CN106202563A - A kind of real time correlation evental news recommends method and system - Google Patents
A kind of real time correlation evental news recommends method and system Download PDFInfo
- Publication number
- CN106202563A CN106202563A CN201610622291.7A CN201610622291A CN106202563A CN 106202563 A CN106202563 A CN 106202563A CN 201610622291 A CN201610622291 A CN 201610622291A CN 106202563 A CN106202563 A CN 106202563A
- Authority
- CN
- China
- Prior art keywords
- event
- news
- data
- user
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of real time correlation evental news and recommend method and system, method includes: the comment on each World Jam such as the 1) news occurred for every day, and the microblogging of correspondence carries out data and crawls, and sets up news storehouse；2) data in news storehouse are carried out degree of depth excavation, set up corresponding event model, and be saved in event base；3) news data browsed user crawls, and relates to the information such as the content of news, title, the website issued；4) data in information user browsed and event base contrast, and match the whole event model of this news and relevant analysis result, and recommend user with intuitive manner.The method and apparatus provided by the present invention, it is possible to use understand the details such as the whole process of the correlating event relevant to certain news, origin, present situation during the efficient real of family, and push relevant news links to user.
Description
Technical field
The present invention relates to data mining and commending system, carry out real time correlation evental news particularly to utilizing data mining
The system recommended, specifically refers to a kind of real time correlation evental news and recommends method and system.
Background technology
We are now into big data age, and every day all can produce ten hundreds of data in the Internet.Along with the Internet
Fast development, each flash-news media begin through the Internet announce news.And people also begin to get used to by the Internet clear
Look at news daily.
But, because news website substantial amounts, so there will be each news website report is all same news,
And because by the large contingent of internet browsing news, the emphasis that everyone is paid close attention to is different, so being entered by the Internet
Row browses news, can take a lot of time and search in oneself required news, and have every day substantial amounts of news to carry out
Announcing, the news following the trail of report etc of more all continuous events can cause the news browsing people's other day to be gone for just to be known
The ins and outs of event.These are a series of results in and browses the efficiency of news very low on the internet.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, it is provided that a kind of real time correlation evental news recommend method and
System, the method can make to understand during user's efficient real the whole process of the correlating event relevant to certain news, origin, present situation etc.
Details, and push relevant news links to user.
It is an object of the invention to be achieved through the following technical solutions: a kind of real time correlation evental news recommends method,
It comprises the steps:
S1: crawl the comment in the news and the microblogging of correspondence and each World Jam occurred every day, set up news storehouse；
S2: data in news storehouse are carried out degree of depth excavation, sets up corresponding event model, and be saved in event base；
S3: the news data browsed user crawls；
S4: the data in the information that user is being browsed and event base contrast, matches the whole event mould of this news
Type and relevant analysis result, and recommend user with intuitive manner.
Data are carried out degree of depth excavation by described step S2 and set up time model and include following sub-step:
S21: process data in news storehouse, integrates the news about same event of different news websites,
On the basis of the degree of depth is excavated, analyze the origin of event, the venation of event, and set up the event model of this event；
S22: on the basis of event model, then process in real time based on the comment data to each World Jam and microblogging, analyze
The common people are for the viewpoint information of this event different phase；
S23: by the data excavated by different classes of storage to event base.
The news data browsed user in described step S3 crawls and mainly crawls what user was browsing
The content of news, title and the website issued.
The information that user is browsed is carried out mating by described step S4 with event model with analyze mainly include as
Lower step:
S41: based on crawling on the basis of user browses news information, set a time window, in query event storehouse
All events in the range of this time；
S42: in the event in the time range found, contrasts information and the event information of news, by text phase
Match with the relevant event of this news like the method for property；
S43: the whole event model of this news and relevant analysis are tied according to the analysis result of the event model in event base
Fruit recommends user.
The information of described news and event information carry out contrast and relate to key word, personage and place.
The described degree of depth is excavated and is included following sub-step:
A. according to timestamp, the origin of event is judged；
B. according to timestamp, event venation is arranged；
C. according to the sentiment analysis of forum's comment, event public's emotion tendency is analyzed；
D. according to the common people to the temperature of the attention-degree analysis event of event and power of influence.
A kind of real time correlation evental news commending system, it includes:
Data crawl module, and this module is mainly used in climbing that each flash-news site information and relevant forum and microblogging are commented on
Take；
News storehouse, storage data crawl all kinds of news and the comment that module crawls；
Event analysis module, this module is mainly used in the information in news storehouse carries out data mining and event modeling；
Event base, preserves all kinds of event informations that event analysis module generates；
Data storage access module, this module is mainly used in data to crawl the data of module acquisition and stores news storehouse, by thing
Part is analyzed the event that module data excavates and event modeling obtains and is stored event base, and provides news storehouse, event base to access and connect
Mouthful；
Client modules, the data that this module is mainly used in the news & event storehouse that user is being browsed contrast, and
And the data results of the news that user browsed is presented to user and carries out the recommendation of related news.
