CN109145218A - A kind of article recommended method and device - Google Patents
A kind of article recommended method and device Download PDFInfo
- Publication number
- CN109145218A CN109145218A CN201811047704.9A CN201811047704A CN109145218A CN 109145218 A CN109145218 A CN 109145218A CN 201811047704 A CN201811047704 A CN 201811047704A CN 109145218 A CN109145218 A CN 109145218A
- Authority
- CN
- China
- Prior art keywords
- article
- target
- rumour
- user
- association
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000005516 engineering process Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000013518 transcription Methods 0.000 description 1
- 230000035897 transcription Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of article recommended method and devices, the article recommended method comprise determining that target article and with the related association article of the target article, the association article includes: the article of refuting a rumour for the target article, and/or, the progress article of the target article, the progress article are the article of the progress about the target article event of interest；Determine the first user for clicking the target article；Recommend the association article to first user.Article recommended method of the invention is that have between the target article that the association article of push and user clicked before and be associated with, so that the article of recommendation is more accurate based on the incidence relation between article.
Description
Technical field
The present invention relates to articles to recommend field, in particular to a kind of article recommended method and device.
Background technique
With the rapid development of informationization technology, the information covered the sky and the earth on network, user requires a great deal of time
Therefrom screen oneself interested article.It is currently, there are the recommended method of some articles, mainly by article text
Attribute is analyzed, and determines the feature tag of article, and obtains the basic information of user and the text of user's click, search
Chapter calculates the portrait information of user, then according to the feature tag of article and the correlation of the portrait information of user, to user
The content for recommending correlation strong.This kind of way of recommendation is by article analysis, the calculation processing of user's portrait, text recommended to the user
Chapter may not be that user wants the article read, and recommend precision not high enough.
Summary of the invention
The purpose of the present invention is to provide a kind of article recommended method and devices, can be closed based on the association between article
System recommends article to user, can be improved the precision of article recommendation.
First aspect present invention provides a kind of article recommended method, comprising:
Determine target article and with the related association article of the target article, the association article includes: to be directed to
The article of refuting a rumour of the target article, and/or, the progress article of the target article, the progress article is about the mesh
Mark the article of the progress of article event of interest；
Determine the first user for clicking the target article；
Recommend the association article to first user.
Optionally, determine target article and with the related association article of the target article before, the method
Further include:
It establishes target article and recalls dictionary；
The article that the target article recalls dictionary is hit in follow-up to recall into target article pond.
Optionally, if the association article is the article of refuting a rumour, determine target article and with the target article
Before related association article, the method also includes:
Foundation article of refuting a rumour recalls dictionary and recalls source, the article of refuting a rumour recall dictionary keyword include refute a rumour,
It starts a rumour, pseudo event, rumor, the source of recalling includes that multiple officials refute a rumour platform；
The article that article of refuting a rumour described in hit is recalled dictionary and recalls source is recalled into article pond of refuting a rumour.
Optionally, determine target article and with the related association article of the target article before, the method
Further include:
Similar multiple target articles are identified in target article pond by the similar identification technology of text；
Article of refuting a rumour corresponding with the multiple target article is identified in the article pond of refuting a rumour；
Establish the incidence relation of the multiple target article Yu the article of refuting a rumour.
Optionally, determine target article and with the related association article of the target article before, the method
Further include:
Article of refuting a rumour is determined in the article pond of refuting a rumour；
Multiple mesh similar with the article of refuting a rumour are identified in target article pond by the similar identification technology of text
Mark article；
Establish the incidence relation of the multiple target article Yu the article of refuting a rumour.
Optionally, if the association article is the progress article, it includes focus incident that the target article, which recalls dictionary,
Dictionary and/or customized concern dictionary, determine target article and with the related association article of the target article
Before, the method also includes:
Similar multiple target articles are identified in target article pond by the similar identification technology of text；
Upper identical event flag is marked for the multiple target article；
According to the uplink time of the multiple target article, the successive of upper event progress is marked for the multiple target article
Sequentially, the incidence relation between multiple target articles is established, wherein mark in multiple articles of same event flag, when upload
Between posterior article be the preceding article of uplink time progress article.
Optionally, before recommending the association article to first user, the method also includes:
Count the interest tags of first user；
Determine that interest tags and the first user coincidence factor are more than or equal to the second user of threshold value, to the second user
Recommend the progress article.
Optionally, before recommending the association article to first user, the method also includes:
The interest tags for counting first user and first user are to the clicking rates of the interest tags；
To the clicking rates of the interest tags by being ordered from large to small, N number of interest for taking clicking rate to be arranged in front
Label is determined as target interest tags, wherein N is integer and is positive number；
Determine include in interest tags one or more of described target interest tags second user, to described
Two users recommend the progress article.
It is optionally, described to recommend the association article to first user, specifically:
Notification bar or information flow by push channel in first user show the association article.
Second aspect of the present invention provides a kind of article recommendation apparatus, comprising:
Article determining module, for determine target article and with the related association article of the target article, it is described
Association article includes: the article of refuting a rumour for the target article, and/or, the progress article of the target article, the progress
Article is the article of the progress about the target article event of interest；
User's determining module, for determining the first user for clicking the target article；
Pushing module, for recommending the association article to first user.
Compared with the prior art, article recommended method provided by the invention is to pass through certain based on the incidence relation between article
One target article recognizes the association article being associated, and is screened by target article to user, and push is associated with
The user of article is determined as clicking the user of target article, pushes compared to all users, improves the precision of user, and
There is incidence relation between the target article clicked before due to the association article of recommendation and user, so that the article recommended
It is more accurate.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to use required in embodiment in order to illustrate more clearly of the technical solution of embodiment of the present invention
Attached drawing be briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not to be seen as
It is the restriction to range, it for those of ordinary skill in the art, without creative efforts, can be with root
Other relevant attached drawings are obtained according to these attached drawings.
Fig. 1 shows the flow chart of article recommended method provided by the present invention；
Fig. 2 shows another flow charts of article recommended method provided by the present invention；
Fig. 3 shows another flow chart of article recommended method provided by the present invention；
Fig. 4 shows another flow chart of article recommended method provided by the present invention；
Fig. 5 shows another flow chart of article recommended method provided by the present invention；
Fig. 6 shows another flow chart of article recommended method provided by the present invention；
Fig. 7 shows another flow chart of article recommended method provided by the present invention；
Fig. 8 shows another flow chart of article recommended method provided by the present invention；
Fig. 9 shows the schematic diagram of article recommendation apparatus provided by the present invention.
Icon:
Article determining module -200；User's determining module -300；Pushing module -400.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
With reference to the accompanying drawing, it elaborates to some embodiments of the present invention.In the absence of conflict, following
Feature in embodiment and embodiment can be combined with each other.
First embodiment
With the development of internet, there is explosive growth in the information of cybertimes, and it is interested that user wants reading oneself
Article time for needing increasingly to grow, it is therefore desirable to it is a kind of that its article recommended method for wanting to read directly is pushed to user,
It includes refering to fig. 1 following steps that embodiments herein, which then provides a kind of article recommended method:
S1: determine target article and with the related association article of the target article.
In this step, target article be associated with article pre-establish between each other it is relevant, i.e., determine it is a certain
After a article, using this article as target article, while according to the available pass to target article of the incidence relation of this article
Join article, it should be noted that being associated with article herein includes the article of refuting a rumour for the target article, and/or, the target
The progress article of article, progress article understanding are the article of the progress about target article event of interest.
It include the article of some news media of official publication and one a few since the article information on network is numerous
Any restrictions are not done in the article of people or tissue publication, the source for obtaining target article and association article, can be any website
Article.
S2: the first user for clicking the target article is determined.
Approach is recalled using target article as user, after determining some article as target article, is clicked according to user
The real-time logs of article, find the first user for clicking target article, these users clicked target article, it is thus possible to think
Read with the associated article of target article, by these users be determined as to its push association article target user.
S3: recommend the association article to first user；Wherein, the mode of recommendation includes but is not limited to use first
The notification bar or information flow at family show the association article.
Above scheme is, by a certain target article of determination, to identify the association of article based on the incidence relation between article
Relationship, obtain with the related association article of this article, and user is screened by target article, to clicking this
The user of target article pushes association article, pushes article compared to all users, this programme improves the accurate of identification user
Degree, enable the user for clicking target article read in time with the associated article of target article, meanwhile, using target article
Directly recall the mode of user, it is ensured that the information transmitting of target article to association article is not abandoned by intermediate treatment link, is guaranteed
The stability of incidence relation transmitting.
It mentions in the foregoing, the association article in step S1 can be the article of refuting a rumour for the target article, can also
Think, to the progress article of target article event of interest, therefore is directed to both of these case, the scheme in the present embodiment can wrap
It includes but is not limited to following two application scenarios:
Scene one: target article be rumour article, association article be target article article of refuting a rumour, rumour article with refute a rumour
There is incidence relation between article, determine the user for clicking rumour article, pushed to these users corresponding with rumour article
It refutes a rumour article.
Scene two: target article is the article of a certain event, and association article is the progress article of the event, for example, target
Event in article progresses to the n-th progress of the event, and the event for being associated with article progresses to the N+1 progress of the event,
It determines the user for clicking the article of event n-th progress, pushes the article that next event is in progress, i.e. N+ to these users
The article of 1 progress.
Optionally, referring to Fig.2, before step S1, the article recommended method further include:
S10: it establishes target article and recalls dictionary.
S11: the article that the target article recalls dictionary is hit into follow-up and is recalled into target article pond.
It applies in this programme in scene a period of time, it includes rumour dictionary that target article, which recalls dictionary, i.e., in some existing platforms
The higher rumour vocabulary of the frequency of occurrences, meanwhile, in order to improve the accuracy rate of target article, when establishing target article and recalling dictionary,
The higher article category of the rumour frequency of occurrences can only be retained, such as: the major class such as health, amusement, society, science and science and technology；
When this programme is applied in scene two, it includes current hotspot event dictionary that target article, which recalls dictionary, and/or, it uses
The concern dictionary of family customization, for example, then the dictionary may be in the vocabulary for detecting that multiple users simultaneously scan in the same time
The vocabulary of current hotspot event adds it to focus incident dictionary, for another example the concern vocabulary that user customizes in advance, subsequent
It wants to continue reading relevant article, then adds it in concern dictionary；
Certainly, target article recalls the combination that dictionary can also be above-mentioned two situations, i.e., establishing simultaneously has multiple dictionaries,
It include one or more of rumour dictionary, focus incident dictionary and customized concern dictionary.
Next it is described in detail for the specific embodiment of two kinds of application scenarios of above scheme.
Optionally, for scene one, be associated with article be target article refute a rumour article when, refering to Fig. 3, step S1 it
Before, the method also includes:
S120: it establishes article of refuting a rumour and recalls dictionary and recall source.
Above-mentioned article of refuting a rumour recall dictionary keyword include refute a rumour, start a rumour, the keyword of refuting a rumour such as pseudo event, rumor, call together
Back source can refute a rumour for authoritative higher official platform, social platform the platform and some public credibility are higher wards off of refuting a rumour
Ballad website.
The article that S121: recalling dictionary for article of refuting a rumour described in hit and recalls source is recalled into article pond of refuting a rumour.
Optionally, after building target article pond and refuting a rumour article pond, for a rumour, it is understood that there may be have multiple
Rumour article, it is also possible to which there are multiple articles of refuting a rumour, therefore before step S1, need to pre-establish rumour article and ward off
The incidence relation of ballad article can include but is not limited to following two embodiment:
Mode one: refering to Fig. 4, comprising the following steps:
S122: similar multiple target articles are identified in target article pond by the similar identification technology of text.
S123: article of refuting a rumour corresponding with the multiple target article is identified in the article pond of refuting a rumour.
It should be noted that there may be multiple articles of refuting a rumour for a certain rumour in article pond of refuting a rumour, therefore,
In the step, it can determine that some most authoritative, most comprehensive article is corresponding as the rumour by way of machine learning
It refutes a rumour article, can also select a certain article of refuting a rumour as the corresponding text of refuting a rumour of the rumour by way of manually adding
Chapter.
S126: the incidence relation of the multiple target article Yu the article of refuting a rumour is established.
Mode two: refering to Fig. 5, comprising the following steps:
S124: article of refuting a rumour is determined in the article pond of refuting a rumour.
S125: it is identified in target article pond by the similar identification technology of text similar more with the article of refuting a rumour
A target article.
S126: the incidence relation of the multiple target article Yu the article of refuting a rumour is established.
Above two mode can establish the incidence relation of multiple target articles with article of refuting a rumour, wherein pass through text
Similarity measures identify similarity, such as keyword, participle, article length to transcription comparison, recall the high article of similarity,
Expand article to recall；After the incidence relation for establishing multiple target articles and article of refuting a rumour, the method determines multiple targets
Some rumour article in article can identify corresponding article of refuting a rumour according to incidence relation, thus to point as target article
Hit the corresponding article of refuting a rumour of user's push of rumour article.
Under the application scenarios for article of refuting a rumour by rumour article to user's push, the user for clicking rumour is realized
Accurate identification, then refute a rumour content accordingly to these users push, allow users to recognize refuting a rumour for these rumours in time
Information.
Optionally, target article pond is being established when being associated with the progress article that article is target article for scene two
Afterwards, refering to Fig. 6, before step S1, the method also includes:
S130: similar multiple target articles are identified in target article pond.
Identify similar multiple articles by the similar identification technology of text, have between these articles similar text,
Sentence etc., it can be considered that these similar multiple articles are a series of progress articles of same event.
S131: upper identical event flag is marked for the multiple target article.
After a series of progress articles for recognizing same event, event flag is stamped for these articles, there is same event
All articles of label, it is believed that there is incidence relation between each other.
S132: the incidence relation between multiple target articles is established.
According to the uplink time of the multiple target articles recognized, upper event progress is marked for the multiple target article
Sequencing establishes the incidence relation between multiple target articles.It should be noted that at this point, progress article is not a certain true
Fixed article, with the variation that event is in progress, progress article is also being changed stepwise, in the multiple texts for being marked with same event flag
Zhang Zhong, the posterior article of uplink time are the progress article of the preceding article of uplink time.
1, progress 2 ... the progress N-1 and progress N for example, a series of progress of a certain event have progressed, for current thing
The progress N of part, the article for being expressed as progress N are determined as the article that is in progress, and the article before the N that is in progress is as target article.
Optionally, after step S132, the incidence relation between multiple target articles is had built up, the present embodiment also provides one
The scheme of kind before step S3, can pass through the emerging of the first user of analysis after the first user of target article is clicked in determination
Interesting label finds the user with same or similar interest, expands the user scope of push, the interest of above-mentioned the first user of analysis
Label, the scheme for the range that extends one's service can include but is not limited to following two embodiment:
Mode one: refering to Fig. 7, comprising the following steps:
S133: the interest tags of statistics first user.
S134: determining that interest tags and the first user coincidence factor are more than or equal to the second user of threshold value, to described the
Two users recommend the progress article.
This kind of mode can find the second user high with the first user interest label coincidence factor, these second users and the
The hobby of one user is quite similar to a certain extent, thus therefore also pushing association article to second user passes through knowledge
The coincidence factor of other interest tags can expand the user for pushing article.
Mode two: refering to Fig. 8, comprising the following steps:
S135: click of the interest tags and first user of statistics first user to the interest tags
Rate；
S136: to the clicking rates of the interest tags by being ordered from large to small, clicking rate is taken to be arranged in front N number of
Interest tags are determined as target interest tags, wherein N is integer and is positive number；
S137: determine include in interest tags one or more of described target interest tags second user, to
The second user recommends the progress article.
High frequency interest tags in interest tags of this kind of mode by obtaining the first user, find emerging with these high frequencies
The second user of interesting label can also achieve the purpose that the user scope for expanding push.
It should be noted that in step sl to the first user push association article, in step S134 and S137 to
With the first user there is the second user push of similar interests hobby to be associated with article, in second user, there are use with first
The user of family overlapping, therefore when pushing association article to these overlapping users, these overlapping users only recommend primary close to it
Join article, does not do repetition push.
In the case where pushing the application scenarios of progress article of event to user, frequently pushed away to all users compared to event progress
It recommends, by the identification to user, improves the precision of recommendation, allow users to recognize oneself vocabulary of interest in time
Article, and the progress of focus incident is grasped in time, meanwhile, it is analyzed, is looked for by the interest tags to these users
To the other user with these users with same interest hobby, association article also is pushed to other user, expands and pushes away
The user scope sent.
Second embodiment
A kind of article recommendation apparatus is present embodiments provided, this article recommendation apparatus is for executing in above-mentioned first embodiment
Method, refering to Fig. 9, comprising:
Article determining module 200, for determine target article and with the related association article of the target article, institute
Stating association article includes: article of refuting a rumour for the target article, and/or, the progress article of the target article, it is described into
Open up the article that article is the progress about the target article event of interest；
User's determining module 300, for determining the first user for clicking the target article；
Pushing module 400, for recommending the association article to first user.
In embodiment provided herein, it should be understood that disclosed device and method, it can also be by other
Mode realize.The apparatus embodiments described above are merely exemplary, for example, the flow chart and block diagram in attached drawing are shown
Device, the architectural framework in the cards of method and computer program product, function of multiple embodiments according to the present invention
And operation.In this regard, each box in flowchart or block diagram can represent one of a module, section or code
Point, a part of the module, section or code includes one or more for implementing the specified logical function executable
Instruction.It should also be noted that function marked in the box can also be attached to be different from some implementations as replacement
The sequence marked in figure occurs.For example, two continuous boxes can actually be basically executed in parallel, they sometimes may be used
To execute in the opposite order, this depends on the function involved.It is also noted that each of block diagram and or flow chart
The combination of box in box and block diagram and or flow chart can be based on the defined function of execution or the dedicated of movement
The system of hardware is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, laptop, server or network equipment etc.) execute the whole of each embodiment the method for the present invention
Or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.It should be noted that, in this document, relational terms such as first and second and the like are used merely to one
A entity or operation with another entity or operate distinguish, without necessarily requiring or implying these entities or operation it
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element.
The above description is only an embodiment of the present invention, is not intended to restrict the invention, for those skilled in the art
For member, the invention may be variously modified and varied.All within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of article recommended method characterized by comprising
Determine target article and with the related association article of the target article, the association article includes: for described
The article of refuting a rumour of target article, and/or, the progress article of the target article, the progress article is about the target text
The article of the progress of chapter event of interest；
Determine the first user for clicking the target article；
Recommend the association article to first user.
2. article recommended method according to claim 1, which is characterized in that determine target article and with the target
Before the related association article of article, the method also includes:
It establishes target article and recalls dictionary；
The article that the target article recalls dictionary is hit in follow-up to recall into target article pond.
3. article recommended method according to claim 2, which is characterized in that if the association article is the text of refuting a rumour
Chapter, determine target article and with the related association article of the target article before, the method also includes:
Foundation article of refuting a rumour recalls dictionary and recalls source, the article of refuting a rumour recall dictionary keyword include refute a rumour, start a rumour,
Pseudo event, rumor, the source of recalling includes that multiple officials refute a rumour platform；
The article that article of refuting a rumour described in hit is recalled dictionary and recalls source is recalled into article pond of refuting a rumour.
4. article recommended method according to claim 3, which is characterized in that determine target article and with the target
Before the related association article of article, the method also includes:
Similar multiple target articles are identified in target article pond by the similar identification technology of text；
Article of refuting a rumour corresponding with the multiple target article is identified in the article pond of refuting a rumour；
Establish the incidence relation of the multiple target article Yu the article of refuting a rumour.
5. article recommended method according to claim 3, which is characterized in that determine target article and with the target
Before the related association article of article, the method also includes:
Article of refuting a rumour is determined in the article pond of refuting a rumour；
Multiple target texts similar with the article of refuting a rumour are identified in target article pond by the similar identification technology of text
Chapter；
Establish the incidence relation of the multiple target article Yu the article of refuting a rumour.
6. article recommended method according to claim 2, which is characterized in that if the association article is the progress text
Chapter, it includes focus incident dictionary and/or customized concern dictionary that the target article, which recalls dictionary, is determining target text
Chapter and with before the related association article of the target article, the method also includes:
Similar multiple target articles are identified in target article pond by the similar identification technology of text；
Upper identical event flag is marked for the multiple target article；
According to the uplink time of the multiple target article, the successive suitable of upper event progress is marked for the multiple target article
Sequence establishes the incidence relation between multiple target articles, wherein mark in multiple articles of same event flag, uplink time
Posterior article is the progress article of the preceding article of uplink time.
7. article recommended method according to claim 6, which is characterized in that recommending the association to first user
Before article, the method also includes:
Count the interest tags of first user；
It determines that interest tags and the first user coincidence factor are more than or equal to the second user of threshold value, recommends to the second user
The progress article.
8. article recommended method according to claim 6, which is characterized in that recommending the association to first user
Before article, the method also includes:
The interest tags for counting first user and first user are to the clicking rates of the interest tags；
To the clicking rates of the interest tags by being ordered from large to small, N number of interest tags for taking clicking rate to be arranged in front
It is determined as target interest tags, wherein N is integer and is positive number；
Determine include in interest tags one or more of described target interest tags second user, to it is described second use
Recommend the progress article in family.
9. article recommended method according to claim 1-6, which is characterized in that described to be pushed away to first user
The association article is recommended, specifically:
Notification bar or information flow by push channel in first user show the association article.
10. a kind of article recommendation apparatus characterized by comprising
Article determining module, for determine target article and with the related association article of the target article, the association
Article includes: the article of refuting a rumour for the target article, and/or, the progress article of the target article, the progress article
For the article of the progress about the target article event of interest；
User's determining module, for determining the first user for clicking the target article；
Pushing module, for recommending the association article to first user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811047704.9A CN109145218B (en) | 2018-09-10 | 2018-09-10 | Article recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811047704.9A CN109145218B (en) | 2018-09-10 | 2018-09-10 | Article recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145218A true CN109145218A (en) | 2019-01-04 |
| CN109145218B CN109145218B (en) | 2021-11-02 |
Family
ID=64824115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811047704.9A Active CN109145218B (en) | 2018-09-10 | 2018-09-10 | Article recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145218B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111078994A (en) * | 2019-11-06 | 2020-04-28 | 珠海健康云科技有限公司 | Portrait-based medical science popularization article recommendation method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103412870A (en) * | 2013-07-09 | 2013-11-27 | 北京深思洛克软件技术股份有限公司 | News pushing method of mobile terminal device news client side software |
| CN103853822A (en) * | 2014-02-24 | 2014-06-11 | 北京奇虎科技有限公司 | Method and device for pushing news information in browser |
| CN105224699A (en) * | 2015-11-17 | 2016-01-06 | Tcl集团股份有限公司 | A kind of news recommend method and device |
| US20160070807A1 (en) * | 2011-10-19 | 2016-03-10 | Zalag Corporation | Methods and apparatuses for generating search expressions from content, for applying search expressions to content collections, and/or for analyzing corresponding search results |
| CN105574213A (en) * | 2016-02-26 | 2016-05-11 | 江苏大学 | Microblog recommendation method and device based on data mining technology |
| CN106202563A (en) * | 2016-08-02 | 2016-12-07 | 西南石油大学 | A kind of real time correlation evental news recommends method and system |
-
2018
- 2018-09-10 CN CN201811047704.9A patent/CN109145218B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160070807A1 (en) * | 2011-10-19 | 2016-03-10 | Zalag Corporation | Methods and apparatuses for generating search expressions from content, for applying search expressions to content collections, and/or for analyzing corresponding search results |
| CN103412870A (en) * | 2013-07-09 | 2013-11-27 | 北京深思洛克软件技术股份有限公司 | News pushing method of mobile terminal device news client side software |
| CN103853822A (en) * | 2014-02-24 | 2014-06-11 | 北京奇虎科技有限公司 | Method and device for pushing news information in browser |
| CN105224699A (en) * | 2015-11-17 | 2016-01-06 | Tcl集团股份有限公司 | A kind of news recommend method and device |
| CN105574213A (en) * | 2016-02-26 | 2016-05-11 | 江苏大学 | Microblog recommendation method and device based on data mining technology |
| CN106202563A (en) * | 2016-08-02 | 2016-12-07 | 西南石油大学 | A kind of real time correlation evental news recommends method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111078994A (en) * | 2019-11-06 | 2020-04-28 | 珠海健康云科技有限公司 | Portrait-based medical science popularization article recommendation method and system |
| CN111078994B (en) * | 2019-11-06 | 2023-04-18 | 珠海健康云科技有限公司 | Portrait-based medical science popularization article recommendation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145218B (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| US20200081977A1 (en) | Keyword extraction method and apparatus, storage medium, and electronic apparatus | |
| CN104281649B (en) | Input method and device and electronic equipment | |
| US20210056571A1 (en) | Determining of summary of user-generated content and recommendation of user-generated content | |
| CN103020845B (en) | A kind of method for pushing and system of mobile application | |
| US11763164B2 (en) | Image-to-image search method, computer-readable storage medium and server | |
| WO2016000555A1 (en) | Methods and systems for recommending social network-based content and news | |
| CN106599278A (en) | Identification method and method of application search intention | |
| WO2017088245A1 (en) | Method and apparatus for recommending reference document | |
| CN111159546B (en) | Event pushing method, event pushing device, computer readable storage medium and computer equipment | |
| CN103077050A (en) | Method, device and equipment for displaying application information | |
| CN104598535A (en) | Event extraction method based on maximum entropy | |
| CN102855309A (en) | Information recommendation method and device based on user behavior associated analysis | |
| EP3401853A1 (en) | Method and device for predicting user problem based on data drive | |
| Riadi | Detection of cyberbullying on social media using data mining techniques | |
| CN104156454A (en) | Search term correcting method and device | |
| CN103106287A (en) | Processing method and processing system for retrieving sentences by user | |
| CN104008180A (en) | Association method of structural data with picture, association device thereof | |
| CN109300474B (en) | Voice signal processing method and device | |
| CN105574030A (en) | Information search method and device | |
| CN110147494A (en) | Information search method, device, storage medium and electronic equipment | |
| CN103942328A (en) | Video retrieval method and video device | |
| CN109101505A (en) | A kind of recommended method, recommendation apparatus and the device for recommendation | |
| CN105786936A (en) | Search data processing method and device | |
| CN111538830A (en) | French retrieval method, French retrieval device, computer equipment and storage 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231213 Address after: Room A-0296, 2nd Floor, Building 3, No. 30 Shixing Street, Shijingshan District, Beijing, 100000 Patentee after: BEIJING PARTICLE INFORMATION TECHONOLOGY Co.,Ltd. Address before: Room 1902, 16 / F, building 2, yard 4, Qiyang Road, Chaoyang District, Beijing Patentee before: Beijing Yidian Wangju Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |