
The problem of family individual demand.
In order to solve the above-mentioned technical problem, the present invention is implemented as follows:
In a first aspect, being applied to electronic equipment the embodiment of the invention provides a kind of method of commending contents, comprising:
Obtain content to be recommended and the corresponding at least two target users portrait of target user;Wherein, different described
Target user's portrait is respectively provided with different domain attributes;
At least two target users corresponding target weight coefficient of portrait and at least two mesh are determined respectively
Mark the matching factor between user's portrait and the content to be recommended;
It is drawn a portrait corresponding matching factor and target weight coefficient according to each target user, determines the target user
Corresponding recommendation index;
When the recommendation index meets default recommendation condition, Xiang Suoshu target user pushes the content to be recommended.
Second aspect, the embodiment of the invention also provides a kind of electronic equipment, comprising:
Module is obtained, for obtaining content to be recommended and the corresponding at least two target users portrait of target user;Its
In, different target user portraits is respectively provided with different domain attributes;
First determining module, for determining the corresponding target weight coefficient of at least two target users portrait respectively,
And the matching factor between at least two target users portrait and the content to be recommended;
Second determining module is used for draw a portrait according to each target user corresponding matching factor and target weight system
Number, determines the corresponding recommendation index of the target user;
Pushing module, described in when the recommendation index meets default recommendation condition, Xiang Suoshu target user is pushed
Content to be recommended.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, which includes processor, memory
And it is stored in the computer program that can be run on the memory and on the processor, the computer program is by the place
The step of reason device realizes content recommendation method of the present invention when executing.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable storages
Computer program is stored on medium, and the step of content recommendation method of the present invention is realized when computer program is executed by processor
Suddenly.
In embodiments of the present invention, electronic equipment content to be recommended available first and target user are corresponding at least
Two target user's portraits, wherein different target user's portraits are respectively provided with different domain attributes, and target user draws a portrait
Domain attribute it is associated with the domain attribute of content to be recommended.Then electronic equipment can determine that at least two targets are used respectively
Each of the corresponding target weight coefficient of each target user portrait and at least two target users portrait in the portrait of family
Matching factor between target user's portrait and content to be recommended, and according to each target user draw a portrait corresponding matching factor and
Target weight coefficient determines the corresponding recommendation index of target user, can be to mesh when recommending index to meet default recommendation condition
It marks user and pushes content to be recommended.In embodiments of the present invention, electronic equipment can determine that target user corresponds to different field
Target user portrait, and based on different target user draw a portrait corresponding target weight coefficient and each target user portrait with to
Matching degree between recommendation, it is determined whether push cross-cutting to target user but led with belonging to each target user portrait
The associated content to be recommended in domain, so as to carry out personalized commending contents to target user in new field.
Detailed description of the invention
Fig. 1 shows the flow chart of one of the embodiment of the present invention one content recommendation method;
Fig. 2 shows the flow charts of one of the embodiment of the present invention two content recommendation method;
Fig. 3 shows the structural block diagram of one of the embodiment of the present invention three electronic equipment;
Fig. 4 shows the structural block diagram of another electronic equipment in the embodiment of the present invention three;
Fig. 5 shows the hardware structural diagram of one of each embodiment of present invention electronic equipment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment one
Referring to Fig.1, the flow chart of the content recommendation method of the embodiment of the present invention one is shown, can specifically include following step
It is rapid:
Step 101, content to be recommended and the corresponding at least two target users portrait of target user are obtained;Wherein, no
Same target user's portrait is respectively provided with different domain attributes.
In embodiments of the present invention, the domain attribute of target user's portrait is associated with the domain attribute of content to be recommended,
Content to be recommended can be software product root according in own service demand or the configuration in the electronic device of client traffic demand
Hold, wherein electronic equipment can be the corresponding server of the software product, server farm etc., the embodiment of the present invention to this not
Make specific limit.Content to be recommended can specifically include advertisement, function, product, UGC (User-generated Content, use
Family original content) and PGC (Professionally-generated Content, professional production content) etc. content,
The present invention is not especially limit this.
Target user namely one of potential user wait judge whether to need to push the content to be recommended.Target user can be with
It is any user that account is registered in the software product or its related product, wherein the related product of the software product can
With the software product for being logged in and being used by same account with the software product, such as cell-phone number, WeChat ID etc., thus electric
Sub- equipment can identify user's portrait that same user accumulates in different software respectively according to same account.Certainly, mesh
Mark user can also be one of the user that electronic equipment is gone out based on preset policy selection, such as can be in member user
One of, the present invention is not especially limit this.
In practical applications, which can also be the corresponding server apparatus of related product of the software product,
Alternatively, the electronic equipment can receive the user data that the corresponding server apparatus of other related products is sent, correspondingly, target
The corresponding at least two target users portrait of user can be the electronic equipment and select from the user data that themselves capture stores
Out, the electronic equipment is sent to by other server apparatus alternatively, can also be, the embodiment of the present invention does not limit this specifically
It is fixed.
Wherein, the corresponding either objective user portrait of target user namely individual's letter in a certain field of target user
The data such as breath, habit, preference, such as can be user in career field, leisure area, trip field, driving field, at home neck
Habit, the preference of the different fields such as domain, health field, Sports Field, consulting field, financing field, education sector, consumer field
Data, the present invention is not especially limit this.
The corresponding different target user's portrait of target user is respectively provided with different domain attributes, and each user draws a portrait
Domain attribute it is associated with the domain attribute of content to be recommended.For example, the corresponding first object user portrait of target user
Domain attribute can be to listen song, that is to say that first object user portrait is target user in habit, the preference data for listening song field,
The domain attribute of the corresponding second target user portrait of target user can be abstract the recreational consumption, that is to say that the second target user draws a portrait
Habit, preference data for target user in abstract the recreational consumption field, the domain attribute of content to be recommended then can be music/performance
Meeting.To which electronic equipment can correspond to target user's portrait of different field based on target user, it is determined whether to target user
Push content to be recommended cross-cutting but associated with each target user portrait fields.
It should be noted that at least two target corresponding for content to be recommended and target user of the embodiment of the present invention is used
The acquisition sequence of family portrait is not especially limited.
Step 102, the corresponding target weight coefficient of at least two target users portrait and at least two mesh are determined respectively
Mark the matching factor between user's portrait and content to be recommended.
In embodiments of the present invention, since the target user of different field draws a portrait and the correlation degree of content to be recommended, with
And the influence degree difference of recommendation is treated, therefore, the corresponding target weight of each target user's portrait can be previously set
Coefficient, and store in the electronic device, alternatively, being also based on drawing as a result, setting each target user for a few users feedback
As corresponding target weight coefficient, the present invention is not especially limit this.Electronic equipment is getting target user couple
After at least two target users portrait answered, the target weight coefficient set of drawing a portrait for each target user can be determined.
In addition, target user portrait content to be recommended between matching factor can characterize target user portrait with wait push away
The degree of correlation between content is recommended, for example, if including the permanent residence information of target user in target user's portrait, and it is to be recommended interior
Appearance be related to place, then when the permanent residence information of target user is identical with the place in content to be recommended, target user portrait and
Matching factor between content to be recommended is larger, and when the permanent residence information of target user is located at the place in content to be recommended
With time saving, the first more above-mentioned situation of matching factor between target user's portrait and content to be recommended is taken second place, and works as target user
Permanent residence information and the place in content to be recommended be located at it is domestic different time saving, target user draw a portrait between content to be recommended
The more above-mentioned second situation of matching factor take second place.
It should be noted that the embodiment of the present invention does not make specifically target weight coefficient and determining for matching factor sequentially
It limits.
Step 103, according to the corresponding matching factor of each target user portrait and target weight coefficient, target user is determined
Corresponding recommendation index.
In embodiments of the present invention, electronic equipment can be according to the corresponding target of each target user of target user portrait
Weight coefficient is weighted summation to the corresponding matching factor of each target user portrait, so as to obtain target user couple
The recommendation index answered.When the corresponding recommendation index of target user is larger, then the target user is that can push content to be recommended
Strong recommended.
Step 104, when recommending index to meet default recommendation condition, content to be recommended is pushed to target user.
In embodiments of the present invention, default recommendation condition can be set in the electronic device in advance, when target user is corresponding
Recommendation index when meeting the default recommendation condition, then can push content to be recommended to target user.
In embodiments of the present invention, electronic equipment content to be recommended available first and target user are corresponding at least
Two target user's portraits, wherein different target user's portraits are respectively provided with different domain attributes, and target user draws a portrait
Domain attribute it is associated with the domain attribute of content to be recommended.Then electronic equipment can determine that at least two targets are used respectively
Each of the corresponding target weight coefficient of each target user portrait and at least two target users portrait in the portrait of family
Matching factor between target user's portrait and content to be recommended, and according to each target user draw a portrait corresponding matching factor and
Target weight coefficient determines the corresponding recommendation index of target user, can be to mesh when recommending index to meet default recommendation condition
It marks user and pushes content to be recommended.In embodiments of the present invention, electronic equipment can determine that target user corresponds to different field
Target user portrait, and based on different target user draw a portrait corresponding target weight coefficient and each target user portrait with to
Matching degree between recommendation, it is determined whether push cross-cutting to target user but led with belonging to each target user portrait
The associated content to be recommended in domain, so as to carry out personalized commending contents to target user in new field.
Embodiment two
Referring to Fig. 2, the flow chart of the content recommendation method of the embodiment of the present invention two is shown, can specifically include following step
It is rapid:
Step 201, content to be recommended and the corresponding at least two target users portrait of target user are obtained;Different
Target user's portrait is respectively provided with different domain attributes, and the field of the domain attribute of target user's portrait and content to be recommended
Attribute is associated.
This step is similar with the realization process of above-mentioned steps 101, and this will not be detailed here.
For example, certain traditional Online Music software, only listens the correlation function in song field originally, now introduces a new function
Can, i.e. concert, the ticket sales function of concert, the original user's portrait of the music software is to user in hobby musically
There is certain understanding.Now, having a cross-cutting content to be recommended, " X days-Shanghai-singer Zhang-price is the concert admission ticket of Y
Sale " is wanted to recommend user, and the domain attribute of the content to be recommended is " performance/concert admission ticket ".It, should for target user
Music software can originally be collected into the corresponding essential information user portrait of target user and music user portrait, and the music is soft
Part can be logged in by the account of another payment software, and therefore, which can also be collected by the payment software
To the corresponding consuming capacity portrait of target user.The corresponding electronic equipment of the application software namely server, it is available to
Recommendation " the concert ticket sales that X days-Shanghai-singer Zhang-price is Y " and the corresponding basic letter of target user
Breath user portrait, music user are drawn a portrait and consuming capacity is drawn a portrait, and these three target users draw a portrait.Referring to such as the following table 1, show each
The user information that includes in a target user portrait, corresponding domain attribute, and the relevance with content to be recommended.
Table 1
It should be noted that the embodiment of the present invention is only with various target user's portraits as listed in Table 1, user information etc.
Data instance is illustrated, and limiting the invention for each data as listed in Table 1.
Step 202, the corresponding relationship based on the user portrait and weight coefficient that prestore, determines that each target user draws respectively
As corresponding target weight coefficient.
In embodiments of the present invention, before this step, following step is can also be performed in electronic equipment, is specifically included: really
Determine the corresponding at least two initial weights coefficient of each target user's portrait;It is at least two initial to this according to A/B Test Strategy
Weight coefficient is adjusted, and obtains target weight coefficient;Each target user is drawn a portrait corresponding with each target weight coefficient
Relationship is stored.
Specifically, either objective user portrait corresponding for target user, electronic equipment can first use the target
Family portrait assigns at least two initial weight coefficients, and an initial weight coefficient can be used as a kind of weight Test Strategy, thus
At least two weight Test Strategies can be obtained.Then electronic equipment can be random to select from all candidate users to be recommended
The user of preset ratio is selected, the user selected can be grouped later, every group is tested plan according to different weights respectively
This method is slightly executed, to push content to be recommended to each user selected, and then can be according to user to recommendation interface
Click condition, to the feedback results such as browsing duration for recommending interface, select user feedback from least two weight Test Strategies
Optimal weight Test Strategy.
Next, electronic equipment can be adjusted the weight coefficient in the optimal weight Test Strategy of user feedback,
Adjustment principle, which may is that, can be turned up the corresponding weight coefficient of recommendation advantageous target user portrait, to recommendation without obvious shadow
The loud corresponding weight coefficient of target user's portrait can be turned down.By different degrees of adjustment, at least two can be obtained again
The new weight coefficient of kind, and then electronic equipment can be from remaining candidate user, then randomly chooses the user of preset ratio, so
After be further continued for repeating the above process, until it is optimal from least two new weight Test Strategies to select user feedback again
Weight Test Strategy.The process can repeat preset times, and weight optimal for the user feedback selected for the last time is surveyed
Each weight coefficient in the weight Test Strategy can be determined as each target user's portrait and corresponded to by examination strategy, electronic equipment
Target weight coefficient, and each target user can be drawn a portrait and the corresponding relationship of each target weight coefficient store.
