CN102831220B - Subject-oriented customized news information extraction system - Google Patents

Subject-oriented customized news information extraction system Download PDF

Info

Publication number
CN102831220B
CN102831220B CN201210300602.XA CN201210300602A CN102831220B CN 102831220 B CN102831220 B CN 102831220B CN 201210300602 A CN201210300602 A CN 201210300602A CN 102831220 B CN102831220 B CN 102831220B
Authority
CN
China
Prior art keywords
topic
information
unit
news
text
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
Application number
CN201210300602.XA
Other languages
Chinese (zh)
Other versions
CN102831220A (en
Inventor
台宪青
王艳军
赵旦谱
楚涌泉
张伟娜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu IoT Research and Development Center
Original Assignee
Jiangsu IoT Research and Development Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu IoT Research and Development Center filed Critical Jiangsu IoT Research and Development Center
Priority to CN201210300602.XA priority Critical patent/CN102831220B/en
Publication of CN102831220A publication Critical patent/CN102831220A/en
Application granted granted Critical
Publication of CN102831220B publication Critical patent/CN102831220B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a subject-oriented customized new information extraction system which comprises a news collecting subsystem, a text processing subsystem and a human-computer interaction subsystem, wherein the news collecting subsystem completes the functions of searching related news about related subjects customized by a user and extracting news texts; the text processing subsystem divides the texts into different categories, detects and tracks topics in the content of the texts on that basis, automatically generates abstracts and establishes corresponding indexes; and the human-computer interaction subsystem firstly analyzes the topics, calculates the hot degree of the topics, presents the hot topics in the groups of subjects of the topics for the user in the sequence of hot degree and simultaneously provides topic retrieval, and the user can artificially screen the obtained content and store intelligence obtained by artificially extracting the screened information into an intelligence library. With the system, news on the internet can be comprehensively collected in time and can be automatically detected, classified and tracked, and intelligence required by the user can be extracted from immense network news by exerting the cognitive ability of the user on intelligence.

Description

A kind of news information extraction system of subject-oriented customization
Technical field
The present invention relates to a kind of news information extraction system, specifically a kind of with news be object subject-oriented customization information extraction system.
Background technology
Today at a high speed flourishing in internet, the information utilizing public information publishing system to collect the field such as political, military, economic, cultural has become one of important channel of an acquisition information.According in information science to the definition of information, so-called information, refers to the real-time information needed within the effective time.At present, the information of 90% all obtains from public information publishing system, and all kinds of news information is undoubtedly the public information of maximum.
But, internet news is magnanimity information source, and be the information space of an opening, distribution, the intrinsic following characteristics of itself oneself through hindering the abundant use of people to internet information resource significantly: the upper available information of Internet is inorganization, various structures form, and is distributed on each website global; Type and the quantity of data and service are all rolling up every day, and thus the utilizability of information and reliability are also constantly changing; Due to the dynamic of information source and the renewal of potential useful information and the problem of preservation, information is usually fuzzy, sometimes or even mistake.
How determining the direction of information acquisition, and find a kind of collection mode efficiently, namely how to look on the internet and how to look for, is carry out a letter of information in the public domain collection problem to be solved.The information retrieval mode provided at present, as search engine, fundamentally can not solve the problem of this respect.Its reason mainly contain following some:
(1) there is suitable distance to the understanding of user interest and between identifying in the interest expression way of user and search engine; Simultaneously in retrieving, have a large amount of incoherent information and be provided to user, produce the phenomenon of " information overload ".All that efficiency is very low with manually coming to judge one by one and collection all information found at present;
(2) one sections of Internet news are difficult to disposable explain oneself to event, along with the passing of event may have new situation, new problem.The result that search engine returns a certain subject events often fragment, discrete, arrangement can not be sorted out in chronological order to an event, form the development track of an event.And the development track that an event is fairly perfect, user's reference can be given, with the development trend of decision event.
(3) search engine is when retrieving information, can not guarantee information ageing and authoritative, and this extracts for information, is a very serious or even fatal weakness.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, the news information extraction system providing a kind of subject-oriented to customize, it can customize according to the interest topic of user, more all sidedly, collection network news in time, automatically carry out newsletter archive extraction, topic detection and topic tracking, form the file classification method centered by topic, and can concentrate and carry out retrieving and browsing, there is provided the relevant information of screening news, final help user extracts relevant information.
In order to solve the problem, the news information extraction system of subject-oriented customization of the present invention comprises: news gathering subsystem, text-processing subsystem and human-machine interaction subsystem; Described news gathering subsystem, the related news of the related subject of search subscriber customization, and extract newsletter archive; Described text-processing subsystem, is divided into different classes by text, carries out topic detection, topic tracking on this basis to the content of text, automatically generates digest simultaneously, sets up corresponding index; Described human-machine interaction subsystem, topic advanced person row is analyzed, calculate the temperature of topic, by hot issue with topic theme as group, with temperature be order present to user, this human-machine interaction subsystem provides topic to retrieve simultaneously, user manually screens according to the content obtained, and the information after screening is deposited into information bank by the information obtained after artificial extraction.
Described news gathering subsystem comprises: focused crawler unit, web database, text extracting unit and text library; Wherein, described focused crawler unit, according to the theme of customization, uses focused crawler to search in internet, in the process of search, carries out the judgement of the Web page subject degree of correlation, preserves the webpage relevant in theme stored in web database; The original web page that described web database comes for storing the collection of focused crawler unit; Described text extracting unit carries out denoising to the webpage inside web database, and half-and-half structurized Internet news carries out structuring extraction, and information aggregate extraction obtained is in a text form stored in text library; Described text library is used for storing the information that text extracting unit transmits.
Described text-processing subsystem comprises: text classification unit, topic detection unit, topic tracking unit, abstract and indexing unit and topic storehouse; Wherein, described text classification unit assigns in basic large class by the text in text library by its content, conveniently carries out next step process; News in text library is included into different topics by described topic detection unit, sets up new topic, collected by the newsletter archive of same topic stored in topic storehouse when needs; The follow-up report of described topic tracking cell tracks topic, sorts in chronological order by same topic, forms the development track of an event, to user's reference, with the development trend of decision event, sequencing information is write back topic storehouse; Described abstract and indexing unit is processed the news content in the topic storehouse sorted out, and generates summary, forms the index database for searching for, and provide search function; Described topic storehouse is used for the news relevant information that information in the text library after storing topic detection cell processing and topic tracking unit and abstract and indexing unit write back, and is supplied to human-machine interaction subsystem and retrieves.
Described human-machine interaction subsystem comprises: topic analytic unit, topic display unit, retrieval feedback unit and information bank; The quantity of the number of days that described topic analytic unit occurs according to topic, report calculates the temperature of topic, carries out the rank of topic temperature simultaneously; The topic relevant to theme is themed as group with topic by described topic display unit, is that order shows the topic information relevant to theme to user, plays the effect of early warning with temperature; Described retrieval feedback unit receives the inquiry request of user, by corresponding information centered by topic, take time as order display, show the place, source of news simultaneously, update time, body release information screens information to help user, the news after screening can manually extract and stored in information bank by user simultaneously; Described information bank is used for the information that memory scan feedback unit provides.
Compared with prior art, the present invention has following beneficial effect:
(1) can theme customization be carried out, and save time.By carrying out theme customization to the focused crawler unit in news gathering subsystem, user can carry out internet information crawl to oneself interested theme, avoids reptile to carry out the crawl of poor efficiency, heavy garbage simultaneously, improves efficiency, save time.
(2) Internet news relevant to theme can be collected more all sidedly, in time.Because focused crawler unit can specified page, website, therefore system comprehensively can be creeped for the content of these websites; The crawl cycle of focused crawler can be customized simultaneously, the website often upgraded is creeped in time, enables the state that the record in web database keeps up-to-date.
(3) system carries out topic detection to news automatically, newsletter archive is pressed topic and sorts out.Topic detection unit processes the content of text in text library, finds new topic, identification text topic, the newsletter archive of same topic is classified as a class, systematic searching and inquiry when being convenient to intelligence analysis.
(4) system carries out topic tracking to news automatically, represents the ins and outs of topic.The follow-up report of topic tracking cell tracks topic, sorts in chronological order by same topic, forms the development track of an event, to user's reference, with the development trend of decision event.
(5) retrieval can concentrated and browsing.Owing to collect and the news information of processing process and topic relevant information are all stored in topic storehouse, be therefore convenient to by browsing search interface and carry out systematic searching and search inquiry being browsed.
(6) give full play to the cognitive ability of user, by man-computer cooperation, realize information extraction effect better.In the examination, leaching process of information, system can provide the relevant information such as source of news, time to user with reference, and simultaneity factor gives full play to the cognitive ability of user, finally extracts the information useful to user.
Accompanying drawing explanation
Fig. 1 is the structural representation of the news information extraction system of a kind of subject-oriented customization proposed in the embodiment of the present invention.
Fig. 2 is the method flow diagram of information leaching process in the embodiment of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the invention will be further described.
As shown in Figure 1, be that the news information extraction system of subject-oriented of the present invention customization comprises three subsystems, be respectively news gathering subsystem 1, text-processing subsystem 2, human-machine interaction subsystem 3.
News gathering subsystem 1 completes the related news of the related subject of search subscriber customization, and extracts the function of newsletter archive.News gathering subsystem 1 comprises: focused crawler unit 102, web database 104, text extracting unit 106 and text library 108.
Focused crawler unit 102 receives the theme of customization, according to the URL table of the page of customization, website or stochastic generation, according to crawl strategy, conduct interviews one by one, degree of subject relativity judgement is carried out to the page of each crawl, by the Page-saving relevant with theme to web database, and the page that theme has nothing to do is given up.Web database 104, capturing the webpage relevant with theme for storing focused crawler unit 102, being supplied to text extracting unit 106 and using.
Text extracting unit 106 reads the news web page in web database 104, denoising is carried out to it, and half-and-half structurized Internet news carries out structuring extraction, comprise: title, source, size text, issuing time, personage, place, the information such as particular content, information aggregate extraction obtained is in a text form stored in text library 108.
The information that text library 108 transmits for storing text extracting unit 106.
Text in text library 108 is divided into different classes by text-processing subsystem 2, carries out topic detection, topic tracking on this basis to the content of text, automatically generates digest simultaneously, sets up corresponding index.Text-processing subsystem 2 comprises: text classification unit 110, topic detection unit 112, topic tracking unit 114, abstract and indexing unit 116 and topic storehouse 118.
Text in text library 108 is assigned in basic large class by its content by text classification unit 110, conveniently carries out next step process.
Topic detection unit 112 reads the content of newsletter archive in text library 108, newsletter archive is included into different topics, set up new topic when needs, the newsletter archive of same topic is collected, and by text and categorizing information stored in topic storehouse 118.
Topic tracking unit 114 follows the trail of the follow-up report of topic, is sorted in chronological order by same topic, forms the development track of an event, to user's reference, with the development trend of decision event, is write back by sequencing information in topic storehouse 118.
Abstract and indexing unit 116 utilizes existing automatic abstract generation technique, and in dialogue exam pool 118, newsletter archive content carries out Automatic Extraction processing, generates the summary info of news content, and is preserved by summary in reply exam pool 118; Utilize search engine global search technology simultaneously, read the content of newsletter archive in topic storehouse 118, text-converted is become index entry, and index entry is stored in index database, for human-machine interaction subsystem 03 provides the function of search information.
Topic storehouse 118 is used for storing the text message and categorizing information that topic detection unit 114 transmits, and provide data source for topic tracking unit 114, abstract and indexing unit 116 and human-machine interaction subsystem 03, receive classification that topic tracking unit 114 transmits, sequencing information simultaneously, the digest information that abstract and indexing unit 116 transmits and index information, and support that human-machine interaction subsystem 03 is according to keywords retrieved.
Human-machine interaction subsystem 3 pairs of topic advanced person row are analyzed, calculate the temperature of topic, hot issue is themed as group with topic, be that order presents to user with time, this subsystem provides topic to retrieve simultaneously, user manually screens according to the content obtained, and the information after screening is deposited into information bank by the information obtained after artificial extraction.Human-machine interaction subsystem 3 comprises: topic analytic unit 120, topic display unit 122, retrieval feedback unit 124 and information bank 126.
Topic analytic unit 120 reads the information in topic storehouse, calculates the temperature of topic, carry out the rank of topic temperature simultaneously according to factors such as the number of days of topic appearance, the quantity of report.
The information that topic display unit 122 utilizes topic analytic unit 120 to transmit, themes as group by the topic relevant to theme with topic, is that order shows the various information relevant to theme to user, plays the effect of early warning with temperature.
Retrieval feedback unit 124 receives the inquiry request of user, retrieve from index database, and corresponding information is transferred from topic storehouse 118, by information centered by topic, take time as order display, show the information such as the analysis result that the place, source of news, update time, body release and topic analytic unit 120 transmit to screen information to help user simultaneously, simultaneously the news after screening can manually extract by user, and by the information after extracting with the form of information stored in information bank 126.
Information bank 126 is used for storing the information transmitted from retrieval feedback unit 124.
As shown in Figure 2, be the process flow diagram of information leaching process in the embodiment of the present invention, with from collection network news, text extracts, text classification, topic detection, topic tracking, automatic abstract, automatic indexing, finally by man-machine interaction, by information, the process extracted stored in information bank is example, describes the workflow corresponding with system of the present invention in detail, comprises the following steps:
Step 201, inputs the information such as theme of news, crawl strategy of customization to focused crawler unit 102;
Step 202, focused crawler unit 102 starts, and starts to capture webpage, and carries out degree of subject relativity judgement, is given up by the webpage irrelevant in theme, the news web page of crawl is put into web database 104;
Step 203, text extracting unit 106 processes the webpage in web database, and by the text after extraction stored in text library 108;
Step 204, the text in text library 108 is assigned in basic large class by its content by text classification unit 110, conveniently carries out next step process;
Step 205, topic detection unit 112 identifies the topic that text library 108 Chinese version content comprises, and text is pressed topic classification, by newsletter archive, topic and classified information stored in topic storehouse 118;
Step 206, topic tracking unit 114 follows the trail of the follow-up report of topic, is sorted in chronological order by the text of same topic;
Step 207, abstract and indexing unit 116 reads the content of topic storehouse 118 text, utilizes automatic Summarization Technique, generates text snippet;
Step 208, abstract and indexing unit 116 utilizes search engine global search technology simultaneously, reads the content of newsletter archive in topic storehouse 118, text-converted is become index entry, and is stored in index database by index entry;
Step 209, the topic that topic analytic unit 120 is talked with in exam pool 118 is analyzed, and calculates topic temperature;
Step 210, the topic relevant to theme is themed as group by temperature with topic by topic display unit 122, is that order shows the topic information relevant to theme to user with temperature;
Step 211, retrieval feedback unit 124 receives the request of user, returns the news information of the serializing sorted out, and shows the information such as source of news;
Step 212, the information that user screens, extracts by retrieval feedback unit 124, stored in information bank 126.
As can be seen from above example, based on the news information extraction system that subject-oriented provided by the present invention customizes, user can be helped to obtain the related news of its subject of interest easily, and automatically the news that theme is relevant is pressed topic classification, by the news of same topic with time-sequencing, hand over the ins and outs of topic very clearly, to user's reference, with the development trend of decision event; Abstract and indexing unit in simultaneity factor can help user from topic storehouse quick-searching to required information, and human-machine interaction subsystem then gives full play to the cognitive ability of technical advantage and people, makes the information extracting maximum value.Under the help of native system, user can easily from vast Internet news rapid extraction to required information.

Claims (1)

1. a news information extraction system for subject-oriented customization, is characterized in that, comprise news gathering subsystem (1), text-processing subsystem (2) and human-machine interaction subsystem (3); Described news gathering subsystem (1), the related news of the related subject of search subscriber customization, and extract newsletter archive; Described text-processing subsystem (2), is divided into different classes by text, carries out topic detection, topic tracking on this basis to the content of text, automatically generates digest simultaneously, sets up corresponding index; Described human-machine interaction subsystem (3), topic advanced person row is analyzed, calculate the temperature of topic, by hot issue with topic theme as group, with temperature be order present to user, this human-machine interaction subsystem provides topic to retrieve simultaneously, user manually screens according to the content obtained, and the information after screening is deposited into information bank by the information obtained after artificial extraction;
Described news gathering subsystem (1) comprising: focused crawler unit (102), web database (104), text extracting unit (106) and text library (108); Wherein, described focused crawler unit (102) is according to the theme of customization, use focused crawler to search in internet, in the process of search, carry out the judgement of the Web page subject degree of correlation, the webpage relevant in theme is preserved stored in web database (104); The original web page that described web database (104) comes for storing focused crawler unit (102) collection; The webpage of described text extracting unit (106) to web database (104) the inside carries out denoising, and half-and-half structurized Internet news carries out structuring extraction, and information aggregate extraction obtained is in a text form stored in text library (108); Described text library (108) is used for storing text extracting unit (106) information that transmits;
Described text-processing subsystem (2) comprising: text classification unit (110), topic detection unit (112), topic tracking unit (114), abstract and indexing unit (116) and topic storehouse (118); Wherein, described text classification unit (110) assigns in basic large class by the text in text library (108) by its content, conveniently carries out next step process; News in text library (108) is included into different topics by described topic detection unit (112), sets up new topic, collected by the newsletter archive of same topic stored in topic storehouse (118) when needs; Described topic tracking unit (114) follows the trail of the follow-up report of topic, is sorted in chronological order by same topic, forms the development track of an event, to user's reference, with the development trend of decision event, sequencing information is write back topic storehouse (118); Described abstract and indexing unit (116) is processed the news content in the topic storehouse (118) sorted out, and generates summary, forms the index database for searching for, and provide search function; Described topic storehouse (118) is used for the news relevant information that information in the text library (108) after storing topic detection unit (112) process and topic tracking unit (114) and abstract and indexing unit (116) write back, and is supplied to human-machine interaction subsystem (3) and retrieves;
Described human-machine interaction subsystem (3) comprising: topic analytic unit (120), topic display unit (122), retrieval feedback unit (124) and information bank (126); The quantity of the number of days that described topic analytic unit (120) occurs according to topic, report calculates the temperature of topic, carries out the rank of topic temperature simultaneously; The topic relevant to theme is themed as group with topic by described topic display unit (122), is that order shows the topic information relevant to theme to user, plays the effect of early warning with temperature; Described retrieval feedback unit (124) receives the inquiry request of user, by corresponding information centered by topic, take time as order display, show the place, source of news simultaneously, update time, body release information screens information to help user, the news after screening can manually extract and stored in information bank (126) by user simultaneously; Described information bank (126) is used for the information that memory scan feedback unit (124) provides.
CN201210300602.XA 2012-08-23 2012-08-23 Subject-oriented customized news information extraction system Active CN102831220B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210300602.XA CN102831220B (en) 2012-08-23 2012-08-23 Subject-oriented customized news information extraction system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210300602.XA CN102831220B (en) 2012-08-23 2012-08-23 Subject-oriented customized news information extraction system

Publications (2)

Publication Number Publication Date
CN102831220A CN102831220A (en) 2012-12-19
CN102831220B true CN102831220B (en) 2015-01-07

Family

ID=47334355

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210300602.XA Active CN102831220B (en) 2012-08-23 2012-08-23 Subject-oriented customized news information extraction system

Country Status (1)

Country Link
CN (1) CN102831220B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114841155A (en) * 2022-04-21 2022-08-02 科技日报社 Intelligent theme content aggregation method and device, electronic equipment and storage medium

Families Citing this family (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103970788A (en) * 2013-02-01 2014-08-06 北京英富森信息技术有限公司 Webpage-crawling-based crawler technology
CN103530398B (en) * 2013-10-23 2016-06-01 合山市科学技术情报研究所 A kind of information collection process and retrieval system
CN103544279A (en) * 2013-10-23 2014-01-29 合山市科学技术情报研究所 Social information processing system
CN103984729A (en) * 2014-05-19 2014-08-13 北京大学 Microblog information tracing method and microblog information tracing method
CN106021244A (en) * 2015-03-17 2016-10-12 北京国双科技有限公司 Method and device for monitoring data
CN104992232A (en) * 2015-08-10 2015-10-21 苏州乐聚一堂电子科技有限公司 Hand-held intelligent electronic device news appointment and reporting method
WO2017028182A1 (en) * 2015-08-18 2017-02-23 郭子明 Method and news display system for prompting information when displaying news information according to keyword
WO2017028184A1 (en) * 2015-08-18 2017-02-23 郭子明 Method and news display system for prompting information when displaying news information according to topic
WO2017028183A1 (en) * 2015-08-18 2017-02-23 郭子明 Method and news display system for displaying news information according to topic
CN105138671A (en) * 2015-09-07 2015-12-09 百度在线网络技术(北京)有限公司 Human-computer interaction guiding method and device based on artificial intelligence
CN106874292B (en) * 2015-12-11 2020-05-05 北京国双科技有限公司 Topic processing method and device
CN105404699A (en) * 2015-12-29 2016-03-16 广州神马移动信息科技有限公司 Method, device and server for searching articles of finance and economics
CN107783973B (en) * 2016-08-24 2022-02-25 慧科讯业有限公司 Method, device and system for monitoring internet media event based on industry knowledge map database
CN106779466A (en) * 2016-12-30 2017-05-31 中国民航信息网络股份有限公司 The processing method and processing device of event
CN107256263A (en) * 2017-06-13 2017-10-17 成都布林特信息技术有限公司 Internet hot spots information automatic monitoring method
CN107273534A (en) * 2017-06-29 2017-10-20 武汉楚鼎信息技术有限公司 A kind of data processing method extracted based on information content, system
CN108519980A (en) * 2018-01-31 2018-09-11 广东易联创富集团有限公司 News push method, apparatus, platform, computer readable storage medium
CN109388708B (en) * 2018-06-15 2022-05-31 云天弈(北京)信息技术有限公司 Personalized customized writing system
CN110147439A (en) * 2018-07-18 2019-08-20 中山大学 A kind of news event detecting method and system based on big data processing technique
CN109325860A (en) * 2018-08-29 2019-02-12 中国科学院自动化研究所 Network public-opinion detection method and system for overseas investment Risk-warning
CN109739975B (en) * 2018-11-15 2021-03-09 东软集团股份有限公司 Hot event extraction method and device, readable storage medium and electronic equipment
CN109635103B (en) * 2018-12-17 2022-05-20 北京百度网讯科技有限公司 Abstract generation method and device
CN112231470A (en) * 2019-06-28 2021-01-15 上海智臻智能网络科技股份有限公司 Topic mining method and device, storage medium and terminal
CN113268651B (en) * 2021-05-27 2023-06-06 清华大学 Automatic abstract generation method and device for search information
CN115017345A (en) * 2022-06-28 2022-09-06 上海哔哩哔哩科技有限公司 Multimedia content processing method, device, computing equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101158963A (en) * 2007-10-31 2008-04-09 中兴通讯股份有限公司 Information acquisition processing and retrieval system
CN101751458A (en) * 2009-12-31 2010-06-23 暨南大学 Network public sentiment monitoring system and method
CN102495872A (en) * 2011-11-30 2012-06-13 中国科学技术大学 Method and device for conducting personalized news recommendation to mobile device users

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100299603A1 (en) * 2009-05-22 2010-11-25 Bernard Farkas User-Customized Subject-Categorized Website Entertainment Database

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101158963A (en) * 2007-10-31 2008-04-09 中兴通讯股份有限公司 Information acquisition processing and retrieval system
CN101751458A (en) * 2009-12-31 2010-06-23 暨南大学 Network public sentiment monitoring system and method
CN102495872A (en) * 2011-11-30 2012-06-13 中国科学技术大学 Method and device for conducting personalized news recommendation to mobile device users

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114841155A (en) * 2022-04-21 2022-08-02 科技日报社 Intelligent theme content aggregation method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN102831220A (en) 2012-12-19

Similar Documents

Publication Publication Date Title
CN102831220B (en) Subject-oriented customized news information extraction system
CN102915335B (en) Based on the information correlation method of user operation records and resource content
CN102708096B (en) Network intelligence public sentiment monitoring system based on semantics and work method thereof
CN103226578B (en) Towards the website identification of medical domain and the method for webpage disaggregated classification
CN103365924B (en) A kind of method of internet information search, device and terminal
CN106095979B (en) URL merging processing method and device
KR101695011B1 (en) System for Detecting and Tracking Topic based on Topic Opinion and Social-influencer and Method thereof
CN103139256B (en) A kind of many tenant network public sentiment method for supervising and system
CN106383887A (en) Environment-friendly news data acquisition and recommendation display method and system
CN104537097A (en) Microblog public opinion monitoring system
CN101751458A (en) Network public sentiment monitoring system and method
CN105718587A (en) Network content resource evaluation method and evaluation system
CN101261629A (en) Specific information searching method based on automatic classification technology
CN105808722B (en) Information discrimination method and system
WO2013146736A1 (en) Synonym relation determination device, synonym relation determination method, and program thereof
KR20090000284A (en) Infomedics prevention system
CN104182482A (en) Method for judging news list page and method for screening news list page
CN106649498A (en) Network public opinion analysis system based on crawler and text clustering analysis
CN112685564A (en) Intelligent science and technology policy classification and pushing method and system
TW201721467A (en) Methods and systems for analyzing reading log and documents corresponding thereof
CN106055546A (en) Optical disk library full-text retrieval system based on Lucene
Weber et al. Journalism history, web archives, and new methods for understanding the evolution of digital journalism
CN112035723A (en) Resource library determination method and device, storage medium and electronic device
Luo et al. Query ambiguity identification based on user behavior information
CN103605742A (en) Method and device for recognizing network resource entity content page

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant