CN109145218B - Article recommendation method and device - Google Patents
Article recommendation method and device Download PDFInfo
- Publication number
- CN109145218B CN109145218B CN201811047704.9A CN201811047704A CN109145218B CN 109145218 B CN109145218 B CN 109145218B CN 201811047704 A CN201811047704 A CN 201811047704A CN 109145218 B CN109145218 B CN 109145218B
- Authority
- CN
- China
- Prior art keywords
- article
- target
- articles
- user
- rumor
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000005516 engineering process Methods 0.000 claims description 7
- 230000002250 progressing effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000004590 computer program Methods 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
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an article recommendation method and an article recommendation device, wherein the article recommendation method comprises the following steps: determining a target article and an associated article associated with the target article, wherein the associated article comprises: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article; determining a first user who clicks the target article; recommending the associated article to the first user. The article recommendation method is based on the association relationship among the articles, and the pushed associated article and the target article clicked by the user before have association, so that the recommended article is more accurate.
Description
Technical Field
The invention relates to the field of article recommendation, in particular to an article recommendation method and device.
Background
With the rapid development of the information technology, users need to spend a lot of time on screening interesting articles from the information spread on the network. At present, there are some article recommendation methods, which mainly analyze attributes of an article text to determine feature tags of the article, acquire basic information of a user and an article clicked and searched by the user, calculate portrait information of the user, and recommend content with strong relevance to the user according to the relevance of the feature tags of the article and the portrait information of the user. The recommendation method is characterized in that through article analysis and user portrait calculation, the articles recommended to the user may not be the articles the user wants to read, and the recommendation accuracy is not high enough.
Disclosure of Invention
The invention aims to provide an article recommendation method and an article recommendation device, which can recommend articles to a user based on the association relationship between the articles and can improve the article recommendation accuracy.
The invention provides an article recommendation method in a first aspect, which comprises the following steps:
determining a target article and an associated article associated with the target article, wherein the associated article comprises: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article;
determining a first user who clicks the target article;
recommending the associated article to the first user.
Optionally, before determining the target article and the associated article associated with the target article, the method further comprises:
establishing a target article recall word bank;
and recalling the article with the post hit in the target article recalling thesaurus into a target article pool.
Optionally, if the associated article is the york article, before determining the target article and the associated article associated with the target article, the method further includes:
establishing an anti-rumor article recall word bank and recall sources, wherein keywords of the anti-rumor article recall word bank comprise anti-rumors, fake news and Chinese sentences, and the recall sources comprise a plurality of official anti-rumor platforms;
recalling the articles hit in the dagger article recall lexicon and recall sources into a dagger article pool.
Optionally, before determining the target article and the associated article associated with the target article, the method further comprises:
identifying a plurality of similar target articles in the target article pool through a text similar identification technology;
identifying a ballad article in the ballad article pool corresponding to the plurality of target articles;
and establishing the association relationship between the target articles and the dagger rumor articles.
Optionally, before determining the target article and the associated article associated with the target article, the method further comprises:
determining a rumor article in the rumor article pool;
identifying a plurality of target articles similar to the PiR article in the target article pool by a text similarity identification technique;
and establishing the association relationship between the target articles and the dagger rumor articles.
Optionally, if the associated article is the progressing article, the target article recall thesaurus includes a hotspot event thesaurus and/or a user-customized attention thesaurus, and before determining the target article and the associated article associated with the target article, the method further includes:
identifying a plurality of similar target articles in the target article pool through a text similar identification technology;
marking the same event mark on the plurality of target articles;
and according to the uploading time of the target articles, marking the sequence of the progress of the events on the target articles, and establishing an association relationship among the target articles, wherein in the articles marked with the same event mark, the article with the later uploading time is the progress article of the article with the earlier uploading time.
Optionally, before recommending the associated article to the first user, the method further comprises:
counting interest tags of the first user;
and determining a second user with the coincidence rate of the interest tag and the first user being more than or equal to a threshold value, and recommending the progress article to the second user.
Optionally, before recommending the associated article to the first user, the method further comprises:
counting interest tags of the first user and the click rate of the first user on the interest tags;
the click rates of the interest tags are arranged in a descending order, and N interest tags with the click rates arranged in the front are determined as target interest tags, wherein N is an integer and is a positive number;
determining a second user whose interest tags include one or more of the target interest tags, and recommending the progress article to the second user.