Corresponding determining 4 initial weight coefficients for example, electronic equipment can draw a portrait for each target user, so as to obtain
Tetra- kinds of weight Test Strategies of A, B, C, D are obtained, then electronic equipment can be randomly choosed from all candidate users to be recommended
10% user pushes, wherein every kind of weight Test Strategy can be directed to 2.5% user.According to user feedback as a result,
Electronic equipment can choose out the best weight Test Strategy A of user feedback, and then electronic equipment can be in weight Test Strategy A
On the basis of, it will be to recommending advantageous target user's portrait weight coefficient to be turned up, it will be on the target user's portrait recommended without influence
Weight coefficient is turned down, and by different degrees of adjustment, can obtain 4 new weight Test Strategy E, F, G, H again, and continue
10% user's push into remaining candidate user, after obtaining user feedback result, electronic equipment can choose out optimal power
Weight Test Strategy F, and by essential information user draw a portrait and weight Test Strategy F in mesh corresponding with essential information user portrait
Mark the corresponding storage of weight coefficient 0.20, by music user draw a portrait and weight Test Strategy F in mesh corresponding with music user portrait
Mark the corresponding storage of weight coefficient 0.55, by consuming capacity user draw a portrait and weight Test Strategy F in draw a portrait with consuming capacity user
The corresponding storage of corresponding target weight coefficient 0.25.
Certainly, in practical applications, the corresponding target weight coefficient of each target user's portrait can also be set manually
It is fixed, and target user is drawn a portrait with the storage of the corresponding relationship of the target weight coefficient set in the electronic device, the present invention is implemented
Example is not especially limited this.
Correspondingly, electronic equipment can be determined from the corresponding relationship that pre-stored user draws a portrait with weight coefficient
The current corresponding target weight coefficient of target user's portrait.
For example, the corresponding relationship of the pre-stored user's portrait of electronic equipment and weight coefficient can be as shown in table 2 below, electricity
Sub- equipment can determine the corresponding target weight coefficient of essential information user portrait from corresponding relationship shown in table 2 respectively
It is 0.20, the corresponding target weight coefficient of music user portrait is 0.55, the corresponding target weight system of consuming capacity user portrait
Number is 0.25.
Table 2
User's portrait | Weight coefficient |
Essential information user portrait | 0.20 |
Music user portrait | 0.55 |
Consuming capacity user portrait | 0.25 |
It should be noted that the embodiment of the present invention is only closed so that the portrait of user shown in table 2 as above is corresponding with weight coefficient
It is illustrated for system, limiting the invention for table 2 as above.
Step 203, each target user's portrait includes the user information of at least one dimension;For each dimension, from
In at least one corresponding preset condition of the dimension, the target preset condition that the user information under the dimension is met is determined;Its
In, each preset condition is based on the user information and content setting to be recommended corresponded under dimension.
In embodiments of the present invention, it may each comprise the user information of at least one dimension in each target user's portrait,
For example, essential information user portrait may include the user information of the dimensions such as gender, age, permanent residence.Can in advance according to
At least two preset conditions are set separately to each dimension in user information under recommendation and each dimension.Correspondingly, for
Any dimension, electronic equipment can determine that the user information under the dimension is accorded with from the corresponding each preset condition of the dimension
The target preset condition of conjunction.
For example, referring to following Table 3, by essential information user draw a portrait corresponding permanent residence dimension user information for, should
Permanent residence dimension is corresponding to be set with 4 preset conditions, and the user information of the permanent residence dimension can be Shanghai, that is to say that target is used
The permanent residence at family is Shanghai, and when concert place is located at Shanghai, electronic equipment can determine that the 1st preset condition " use by target
Family permanent residence and concert place are located at same city " it is that the target that is met of the user information under the permanent residence dimension is preset
Condition.
Table 3
It should be noted that the embodiment of the present invention only carries out for the preset condition shown in the table 3 as above and matching score value
Illustrate, limiting the invention for table 3 as above.
Step 204, the corresponding matching score value of each target preset condition is determined respectively.
In embodiments of the present invention, electronic equipment can be from preset condition with the corresponding relationship for matching score value, and difference is true
Determine the corresponding matching score value of each target preset condition.
For example, electronic equipment can determine mesh from preset condition shown in table 3 as above with the corresponding relationship for matching score value
Marking preset condition " target user's permanent residence is located at same city with concert place " corresponding matching score value is 3.
Step 205, the corresponding matching score value of each target preset condition in same target user portrait is added, is obtained
Matching factor between each target user's portrait and content to be recommended.
In embodiments of the present invention, electronic equipment can be by each target preset condition pair in same target user portrait
The matching score value answered is added, so as to obtain the matching factor between each target user's portrait and content to be recommended respectively.
For example, electronic equipment can be with the corresponding matching score value phase of target preset condition each in essential information user portrait
Add, it is hereby achieved that the matching factor between essential information user portrait and content to be recommended is 6.Electronic equipment can be with music
The corresponding matching score value of each target preset condition is added in user's portrait, it is hereby achieved that music user draw a portrait with it is to be recommended
Matching factor between content is 8.Electronic equipment can be with corresponding of each target preset condition in consuming capacity user portrait
It is added with score value, it is hereby achieved that the matching factor between consuming capacity user portrait and content to be recommended is 2.
Step 206, according to the corresponding matching factor of each target user portrait and target weight coefficient, target user is determined
Corresponding recommendation index.
In the embodiment of the present invention, this step can be specifically accomplished in the following manner, comprising: by the same target user of correspondence
The matching factor and target weight multiplication of portrait obtain the corresponding recommendation of each target user's portrait;By each target
The corresponding recommendation of user's portrait is added, and obtains the corresponding recommendation index of target user.
Wherein, electronic equipment can be right according to the corresponding target weight coefficient of each target user of target user portrait
Each target user corresponding matching factor of drawing a portrait is weighted summation, and so as to obtain, target user is corresponding to be recommended to refer to
Number.When the corresponding recommendation index of target user is larger, then the target user is the strong recommendation that can push content to be recommended
Object.When the corresponding recommendation index of target user is smaller, then the target user as content to be recommended recommended can
Energy property is smaller.
In another implementation, electronic equipment can also be by each target preset condition in each target user portrait
Corresponding matching score value obtains each product, then may be used respectively with the target weight multiplication of corresponding target user portrait
To obtain the corresponding recommendation index of target user for each product addition.The embodiment of the present invention is for determining that target user is corresponding
The specific implementation of recommendation index be not especially limited.
For example, electronic equipment can be by the matching factor 6 and target weight coefficient 0.20 of corresponding essential information user portrait
It is multiplied, obtaining the corresponding recommendation of essential information user portrait is 1.2;Electronic equipment can be by of corresponding music user portrait
Distribution coefficient 8 is multiplied with target weight coefficient 0.55, and obtaining the corresponding recommendation of music user portrait is 4.4;Electronic equipment can be with
The matching factor 2 of corresponding consuming capacity user portrait is multiplied with target weight coefficient 0.25, obtains consuming capacity user portrait
Corresponding recommendation is 0.5.Then, electronic equipment can be by the corresponding recommendation 1.2 of essential information user portrait, music user
Corresponding recommendation 4.4 of drawing a portrait and the corresponding recommendation 0.5 of consuming capacity user portrait are added, and it is corresponding to obtain target user
Recommendation index be 6.1.
Step 207, when recommending index to meet default recommendation condition, content to be recommended is pushed to target user.
In embodiments of the present invention, when the corresponding recommendation index of target user meets default recommendation condition, electronic equipment
The corresponding recommendation information of the content to be recommended can be sent by the terminal that software account logs in target user.In concrete application
In, which can specifically not limit this for the information of the forms such as text, image, video, voice, the embodiment of the present invention
It is fixed.And then the corresponding terminal of target user can show the recommendation information, so that target user can check.
Optionally, this step can specifically be accomplished in the following manner, comprising: when recommendation index is greater than or equal to preset value
When, content to be recommended is pushed to target user;And/or when recommendation index is in the corresponding recommendation index of each pre-selected users
The ranking that sorts is less than or equal to default ranking, pushes content to be recommended to target user;Each pre-selected users are corresponding to recommend to refer to
Number is arranged according to sequence from big to small.
It that is to say that default recommendation condition can be greater than or equal to preset value for recommendation index, and/or, recommend index each
The corresponding sequence ranking recommended in index of pre-selected users is less than or equal to default ranking.Wherein, each pre-selected users be to
All potential users for judging whether to need to push the content to be recommended, correspondingly, target user is in each pre-selected users
Any one.
Wherein, recommending index when the corresponding recommendation index of target user is greater than or equal to preset value and/or target user
When in the top in each pre-selected users arranged from big to small, illustrate to push content to be recommended to target user, in very great Cheng
The individual demand that target user may be met on degree is easier to obtain preferable user feedback.
For example, the corresponding recommendation index of target user can be 6.1, it is greater than preset value 4.5, so that electronic equipment can be to
Target user pushes content to be recommended " the concert ticket sales that X days-Shanghai-singer Zhang-price is Y ".
In embodiments of the present invention, electronic equipment content to be recommended available first and target user are corresponding at least
Two target user's portraits, wherein different target user's portraits are respectively provided with different domain attributes, and target user draws a portrait
Domain attribute it is associated with the domain attribute of content to be recommended.Then electronic equipment can determine that at least two targets are used respectively
The corresponding target weight coefficient of each target user portrait in the portrait of family, and respectively from each dimension in target user's portrait
In corresponding each preset condition, the target preset condition that the user information under each dimension is met is determined, and then true respectively
Determine the corresponding matching score value of each target preset condition, and each target preset condition in same target user portrait is corresponding
Matching score value be added, obtain the matching factor between each target user portrait and content to be recommended.It later, can be according to every
A target user draws a portrait corresponding matching factor and target weight coefficient, determines the corresponding recommendation index of target user, works as recommendation
When index meets default recommendation condition, content to be recommended can be pushed to target user.In embodiments of the present invention, electronic equipment
It can determine that target user corresponds to target user's portrait of different field, and based on the corresponding target power of different target user portrait
Weight coefficient is weighted summation to the matching factor between each target user portrait and content to be recommended, to obtain target use
The corresponding recommendation index in family, and then when recommending index to meet default recommendation condition, it is determined that can be pushed to target user across
Field but content to be recommended associated with each target user portrait fields, so as to use in new field target
Family carries out personalized commending contents.
Embodiment three
Referring to Fig. 3, the structural block diagram of a kind of electronic equipment 300 of the embodiment of the present invention three is shown, can specifically include:
Module 301 is obtained, is drawn for obtaining content to be recommended and corresponding at least two target user of target user
Picture;Wherein, different target users portrait is respectively provided with different domain attributes;
Specifically, the domain attribute of target user's portrait is associated with the domain attribute of the content to be recommended.
First determining module 302, for determining the corresponding target weight system of at least two target users portrait respectively
Matching factor between the several and described at least two target users portrait and the content to be recommended;
Second determining module 303 is used for draw a portrait according to each target user corresponding matching factor and target weight
Coefficient determines the corresponding recommendation index of the target user;
Pushing module 304, for when the recommendation index meets default recommendation condition, Xiang Suoshu target user to push institute
State content to be recommended.
Optionally, referring to Fig. 4, each target user's portrait includes the user information of at least one dimension;It is described
First determining module 302 includes:
First determines submodule 3021, true respectively for the corresponding relationship based on the user portrait and weight coefficient that prestore
Determine the corresponding target weight coefficient of each target user's portrait;
Second determines submodule 3022, is used for for each dimension, from least one corresponding preset condition of the dimension
In, determine the target preset condition that the user information under the dimension is met;Wherein, each preset condition is based on corresponding to
User information and the content setting to be recommended under dimension;
Third determines submodule 3023, for determining the corresponding matching score value of each target preset condition respectively;
First is added submodule 3024, for by each of the same target user portrait target preset condition
Corresponding matching score value is added, and obtains the matching factor between each target user's portrait and the content to be recommended.
Optionally, referring to Fig. 4, second determining module 303 includes:
Multiplication submodule 3031, for the matching factor and target weight coefficient of same target user's portrait will to be corresponded to
It is multiplied, obtains the corresponding recommendation of each target user's portrait;
Second is added submodule 3032, and the corresponding recommendation that is used to draw a portrait each target user is added, and obtains institute
State the corresponding recommendation index of target user.
Optionally, referring to Fig. 4, the electronic equipment 300 further include:
Third determining module 305, for determining each target user's portrait corresponding at least two initial weight system
Number;
Module 306 is adjusted, for being adjusted, obtaining at least two initial weights coefficient according to A/B Test Strategy
Obtain target weight coefficient;
Memory module 307, for by each target user portrait pass corresponding with each target weight coefficient
System is stored.
Optionally, referring to Fig. 4, the pushing module 304 includes:
First push submodule 3041, for when the recommendation index is greater than or equal to preset value, Xiang Suoshu target to be used
Family pushes the content to be recommended;
And/or
Second push submodule 3042, for when the recommendation index is in the corresponding recommendation index of each pre-selected users
The ranking that sorts is less than or equal to default ranking, and Xiang Suoshu target user pushes the content to be recommended;Each pre-selected users
It is corresponding that index is recommended to arrange according to sequence from big to small.
Electronic equipment provided in an embodiment of the present invention can be realized electronic equipment in the embodiment of the method for Fig. 1 and Fig. 2 and realize
Each process, to avoid repeating, which is not described herein again.
In embodiments of the present invention, electronic equipment can obtain content and target to be recommended by obtaining module first
The corresponding at least two target users portrait of user, wherein different target user's portraits are respectively provided with different domain attributes,
And the domain attribute of target user's portrait is associated with the domain attribute of content to be recommended.Then electronic equipment can pass through first
Determining module determines the corresponding target weight coefficient of each target user portrait at least two target users portrait respectively,
And at least two each target user portrait in target user's portrait and the matching factor between content to be recommended, and can be with
Determine that target is used according to the corresponding matching factor of each target user portrait and target weight coefficient by the second determining module
The corresponding recommendation index in family can be pushed by pushing module to target user when recommending index to meet default recommendation condition
Content to be recommended.In embodiments of the present invention, electronic equipment can determine that target user corresponds to target user's picture of different field
Picture, and based on different target user draw a portrait corresponding target weight coefficient and each target user portrait with content to be recommended it
Between matching degree, it is determined whether to target user push it is cross-cutting but with each target user draw a portrait fields it is associated
Content to be recommended, so as to carry out personalized commending contents to target user in new field.
Example IV
The hardware structural diagram of Fig. 5 a kind of electronic equipment of each embodiment to realize the present invention,
The electronic equipment 500 includes but is not limited to: radio frequency unit 501, network module 502, audio output unit 503, defeated
Enter unit 504, sensor 505, display unit 506, user input unit 507, interface unit 508, memory 509, processor
The components such as 510 and power supply 511.It will be understood by those skilled in the art that electronic devices structure shown in Fig. 5 is not constituted
Restriction to electronic equipment, electronic equipment may include than illustrating more or fewer components, perhaps combine certain components or
Different component layouts.In embodiments of the present invention, electronic equipment include but is not limited to mobile phone, tablet computer, laptop,
Palm PC, car-mounted terminal, wearable device and pedometer etc..
Wherein, processor 510, for obtaining content to be recommended and corresponding at least two target user of target user
Portrait;Wherein, different target users portrait is respectively provided with different domain attributes;At least two mesh is determined respectively
User is marked to draw a portrait between corresponding target weight coefficient and at least two target user portrait and the content to be recommended
Matching factor;It is drawn a portrait corresponding matching factor and target weight coefficient according to each target user, determines the target
The corresponding recommendation index of user;When the recommendation index meets default recommendation condition, Xiang Suoshu target user push it is described to
Recommendation.
In embodiments of the present invention, electronic equipment content to be recommended available first and target user are corresponding at least
Two target user's portraits, wherein different target user's portraits are respectively provided with different domain attributes, and target user draws a portrait
Domain attribute it is associated with the domain attribute of content to be recommended.Then electronic equipment can determine that at least two targets are used respectively
Each of the corresponding target weight coefficient of each target user portrait and at least two target users portrait in the portrait of family
Matching factor between target user's portrait and content to be recommended, and according to each target user draw a portrait corresponding matching factor and
Target weight coefficient determines the corresponding recommendation index of target user, can be to mesh when recommending index to meet default recommendation condition
It marks user and pushes content to be recommended.In embodiments of the present invention, electronic equipment can determine that target user corresponds to different field
Target user portrait, and based on different target user draw a portrait corresponding target weight coefficient and each target user portrait with to
Matching degree between recommendation, it is determined whether push cross-cutting to target user but led with belonging to each target user portrait
The associated content to be recommended in domain, so as to carry out personalized commending contents to target user in new field.
It should be understood that the embodiment of the present invention in, radio frequency unit 501 can be used for receiving and sending messages or communication process in, signal
Send and receive, specifically, by from base station downlink data receive after, to processor 510 handle;In addition, by uplink
Data are sent to base station.In general, radio frequency unit 501 includes but is not limited to antenna, at least one amplifier, transceiver, coupling
Device, low-noise amplifier, duplexer etc..In addition, radio frequency unit 501 can also by wireless communication system and network and other set
Standby communication.
Electronic equipment provides wireless broadband internet by network module 502 for user and accesses, and such as user is helped to receive
It sends e-mails, browse webpage and access streaming video etc..
Audio output unit 503 can be received by radio frequency unit 501 or network module 502 or in memory 509
The audio data of storage is converted into audio signal and exports to be sound.Moreover, audio output unit 503 can also provide and electricity
The relevant audio output of specific function that sub- equipment 500 executes is (for example, call signal receives sound, message sink sound etc.
Deng).Audio output unit 503 includes loudspeaker, buzzer and receiver etc..
Input unit 504 is for receiving audio or video signal.Input unit 504 may include graphics processor
(Graphics Processing Unit, GPU) 5041 and microphone 5042, graphics processor 5041 is in video acquisition mode
Or the image data of the static images or video obtained in image capture mode by image capture apparatus (such as camera) carries out
Reason.Treated, and picture frame may be displayed on display unit 506.Through graphics processor 5041, treated that picture frame can be deposited
Storage is sent in memory 509 (or other storage mediums) or via radio frequency unit 501 or network module 502.Mike
Wind 5042 can receive sound, and can be audio data by such acoustic processing.Treated audio data can be
The format output that mobile communication base station can be sent to via radio frequency unit 501 is converted in the case where telephone calling model.
Electronic equipment 500 further includes at least one sensor 505, such as optical sensor, motion sensor and other biographies
Sensor.Specifically, optical sensor includes ambient light sensor and proximity sensor, wherein ambient light sensor can be according to environment
The light and shade of light adjusts the brightness of display panel 5061, and proximity sensor can close when electronic equipment 500 is moved in one's ear
Display panel 5061 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (general
For three axis) size of acceleration, it can detect that size and the direction of gravity when static, can be used to identify electronic equipment posture (ratio
Such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap);It passes
Sensor 505 can also include fingerprint sensor, pressure sensor, iris sensor, molecule sensor, gyroscope, barometer, wet
Meter, thermometer, infrared sensor etc. are spent, details are not described herein.
Display unit 506 is for showing information input by user or being supplied to the information of user.Display unit 506 can wrap
Display panel 5061 is included, liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode can be used
Forms such as (Organic Light-Emitting Diode, OLED) configure display panel 5061.
User input unit 507 can be used for receiving the number or character information of input, and generate the use with electronic equipment
Family setting and the related key signals input of function control.Specifically, user input unit 507 include touch panel 5071 and
Other input equipments 5072.Touch panel 5071, also referred to as touch screen collect the touch operation of user on it or nearby
(for example user uses any suitable objects or attachment such as finger, stylus on touch panel 5071 or in touch panel 5071
Neighbouring operation).Touch panel 5071 may include both touch detecting apparatus and touch controller.Wherein, touch detection
Device detects the touch orientation of user, and detects touch operation bring signal, transmits a signal to touch controller;Touch control
Device processed receives touch information from touch detecting apparatus, and is converted into contact coordinate, then gives processor 510, receiving area
It manages the order that device 510 is sent and is executed.Furthermore, it is possible to more using resistance-type, condenser type, infrared ray and surface acoustic wave etc.
