CN106815364A - Content delivery method and device - Google Patents
Content delivery method and device Download PDFInfo
- Publication number
- CN106815364A CN106815364A CN201710055194.9A CN201710055194A CN106815364A CN 106815364 A CN106815364 A CN 106815364A CN 201710055194 A CN201710055194 A CN 201710055194A CN 106815364 A CN106815364 A CN 106815364A
- Authority
- CN
- China
- Prior art keywords
- content
- user
- interest tags
- hot
- hot 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.)
- 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 Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses content delivery method and device.One specific embodiment of the method includes:Hot content storehouse to be pushed is obtained, hot content storehouse includes at least one temperature data more than first threshold and is configured with the hot content of tag attributes;Hot content storehouse is matched with the interest tags set of user based on tag attributes, to determine object content, wherein, interest tags set is what the sharing data based on user was set up;And push object content.The implementation method can accurately and rapidly match user's content interested, improve content push efficiency.
Description
Technical field
The application is related to field of computer technology, and in particular to push technology field, more particularly to content delivery method and
Device.
Background technology
With the development of network technology, social platform is increasingly becoming a kind of important means that user obtains information.Social activity is flat
Platform can enter the platform rear line pushed information in user.Current social platform generally carries out letter by following two modes
Breath is pushed:A kind of is to push the related information of the subscription according to the subscription of user, and another kind is according to heat such as comment amount, attention rates
Degrees of data pushes current temperature information higher to user.The former needs user actively to subscribe to information labels interested, when
User can not accurately push away when being not provided with subscription information or current information to be pushed storehouse in the absence of the information related to the subscription
Send the content that user is interested;The latter do not consider then user preference whether with push information matches, row information is entered at random and is pushed away
Send, the information specific aim of push is poor, and pushing efficiency has to be hoisted.
The content of the invention
In order to solve above-mentioned one or more technical problems of the prior art, this application provides content promote method and
Device.
On the one hand, this application provides a kind of content delivery method, including:Hot content storehouse to be pushed is obtained, it is popular
Content library includes at least one temperature data more than first threshold and is configured with the hot content of tag attributes;Based on tag attributes
Hot content storehouse is matched with the interest tags set of user, to determine object content, wherein, interest tags set is base
Set up in the sharing data of user;And push object content.
In some optional implementations, it is above-mentioned based on tag attributes by the interest tags collection of hot content storehouse and user
Conjunction is matched, to determine object content, including:Each interest tags in interest tags set by tag attributes with user enter
Row matching;The matching degree of at least one of the interest tags set by tag attributes and user interest tags is higher than preset matching
The hot content of threshold value is spent as object content.
In some optional implementations, above-mentioned hot content storehouse also includes that at least one temperature data is more than the second threshold
The hot content of value and non-label allocation attribute, it is above-mentioned based on tag attributes by the interest tags set of hot content storehouse and user
Matched, to determine object content, also included:When temperature data are more than first threshold and are configured with the hot topic of tag attributes
When not existing the hot content matched with the interest tags in the interest tags set of user in appearance, at least one temperature number
According to the heat that lookup in the hot content more than Second Threshold and non-label allocation attribute is associated with the interest tags set of user
Door content, to determine object content.
In some optional implementations, first threshold is less than Second Threshold.
In some optional implementations, the above method for pushing also includes setting up the interest tags set of user
Step, including:Behavioural information in response to detecting user's sharing contents, obtains shared content;In sharing to user
Appearance is modeled analysis, extracts interest based on splitting glass opaque of the effective keyword in the content that user shares as user
Label;For interest tags configure effective time, and the interest tags based on splitting glass opaque are added to the interest tags collection of user
Close.
In some optional implementations, the interest tags based on splitting glass opaque are being added to the interest tags of user
After set, it is above-mentioned set up user interest tags set the step of also include:Judge that each interest tags are according to effective time
No failure;The interest tags for failing are removed from interest tags set.
In some optional implementations, the above method for pushing also includes being hot content label allocation attribute
Step, including:Temperature data are extracted more than the keyword in the hot content of first threshold;It is that temperature data are big based on keyword
In the hot content label allocation attribute of first threshold.
Second aspect, this application provides a kind of content push device, including:Acquiring unit, is configured to obtain and waits to push away
The hot content storehouse sent, hot content storehouse includes at least one temperature data more than first threshold and is configured with the heat of tag attributes
Door content;Matching unit, is configured to be matched hot content storehouse with the interest tags set of user based on tag attributes,
To determine object content, wherein, interest tags set is what the sharing data based on user was set up;And push unit, configuration
For pushing object content.
In some optional implementations, above-mentioned matching unit is further used for determining in target as follows
Hold:Each interest tags in interest tags set by above-mentioned tag attributes with user are matched;By tag attributes and user
At least one of interest tags set interest tags hot content of the matching degree higher than preset matching degree threshold value as mesh
Mark content.
In some optional implementations, above-mentioned hot content storehouse also includes that at least one temperature data is more than the second threshold
The hot content of value and non-label allocation attribute;Matching unit is further used for determining object content as follows:Work as heat
Degrees of data is more than first threshold and is configured with the hot content of tag attributes the interest tags set phase not existed with user
During the hot content matched somebody with somebody, searched in hot content of at least one temperature data more than Second Threshold and non-label allocation attribute
The hot content being associated with the interest tags set of user, to determine object content.
In some optional implementations, above-mentioned first threshold is less than above-mentioned Second Threshold.
In some optional implementations, the above pusher also includes creating unit, is configured to set up and uses
The interest tags set at family.Above-mentioned creating unit is configured to set up as follows the interest tags set of user:Response
In the behavioural information for detecting user's sharing contents, shared content is obtained;Analysis is modeled to the content that user shares,
Extract interest tags based on splitting glass opaque of the effective keyword in the content that user shares as user;It is interest tags
Configuration effective time, and the interest tags based on splitting glass opaque are added to the interest tags set of user.
In some optional implementations, above-mentioned creating unit is also configured to:Each interest is judged according to effective time
Whether label fails;The interest tags for failing are removed from interest tags set.