Optionally, the recommending the associated article to the first user specifically includes:
and displaying the associated article on a notification bar or an information flow of the first user through a push channel.
A second aspect of the present invention provides an article recommendation apparatus, including:
an article determination module configured to determine a target article and an associated article associated with the target article, where the associated article includes: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article;
the user determination module is used for determining a first user clicking the target article;
and the pushing module is used for recommending the associated article to the first user.
Compared with the prior art, the article recommendation method provided by the invention has the advantages that based on the association relationship among the articles, the associated article associated with the article is identified through a certain target article, the user is screened through the target article, the user pushing the associated article is determined as the user clicking the target article, the accuracy of the user is improved compared with the user pushing the associated article to all users, and the recommended article is more accurate due to the association relationship between the recommended associated article and the target article clicked before by the user.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a flow chart illustrating an article recommendation method provided by the present invention;
FIG. 2 is another flow chart of an article recommendation method provided by the present invention;
FIG. 3 is another flow chart of an article recommendation method provided by the present invention;
FIG. 4 is another flow chart of an article recommendation method provided by the present invention;
FIG. 5 is another flow chart of an article recommendation method provided by the present invention;
FIG. 6 is another flow chart of an article recommendation method provided by the present invention;
FIG. 7 is another flow chart of an article recommendation method provided by the present invention;
FIG. 8 is another flow chart of an article recommendation method provided by the present invention;
fig. 9 shows a schematic diagram of an article recommendation device provided by the present invention.
Icon:
article determination module-200; a user determination module-300; push module-400.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
First embodiment
With the development of the internet, the information in the network era is explosively increased, and it takes longer and longer for a user to read an article which the user wants to be interested in, so that an article recommendation method for directly pushing the article which the user wants to read is needed, which is provided by the embodiment of the present application, and referring to fig. 1, includes the following steps:
s1: a target article and associated articles associated with the target article are determined.
In this step, a relationship is pre-established between the target article and the associated article, that is, after a certain article is determined, the article is taken as the target article, and the associated article of the target article can be obtained according to the relationship of the article, where it should be noted that the associated article includes a rumor article for the target article, and/or a progress article of the target article, and the progress article is understood as an article about the progress of an event that the target article is concerned with.
Because the article information on the network is numerous, including articles published by official news media and articles published by individuals or organizations, the sources of the obtained target articles and the associated articles are not limited at all, and the articles can be articles of any website.
S2: determining a first user that clicked on the target article.
The method comprises the steps that a target article is used as a user recall way, after a certain article is determined to be used as the target article, a first user clicking the target article is found according to a real-time log of the article clicked by the user, and the users click the target article, so that the users possibly want to read the article associated with the target article and are determined as target users pushing the associated article to the users.
S3: recommending the associated article to the first user; the recommended manner includes, but is not limited to, displaying the associated article in a notification bar or an information stream of the first user.
According to the scheme, the association relation between the articles is identified by determining a certain target article based on the association relation between the articles, the association relation between the articles is obtained, the user is screened through the target article, the association articles are pushed to the user clicking the target article, and compared with the method of pushing the articles to all users, the accuracy of identifying the user is improved, the user clicking the target article can read the articles associated with the target article in time, meanwhile, the information transmission from the target article to the association articles is guaranteed not to be abandoned by an intermediate processing link in a mode that the target article is directly recalled to the user, and the stability of the transmission of the association relation is guaranteed.
As mentioned in the foregoing, the associated article in step S1 may be an article for a ballad directed to the target article, or may be an article for a progress of an event that is of interest to the target article, so for these two cases, the solution in this embodiment may include, but is not limited to, the following two application scenarios:
scene one: the target article is a rumor article, the association article is a rumor article of the target article, the rumor article and the rumor article have an association relationship, users clicking the rumor article are determined, and the rumor article corresponding to the rumor article is pushed to the users.
Scene two: the target article is an article of an event, and the associated article is a progress article of the event, for example, the event in the target article progresses to the nth progress of the event, the event progress of the associated article progresses to the N +1 th progress of the event, a user who clicks the article of the nth progress of the event is determined, and the article of the next progress of the event, that is, the N +1 th progress article, is pushed to the users.
Optionally, referring to fig. 2, before step S1, the article recommendation method further includes:
s10: and establishing a target article recall word bank.
S11: and recalling the article with the post hit in the target article recalling thesaurus into a target article pool.
When the method is applied to a scene one, the target article recall lexicon comprises a rumor lexicon, namely rumor vocabularies with high occurrence frequency in some existing platforms, and meanwhile, in order to improve the accuracy of the target article, when the target article recall lexicon is established, only the article categories with high rumor occurrence frequency can be reserved, for example: health, entertainment, social, scientific, and scientific;
when the method is applied to the scene two, the target article recall word bank comprises a current hot event word bank and/or a user customized attention word bank, for example, when words searched by a plurality of users simultaneously within the same time are detected, the word bank possibly is the words of the current hot event, the words are added into the hot event word bank, for example, the attention words customized by the user in advance are added into the attention word bank, and then the related articles are added into the attention word bank when the user wants to continuously read the related articles;
of course, the target article recall lexicon may also be a combination of the above two cases, that is, a plurality of lexicons are simultaneously established, including one or more of the rumor lexicon, the hotspot event lexicon, and the user-customized attention lexicon.
The following is a detailed description of two application scenarios of the above-described scheme.
Alternatively, for scenario one, when the associated article is an article in the nursery rhyme of the target article, referring to fig. 3, before step S1, the method further includes:
s120: and establishing a recall lexicon and a recall source of the daghew articles.
The keywords of the tuning article recall word library include tuning keywords such as tuning rumors, fake news, popular dialects, etc., and the recall sources can be official tuning rumors platforms with high authority, tuning rumors platforms of social platforms and tuning rumors websites with high public credibility.
S121: recalling the articles hit in the dagger article recall lexicon and recall sources into a dagger article pool.
Alternatively, after the target article pool and the nursery rhyme article pool are built, there may be a plurality of nursery rhyme articles and a plurality of nursery rhyme articles for a nursery rhyme, and therefore, before step S1, the association relationship between the nursery rhyme article and the nursery rhyme article needs to be pre-established, which may include, but is not limited to, the following two embodiments:
the first method is as follows: referring to fig. 4, the following steps are included:
s122: identifying a plurality of similar target articles in the target article pool through a text similarity identification technology.
S123: identifying, in the PiR article pool, PiR articles corresponding to the plurality of target articles.
It should be noted that, in the nursery rhyme article pool, there may be a plurality of nursery rhyme articles for a certain rumor, therefore, in this step, a most authoritative and comprehensive article can be determined as the nursery rhyme article corresponding to the rumor by a machine learning method, and a nursery rhyme article can be selected as the nursery rhyme article corresponding to the rumor by a manual adding method.
S126: and establishing the association relationship between the target articles and the dagger rumor articles.
The second method comprises the following steps: referring to fig. 5, the following steps are included:
s124: and determining the rumor splitting article in the rumor splitting article pool.
S125: identifying a plurality of target articles in the target article pool that are similar to the PiR article by a text-similar identification technique.
S126: and establishing the association relationship between the target articles and the dagger rumor articles.
The two modes can establish the incidence relation between a plurality of target articles and the dagger articles, wherein the similarity, such as keywords, word segmentation, article length and articles with high recall similarity, is contrasted and identified for the text through text similarity calculation, and article recall is expanded; after the association relationship between the target articles and the rumor articles is established, the method determines a rumor article in the target articles as the target article, and identifies the corresponding rumor article according to the association relationship, so that the corresponding rumor article is pushed to a user clicking the rumor article.
Under the application scene of pushing the rumor-splitting article to the users through the rumor article, the users who click the rumors are accurately identified, and then corresponding rumor-splitting contents are pushed to the users, so that the users can timely know the rumor-splitting information of the rumors.
Optionally, for scenario two, when the associated article is a progressive article of the target article, after the target article pool is established, referring to fig. 6, before step S1, the method further includes:
s130: a plurality of similar target articles are identified in a pool of target articles.
A plurality of similar articles are identified through a text similarity identification technology, and the articles have similar texts, sentences and the like, so that the similar articles can be considered as a series of advanced articles of the same event.
S131: the plurality of target articles are marked with the same event marker.
After a series of articles in progress of the same event are identified, event markers are marked on the articles, and all the articles with the same event marker can be considered to have an association relationship with each other.
S132: and establishing an incidence relation among a plurality of target articles.
According to the identified uploading time of the target articles, marking the sequence of the event progress for the target articles, and establishing the association relationship among the target articles. In this case, the progress sentence is not a certain sentence, and the progress sentence is gradually changed as the event progresses, and among a plurality of sentences marked with the same event mark, the sentence with the later upload time is the progress sentence with the earlier upload time.
For example, a series of progresses of an event has progress 1, progress 2 … … progress N-1, and progress N, and for progress N of the current event, an article indicated as progress N is determined to be a progress article, and an article before progress N is a target article.
Optionally, after step S132, the association relationships among a plurality of target articles have been established, this embodiment further provides a scheme, after determining that the first user clicks the target article, and before step S3, the pushed user range may be expanded by analyzing the interest tags of the first user to find users with the same or similar interests, where the scheme for expanding the user range may include, but is not limited to, the following two embodiments:
the first method is as follows: referring to fig. 7, the following steps are included:
s133: and counting interest tags of the first user.
S134: and determining a second user with the coincidence rate of the interest tag and the first user being more than or equal to a threshold value, and recommending the progress article to the second user.
According to the method, the second users with high overlapping rate of the interest labels of the first users can be found, the interest love of the second users is quite similar to that of the first users to a certain extent, and the associated articles are pushed to the second users, so that the users pushing the articles can be expanded by identifying the overlapping rate of the interest labels.
The second method comprises the following steps: referring to fig. 8, the following steps are included:
s135: counting interest tags of the first user and the click rate of the first user on the interest tags;
s136: the click rates of the interest tags are arranged in a descending order, and N interest tags with the click rates arranged in the front are determined as target interest tags, wherein N is an integer and is a positive number;
s137: determining a second user whose interest tags include one or more of the target interest tags, and recommending the progress article to the second user.
The method can also achieve the purpose of expanding the range of pushed users by obtaining the high-frequency interest tags in the interest tags of the first user and finding the second user with the high-frequency interest tags.
It should be noted that, in step S1, the associated article is pushed to the first user, in steps S134 and S137, the associated article is pushed to the second user who has a similar interest and love to the first user, and in the second user, there are users overlapping with the first user, so when pushing the associated article to these overlapping users, these overlapping users recommend the associated article only once to them, and do not do repeated pushing.
Under the application scene of pushing the progress articles of the events to the users, the articles are frequently recommended to all users compared with the progress of the events, the recommendation accuracy is improved through the identification of the users, the users can timely know the articles of the words concerned by the users and timely master the progress of the hot events, meanwhile, through the analysis of the interest tags of the users, other users having the same interest and hobbies with the users are found, the associated articles are also pushed to the other users, and the pushed user range is expanded.
Second embodiment
The present embodiment provides an article recommendation apparatus for executing the method in the first embodiment, with reference to fig. 9, including:
an article determination module 200, configured to determine a target article and an associated article associated with the target article, where the associated article includes: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article;
a user determination module 300, configured to determine a first user who clicked on the target article;
a pushing module 400, configured to recommend the associated article to the first user.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An article recommendation method, comprising:
determining a target article and an associated article associated with the target article, wherein the associated article comprises: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article, the target article comprising a rumor article;
determining a first user who clicks the target article;
recommending the associated article to the first user;
before the determining the target article and the associated article associated with the target article, further comprising:
establishing a target article recall word bank;
recalling the article with the post hitting the target article recall lexicon into a target article pool;
establishing an anti-rumor article recall word bank and recall sources, wherein keywords of the anti-rumor article recall word bank comprise anti-rumors, fake news and Chinese sentences, and the recall sources comprise a plurality of official anti-rumor platforms;
recalling the articles hit in the dagger article recall lexicon and recall sources into a dagger article pool;
establishing an association relationship between the plurality of target articles and the ballad articles based on the target article pool and the ballad article pool.
2. The article recommendation method according to claim 1, wherein the establishing the association relationship between the plurality of target articles and the nursery rhyme articles based on the target article pool and the nursery rhyme article pool comprises:
identifying a plurality of similar target articles in the target article pool through a text similar identification technology;
identifying a ballad article in the ballad article pool corresponding to the plurality of target articles;
and establishing the association relationship between the target articles and the dagger rumor articles.
3. The article recommendation method according to claim 1, wherein the establishing the association relationship between the plurality of target articles and the nursery rhyme articles based on the target article pool and the nursery rhyme article pool comprises:
determining a rumor article in the rumor article pool;
identifying a plurality of target articles similar to the PiR article in the target article pool by a text similarity identification technique;
and establishing the association relationship between the target articles and the dagger rumor articles.
4. The article recommendation method according to claim 1, wherein if the associated article is the progressing article, the target article recall thesaurus comprises a hotspot event thesaurus and/or a user-customized attention thesaurus, and before determining the target article and the associated article associated with the target article, the method further comprises:
identifying a plurality of similar target articles in the target article pool through a text similar identification technology;
marking the same event mark on the plurality of target articles;
and according to the uploading time of the target articles, marking the sequence of the progress of the events on the target articles, and establishing an association relationship among the target articles, wherein in the articles marked with the same event mark, the article with the later uploading time is the progress article of the article with the earlier uploading time.
5. The article recommendation method according to claim 4, wherein before recommending the associated article to the first user, the method further comprises:
counting interest tags of the first user;
and determining a second user with the coincidence rate of the interest tag and the first user being more than or equal to a threshold value, and recommending the progress article to the second user.
6. The article recommendation method according to claim 4, wherein before recommending the associated article to the first user, the method further comprises:
counting interest tags of the first user and the click rate of the first user on the interest tags;
the click rates of the interest tags are arranged in a descending order, and N interest tags with the click rates arranged in the front are determined as target interest tags, wherein N is an integer and is a positive number;
determining a second user whose interest tags include one or more of the target interest tags, and recommending the progress article to the second user.
7. The article recommendation method according to any one of claims 1-4, wherein the recommending the associated article to the first user specifically is:
and displaying the associated article on a notification bar or an information flow of the first user through a push channel.
8. An article recommendation device, comprising:
an article determination module configured to determine a target article and an associated article associated with the target article, where the associated article includes: a rumor article for the target article, and/or a progression article of the target article, the progression article being an article on a progression of an event of interest of the target article, the target article comprising a rumor article;
the user determination module is used for determining a first user clicking the target article;
the pushing module is used for recommending the associated article to the first user;
before the determining the target article and the associated article associated with the target article, further comprising:
establishing a target article recall word bank;
recalling the article with the post hitting the target article recall lexicon into a target article pool;
establishing an anti-rumor article recall word bank and recall sources, wherein keywords of the anti-rumor article recall word bank comprise anti-rumors, fake news and Chinese sentences, and the recall sources comprise a plurality of official anti-rumor platforms;
recalling the articles hit in the dagger article recall lexicon and recall sources into a dagger article pool;
establishing an association relationship between the plurality of target articles and the ballad articles based on the target article pool and the ballad article pool.
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 CN109145218A (en) | 2019-01-04 |
| CN109145218B true 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) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (5)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9600587B2 (en) * | 2011-10-19 | 2017-03-21 | 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 |
-
2018
- 2018-09-10 CN CN201811047704.9A patent/CN109145218B/en active Active
Patent Citations (5)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145218A (en) | 2019-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145153B (en) | Intention category identification method and device | |
| CN107256267B (en) | Query method and device | |
| CN109376309B (en) | Document recommendation method and device based on semantic tags | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN105488024B (en) | The abstracting method and device of Web page subject sentence | |
| CN109508414B (en) | Synonym mining method and device | |
| CN107229668B (en) | Text extraction method based on keyword matching | |
| US8386240B2 (en) | Domain dictionary creation by detection of new topic words using divergence value comparison | |
| CN103177075B (en) | The detection of Knowledge based engineering entity and disambiguation | |
| CN108874996B (en) | Website classification method and device | |
| WO2016000555A1 (en) | Methods and systems for recommending social network-based content and news | |
| CN103853834B (en) | Text structure analysis-based Web document abstract generation method | |
| CN103793434A (en) | Content-based image search method and device | |
| US9529847B2 (en) | Information processing apparatus, information processing method, and program for extracting co-occurrence character strings | |
| Riadi | Detection of cyberbullying on social media using data mining techniques | |
| CN110990696B (en) | Method and device for recommending search intention | |
| CN102855309A (en) | Information recommendation method and device based on user behavior associated analysis | |
| CN108763369B (en) | Video searching method and device | |
| CN105550217B (en) | Scene music searching method and scene music searching device | |
| WO2015084757A1 (en) | Systems and methods for processing data stored in a database | |
| US20120330986A1 (en) | Information processing apparatus, information processing method, and program | |
| CN109145218B (en) | Article recommendation method and device | |
| CN114036283A (en) | Text matching method, device, equipment and readable storage medium | |
| CN111859079A (en) | Information searching method and device, computer equipment and storage medium | |
| US20230090601A1 (en) | System and method for polarity analysis |
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 |