Seed type realizes touch panel 5071.In addition to touch panel 5071, user input unit 507 can also include other input equipments
5072.Specifically, other input equipments 5072 can include but is not limited to physical keyboard, function key (such as volume control button,
Switch key etc.), trace ball, mouse, operating stick, details are not described herein.
Further, touch panel 5071 can be covered on display panel 5061, when touch panel 5071 is detected at it
On or near touch operation after, send processor 510 to determine the type of touch event, be followed by subsequent processing device 510 according to touching
The type for touching event provides corresponding visual output on display panel 5061.Although in Fig. 5, touch panel 5071 and display
Panel 5061 is the function that outputs and inputs of realizing electronic equipment as two independent components, but in some embodiments
In, can be integrated by touch panel 5071 and display panel 5061 and realize the function that outputs and inputs of electronic equipment, it is specific this
Place is without limitation.
Interface unit 508 is the interface that external device (ED) is connect with electronic equipment 500.For example, external device (ED) may include having
Line or wireless head-band earphone port, external power supply (or battery charger) port, wired or wireless data port, storage card end
Mouth, port, the port audio input/output (I/O), video i/o port, earphone end for connecting the device with identification module
Mouthful etc..Interface unit 508 can be used for receiving the input (for example, data information, electric power etc.) from external device (ED) and
By one or more elements that the input received is transferred in electronic equipment 500 or can be used in 500 He of electronic equipment
Data are transmitted between external device (ED).
Memory 509 can be used for storing software program and various data.Memory 509 can mainly include storing program area
The storage data area and, wherein storing program area can (such as the sound of application program needed for storage program area, at least one function
Sound playing function, image player function etc.) etc.;Storage data area can store according to mobile phone use created data (such as
Audio data, phone directory etc.) etc..In addition, memory 509 may include high-speed random access memory, it can also include non-easy
The property lost memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Processor 510 is the control centre of electronic equipment, utilizes each of various interfaces and the entire electronic equipment of connection
A part by running or execute the software program and/or module that are stored in memory 509, and calls and is stored in storage
Data in device 509 execute the various functions and processing data of electronic equipment, to carry out integral monitoring to electronic equipment.Place
Managing device 510 may include one or more processing units;Preferably, processor 510 can integrate application processor and modulatedemodulate is mediated
Manage device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is main
Processing wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 510.
Electronic equipment 500 can also include the power supply 511 (such as battery) powered to all parts, it is preferred that power supply 511
Can be logically contiguous by power-supply management system and processor 510, to realize management charging by power-supply management system, put
The functions such as electricity and power managed.
In addition, electronic equipment 500 includes some unshowned functional modules, details are not described herein.
Preferably, the embodiment of the present invention also provides a kind of electronic equipment, including processor 510, and memory 509 is stored in
On memory 509 and the computer program that can run on the processor 510, the computer program are executed by processor 510
Each process of Shi Shixian above content recommended method embodiment, and identical technical effect can be reached, to avoid repeating, here
It repeats no more.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program realizes each process of above content recommended method embodiment, and energy when the computer program is executed by processor
Reach identical technical effect, to avoid repeating, which is not described herein again.Wherein, the computer readable storage medium, such as only
Read memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, abbreviation
RAM), magnetic or disk etc..
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal (can be mobile phone, computer, service
Device, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form belongs within protection of the invention.
Claims (12)
1. a kind of content recommendation method is applied to electronic equipment, which is characterized in that the described method includes:
Obtain content to be recommended and the corresponding at least two target users portrait of target user;Wherein, the different target
User's portrait is respectively provided with different domain attributes;
Determine that at least two target users corresponding target weight coefficient of portrait and at least two target are used respectively
Matching factor between family portrait and the content to be recommended;
It is drawn a portrait corresponding matching factor and target weight coefficient according to each target user, determines that the target user is corresponding
Recommendation index;
When the recommendation index meets default recommendation condition, Xiang Suoshu target user pushes the content to be recommended.
2. the method according to claim 1, wherein each target user's portrait includes at least one dimension
The user information of degree;It is described to determine that at least two target user draws a portrait corresponding target weight coefficient and described respectively
At least two target users portrait the content to be recommended between matching factor the step of, comprising:
Based on the corresponding relationship of the user portrait and weight coefficient that prestore, determine that each target user's portrait is corresponding respectively
Target weight coefficient;
The user information under the dimension is determined from least one corresponding preset condition of the dimension for each dimension
The target preset condition met;Wherein, each preset condition is based on user information under corresponding dimension and described wait push away
Recommend content setting;
The corresponding matching score value of each target preset condition is determined respectively;
Each of same target user's portrait corresponding matching score value of the target preset condition is added, is obtained each
Matching factor between target user's portrait and the content to be recommended.
3. the method according to claim 1, wherein described draw a portrait corresponding according to each target user
Distribution coefficient and target weight coefficient, the step of determining the target user corresponding recommendation index, comprising:
By the matching factor and target weight multiplication of the same target user's portrait of correspondence, obtains each target and use
The corresponding recommendation of family portrait;
Each target user corresponding recommendation of drawing a portrait is added, the corresponding recommendation index of the target user is obtained.
4. the method according to claim 1, wherein described determine at least two target users portrait respectively
Matching factor between corresponding target weight coefficient and at least two target user portrait and the content to be recommended
The step of before, further includes:
Determine the corresponding at least two initial weights coefficient of each target user's portrait;
According to A/B Test Strategy, at least two initial weights coefficient is adjusted, obtains target weight coefficient;
The corresponding relationship of each target user's portrait and each target weight coefficient is stored.
5. the method according to claim 1, wherein described when the recommendation index meets default recommendation condition
When, Xiang Suoshu target user push the content to be recommended the step of, comprising:
When the recommendation index is greater than or equal to preset value, Xiang Suoshu target user pushes the content to be recommended;
And/or
Ranking is preset when the recommendation index is less than or equal in the corresponding sequence ranking recommended in index of each pre-selected users,
The content to be recommended is pushed to the target user;Each pre-selected users are corresponding to recommend index according to from big to small
Sequence arranges.
6. a kind of electronic equipment characterized by comprising
Module is obtained, for obtaining content to be recommended and the corresponding at least two target users portrait of target user;Wherein,
Different target user portraits are respectively provided with different domain attributes;
First determining module, for determining that at least two target user draws a portrait corresponding target weight coefficient respectively, and
Matching factor between at least two target users portrait and the content to be recommended;
Second determining module is used for draw a portrait according to each target user corresponding matching factor and target weight coefficient, really
Determine the corresponding recommendation index of the target user;
Pushing module, for when the recommendation index meets default recommendation condition, Xiang Suoshu target user push to be described wait push away
Recommend content.
7. electronic equipment according to claim 6, which is characterized in that each target user's portrait includes at least one
The user information of a dimension;First determining module includes:
First determines submodule, for the corresponding relationship based on the user portrait and weight coefficient that prestore, determines each institute respectively
State the corresponding target weight coefficient of target user's portrait;
Second determines submodule, for determining institute from least one corresponding preset condition of the dimension for each dimension
State the target preset condition that the user information under dimension is met;Wherein, each preset condition is based under corresponding dimension
User information and the content setting to be recommended;
Third determines submodule, for determining the corresponding matching score value of each target preset condition respectively;
First is added submodule, for by corresponding of the target preset condition of each of same target user portrait
It is added with score value, obtains the matching factor between each target user's portrait and the content to be recommended.
8. electronic equipment according to claim 6, which is characterized in that second determining module includes:
Multiplication submodule is obtained for that will correspond to the matching factor and target weight multiplication of same target user's portrait
Obtain the corresponding recommendation of each target user's portrait;
Second is added submodule, and the corresponding recommendation that is used to draw a portrait each target user is added, and obtains the target and uses
The corresponding recommendation index in family.
9. electronic equipment according to claim 6, which is characterized in that the electronic equipment further include:
Third determining module, for determining the corresponding at least two initial weights coefficient of each target user's portrait;
Module is adjusted, for being adjusted at least two initial weights coefficient according to A/B Test Strategy, obtains target
Weight coefficient;
Memory module, for depositing the corresponding relationship of each target user's portrait and each target weight coefficient
Storage.
10. electronic equipment according to claim 6, which is characterized in that the pushing module includes:
First push submodule, for when the recommendation index is greater than or equal to preset value, Xiang Suoshu target user to push institute
State content to be recommended;
And/or
Second push submodule, for when the recommendation index is in the corresponding sequence ranking recommended in index of each pre-selected users
Less than or equal to default ranking, Xiang Suoshu target user pushes the content to be recommended;Each pre-selected users are corresponding to be pushed away
Index is recommended to arrange according to sequence from big to small.
11. a kind of electronic equipment, which is characterized in that including processor, memory and be stored on the memory and can be in institute
The computer program run on processor is stated, such as claim 1 to 5 is realized when the computer program is executed by the processor
Any one of described in content recommendation method the step of.
12. a kind of computer readable storage medium, which is characterized in that store computer journey on the computer readable storage medium
Sequence, the content recommendation method as described in any one of claims 1 to 5 is realized when the computer program is executed by processor
Step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910677414.0A CN110472145B (en) | 2019-07-25 | 2019-07-25 | Content recommendation method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910677414.0A CN110472145B (en) | 2019-07-25 | 2019-07-25 | Content recommendation method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110472145A true CN110472145A (en) | 2019-11-19 |
CN110472145B CN110472145B (en) | 2022-11-29 |
Family
ID=68508330
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910677414.0A Active CN110472145B (en) | 2019-07-25 | 2019-07-25 | Content recommendation method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110472145B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111143697A (en) * | 2020-01-02 | 2020-05-12 | 腾讯科技(深圳)有限公司 | Content recommendation method and related device |
CN111241394A (en) * | 2020-01-07 | 2020-06-05 | 腾讯科技(深圳)有限公司 | Data processing method and device, computer readable storage medium and electronic equipment |
CN111709813A (en) * | 2020-06-19 | 2020-09-25 | 深圳市赛宇景观设计工程有限公司 | Commodity recommendation method based on big data line |
CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
CN111782877A (en) * | 2020-07-06 | 2020-10-16 | 聚好看科技股份有限公司 | Server, display equipment and video searching and sorting method thereof |
CN112035743A (en) * | 2020-08-28 | 2020-12-04 | 腾讯科技(深圳)有限公司 | Data recommendation method and device, computer equipment and storage medium |
CN112269928A (en) * | 2020-10-23 | 2021-01-26 | 百度在线网络技术(北京)有限公司 | User recommendation method and device, electronic equipment and computer readable medium |
CN112309390A (en) * | 2020-03-05 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information interaction method and device |
CN112511865A (en) * | 2020-12-10 | 2021-03-16 | 杭州次元岛科技有限公司 | Video content recommendation system based on social media |
CN112749558A (en) * | 2020-09-03 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Target content acquisition method and device, computer equipment and storage medium |
CN113055423A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN113127723A (en) * | 2019-12-31 | 2021-07-16 | Oppo(重庆)智能科技有限公司 | User portrait processing method, device, server and storage medium |
WO2022016522A1 (en) * | 2020-07-24 | 2022-01-27 | 华为技术有限公司 | Recommendation model training method and apparatus, recommendation method and apparatus, and computer-readable medium |
CN116433082A (en) * | 2023-03-22 | 2023-07-14 | 北京游娱网络科技有限公司 | Evaluation report generation method and device, electronic equipment and storage medium |
CN117114820A (en) * | 2023-10-23 | 2023-11-24 | 广州伊的家网络科技有限公司 | Method and system for calculating optimal push index of offline user and online user |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150269256A1 (en) * | 1999-06-28 | 2015-09-24 | Gracenote, Inc. | System and method for cross-library recommendation |
CN105574110A (en) * | 2015-12-14 | 2016-05-11 | 北京奇虎科技有限公司 | Intelligent game recommending method and device |
CN106446045A (en) * | 2016-08-31 | 2017-02-22 | 上海交通大学 | Method and system for building user portrait based on conversation interaction |
CN107145536A (en) * | 2017-04-19 | 2017-09-08 | 畅捷通信息技术股份有限公司 | User's portrait construction method and device and recommendation method and apparatus |
CN108154401A (en) * | 2018-01-15 | 2018-06-12 | 网易无尾熊(杭州)科技有限公司 | User's portrait depicting method, device, medium and computing device |
CN108520058A (en) * | 2018-03-30 | 2018-09-11 | 维沃移动通信有限公司 | A kind of Business Information recommends method and mobile terminal |
CN108711075A (en) * | 2018-05-22 | 2018-10-26 | 阿里巴巴集团控股有限公司 | A kind of Products Show method and apparatus |
CN108769159A (en) * | 2018-05-16 | 2018-11-06 | 北京豆果信息技术有限公司 | A kind of electronic cookbook intelligent recommendation method |
CN109493199A (en) * | 2019-01-04 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
CN109783730A (en) * | 2019-01-03 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
-
2019
- 2019-07-25 CN CN201910677414.0A patent/CN110472145B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150269256A1 (en) * | 1999-06-28 | 2015-09-24 | Gracenote, Inc. | System and method for cross-library recommendation |
CN105574110A (en) * | 2015-12-14 | 2016-05-11 | 北京奇虎科技有限公司 | Intelligent game recommending method and device |
CN106446045A (en) * | 2016-08-31 | 2017-02-22 | 上海交通大学 | Method and system for building user portrait based on conversation interaction |
CN107145536A (en) * | 2017-04-19 | 2017-09-08 | 畅捷通信息技术股份有限公司 | User's portrait construction method and device and recommendation method and apparatus |
CN108154401A (en) * | 2018-01-15 | 2018-06-12 | 网易无尾熊(杭州)科技有限公司 | User's portrait depicting method, device, medium and computing device |
CN108520058A (en) * | 2018-03-30 | 2018-09-11 | 维沃移动通信有限公司 | A kind of Business Information recommends method and mobile terminal |
CN108769159A (en) * | 2018-05-16 | 2018-11-06 | 北京豆果信息技术有限公司 | A kind of electronic cookbook intelligent recommendation method |
CN108711075A (en) * | 2018-05-22 | 2018-10-26 | 阿里巴巴集团控股有限公司 | A kind of Products Show method and apparatus |
CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
CN109783730A (en) * | 2019-01-03 | 2019-05-21 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
CN109493199A (en) * | 2019-01-04 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
关梓骜: ""基于大数据技术的用户画像系统的设计与研究——以"心发现"平台为例"", 《中国优秀博硕士学位论文全文数据库(硕士) 经济与管理科学辑》 * |
李冰: ""基于Hadoop的个性化视频推荐系统的设计与实现"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113055423A (en) * | 2019-12-27 | 2021-06-29 | Oppo广东移动通信有限公司 | Policy pushing method, policy execution method, device, equipment and medium |
CN113127723B (en) * | 2019-12-31 | 2023-07-14 | Oppo(重庆)智能科技有限公司 | User portrait processing method, device, server and storage medium |
CN113127723A (en) * | 2019-12-31 | 2021-07-16 | Oppo(重庆)智能科技有限公司 | User portrait processing method, device, server and storage medium |
CN111143697B (en) * | 2020-01-02 | 2023-03-21 | 腾讯科技(深圳)有限公司 | Content recommendation method and related device |
CN111143697A (en) * | 2020-01-02 | 2020-05-12 | 腾讯科技(深圳)有限公司 | Content recommendation method and related device |
CN111241394A (en) * | 2020-01-07 | 2020-06-05 | 腾讯科技(深圳)有限公司 | Data processing method and device, computer readable storage medium and electronic equipment |
CN111241394B (en) * | 2020-01-07 | 2023-09-22 | 腾讯科技(深圳)有限公司 | Data processing method, data processing device, computer readable storage medium and electronic equipment |
CN112309390A (en) * | 2020-03-05 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information interaction method and device |
CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
CN111709813B (en) * | 2020-06-19 | 2021-04-16 | 省广营销集团有限公司 | Commodity recommendation method based on big data line |
CN111709813A (en) * | 2020-06-19 | 2020-09-25 | 深圳市赛宇景观设计工程有限公司 | Commodity recommendation method based on big data line |
CN111782877B (en) * | 2020-07-06 | 2023-11-03 | 聚好看科技股份有限公司 | Server, display device and video search ordering method thereof |
CN111782877A (en) * | 2020-07-06 | 2020-10-16 | 聚好看科技股份有限公司 | Server, display equipment and video searching and sorting method thereof |
WO2022016522A1 (en) * | 2020-07-24 | 2022-01-27 | 华为技术有限公司 | Recommendation model training method and apparatus, recommendation method and apparatus, and computer-readable medium |
CN112035743A (en) * | 2020-08-28 | 2020-12-04 | 腾讯科技(深圳)有限公司 | Data recommendation method and device, computer equipment and storage medium |
CN112035743B (en) * | 2020-08-28 | 2021-10-15 | 腾讯科技(深圳)有限公司 | Data recommendation method and device, computer equipment and storage medium |
CN112749558A (en) * | 2020-09-03 | 2021-05-04 | 腾讯科技(深圳)有限公司 | Target content acquisition method and device, computer equipment and storage medium |
CN112749558B (en) * | 2020-09-03 | 2023-11-24 | 腾讯科技(深圳)有限公司 | Target content acquisition method, device, computer equipment and storage medium |
CN112269928A (en) * | 2020-10-23 | 2021-01-26 | 百度在线网络技术(北京)有限公司 | User recommendation method and device, electronic equipment and computer readable medium |
CN112511865A (en) * | 2020-12-10 | 2021-03-16 | 杭州次元岛科技有限公司 | Video content recommendation system based on social media |
CN116433082A (en) * | 2023-03-22 | 2023-07-14 | 北京游娱网络科技有限公司 | Evaluation report generation method and device, electronic equipment and storage medium |
CN116433082B (en) * | 2023-03-22 | 2023-12-26 | 北京游娱网络科技有限公司 | Evaluation report generation method and device, electronic equipment and storage medium |
CN117114820A (en) * | 2023-10-23 | 2023-11-24 | 广州伊的家网络科技有限公司 | Method and system for calculating optimal push index of offline user and online user |
Also Published As
Publication number | Publication date |
---|---|
CN110472145B (en) | 2022-11-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110472145A (en) | A kind of content recommendation method and electronic equipment | |
CN107707828B (en) | A kind of method for processing video frequency and mobile terminal | |
CN108347704A (en) | Information recommendation method and mobile terminal | |
CN110222212A (en) | A kind of display control method and terminal device | |
CN106528745A (en) | Method and device for recommending resources on mobile terminal, and mobile terminal | |
CN108156228A (en) | A kind of ad data method for pushing and device | |
CN108334539A (en) | Object recommendation method, mobile terminal and computer readable storage medium | |
CN108121803A (en) | A kind of method and server of definite page layout | |
CN109032719A (en) | A kind of object recommendation method and terminal | |
CN108920119A (en) | A kind of sharing method and mobile terminal | |
CN109409244A (en) | A kind of object puts the output method and mobile terminal of scheme | |
CN109410004A (en) | A kind of recommended method, device and mobile terminal | |
CN108897473A (en) | A kind of interface display method and terminal | |
CN107908765A (en) | A kind of game resource processing method, mobile terminal and server | |
CN110046015A (en) | Using sharing method and terminal | |
CN108616448A (en) | A kind of the path recommendation method and mobile terminal of Information Sharing | |
CN108733274A (en) | A kind of icon display method and terminal device | |
CN109388456A (en) | A kind of head portrait selection method and mobile terminal | |
CN110457086A (en) | A kind of control method of application program, mobile terminal and server | |
CN108519089A (en) | A kind of more people's route planning methods and terminal | |
CN110442281A (en) | A kind of application icon display methods and terminal | |
CN110069675A (en) | A kind of search method and mobile terminal | |
CN110162653A (en) | A kind of picture and text sort recommendations method and terminal device | |
CN109726303A (en) | A kind of image recommendation method and terminal | |
CN108712321A (en) | A kind of reminding method and mobile terminal of message |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |