CN106250550A - A kind of method and apparatus of real time correlation news content recommendation - Google Patents
A kind of method and apparatus of real time correlation news content recommendation Download PDFInfo
- Publication number
- CN106250550A CN106250550A CN201610664122.XA CN201610664122A CN106250550A CN 106250550 A CN106250550 A CN 106250550A CN 201610664122 A CN201610664122 A CN 201610664122A CN 106250550 A CN106250550 A CN 106250550A
- Authority
- CN
- China
- Prior art keywords
- content
- news
- history
- news content
- text feature
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses the method and device of the content recommendation of a kind of real time correlation news.The method includes: obtains history news content and the association content of described history news content, sets up content library, and extract text feature；Obtain user and currently browse news content；Present News text feature is extracted from the described news content that currently browses；The content that associates of described Present News text feature with the history news content in described content library and/or described history news content is carried out Semantic Similarity coupling；According to matching result, from the association content of history news content and/or described history news content, select object content, push to described user.The embodiment of the present invention realizes people when browsing news, and automatic propelling movement currently browses news content, and the high-quality discussion that people are to this event, in order to the ins and outs of paid close attention to news are understood on user's rapid system ground.
Description
Technical field
The present invention relates to semantic computation and commending system, particularly to a kind of real time correlation news content recommendation method and
Device.
Background technology
Along with popularizing of the Internet, the particularly fast development of mobile Internet, on the Internet, every day all can produce magnanimity
Content.Each flash-news media, new media, such as People's Daily, Tengxun's news, today's tops etc., issue also by the Internet and
Disseminating news, netizens, also at social networks, as known, carry out extensive and deep discussion to all kinds of events.
Because source of news is wide, communication channel is many, the dispersion that on the Internet, the propagation of same or similar news is suitable, so
When learning news by the Internet, can take considerable time and retrieve oneself news interested and its ins and outs.Additionally,
The cost time is also required to for the concern of the discussion of news and goes retrieval, result in and learn completely there is quality news on the internet
Efficiency is the lowest.
Summary of the invention
In view of this, the embodiment of the present invention provides the method and device of the content recommendation of a kind of real time correlation news, solves
User browses the problem that news is inefficient on the internet.
First aspect, the method embodiments providing the content recommendation of a kind of real time correlation news, including:
Obtain history news content and the association content of described history news content, set up content library, and it is special to extract text
Levy；
Obtain user and currently browse news content；
Present News text feature is extracted from the described news content that currently browses；
By in the history news content in described Present News text feature and described content library and/or described history news
The association content held carries out Semantic Similarity coupling；
According to matching result, from the association content of history news content and/or described history news content, select target
Content, pushes to described user.
Second aspect, embodiments provides the device of the content recommendation of a kind of real time correlation news, including:
Content library sets up module, for obtaining history news content and the association content of described history news content, sets up
Content library, and extract history newsletter archive feature；
Present News acquisition module, is used for obtaining user and currently browses news content；
Text character extraction module, for extracting Present News text feature from the described news content that currently browses；
Similarity matching module, for by described Present News text feature and the history news content in described content library
And/or the association content of described history news content carries out Semantic Similarity coupling；
Info push module, for according to matching result, from history news content and/or the pass of described history news content
Connection content selects object content, pushes to described user.
As shown from the above technical solution, the embodiment of the present invention realizes people when browsing news, and automatic propelling movement currently browses
News content, and the high-quality discussion that people are to this event, in order to the next imperial of paid close attention to news is understood on user's rapid system ground
Remove arteries and veins
Accompanying drawing explanation
Figure 1A is the method flow schematic diagram of the content recommendation of a kind of real time correlation news that the embodiment of the present invention one provides；
Figure 1B is the method flow schematic diagram of a kind of Text character extraction in the embodiment of the present invention one；
Fig. 2 is the content recommendation method flow schematic diagram of a kind of real time correlation news in the embodiment of the present invention two；
Fig. 3 A is the apparatus structure schematic diagram of the content recommendation of a kind of real time correlation news in the embodiment of the present invention three；
Fig. 3 B is the Text character extraction modular unit structural representation in the embodiment of the present invention three.
Detailed description of the invention
Further illustrate technical scheme below in conjunction with the accompanying drawings and by detailed description of the invention.May be appreciated
It is that specific embodiment described herein is only used for explaining the present invention, rather than limitation of the invention.Further need exist for explanation
It is, for the ease of describing, accompanying drawing to illustrate only part related to the present invention rather than entire infrastructure.
Embodiment one
Figure 1A is the method flow schematic diagram of the content recommendation of a kind of real time correlation news that the embodiment of the present invention one provides.
The method can be performed by the device of the method for the content recommendation of real time correlation news, and this device can be by software and/or hard
The mode of part realizes, and generally can be performed by the server of the recommendation service providing real time correlation news.As shown in Figure 1A, should
Method includes:
S110, acquisition history news content and the association content of described history news content, set up content library, and extract literary composition
Eigen；
Before mutual with user profile, the history news content that server memory can be stored up by server according to ad hoc rule
With associate classifying content, and extract the text feature in each history news content and association content, and will get
History news content with associate content and corresponding text feature is saved in the content library created.The text is special
Take over for use in news content and news content, associate content and associate content, news content and the Rapid matching associated between content.Can
Choosing, described association content is the information such as user's message to news content, discussion.
The concrete grammar of Text character extraction can refer in S130 currently browsing news content extraction Present News text
The method of feature, skips over herein.
S120, acquisition user currently browse news content；
News information classification is selected according to self-demand by user's request by active user, sends to providing real-time
The server of the recommendation service of association news, the server of the described recommendation service providing real time correlation news can be high in the clouds clothes
Business device.Relevant news information is back to visitor according to present instruction by the server that can provide the recommendation service of real time correlation news
Family end application program or web browser, carry out selection for user and browse.
Server obtains user and currently browses news content.The news content currently browsed include news web page title,
Summary and text.
S130, extract Present News text feature from the described news content that currently browses.
Described currently browse the news content that news content i.e. user is browsing.Newsletter archive is extracted from news content
Step is concrete as shown in Figure 1B.
S131: the described news content that currently browses is carried out pretreatment；
Concrete, language material is carried out, removes garbage, use participle instrument carry out participle and remove stop words.
S132: pretreated content is carried out morphological analysis, and extracts key word information；
Concrete, on the pretreated language material of S131, by statistical method, including but not limited to TF-IDF, TF-IWF,
BM25, calculates the weighted value s of each word in language material, and sets up keyword models, extract first kind text feature, i.e. key word.
Illustrating as a example by TF-IWF, following formula is the weight method calculating each word by TF-IWF.
Wherein, wijRepresenting the i-th word in jth piece language material, N (w) represents the word frequency of word w, wiRepresent that word i is in corpus
Word frequency, K represents the word number sum in jth piece language material, wkjRepresenting the word frequency of kth word in jth piece language material, L represents content
Word number sum in storehouse, wlRepresent the word frequency of l word in content library.
S133: pretreated content is trained topic model, and extracts subject information；
Concrete, on the pretreated language material of S131, train topic model, and extract the theme of every language material,
Further, this topic model is that document subject matter generates model (Latent Dirichlet Allocation, LDA).
S134: pretreated content is trained phrase semantic model；
Concrete, on the pretreated language material of S131, train phrase semantic model, further, this phrase semantic mould
Type is text depth representing model (Word2Vec).
S135: determine according to the key word information obtained, subject information and phrase semantic model and currently browse news content
Text feature, text feature be such as the feature representation in Figure 1B.
Further, it is assumed that the keyword of browsed news is K (n), theme is T (n), and the most described feature representation is:
F (n)=K (n) U T (n)
I.e. the keyword to browsed news is K (n) and theme T (n) takes union.
It should be noted that described key word information, described subject information and described phrase semantic model three are arranged side by side
Relation, further, described feature representation is by described key word information and/or described subject information and/or described phrase semantic
Model determines and obtains.Corresponding, before S135 performs, need to perform at least one in S132, S133 and S134 three.
S140, by the history news content in described Present News text feature and described content library and/or described history
The association content of news content carries out Semantic Similarity coupling.
Described Semantic Similarity coupling is specifically, use the set algorithm described Present News text feature of calculating interior with described
Similarity coupling between history news content and/or the text feature of the association content of described history news content in Rong Ku
Degree；The history news content that described similarity matching degree exceedes predetermined threshold value is screened.
Further, carry out with described Present News text feature that Semantic Similarity mates is history newsletter archive feature
And/or history news association content text feature.
On the basis of S130, it is assumed that the key word of content c in content library is K (c), theme is T (c), feature representation
For:
F (c)=K (c) U T (c)
I.e. key word K (c) and theme T (c) to content c in content library takes union.
Carrying out described Semantic Similarity coupling can have multiple method to calculate, optionally, by following method calculating matching degree:
Ibid, " U ", " I " represents respectively variable takes union and take common factor.
Optionally, by following method calculating matching degree:
Wherein, F (*)iRepresenting the i-th word in feature representation, W (i) represents the word drawn in the Word2Vec model of word i
Vector, F (*)diffFor the word being not participating in Semantic Similarity Measurement, K represents the word number sum in jth piece language material.
S150, according to matching result, from the association content of history news content and/or described history news content select
Object content, pushes to described user.
Described object content includes the news content that the contents such as browsing content title current with user, summary, text are close
With associate content, and push the news content that obtains of coupling and/or association content to user.
In sum, according to the technical scheme of the present embodiment, solve user and browse news poor efficiency on the internet and ask
Topic, utilizes semantic computation and recommended technology, it is achieved people are while browsing news, and automatic propelling movement currently browses in news association
Hold, in order to it systematically understands the ins and outs of paid close attention to news.
Embodiment two
Fig. 2 is the method flow schematic diagram of the content recommendation of a kind of real time correlation news that the embodiment of the present invention two provides.
The present embodiment is optimized on the basis of embodiment one, further by user feedback data to content library and Matching Model
It is updated.As in figure 2 it is shown, the method includes:
S210, acquisition history news content and the association content of described history news content, set up content library, and extract literary composition
Eigen；
S220, acquisition user currently browse news content；
S230, extract Present News text feature from the described news content that currently browses；
S240, by the history news content in described Present News text feature and described content library and/or described history
The association content of news content carries out Semantic Similarity coupling；
S250, according to matching result, from the association content of history news content and/or described history news content select
Object content, pushes to described user；
S260, acquisition user's feedback data to object content, according to described feedback data to described content library or coupling
Model is updated.
The described feedback data to object content can have the investigation that fills in questionnaires, the clicking rate of pushed information, to pushed information
The various ways such as it is identified to obtain, it will be appreciated that for user's satisfaction to pushed information.Optionally, feedback data content is
User's clicking rate within the unit interval to arbitrary pushed information.
Concrete, described pushed information includes a plurality of news content or association content, when described clicking rate is less than presetting threshold
Value, then remove this news content or association content from this pushed information, and to this news content or association content
Text feature extracts again, and then carries out described content library or Matching Model more thus improve the accuracy of pushed information, increases
Strong Consumer's Experience.
Concrete, when " patch of pouring water " occurs in pushed information, pure expression, the insignificant news content such as pure symbol or association are interior
Hold, and when described clicking rate is less than predetermined threshold value, this news content or association content is removed from described content library, reduces
The meaningless content impact on pushed information in content library, allows users to get more fast and accurately and currently browse
News content association content.
In sum, the feedback data got according to the technical scheme of the present embodiment judges the accurate of pushed information
Degree, and then update content storehouse or Matching Model, improve the accuracy of pushed information, allow users to obtain more fast and accurately
To with currently browse news content and associate content, and then understand the ins and outs of paid close attention to news, and without manual information retrieval, waste
Time.
Embodiment three
Fig. 3 is the apparatus structure schematic diagram of the content recommendation of the real time correlation news that the embodiment of the present invention three provides.Such as Fig. 3
Shown in, this device includes: content library sets up module 310, Present News acquisition module 320, Text character extraction module 330, phase
Like property matching module 340 and info push module 350.
Wherein, content library sets up module 310, in the association obtaining history news content and described history news content
Hold, set up content library, and extract text feature；
Present News acquisition module 320, is used for obtaining user and currently browses news content；
Text character extraction module 330, for extracting Present News text feature from the described news content that currently browses；
Similarity matching module 340, for by described Present News text feature and the history news in described content library
The association content of content and/or described history news content carries out Semantic Similarity coupling；
Info push module 350, for according to matching result, from history news content and/or described history news content
Association content in select object content, push to described user.
Further, this system also includes:
Feedback data acquisition module, for according to matching result, selects object content, to described from history news content
After user pushes, obtain user's feedback data to object content, according to described feedback data to described content library or coupling
Model is updated.
Further, described history news content and the described news content that currently browses include the title of news web page, pluck
Want and text.
Further, described Text character extraction module, including:
Pretreatment unit 331, for carrying out pretreatment to the described news content that currently browses；
Keyword message extraction unit 332, for pretreated content carries out morphological analysis, and extracts key word letter
Breath；
Subject information extraction unit 333, for pretreated content trains topic model, and extracts theme letter
Breath；
Phrase semantic model acquiring unit 334, for training phrase semantic model to pretreated content；
Text feature determines unit 335, for true according to key word information, subject information and the phrase semantic model obtained
The text feature of news content is browsed before settled.
Further, described similarity matching module includes:
Matching degree computing unit, uses set algorithm to calculate described Present News text feature and going through in described content library
Similarity matching degree between the text feature of the association content of history news content and/or described history news content；
Information sifting unit, filters out for described similarity matching degree exceedes the history news content of given threshold value
Come.
In sum, according to the technical scheme of the present embodiment, by data mining and semantic computation, to history news information
Mate with the carrying out of the technical characteristic currently browsing news information, and to user push with currently browse news content associate in
Hold, thus allow users to the information that quick obtaining is wanted, and then from the degree of depth and range, solve to read on user network news
Inefficient.
It is real that the device of the content recommendation of the real time correlation news that the embodiment of the present invention is provided may be used for performing the present invention
The method executing the content recommendation of the real time correlation news that example is provided, possesses corresponding function and beneficial effect.Not in this enforcement
The ins and outs of detailed description in example, can be found in the side of the content recommendation of the real time correlation news that any embodiment of the present invention provides
Method.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although by above example, the present invention is carried out
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other Equivalent embodiments more can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (10)
1. the method for the content recommendation of a real time correlation news, it is characterised in that including:
Obtain history news content and the association content of described history news content, set up content library, and extract text feature；
Obtain user and currently browse news content；
Present News text feature is extracted from the described news content that currently browses；
By the history news content in described Present News text feature and described content library and/or described history news content
Association content carries out Semantic Similarity coupling；
According to matching result, from the association content of history news content and/or described history news content, select object content,
Push to described user.
Described method the most according to claim 1, it is characterised in that according to matching result, selects from history news content
Object content, after described user pushes, also includes:
Obtain user's feedback data to object content, according to described feedback data, described content library or Matching Model are carried out more
Newly.
Described method the most according to claim 1, it is characterised in that:
Described history news content and the described news content that currently browses include the title of news web page, summary and text.
Described method the most according to claim 1, it is characterised in that extract current new from the described news content that currently browses
Hear text feature, including:
The described news content that currently browses is carried out pretreatment；
Pretreated content is carried out morphological analysis, and extracts key word information；
Pretreated content is trained topic model, and extracts subject information；
Pretreated content is trained phrase semantic model；
Determine that according to the key word information obtained, subject information and phrase semantic model the text currently browsing news content is special
Levy.
Described method the most according to claim 1, it is characterised in that by described Present News text feature and described content library
In history news content and/or the association content of described history news content carry out Semantic Similarity coupling and include:
Set algorithm is used to calculate described Present News text feature and the history news content in described content library and/or described
Similarity matching degree between the text feature of the association content of history news content；
The history news content that described similarity matching degree exceedes predetermined threshold value is screened.
6. the device of the content recommendation of a real time correlation news, it is characterised in that including:
Content library sets up module, for obtaining history news content and the association content of described history news content, sets up content
Storehouse, and extract text feature；
Present News acquisition module, is used for obtaining user and currently browses news content；
Text character extraction module, for extracting Present News text feature from the described news content that currently browses；
Similarity matching module, for by the history news content in described Present News text feature and described content library and/
Or the association content of described history news content carries out Semantic Similarity coupling；
Info push module, for according to matching result, in the association of history news content and/or described history news content
Appearance selects object content, pushes to described user.
Described device the most according to claim 6, it is characterised in that also include:
Feedback data acquisition module, for according to matching result, from history news content and/or the pass of described history news content
Connection content selects object content, after described user pushes, obtains user's feedback data to object content, according to described
Described content library or Matching Model are updated by feedback data.
Described device the most according to claim 6, it is characterised in that:
Described history news content and the described news content that currently browses include the title of news web page, summary and text.
Described device the most according to claim 6, it is characterised in that described Text character extraction module includes:
Pretreatment unit, for carrying out pretreatment to the described news content that currently browses；
Keyword message extraction unit, for pretreated content is carried out morphological analysis, and extracts key word information；
Subject information extraction unit, for pretreated content is trained topic model, and extracts subject information；
Phrase semantic model acquiring unit, for training phrase semantic model to pretreated content；
Text feature determines unit, for determining currently according to the key word information, subject information and the phrase semantic model that obtain
Browse the text feature of news content.
Described device the most according to claim 6, it is characterised in that described similarity matching module includes:
Matching degree computing unit, for using set algorithm to calculate described Present News text feature and going through in described content library
Similarity matching degree between the text feature of the association content of history news content and/or described history news content；
Information sifting unit, screens for described similarity matching degree exceedes the history news content of predetermined threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610664122.XA CN106250550A (en) | 2016-08-12 | 2016-08-12 | A kind of method and apparatus of real time correlation news content recommendation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610664122.XA CN106250550A (en) | 2016-08-12 | 2016-08-12 | A kind of method and apparatus of real time correlation news content recommendation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106250550A true CN106250550A (en) | 2016-12-21 |
Family
ID=57593331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610664122.XA Pending CN106250550A (en) | 2016-08-12 | 2016-08-12 | A kind of method and apparatus of real time correlation news content recommendation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106250550A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951331A (en) * | 2017-02-28 | 2017-07-14 | 珠海市魅族科技有限公司 | A kind of method and device of data transfer |
| CN108200150A (en) * | 2017-12-29 | 2018-06-22 | 广州中幼信息科技有限公司 | A kind of implementation method of distributed content orientation push |
| CN108427761A (en) * | 2018-03-21 | 2018-08-21 | 腾讯科技（深圳）有限公司 | A kind of method, terminal, server and the storage medium of media event processing |
| WO2018166402A1 (en) * | 2017-03-14 | 2018-09-20 | 广州市动景计算机科技有限公司 | Interactive information display method and device |
| CN111026910A (en) * | 2018-10-09 | 2020-04-17 | 北京奇虎科技有限公司 | Video recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111581359A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | News recommendation method and device |
| CN111666473A (en) * | 2019-03-07 | 2020-09-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle equipment and vehicle equipment news tracing method |
| CN112992154A (en) * | 2021-05-08 | 2021-06-18 | 北京远鉴信息技术有限公司 | Voice identity determination method and system based on enhanced voiceprint library |
| CN113254772A (en) * | 2021-05-31 | 2021-08-13 | 温州行动者网络科技有限公司 | Information pushing method based on big data |
| CN113343024A (en) * | 2021-08-04 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN114386421A (en) * | 2022-01-13 | 2022-04-22 | 平安科技（深圳）有限公司 | Similar news detection method and device, computer equipment and storage medium |
| CN116383372A (en) * | 2023-04-14 | 2023-07-04 | 信域科技(沈阳)有限公司 | Data analysis method and system based on artificial intelligence |
| CN116738968A (en) * | 2023-08-14 | 2023-09-12 | 宁波深擎信息科技有限公司 | Content linking method, device, computer equipment and storage medium |
| CN116881575A (en) * | 2023-09-08 | 2023-10-13 | 腾讯科技（深圳）有限公司 | Content pushing method, device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090018988A1 (en) * | 2007-07-11 | 2009-01-15 | International Business Machines Corporation | Method and system for creating semantic relationships using hyperlinks |
| CN101694659A (en) * | 2009-10-20 | 2010-04-14 | 浙江大学 | Individual network news recommending method based on multitheme tracing |
| CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
| CN103389975A (en) * | 2012-05-07 | 2013-11-13 | 腾讯科技（深圳）有限公司 | News recommending method and system |
| CN104615746A (en) * | 2015-02-11 | 2015-05-13 | 腾讯科技（深圳）有限公司 | News data generation and display method and device |
| CN105512282A (en) * | 2015-12-07 | 2016-04-20 | 小米科技有限责任公司 | Notification method and device and terminal |
-
2016
- 2016-08-12 CN CN201610664122.XA patent/CN106250550A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090018988A1 (en) * | 2007-07-11 | 2009-01-15 | International Business Machines Corporation | Method and system for creating semantic relationships using hyperlinks |
| CN101694659A (en) * | 2009-10-20 | 2010-04-14 | 浙江大学 | Individual network news recommending method based on multitheme tracing |
| CN103389975A (en) * | 2012-05-07 | 2013-11-13 | 腾讯科技（深圳）有限公司 | News recommending method and system |
| CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
| CN104615746A (en) * | 2015-02-11 | 2015-05-13 | 腾讯科技（深圳）有限公司 | News data generation and display method and device |
| CN105512282A (en) * | 2015-12-07 | 2016-04-20 | 小米科技有限责任公司 | Notification method and device and terminal |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951331A (en) * | 2017-02-28 | 2017-07-14 | 珠海市魅族科技有限公司 | A kind of method and device of data transfer |
| WO2018166402A1 (en) * | 2017-03-14 | 2018-09-20 | 广州市动景计算机科技有限公司 | Interactive information display method and device |
| CN108200150A (en) * | 2017-12-29 | 2018-06-22 | 广州中幼信息科技有限公司 | A kind of implementation method of distributed content orientation push |
| CN108427761A (en) * | 2018-03-21 | 2018-08-21 | 腾讯科技（深圳）有限公司 | A kind of method, terminal, server and the storage medium of media event processing |
| CN111026910A (en) * | 2018-10-09 | 2020-04-17 | 北京奇虎科技有限公司 | Video recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111026910B (en) * | 2018-10-09 | 2024-04-05 | 三六零科技集团有限公司 | Video recommendation method, device, electronic equipment and computer readable storage medium |
| CN111666473A (en) * | 2019-03-07 | 2020-09-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle equipment and vehicle equipment news tracing method |
| CN111581359A (en) * | 2020-04-21 | 2020-08-25 | 北京龙云科技有限公司 | News recommendation method and device |
| CN112992154A (en) * | 2021-05-08 | 2021-06-18 | 北京远鉴信息技术有限公司 | Voice identity determination method and system based on enhanced voiceprint library |
| CN113254772B (en) * | 2021-05-31 | 2022-01-11 | 山东远桥信息科技有限公司 | Information pushing method based on big data |
| CN113254772A (en) * | 2021-05-31 | 2021-08-13 | 温州行动者网络科技有限公司 | Information pushing method based on big data |
| CN113343024B (en) * | 2021-08-04 | 2021-12-07 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN113343024A (en) * | 2021-08-04 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN114386421A (en) * | 2022-01-13 | 2022-04-22 | 平安科技（深圳）有限公司 | Similar news detection method and device, computer equipment and storage medium |
| CN116383372A (en) * | 2023-04-14 | 2023-07-04 | 信域科技(沈阳)有限公司 | Data analysis method and system based on artificial intelligence |
| CN116383372B (en) * | 2023-04-14 | 2023-11-24 | 北京创益互联科技有限公司 | Data analysis method and system based on artificial intelligence |
| CN116738968A (en) * | 2023-08-14 | 2023-09-12 | 宁波深擎信息科技有限公司 | Content linking method, device, computer equipment and storage medium |
| CN116738968B (en) * | 2023-08-14 | 2023-11-24 | 宁波深擎信息科技有限公司 | Content linking method, device, computer equipment and storage medium |
| CN116881575A (en) * | 2023-09-08 | 2023-10-13 | 腾讯科技（深圳）有限公司 | Content pushing method, device, computer equipment and storage medium |
| CN116881575B (en) * | 2023-09-08 | 2023-11-21 | 腾讯科技（深圳）有限公司 | Content pushing method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106250550A (en) | A kind of method and apparatus of real time correlation news content recommendation | |
| Gurini et al. | Temporal people-to-people recommendation on social networks with sentiment-based matrix factorization | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN107220352B (en) | Method and device for constructing comment map based on artificial intelligence | |
| Li et al. | Filtering out the noise in short text topic modeling | |
| CN103853824B (en) | In-text advertisement releasing method and system based on deep semantic mining | |
| CN106682192B (en) | Method and device for training answer intention classification model based on search keywords | |
| CN104484431B (en) | A kind of multi-source Personalize News webpage recommending method based on domain body | |
| CN104899273B (en) | A kind of Web Personalization method based on topic and relative entropy | |
| KR20160055930A (en) | Systems and methods for actively composing content for use in continuous social communication | |
| CN110781317A (en) | Method and device for constructing event map and electronic equipment | |
| CN105893344A (en) | User semantic sentiment analysis-based response method and device | |
| CN107402912B (en) | Method and device for analyzing semantics | |
| CN110968782A (en) | Student-oriented user portrait construction and application method | |
| CN104484343A (en) | Topic detection and tracking method for microblog | |
| CN109800350A (en) | A kind of Personalize News recommended method and system, storage medium | |
| CN104077417A (en) | Figure tag recommendation method and system in social network | |
| CN107544959B (en) | Evaluation object extraction method and device | |
| CN106227714A (en) | A kind of method and apparatus obtaining the key word generating poem based on artificial intelligence | |
| CN105183717A (en) | OSN user emotion analysis method based on random forest and user relationship | |
| CN108932322A (en) | A kind of geographical semantics method for digging based on text big data | |
| CN103177036A (en) | Method and system for label automatic extraction | |
| US20110314059A1 (en) | Mobile search method and apparatus | |
| Qi et al. | Mapping consumer sentiment toward wireless services using geospatial twitter data | |
| CN109063147A (en) | Online course forum content recommendation method and system based on text similarity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161221 |
|
| RJ01 | Rejection of invention patent application after publication |