In some optional implementations, the above pusher also includes dispensing unit, for being hot content
Label allocation attribute;Above-mentioned dispensing unit is used to configure as follows the tag attributes of hot content:Extract temperature data
More than the keyword in the hot content of first threshold;It is that temperature data are matched somebody with somebody more than the hot content of first threshold based on keyword
Put tag attributes.
Content delivery method and device that the application is provided, by obtaining hot content storehouse to be pushed, wherein in popular
Rong Ku includes at least one temperature data more than first threshold and is configured with the hot content of tag attributes, then by hot content
Storehouse is matched with the interest tags set of user, and to determine object content, wherein interest tags set is dividing based on user
Data foundation is enjoyed, object content is finally pushed, the splitting glass opaque based on user is realized and is targetedly pushed, and
For hot content label allocation attribute is conducive to accurately and rapidly matching user's content interested in hot content storehouse,
Pushing efficiency can be lifted.
Brief description of the drawings
Non-limiting example is described in detail with reference to what the following drawings was made by reading, other features,
Objects and advantages will become more apparent upon:
Fig. 1 is that the application can apply to exemplary system architecture figure therein;
Fig. 2 is the flow chart of the one embodiment according to present context method for pushing;
Fig. 3 is a principle schematic for application scenarios according to present context method for pushing;
Fig. 4 is the principle schematic of another application scenarios according to present context method for pushing;
Fig. 5 is the flow chart of another embodiment according to present context method for pushing;
Fig. 6 is a structural representation according to present context pusher;
Fig. 7 is adapted for the structural representation of the computer system of the terminal device for realizing the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that, in order to
Be easy to description, be illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 is used to be provided between terminal device 101,102,103 and server 105 medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User 110 can be interacted by network 104 with using terminal equipment 101,102,103 with server 105, with receive or
Send message etc..Social networking application can be installed on terminal device 101,102,103.
Terminal device 101,102,103 can be the various electronic equipments with display screen, including but not limited to intelligent hand
Machine, panel computer, E-book reader, pocket computer on knee, desktop computer, intelligent watch etc..
Server 105 can be to provide the server of various services, such as to display on terminal device 101,102,103
Social network content provides the social network server that data are supported.Social network server can be to the user 110 that receives
The content acquisition request sent by terminal device 101,102,103 is processed, and by result (such as in social networks
Friend issue content) feed back to terminal device 101,102,103.
It should be noted that the content delivery method device that the embodiment of the present application is provided can be performed by server 105,
Correspondingly, content push device can be arranged in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the flow 200 of the one embodiment according to present context method for pushing.Such as
Shown in Fig. 2, the flow 200 of the content delivery method that the application is provided is comprised the following steps:
Step 201, obtains hot content storehouse to be pushed.
In the present embodiment, content delivery method operation electronic equipment (such as server 105 shown in Fig. 1) thereon can
To obtain hot content storehouse.Wherein, hot content storehouse includes announced content, specifically includes at least one temperature data and is more than
First threshold and it is configured with the hot content of tag attributes.
Different users can issue content in social network-i i-platform, and backstage information editor can send out on information platform
Content can have been issued in cloth content, social network-i i-platform or information platform with substantial amounts of.These have issued the temperature of content
Data can read number, comment number, forward number, collection number, thumb up number to draw by counting it, read number, comment number, forwarding
Number, collection number, thumb up number are higher, then the value of temperature data is higher;Alternatively, the temperature data for having issued content can be sent out with it
Cloth time correlation, the temperature data value of the content of more early issue is lower.Above-mentioned electronic equipment can set up heat according to temperature data
Door content library, for example, be added to hot content storehouse more than the content of a certain value using temperature data as hot content.
In the present embodiment, above-mentioned hot content storehouse includes at least one temperature data more than first threshold and is configured with mark
Sign the hot content of attribute.Above-mentioned electronic equipment can be the label allocations such as a part of hot content, used as these hot contents
Tag attributes.Specifically, tag attributes be can including for hot content or the theme stronger with hot content relevance
Keyword, category keywords, content-keyword etc., can be drawn and be stored by above-mentioned electronic equipment based on text analyzing.One
In a little optional implementations, hot content can include label symbol, then can make the content cited in the label symbol
It is the label of the hot content, such as certain content includes label symbol " # ", then can be by comprising two hot topics of label symbol
A label of the content between two label symbols directly as the hot content is extracted in content.Further, it is each
Item hot content can be configured with one or more labels, and each hot content can be simultaneously obtained when hot content storehouse is obtained
Whole labels.
It should be noted that above-mentioned hot content can be the content of the forms such as word, image, video, audio, Ke Yiwei
Original hot content, such as one blog;Can also be certain the popular reply of content, such as thumb up number is more to return
It is multiple.Above-mentioned electronic equipment can will meet pre-conditioned various forms of hot contents and store to hot content to be pushed
Storehouse, the hot content storehouse can be stored in above-mentioned electronic equipment, it is also possible to be stored in and the communication connection of above-mentioned electronic equipment
In other equipment.When in above-mentioned hot content library storage and other equipment, above-mentioned electronic equipment can receive it by network
The hot content storehouse that his equipment sends.
Step 202, is matched hot content storehouse with the interest tags set of user based on tag attributes, to determine mesh
Mark content.
After the hot content storehouse comprising the hot content with tag attributes is got, above-mentioned electronic equipment can be with base
Every hot content is matched with the interest tags set of user in the tag attributes of hot content.Wherein, interest tags
Set is what the sharing data based on user was set up, can include at least one user label interested.Above-mentioned user's is emerging
Interesting tag set can pre-build and store in above-mentioned electronic equipment.
In concrete implementation, when user enters social networking application or information application, the background server of the application
Detect new user and enter application, the logon information of the user, such as ID, password etc. can be obtained, and find out and this
The corresponding interest tags set of logon information of user.If user does not log in, the device id can be found out according to device id etc.
The interest tags set of corresponding user.
User, can be by content interested when content interested is seen in social networking application or in information application
Friend is shared with, and generally splitting glass opaque can more clearly reflect the point of interest of user compared to behaviors such as reply, thumb ups, change
Yan Zhi, the interest-degree of content of the user to sharing would generally be higher than user to reply or the interest-degree of the content of thumb up.It is above-mentioned emerging
Interest tags in interesting tag set can be based on the splitting glass opaque to user in the social networking application or information application
What the analysis that data are carried out was extracted, content and user that wherein the splitting glass opaque data of user can be shared including user
The temporal information of sharing contents.Specifically, what above-mentioned electronic equipment can in advance obtain that user in predetermined amount of time shares is complete
Portion's content, and user's keyword interested is extracted from the content shared, in these keywords can be shared for user
Topic, affiliated classification for being included in appearance etc..
In the present embodiment, above-mentioned electronic equipment can be by the interest tags in the interest tags set of user and step
Content in the hot content storehouse obtained in 201 is matched, so that it is determined that going out the object content pushed for user.Specifically,
May determine that whether the label of hot content is consistent with the label in the interest tags set of user, if unanimously, can determine
The hot content is object content.Generally, the interest tags of user can be interest keyword, and the tag attributes of hot content can
Think content-keyword, it can be determined that whether content-keyword is consistent with interest keyword, the content-keyword correspondence if being consistent
Hot content be object content.
In some optional implementations of the present embodiment, can be by the tag attributes of above-mentioned hot content with user's
Each interest tags in interest tags set are matched, and by least in the interest tags set of tag attributes and user
The matching degree of individual interest tags is higher than the hot content of preset matching degree threshold value as object content.Specifically, for user
Each interest tags in interest tags set, can calculate the tag attributes of hot content and the matching degree of the interest tags,
If matching degree exceedes default matching degree threshold value, the corresponding hot content of the tag attributes can be determined for user is interested
Content, can be using user content interested as object content to be pushed.
In further implementation, if the tag attributes of hot content include multiple labels, can also be according to
The number of labels of the interest tags sets match of each hot content and user determines object content, for example can by with user
Interest tags sets match the most hot content of number of labels as object content.Alternatively, can be combined with matching
Degree and the number of labels of matching determine object content, for example, can be higher than the number of labels of default matching degree threshold value by matching degree
Most hot contents are used as object content.
Step 203, pushes object content.
After object content determines, object content can be pushed to user by above-mentioned electronic equipment.Specifically, Ke Yi
Object content is actively pushed into the currently used terminal device of user and with messagewindow in the case of having obtained push authority
Form be shown, or object content can be illustrated in head in user after social networking application or information application is entered
Page or other default positions.
For above-described embodiment of the application, the scene of application can be, social network-i i-platform can current temperature compared with
The content with tag attributes is found out in the content of other users issue high, then in these contents with tag attributes
Find out the content matched with the interest tags set of user, and by the terminal device of these content push to user.
With further reference to Fig. 3, the principle it illustrates an application scenarios according to present context method for pushing is shown
It is intended to.As shown in figure 3, user is clicked on the terminal device 31 after application icon enters social networking application, social networking application
Background server 32 can obtain the ID of user, and searched according to ID, comprising " silver-colored soul ", " teenager group
The set of the interest tags such as magical drift ", " slaughter cry of a deer obtain the Nobel Prize ", " North China cooling ", then in hot content storehouse Zhong Bao
Search whether have and above-mentioned user interest label one in hot content containing tag attributes and temperature data more than first threshold
The label of cause, when wherein one hot content is found, " the magical drift # of the juvenile groups of # is parsed:Look up to and redeem ... " there is mark
Sign the attribute magical drift of group " teenager ", then can by the terminal device 31 of the content push to user, thus user be with
Put and can also push content interested to user in the case of subscribing to message or type, improve the specific aim of content push.
The content delivery method that the above embodiments of the present application are provided, can utilize the emerging of the sharing data foundation based on user
Interesting tag set carries out content push, can realize accurate, rich targetedly pushing;Also, in the object content choosing for pushing
Select the middle label of hot content using configured tag attributes to be matched with the interest tags of user, matching can be lifted
Efficiency and accuracy, so as to improve pushing efficiency.
In some optional implementations of the application, above-mentioned hot content storehouse can also include at least one temperature number
According to the hot content more than Second Threshold and non-label allocation attribute, at this moment, in above-mentioned steps 202, can be further according to
Following manner determines object content:When temperature data do not exist more than first threshold and in being configured with the hot content of tag attributes
During the hot content matched with the interest tags in the interest tags set of user, second is more than at least one temperature data
The hot content that lookup is associated with the interest tags set of user in the hot content of threshold value and non-label allocation attribute, with true
Make object content.If that is, above-mentioned temperature data more than first threshold and be configured with the hot content of tag attributes with
The match is successful for the interest tags set of user, then can be further in temperature data more than Second Threshold and non-label allocation category
Matched in the hot content of property, and using the hot content that the match is successful as object content.
Specifically, above-mentioned temperature data can be carried out more than the hot content of Second Threshold and non-label allocation attribute
Semantic analysis, draws the semantic keywords of the hot content, and the semantic keywords are matched with the interest tags of user.
The semantic relevancy of the two can be calculated in matching, the preset keyword degree of correlation that can be for example based on each interest tags is arranged
Table calculates semantic relevancy.For example, if interest tags are " De Yun societies cross-talk performance ", its preset keyword list can be with
Including following keyword:" Guo Degang ", " Beijing cross-talk performance ", " ticketing service " etc., wherein each keyword has semantic relevancy
Data, and the semantic relevancy data of each keyword with different, and then can draw the corresponding hot content of these keywords
The degree of correlation, the hot content according to relevancy ranking from each temperature data more than Second Threshold and non-label allocation attribute afterwards
Determine object content.
In some optional implementations, can be pre-build based on label on the basis of above-mentioned hot content storehouse
Hot content list and the hot content list based on temperature.Wherein, the hot content list based on label includes at least one
Temperature data are more than first threshold and are configured with the hot content of tag attributes, and the hot content list based on temperature is included at least
One temperature data is more than Second Threshold and the hot content of non-label allocation attribute.In specific application, can first in base
The hot content with the interest tags sets match of user is searched whether in the hot content list of label, if not searching
Arrive, the hot content being associated with the interest tags of user can be further searched in the hot content list based on temperature,
And then the object content found in the hot content list based on temperature is pushed to user.Alternatively, above-mentioned first threshold can
With less than above-mentioned Second Threshold, i.e., the minimum value of the temperature data of the hot content in hot content list based on label can be with
Less than the minimum value of the temperature data of the hot content in the hot content list based on temperature, so, comprehensive consideration user's
The temperature data of interest tags and hot content to be pushed, can lift the accuracy of push.
With continued reference to Fig. 4, the principle it illustrates another application scenarios according to present context method for pushing is shown
It is intended to.From unlike scene shown in Fig. 3, in scene shown in Fig. 4, server 42 does not find in current hot content
The content of the tag attributes with the interest tags set corresponding to user, then continue to be searched and interest in current hot content
The related or similar content of label.The content for finding non-label allocation attribute in current hot content " understands antimalarial sweet wormwood
Element ... ", the way ... of health preserving soup " winter keep out the cold " are respectively with the interest tags of user " slaughter cry of a deer obtain the Nobel Prize ", " cold wave comes
Attack " degree of correlation is higher, then this two contents are pushed to the terminal device 41 of user as object content.Thus, with mark
When in the hot content of label attribute in the absence of the content matched with the interest tags set of user, it is possible to use content total quantity
The larger current hot content set search user interest degree for not configuring content tab content higher, it is achieved thereby that precisely
Content push.
Fig. 5 is refer to, it illustrates the flow chart of another embodiment according to present context method for pushing.Content
The flow 500 of method for pushing, comprises the following steps:
Step 501, sets up the interest tags set of user.
In the present embodiment, above-mentioned electronic equipment can set up the interest tags collection of user according to the sharing data of user
Close.Specifically, can detect whether to produce the behavioural information of sharing contents on backstage first, for example, can detect sharing contents
Interface whether be called, can determine to generate the row of user's sharing contents when the interface for detecting sharing contents is called
It is information, afterwards in response to detecting the behavioural information of user's sharing contents, obtains shared content.Wherein, user shares
Content can be announced content, the content is shared with friend by user, that is, show user to the interest-degree of the content compared with
Height, therefore the interest tags extracted from the content that user shares can more accurately characterize the hobby of user.Then can be with
Analysis is modeled to the content that user shares, the effective keyword in the content that the user shares is extracted as the use
The interest tags based on splitting glass opaque at family.Keyword extraction mould can be set up in modeling analysis using methods such as machine learning
Type, extracts the effective crucial keyword of the content topic, type and related information that characterize shared, as the interest of user
Label.Then can also be the interest tags configuration effective time of user, and the interest tags based on splitting glass opaque are based on to divide
Enjoy the interest tags of behavior added to the interest tags set of user.
In the step of interest tags set that user is set up above-mentioned, the user's that can be based in predetermined amount of time sharing
The behavioural information of content sets up above-mentioned interest tags set.Above-mentioned electronic equipment can collect user in predetermined amount of time and be shared
All the elements, and effective keyword extraction is carried out to every content, the effective keyword of generation interest tags is for can be to characterize
The notional word or sentence of content topic, type and the related information shared.Effective time can be configured afterwards, by each interest mark
Storage corresponding with user profile is signed, so that when content is pushed corresponding interest tags collection can be found according to user profile
Close.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can also judge each according to effective time
Whether interest tags are failed, and the interest tags for failing are removed from the interest tags set of user.It is alternatively possible to one
The fixed time cycle detects whether each interest tags fail, and the interest tags of failure are periodically removed from the interest tags of user,
Ensure user interest tags set it is ageing, and then lifted content push accuracy.
Step 502, is hot content label allocation attribute.
Generally, hot content is temperature content higher.In the present embodiment, can be according to comment number, thumb up number, forwarding
The data such as number calculate the temperature data for having issued content, select hot content of the temperature data more than first threshold, and extract this
Keyword in a little hot contents, is that temperature data configure mark more than the hot content of first threshold based on the keyword for extracting
Sign attribute.The keyword that will directly can for example extract as corresponding hot content tag attributes, also can by with extraction
The semantic similar word of the keyword that goes out, word, sentence as corresponding hot content tag attributes.
In some optional implementations, label symbol, such as " # ", " * " etc., these symbols are included in hot content
Can be pre-defined on the backstage of social networking application or information class application, such as definition of symbol " # " can be accorded with for topic, then
Tag attributes of the content cited in these label symbols as hot content can be directly extracted in hot content, or
Say, can directly using the content cited in these label symbols as keyword, and correspondence is configured to the label category of hot content
Property.
Step 503, obtains hot content storehouse to be pushed.
When content is pushed, above-mentioned electronic equipment can obtain to be pushed from the content data base that can be currently pushed
Hot content storehouse, wherein, the hot content storehouse includes that at least one is configured with the hot topic of tag attributes in above-mentioned steps 502
Hold.
Step 504, is matched hot content storehouse with the interest tags set of user based on tag attributes, to determine mesh
Mark content.
In the present embodiment, above-mentioned electronic equipment can be based on the tag attributes of hot content by every hot content and walk
The interest tags set of rapid 501 users for being set up is matched.Specific matching way can include but is not limited to keyword
Matching, relatedness computation etc., can be using matching degree is higher or the degree of correlation is higher hot content as object content.Or upper
When not finding the hot content of matching in the hot content for stating label allocation attribute in step 502, can be in non-label allocation
Continue to match in the hot content of attribute, object content is determined according to matching result.Specifically, can be by the hot topic that the match is successful
Content is used as object content.In actual applications, if the match is successful, can also be according to issuing time, temperature data or random
The hot content of at least one non-label allocation attribute is selected as object content.
Step 505, pushes object content.
After object content determines, object content can be pushed to user by above-mentioned electronic equipment.Specifically, Ke Yi
Obtain and object content is actively pushed into the currently used terminal device of user and with messagewindow in the case of pushing authority
Form is shown, or object content can be illustrated in into homepage in user after social networking application or information application is entered
Or other default positions.
It should be noted that the above-mentioned step 503 realized in flow, step 504 and step 505 respectively with previous embodiment
In step 201, step 202 and step 203 it is identical, will not be repeated here.
Compared with embodiment illustrated in fig. 2, the content delivery method of embodiment illustrated in fig. 5 increased sets up dividing based on user
The step of enjoying the interest tags set of behavior and the step of for hot content label allocation attribute in hot content storehouse, is not having
There is the interest tags set of prestored user or can also be pushed to user in the case of not being pre-configured with hot content tag attributes
Content interested, further improves pushing efficiency.
With further reference to Fig. 6, as the realization to above-mentioned each figure shown device, this application provides a kind of content push dress
The one embodiment put, the device embodiment is corresponding with the device embodiment shown in Fig. 2, specifically can apply to various electronics
In equipment (such as the server 105 shown in Fig. 1).
As shown in fig. 6, content push device 600 includes acquiring unit 601, matching unit 602 and push unit 603.
Wherein, acquiring unit 601 may be configured to obtain hot content storehouse to be pushed, and the hot content storehouse includes at least one heat
Degrees of data is more than first threshold and is configured with the hot content of tag attributes;Matching unit 602 may be configured to based on label
Attribute is matched hot content storehouse with the interest tags set of user, to determine object content, wherein, interest tags set
It is what the sharing data based on user was set up;Push unit 603 may be configured to push object content.
In the present embodiment, acquiring unit 601 can calculate the temperature data of current distribution of content to determine in hot topic
Hold, set up hot content storehouse, and can be the label allocations such as a part of hot content, the label as these hot contents belongs to
Property.Tag attributes can be semantic and keynote message the keyword of emphasis for representing hot content.
Matching unit 602 can be based on the tag attributes of the hot content acquired in acquiring unit 601 and the interest of user
Tag set matches.Wherein, the interest tags set of user can include one or more interest tags, each interest tags
One or more interest point informations of user can be characterized.Matching unit may determine that the tag attributes of hot content with user's
Whether interest tags are consistent, or determine whether hot content is user's content interested according to the degree of correlation of the two, if so,
Then using corresponding hot content as object content.
In this some optional implementation implemented, above-mentioned matching unit 602 is further used for as follows
Determine object content:Each interest tags in interest tags set by tag attributes with user are matched;By tag attributes
With the hot content of the matching degree higher than preset matching degree threshold value of at least one of the interest tags set of user interest tags
As object content.I.e. matching unit 602 can calculate each tag attributes of hot content and matching for user interest label
Degree, if matching degree is higher than preset matching degree threshold value, using corresponding hot content as object content.It is possible to further root
According to above-mentioned tag attributes and the Semantic Similarity Measurement matching degree of above-mentioned interest tags, semantic feature specifically can be first analyzed,
The similarity of semantic feature is calculated afterwards.Specifically can use existing various similarity calculating methods, such as cosine similarity,
Pearson correlation coefficient etc., the application is not limited this.
Further, above-mentioned hot content storehouse also includes that at least one temperature data is more than Second Threshold and non-label allocation
The hot content of attribute.At this moment, matching unit 602 is further used for determining object content as follows:When temperature data
More than first threshold and it is configured with the hot content of tag attributes in the absence of the interest mark in the interest tags set with user
During the hot content that label match, at least one temperature data more than Second Threshold and the hot content of non-label allocation attribute
It is middle to search the hot content being associated with the interest tags set of user, to determine object content.Alternatively, above-mentioned first threshold
Value is less than above-mentioned Second Threshold.
Object content determined by matching unit 602 can be pushed to user by push unit 603.Specifically, push
Object content actively can be pushed to the currently used terminal device of user by unit 603 in the case where push authority has been obtained
And be shown in the form of messagewindow, or can be in user after social networking application or information application is entered, by target
Content displaying is in homepage or other default positions.
In some optional implementations of the present embodiment, the above pusher 600 also includes creating unit, matches somebody with somebody
Put the interest tags set for setting up user.Specifically, creating unit 600 is configured to set up user as follows
Interest tags set:Behavioural information in response to detecting user's sharing contents, obtains shared content;User is shared
Content be modeled analysis, extract effective keyword in the content that user shares as user based on splitting glass opaque
Interest tags;For interest tags configure effective time, and the interest tags based on splitting glass opaque are added to the interest mark of user
Sign set.
Further, above-mentioned creating unit is also configured to:Judge whether each interest tags fail according to effective time;Will
The interest tags of failure are removed from interest tags set.
In some optional implementations of the present embodiment, the above pusher 600 also includes dispensing unit, uses
Hot content label allocation attribute in the hot content storehouse obtained for acquiring unit 601.Dispensing unit specifically for according to
Following manner configures the tag attributes of hot content:Temperature data are extracted more than the key in the hot content of above-mentioned first threshold
Word;It is hot content label allocation attribute of the temperature data more than above-mentioned first threshold based on keyword.
The content push device that the above embodiments of the present application are provided, can utilize the emerging of the sharing data foundation based on user
Interesting tag set carries out content push, can realize accurate, rich targetedly pushing;Also, in the object content choosing for pushing
Select the middle label of hot content using configured tag attributes to be matched with the interest tags of user, matching can be lifted
Efficiency and accuracy, so as to improve pushing efficiency.
It should be appreciated that each step phase in all units described in device 600 and the device referring to figs. 2 and 5 description
Correspondence.Thus, the operation and feature above with respect to content delivery method description is equally applicable to device 600 and the list for wherein including
Unit, will not be repeated here.Corresponding units in device 500 can cooperate with the unit in terminal device and/or server
To realize the scheme of the embodiment of the present application.
It will be understood by those skilled in the art that the above pusher 600 also includes some other known features, for example
Processor, memory etc., in order to unnecessarily obscure embodiment of the disclosure, these known structures are not shown in figure 6.
Below with reference to Fig. 7, it illustrates the calculating for being suitable to terminal device or server for realizing the embodiment of the present application
The structural representation of machine system 700.
As shown in fig. 7, computer system 700 includes CPU (CPU) 701, it can be according to storage read-only
Program in memory (ROM) 702 or be loaded into program in random access storage device (RAM) 703 from storage part 708 and
Perform various appropriate actions and treatment.In RAM 703, the system that is also stored with 700 operates required various programs and data.
CPU 701, ROM 702 and RAM 703 are connected with each other by bus 704.Input/output (I/O) interface 705 is also connected to always
Line 704.
I/O interfaces 705 are connected to lower component:Including the importation 706 of keyboard, mouse etc.;Penetrated including such as negative electrode
The output par, c 707 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage part 708 including hard disk etc.;
And the communications portion 709 of the NIC including LAN card, modem etc..Communications portion 709 via such as because
The network of spy's net performs communication process.Driver 710 is also according to needing to be connected to I/O interfaces 705.Detachable media 711, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., as needed on driver 710, in order to read from it
Computer program be mounted into as needed storage part 708.
Especially, in accordance with an embodiment of the present disclosure, the process above with reference to flow chart description may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being tangibly embodied in machine readable
Computer program on medium, the computer program includes the program code for the device shown in execution flow chart.At this
In the embodiment of sample, the computer program can be downloaded and installed by communications portion 709 from network, and/or from removable
Medium 711 is unloaded to be mounted.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, device and computer journey
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
One part for module, program segment or code of table a, part for the module, program segment or code includes one or more
Executable instruction for realizing the logic function of regulation.It should also be noted that in some realizations as replacement, institute in square frame
The function of mark can also occur with different from the order marked in accompanying drawing.For example, two square frame reality for succeedingly representing
On can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also
It is noted that the combination of the square frame in each square frame and block diagram and/or flow chart in block diagram and/or flow chart, Ke Yiyong
Perform the function of regulation or the special hardware based system of operation to realize, or can be referred to computer with specialized hardware
The combination of order is realized.
Being described in involved unit in the embodiment of the present application can be realized by way of software, it is also possible to by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor bag
Include acquiring unit, matching unit and push unit.Wherein, the title of these units is not constituted to the unit under certain conditions
The restriction of itself, for example, acquiring unit be also described as " obtain it is to be pushed, be more than including at least one temperature data
First threshold and be configured with tag attributes hot content hot content storehouse unit ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media, the non-volatile calculating
Machine storage medium can be the nonvolatile computer storage media included in device described in above-described embodiment;Can also be
Individualism, without the nonvolatile computer storage media allocated into terminal.Above-mentioned nonvolatile computer storage media is deposited
One or more program is contained, when one or more of programs are performed by an equipment so that the equipment:Obtain
Hot content storehouse to be pushed, the hot content storehouse includes at least one temperature data more than first threshold and is configured with label
The hot content of attribute;The hot content storehouse is matched with the interest tags set of user based on the tag attributes,
To determine object content, wherein, the interest tags set is what the sharing data based on the user was set up;Push the mesh
Mark content.
Above description is only the preferred embodiment and the explanation to institute's application technology principle of the application.People in the art
Member is it should be appreciated that involved invention scope in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where the inventive concept is not departed from, is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (14)
1. a kind of content delivery method, it is characterised in that methods described includes:
Hot content storehouse to be pushed is obtained, the hot content storehouse includes at least one temperature data more than first threshold and matches somebody with somebody
It is equipped with the hot content of tag attributes;
The hot content storehouse is matched with the interest tags set of user based on the tag attributes, to determine in target
Hold, wherein, the interest tags set is what the sharing data based on the user was set up;And
Push the object content.
2. method according to claim 1, it is characterised in that it is described based on the tag attributes by the hot content storehouse
Matched with the interest tags set of user, to determine object content, including:
Each interest tags in interest tags set by the tag attributes with the user are matched;
By the matching degree of at least one of tag attributes and the interest tags set of user interest tags higher than default
Hot content with degree threshold value is used as the object content.
3. method according to claim 2, it is characterised in that the hot content storehouse also includes at least one temperature data
More than Second Threshold and the hot content of non-label allocation attribute;
It is described the hot content storehouse is matched with the interest tags set of user based on the tag attributes, to determine mesh
Mark content, also includes:
When the temperature data do not exist with the user's more than first threshold and in being configured with the hot content of tag attributes
During the hot content that the interest tags in interest tags set match, Second Threshold is more than in described at least one temperature data
And the hot content being associated with the interest tags set of the user is searched in the hot content of non-label allocation attribute, with true
Make the object content.
4. method according to claim 3, it is characterised in that the first threshold is less than the Second Threshold.
5. method according to claim 1, it is characterised in that methods described also includes setting up the interest tags set of user
The step of, including:
Behavioural information in response to detecting user's sharing contents, obtains shared content;
Analysis is modeled to the content that user shares, the effective keyword in the content that the user shares is extracted as institute
State the interest tags based on splitting glass opaque of user;
For the interest tags configure effective time, and by the interest tags based on splitting glass opaque added to the user's
Interest tags set.
6. method according to claim 5, it is characterised in that be added to by the interest tags based on splitting glass opaque
After the interest tags set of the user, it is described set up user interest tags set the step of also include:
Judge whether each interest tags fail according to the effective time;
The interest tags for failing are removed from the interest tags set.
7. method according to claim 1, it is characterised in that methods described also includes being the hot content label allocation
The step of attribute, including:
Temperature data are extracted more than the keyword in the hot content of the first threshold;
It is hot content label allocation attribute of the temperature data more than the first threshold based on the keyword.
8. a kind of content push device, it is characterised in that described device includes:
Acquiring unit, is configured to obtain hot content storehouse to be pushed, and the hot content storehouse includes at least one temperature number
According to more than first threshold and being configured with the hot content of tag attributes;
Matching unit, is configured to carry out the hot content storehouse with the interest tags set of user based on the tag attributes
Matching, to determine object content, wherein, the interest tags set is what the sharing data based on the user was set up;And
Push unit, is configured to push the object content.
9. device according to claim 8, it is characterised in that the matching unit is further configured to according to such as lower section
Formula determines the object content:
Each interest tags in interest tags set by the tag attributes with the user are matched;
By the matching degree of at least one of tag attributes and the interest tags set of user interest tags higher than default
Hot content with degree threshold value is used as the object content.
10. device according to claim 9, it is characterised in that the hot content storehouse also includes at least one temperature number
According to the hot content more than Second Threshold and non-label allocation attribute;
The matching unit is further configured to determine the object content as follows:
When the temperature data do not exist with the user's more than first threshold and in being configured with the hot content of tag attributes
During the hot content that the interest tags in interest tags set match, Second Threshold is more than in described at least one temperature data
And the hot content being associated with the interest tags set of the user is searched in the hot content of non-label allocation attribute, with true
Make the object content.
11. devices according to claim 10, it is characterised in that the first threshold is less than the Second Threshold.
12. devices according to claim 8, it is characterised in that described device also includes creating unit, are configured to set up
The interest tags set of user;
The creating unit is configured to set up as follows the interest tags set of the user:
Behavioural information in response to detecting user's sharing contents, obtains shared content;
Analysis is modeled to the content that user shares, the effective keyword in the content that the user shares is extracted as institute
State the interest tags based on splitting glass opaque of user;
For the interest tags configure effective time, and by the interest tags based on splitting glass opaque added to the user's
Interest tags set.
13. devices according to claim 12, it is characterised in that the creating unit is also configured to:
Judge whether each interest tags fail according to the effective time;
The interest tags for failing are removed from the interest tags set.
14. devices according to claim 8, it is characterised in that described device also includes dispensing unit, for being the heat
Door content label allocation attribute;
The dispensing unit is used to configure as follows the tag attributes of hot content:
Temperature data are extracted more than the keyword in the hot content of the first threshold;
It is hot content label allocation attribute of the temperature data more than the first threshold based on the keyword.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710055194.9A CN106815364A (en) | 2017-01-24 | 2017-01-24 | Content delivery method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710055194.9A CN106815364A (en) | 2017-01-24 | 2017-01-24 | Content delivery method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106815364A true CN106815364A (en) | 2017-06-09 |
Family
ID=59110956
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710055194.9A Pending CN106815364A (en) | 2017-01-24 | 2017-01-24 | Content delivery method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106815364A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107562884A (en) * | 2017-09-04 | 2018-01-09 | 百度在线网络技术(北京)有限公司 | A kind of information flow shows method, apparatus, server and storage medium |
CN108183931A (en) * | 2017-12-04 | 2018-06-19 | 中国电子科技集团公司第三十研究所 | A kind of distribution subscription matching process based on demand management tree shape model |
CN108228794A (en) * | 2017-12-29 | 2018-06-29 | 三角兽(北京)科技有限公司 | Apparatus for management of information, information processing unit and automatically reply/comment method |
CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技(深圳)有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
CN109033180A (en) * | 2018-06-26 | 2018-12-18 | 深圳市爱的网络科技有限公司 | A kind of information-pushing method, device, computer installation and computer readable storage medium |
CN109151043A (en) * | 2018-09-06 | 2019-01-04 | 北京赛佰特科技有限公司 | Message delivery system based on cloud service |
CN109740056A (en) * | 2018-12-28 | 2019-05-10 | 丹翰智能科技(上海)有限公司 | It is a kind of for provide a user customization financial information method and apparatus |
CN110309358A (en) * | 2018-03-27 | 2019-10-08 | 京东方科技集团股份有限公司 | A kind of resource recommendation method and system |
CN110362741A (en) * | 2019-06-11 | 2019-10-22 | 新浪网技术(中国)有限公司 | A kind of intelligent delivery method and system of Feed stream information |
CN110795660A (en) * | 2019-09-26 | 2020-02-14 | 北京大米科技有限公司 | Data analysis method, data analysis device, electronic device, and medium |
CN110941763A (en) * | 2019-12-02 | 2020-03-31 | 深圳市云歌人工智能技术有限公司 | Content push method and device and storage medium |
CN111125526A (en) * | 2019-12-24 | 2020-05-08 | 腾讯科技(深圳)有限公司 | Content pushing method and device based on artificial intelligence and electronic equipment |
CN111177123A (en) * | 2019-12-30 | 2020-05-19 | 联想(北京)有限公司 | Method, apparatus, electronic device and medium for optimizing tag library |
CN113190744A (en) * | 2021-04-20 | 2021-07-30 | 北京异乡旅行网络科技有限公司 | Information processing and device for content management system |
US20220272392A1 (en) * | 2019-07-31 | 2022-08-25 | Shanghai Hode Information Technology Co., Ltd. | Burst traffic processing method, computer device and readable storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8091032B2 (en) * | 2006-11-30 | 2012-01-03 | Red Hat, Inc. | Automatic generation of content recommendations weighted by social network context |
CN103177107A (en) * | 2013-03-27 | 2013-06-26 | 百度在线网络技术(北京)有限公司 | Recommendation method and device |
CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
CN104834695A (en) * | 2015-04-24 | 2015-08-12 | 南京邮电大学 | Activity recommendation method based on user interest degree and geographic position |
CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Data recommendation method and device for application program |
CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
CN105912650A (en) * | 2016-04-07 | 2016-08-31 | 腾讯科技(深圳)有限公司 | Method and apparatus of recommending songs |
CN106296445A (en) * | 2016-08-01 | 2017-01-04 | 国网浙江省电力公司 | A kind of power customer label construction method |
CN106326289A (en) * | 2015-06-30 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Contact person matching method and apparatus |
-
2017
- 2017-01-24 CN CN201710055194.9A patent/CN106815364A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8091032B2 (en) * | 2006-11-30 | 2012-01-03 | Red Hat, Inc. | Automatic generation of content recommendations weighted by social network context |
CN103177107A (en) * | 2013-03-27 | 2013-06-26 | 百度在线网络技术(北京)有限公司 | Recommendation method and device |
CN104216965A (en) * | 2014-08-21 | 2014-12-17 | 北京金山安全软件有限公司 | Information recommendation method and device |
CN104834695A (en) * | 2015-04-24 | 2015-08-12 | 南京邮电大学 | Activity recommendation method based on user interest degree and geographic position |
CN106326289A (en) * | 2015-06-30 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Contact person matching method and apparatus |
CN105095470A (en) * | 2015-08-03 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Data recommendation method and device for application program |
CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
CN105912650A (en) * | 2016-04-07 | 2016-08-31 | 腾讯科技(深圳)有限公司 | Method and apparatus of recommending songs |
CN106296445A (en) * | 2016-08-01 | 2017-01-04 | 国网浙江省电力公司 | A kind of power customer label construction method |
Non-Patent Citations (1)
Title |
---|
张余等: "《2015中国互联网电视发展蓝皮书》", 31 January 2016, 中国传媒大学出版社 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107562884A (en) * | 2017-09-04 | 2018-01-09 | 百度在线网络技术(北京)有限公司 | A kind of information flow shows method, apparatus, server and storage medium |
CN108399565A (en) * | 2017-10-09 | 2018-08-14 | 平安科技(深圳)有限公司 | Financial product recommendation apparatus, method and computer readable storage medium |
CN108183931A (en) * | 2017-12-04 | 2018-06-19 | 中国电子科技集团公司第三十研究所 | A kind of distribution subscription matching process based on demand management tree shape model |
CN108228794A (en) * | 2017-12-29 | 2018-06-29 | 三角兽(北京)科技有限公司 | Apparatus for management of information, information processing unit and automatically reply/comment method |
CN110309358A (en) * | 2018-03-27 | 2019-10-08 | 京东方科技集团股份有限公司 | A kind of resource recommendation method and system |
CN109033180A (en) * | 2018-06-26 | 2018-12-18 | 深圳市爱的网络科技有限公司 | A kind of information-pushing method, device, computer installation and computer readable storage medium |
CN109151043A (en) * | 2018-09-06 | 2019-01-04 | 北京赛佰特科技有限公司 | Message delivery system based on cloud service |
CN109740056A (en) * | 2018-12-28 | 2019-05-10 | 丹翰智能科技(上海)有限公司 | It is a kind of for provide a user customization financial information method and apparatus |
CN110362741A (en) * | 2019-06-11 | 2019-10-22 | 新浪网技术(中国)有限公司 | A kind of intelligent delivery method and system of Feed stream information |
CN110362741B (en) * | 2019-06-11 | 2022-02-25 | 新浪网技术(中国)有限公司 | Intelligent issuing method and system of Feed stream information |
US20220272392A1 (en) * | 2019-07-31 | 2022-08-25 | Shanghai Hode Information Technology Co., Ltd. | Burst traffic processing method, computer device and readable storage medium |
US11889133B2 (en) * | 2019-07-31 | 2024-01-30 | Shanghai Hode Information Technology Co., Ltd. | Burst traffic processing method, computer device and readable storage medium |
CN110795660A (en) * | 2019-09-26 | 2020-02-14 | 北京大米科技有限公司 | Data analysis method, data analysis device, electronic device, and medium |
CN110941763A (en) * | 2019-12-02 | 2020-03-31 | 深圳市云歌人工智能技术有限公司 | Content push method and device and storage medium |
CN111125526A (en) * | 2019-12-24 | 2020-05-08 | 腾讯科技(深圳)有限公司 | Content pushing method and device based on artificial intelligence and electronic equipment |
CN111177123A (en) * | 2019-12-30 | 2020-05-19 | 联想(北京)有限公司 | Method, apparatus, electronic device and medium for optimizing tag library |
CN113190744A (en) * | 2021-04-20 | 2021-07-30 | 北京异乡旅行网络科技有限公司 | Information processing and device for content management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106815364A (en) | Content delivery method and device | |
Nie et al. | Identifying users across social networks based on dynamic core interests | |
RU2595594C2 (en) | Method and apparatus for automatically summarising contents of electronic documents | |
US8725717B2 (en) | System and method for identifying topics for short text communications | |
Cao et al. | Mashup service clustering based on an integration of service content and network via exploiting a two-level topic model | |
US20160357872A1 (en) | Event networks and event view construction and display | |
US20150178265A1 (en) | Content Recommendation System using a Neural Network Language Model | |
CN109819284A (en) | A kind of short video recommendation method, device, computer equipment and storage medium | |
JP2020507861A (en) | Method and apparatus for providing search results | |
CN111177538B (en) | User interest label construction method based on unsupervised weight calculation | |
US10341278B2 (en) | Adaptive presentation of comments based on sentiment | |
KR20160057475A (en) | System and method for actively obtaining social data | |
WO2014000576A1 (en) | Network searching method and network searching system | |
CN106030571A (en) | Dynamically modifying elements of user interface based on knowledge graph | |
CN106484764A (en) | User's similarity calculating method based on crowd portrayal technology | |
US20150379074A1 (en) | Identification of intents from query reformulations in search | |
CN103577549A (en) | Crowd portrayal system and method based on microblog label | |
CN103136228A (en) | Image search method and image search device | |
CN114143216A (en) | System and method for network-based advertisement data traffic latency reduction | |
US20140365868A1 (en) | Method, server, browser, and system for recommending text information | |
US11880401B2 (en) | Template generation using directed acyclic word graphs | |
US11574123B2 (en) | Content analysis utilizing general knowledge base | |
CN105740481A (en) | Search recommending method and device | |
CN114154013A (en) | Video recommendation method, device, equipment and storage medium | |
CN114417157B (en) | Data pushing method and device, computer equipment and computer medium |
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: 20170609 |
|
RJ01 | Rejection of invention patent application after publication |