Described event analysis module realizes the analysis of event venation, event origin, event power of influence and the masses event
The analysis of emotion.
The invention has the beneficial effects as follows: the invention provides a kind of real time correlation evental news and recommend method and system, energy
Enough realize people browsing news when, understand the situation that event occurs in further detail, and relevant news can be pushed to reading
Person, it is to avoid they go to lose time in searching related news again.Solving in the biggest data, every day, news report was various
In the case of, the problem inefficient when browsing news.Also people are allowed can be better understood by the truth of news, to a certain degree
On alleviate the propagation of rumour.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the present invention；
Fig. 2 is system module schematic diagram.
Detailed description of the invention
Technical scheme is described in further detail below in conjunction with the accompanying drawings, but protection scope of the present invention is not limited to
The following stated.
As it is shown in figure 1, a kind of real time correlation evental news recommends method, it comprises the steps:
S1: crawl the comment in the news and the microblogging of correspondence and each World Jam occurred every day, set up news storehouse；
S2: data in news storehouse are carried out degree of depth excavation, sets up corresponding event model, and be saved in event base；
S3: the news data browsed user crawls；
S4: the data in the information that user is being browsed and event base contrast, matches the whole event mould of this news
Type and relevant analysis result, and recommend user with intuitive manner.
Data are carried out degree of depth excavation by described step S2 and set up time model and include following sub-step:
S21: process data in news storehouse, integrates the news about same event of different news websites,
On the basis of the degree of depth is excavated, analyze the origin of event, the venation of event, and set up the event model of this event；
S22: on the basis of event model, then process in real time based on the comment data to each World Jam and microblogging, analyze
The common people are for the viewpoint information of this event different phase；
S23: by the data excavated by different classes of storage to event base.
The news data browsed user in described step S3 crawls and mainly crawls what user was browsing
The content of news, title and the website issued.
The information that user is browsed is carried out mating by described step S4 with event model with analyze mainly include as
Lower step:
S41: based on crawling on the basis of user browses news information, set a time window, in query event storehouse
All events in the range of this time；
S42: in the event in the time range found, contrasts information and the event information of news, by text phase
Match with the relevant event of this news like the method for property；
S43: the whole event model of this news and relevant analysis are tied according to the analysis result of the event model in event base
Fruit recommends user.
The information of described news and event information carry out contrast and relate to key word, personage and place.
The described degree of depth is excavated and is included following sub-step:
A. according to timestamp, the origin of event is judged；
B. according to timestamp, event venation is arranged；
C. according to the sentiment analysis of forum's comment, event public's emotion tendency is analyzed；
D. according to the common people to the temperature of the attention-degree analysis event of event and power of influence.
As in figure 2 it is shown, a kind of real time correlation evental news commending system, it includes:
Data crawl module, and this module is mainly used in climbing that each flash-news site information and relevant forum and microblogging are commented on
Take；
News storehouse, storage data crawl all kinds of news and the comment that module crawls；
Event analysis module, this module is mainly used in the information in news storehouse carries out data mining and event modeling；
Event base, preserves all kinds of event informations that event analysis module generates；
Data storage access module, this module is mainly used in data to crawl the data of module acquisition and stores news storehouse, by thing
Part is analyzed the event that module data excavates and event modeling obtains and is stored event base, and provides news storehouse, event base to access and connect
Mouthful；
Client modules, the data that this module is mainly used in the news & event storehouse that user is being browsed contrast, and
And the data results of the news that user browsed is presented to user and carries out the recommendation of related news.
Described event analysis module realizes the analysis of event venation, event origin, event power of influence and the masses event
The analysis of emotion.
In one embodiment, using browser plug-in as the enforcement carrier of the present invention, main flow is as follows:
Comment in step 1, the news occurred for every day, and each World Jam such as the microblogging of correspondence carries out data and crawls, and builds
Vertical news storehouse.Main website includes: Netease, Tengxun, People's Net, the ends of the earth, the news of each big website and the climbing of related commentary such as 91
Take.
Step 2, the data crawled from each flash-news and forum's platform are carried out degree of depth excavation, set up corresponding event mould
Type, and be saved in event base.It is broadly divided into four steps: data prediction, affair clustering, event sentiment analysis, event shadow
The power of sound judges.Wherein, the timestamp that event venation can occur based on event in affair clustering carries out venation and portrays.Then building
Event model and the analysis result of mould are stored in event base.
Step 3, user side install client modules, in example of the present invention client modules be a general browser insert
Part, after having configured the plug-in unit used by browser, just can crawl the news that user is browsing in real time by this plug-in unit, will capture
To news contrast with the data in event base, and the data results of the news that user is browsed is presented to user
And carry out the recommendation of related news.
Claims (8)
1. a real time correlation evental news recommends method, it is characterised in that it comprises the steps:
S1: crawl the comment in the news and the microblogging of correspondence and each World Jam occurred every day, set up news storehouse；
S2: data in news storehouse are carried out degree of depth excavation, sets up corresponding event model, and be saved in event base；
S3: the news data browsed user crawls；
S4: the data in the information that user is being browsed and event base contrast, matches the whole event mould of this news
Type and relevant analysis result, and recommend user with intuitive manner.
A kind of real time correlation evental news the most according to claim 1 recommends method, it is characterised in that: described step S2
In data are carried out degree of depth excavation and set up time model and include following sub-step:
S21: process data in news storehouse, integrates the news about same event of different news websites,
On the basis of the degree of depth is excavated, analyze the origin of event, the venation of event, and set up the event model of this event；
S22: on the basis of event model, then process in real time based on the comment data to each World Jam and microblogging, analyze
The common people are for the viewpoint information of this event different phase；
S23: by the data excavated by different classes of storage to event base.
A kind of real time correlation evental news the most according to claim 1 recommends method, it is characterised in that: described step S3
In news data that user is being browsed crawl and mainly crawl the content of the news that user is browsing, title and sent out
The website of cloth.
A kind of real time correlation evental news the most according to claim 1 recommends method, it is characterised in that: described step S4
Middle carry out mating with event model by the information that user is browsed mainly comprise the steps: with analyzing
S41: based on crawling on the basis of user browses news information, set a time window, in query event storehouse
All events in the range of this time；
S42: in the event in the time range found, contrasts information and the event information of news, by text phase
Match with the relevant event of this news like the method for property；
S43: the whole event model of this news and relevant analysis are tied according to the analysis result of the event model in event base
Fruit recommends user.
A kind of real time correlation evental news the most according to claim 4 recommends method, it is characterised in that: described news
Information and event information carry out contrast and relate to key word, personage and place.
A kind of real time correlation evental news the most according to claim 2 recommends method, it is characterised in that: the described degree of depth is dug
Dig and include following sub-step:
A. according to timestamp, the origin of event is judged；
B. according to timestamp, event venation is arranged；
C. according to the sentiment analysis of forum's comment, event public's emotion tendency is analyzed；
D. according to the common people to the temperature of the attention-degree analysis event of event and power of influence.
7. a real time correlation evental news commending system, it is characterised in that it includes:
Data crawl module, and this module is mainly used in climbing that each flash-news site information and relevant forum and microblogging are commented on
Take；
News storehouse, storage data crawl all kinds of news and the comment that module crawls；
Event analysis module, this module is mainly used in the information in news storehouse carries out data mining and event modeling；
Event base, preserves all kinds of event informations that event analysis module generates；
Data storage access module, this module is mainly used in data to crawl the data of module acquisition and stores news storehouse, by thing
Part is analyzed the event that module data excavates and event modeling obtains and is stored event base, and provides news storehouse, event base to access and connect
Mouthful；
Client modules, the data that this module is mainly used in the news & event storehouse that user is being browsed contrast, and
And the data results of the news that user browsed is presented to user and carries out the recommendation of related news.
A kind of real time correlation evental news commending system the most according to claim 7, it is characterised in that described event is divided
Analysis module realizes the analysis of event venation, event origin, event power of influence and masses' analysis to event emotion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610622291.7A CN106202563A (en) | 2016-08-02 | 2016-08-02 | A kind of real time correlation evental news recommends method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610622291.7A CN106202563A (en) | 2016-08-02 | 2016-08-02 | A kind of real time correlation evental news recommends method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106202563A true CN106202563A (en) | 2016-12-07 |
Family
ID=57496978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610622291.7A Pending CN106202563A (en) | 2016-08-02 | 2016-08-02 | A kind of real time correlation evental news recommends method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106202563A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649780A (en) * | 2016-12-28 | 2017-05-10 | 北京百度网讯科技有限公司 | Information providing method and device based on artificial intelligence |
| CN109145218A (en) * | 2018-09-10 | 2019-01-04 | 北京点网聚科技有限公司 | A kind of article recommended method and device |
| CN109241402A (en) * | 2018-07-31 | 2019-01-18 | 成都华栖云科技有限公司 | A kind of virtual comment machine introduction method based on news content |
| CN110245243A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | The method and apparatus of news retrieval, electronic equipment, computer-readable medium |
| CN110309312A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of correlating event acquisition methods and device |
| CN110502299A (en) * | 2019-08-12 | 2019-11-26 | 南京大众书网图书文化有限公司 | It is a kind of for providing the method and apparatus of novel information |
| 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 |
| CN111782907A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | News classification method and device and electronic equipment |
| CN113268598A (en) * | 2021-05-26 | 2021-08-17 | 平安科技（深圳）有限公司 | Event context generation method and device, terminal equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020159A (en) * | 2012-11-26 | 2013-04-03 | 百度在线网络技术（北京）有限公司 | Method and device for news presentation facing events |
| CN103164427A (en) * | 2011-12-13 | 2013-06-19 | 中国移动通信集团公司 | Method and device of news aggregation |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN104915446A (en) * | 2015-06-29 | 2015-09-16 | 华南理工大学 | Automatic extracting method and system of event evolving relationship based on news |
-
2016
- 2016-08-02 CN CN201610622291.7A patent/CN106202563A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103164427A (en) * | 2011-12-13 | 2013-06-19 | 中国移动通信集团公司 | Method and device of news aggregation |
| CN103020159A (en) * | 2012-11-26 | 2013-04-03 | 百度在线网络技术（北京）有限公司 | Method and device for news presentation facing events |
| CN104573054A (en) * | 2015-01-21 | 2015-04-29 | 杭州朗和科技有限公司 | Information pushing method and equipment |
| CN104915446A (en) * | 2015-06-29 | 2015-09-16 | 华南理工大学 | Automatic extracting method and system of event evolving relationship based on news |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649780B (en) * | 2016-12-28 | 2020-11-24 | 北京百度网讯科技有限公司 | Information providing method and device based on artificial intelligence |
| US10733197B2 (en) | 2016-12-28 | 2020-08-04 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for providing information based on artificial intelligence |
| CN106649780A (en) * | 2016-12-28 | 2017-05-10 | 北京百度网讯科技有限公司 | Information providing method and device based on artificial intelligence |
| CN110309312A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of correlating event acquisition methods and device |
| CN109241402A (en) * | 2018-07-31 | 2019-01-18 | 成都华栖云科技有限公司 | A kind of virtual comment machine introduction method based on news content |
| CN109145218A (en) * | 2018-09-10 | 2019-01-04 | 北京点网聚科技有限公司 | A kind of article recommended method and device |
| CN109145218B (en) * | 2018-09-10 | 2021-11-02 | 北京一点网聚科技有限公司 | Article 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 |
| CN110245243A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | The method and apparatus of news retrieval, electronic equipment, computer-readable medium |
| CN110502299A (en) * | 2019-08-12 | 2019-11-26 | 南京大众书网图书文化有限公司 | It is a kind of for providing the method and apparatus of novel information |
| CN111782907A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | News classification method and device and electronic equipment |
| CN111782907B (en) * | 2020-07-01 | 2024-03-01 | 北京知因智慧科技有限公司 | News classification method and device and electronic equipment |
| CN113268598A (en) * | 2021-05-26 | 2021-08-17 | 平安科技（深圳）有限公司 | Event context generation method and device, terminal equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106202563A (en) | A kind of real time correlation evental news recommends method and system | |
| AU2010330720B2 (en) | System and method for attentive clustering and related analytics and visualizations | |
| CN103023714B (en) | The liveness of topic Network Based and cluster topology analytical system and method | |
| CN104536956A (en) | A Microblog platform based event visualization method and system | |
| CN102541937B (en) | Webpage information detection method and system | |
| CN104899273A (en) | Personalized webpage recommendation method based on topic and relative entropy | |
| CN103399883A (en) | Method and system for performing personalized recommendation according to user interest points/concerns | |
| CN104462385A (en) | Personalized movie similarity calculation method based on user interest model | |
| CN103425763B (en) | User based on SNS recommends method and device | |
| CN103020159A (en) | Method and device for news presentation facing events | |
| CN105718590A (en) | Multi-tenant oriented SaaS public opinion monitoring system and method | |
| CN103593413A (en) | Meta-search engine personalizing method based on Agent | |
| CN102253943B (en) | Webpage rating method and webpage rating system | |
| CN102779190A (en) | Rapid detection method for hot issues of timing sequence massive network news | |
| CN106021418A (en) | News event clustering method and device | |
| CN103605715A (en) | Method and device used for data integration processing of multiple data sources | |
| CN103577404A (en) | Microblog-oriented discovery method for new emergencies | |
| CN104516961A (en) | Topic digging and topic trend analysis method and system based on region | |
| CN106033445A (en) | Method and device for obtaining article association degree data | |
| CN104391978A (en) | Method and device for storing and processing web pages of browsers | |
| CN106021351A (en) | An aggregation extraction method and device for news events | |
| Rehman et al. | Building socially-enabled event-enriched maps | |
| CN112000866B (en) | Internet data analysis method, device, electronic device and medium | |
| CN104391958B (en) | The correlation detection methods and device of Webpage search keyword | |
| Milić et al. | Framework for open data mining in e-government |
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: 20161207 |
|
| RJ01 | Rejection of invention patent application after publication |