CN106294619A - Public sentiment intelligent supervision method - Google Patents
Public sentiment intelligent supervision method Download PDFInfo
- Publication number
- CN106294619A CN106294619A CN201610621688.4A CN201610621688A CN106294619A CN 106294619 A CN106294619 A CN 106294619A CN 201610621688 A CN201610621688 A CN 201610621688A CN 106294619 A CN106294619 A CN 106294619A
- Authority
- CN
- China
- Prior art keywords
- text
- public
- opinion
- public sentiment
- emergency event
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- 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)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of public sentiment intelligent supervision method and public sentiment intelligent monitoring system.Public sentiment intelligent supervision method according to the present invention includes: step S1: utilizes lists of keywords and network public-opinion site list that city emergency event is relevant, obtains network public-opinion text；Step S2: resolve public sentiment text, obtains main body, object object and emergency event signature identification in emergency event；Step S3: main body, object object and emergency event signature identification in emergency event are carried out semantic similarity analysis and assessment, carries out clustering processing, and determines the focus incident classification belonging to network public-opinion text public sentiment text；Step S4: the result exporting clustering processing and the focus incident classification belonging to network public-opinion text determined.With it, can quickly, accurately identify the vocabulary such as the significant strong place name of affair character, name, institution term, and the public sentiment event described in it is carried out more deeply, careful portraying.
Description
Technical field
The present invention relates to networking technology area and language processing techniques field, particularly relate to one and utilize website carriage
The public sentiment intelligent supervision method of feelings text analyzing city emergency event.
Background technology
Along with the development of Web2.0 technology, the digitized new media such as network, mobile phone develops rapidly, and progressively replace newpapers and periodicals,
The traditional media such as broadcast, TV become the Main Means of public information exchange.Network text is issued and the convenience of diffusion also makes
Obtain it in Urban Emergency, critical incident, Mass disturbance, play the significantly more effect added fuel to the flames.Therefore, right
Network public-opinion is rationally supervised and guides, for maintaining social harmony to stablize significant.
Understanding and process currently for Chinese text mainly stay in the keyword extraction comparison stage in text,
Deep understanding and analysis deficiency for text.In other words, existing method cannot be further appreciated by and process described in text
Crucial situation, the most sensitive to the place name mentioned in text, name, institution term, and method effectiveness is easily by text
The noise vocabulary (such as wrong word, meaningless text) of middle appearance disturbs and produces considerable influence.For to comprise daily natural language
Speech exchange is the excavation of main network public-opinion text, and existing method is the most helpless, less with carrying focus in network public-opinion
Event carries out accurately identifying and intelligent supervision.
Therefore, those skilled in the art be devoted to develop one utilize natural language processing technique Intelligent Understanding city should
Urgent thing part is correlated with the technical scheme of public sentiment text.
Summary of the invention
Because the drawbacks described above of prior art, the technical problem to be solved is to provide one and utilizes nature language
Speech treatment technology Intelligent Understanding city emergency event is correlated with the text analyzing method of public sentiment text, and develops a set of corresponding carriage
Feelings supervisory systems, it is possible to the focus incident identified in network public-opinion the most timely and accurately also carries out trend analysis to it.
For achieving the above object, the invention provides a kind of public sentiment intelligent supervision method, including:
Step S1: utilize lists of keywords and network public-opinion site list that city emergency event is relevant, obtain network carriage
Feelings text；
Step S2: resolve public sentiment text, obtains main body, object object and emergency event feature in emergency event
Mark；
Step S3: main body, object object and emergency event signature identification in emergency event are carried out semantic similarity and comments
Estimate analysis, public sentiment text is carried out clustering processing, and determines the focus incident classification belonging to network public-opinion text；
Step S4: the result exporting clustering processing and the focus incident classification belonging to network public-opinion text determined.
As preferably, network public-opinion text includes: the passing newsletter archive relevant to city emergency event and network carriage
Feelings real-time text；Wherein relevant to city emergency event passing newsletter archive is based on web crawlers technical limit spacing, network public-opinion
Real-time text subscribes to technical limit spacing based on RSS.
As preferably, affair character mark includes place name, name and mechanism's name.
As preferably, use name Entities Matching technology based on dictionary to extract described affair character and identify:
By comparison ground thesaurus, people's thesaurus, mechanism's thesaurus, the place name mentioned in extraction newsletter archive, name, group
Loom structure name.
As preferably, after affair character mark being detected, combined with context carry out secondary judgement, specify event
Signature identification.
As preferably, in step s 2, the Chinese text of public sentiment text is carried out word segmentation processing, then utilizes part of speech to divide
Analysis method and syntactic analysis method, extract the crucial letter in the subject composition of every, text words, predicate composition, object component respectively
Cease, and classified finishing is event body, event behavior and event object.
As preferably, in step s3, public sentiment text is carried out clustering processing and includes:
S3.1: the passing newsletter archive cluster relevant to city emergency event；
S3.2: network public-opinion real-time text is compared with each key word clustered and differentiates；
S3.3: network public-opinion real-time text is ranged each cluster.
As preferably, directly carry out the poly-of the passing newsletter archive relevant to city emergency event by search key word
Class, and build the text case library of all kinds of focus incident.
As preferably, in step s3, for the cluster of the network public-opinion real-time text without key word, by calculating net
Network public sentiment real-time text and the semantic similarity of each focus incident text case library, and filtering rule is set, network public-opinion is real
Time text cluster to the most most like focus incident case library, and with the keyword of case library, network public-opinion real-time text is carried out class
Do not mark.
As preferably, in step s 4, export in the way of the semantic model statement of specification the result of clustering processing with
And the focus incident classification belonging to network public-opinion text determined.
The present invention at least has the advantage that
(1) it is only capable of the problem of special key word in structured text that identifies for existing public sentiment text analyzing method, carries
Go out a kind of method based on natural language technology, it is possible to fully understand the semantic information contained in natural language text, and from
In Concept Semantic aspect, incidence relation between text is made assessment.
(2) for existing public sentiment text analyzing method problem low, ropy to massive network public sentiment text-processing efficiency,
Propose the contrast of a kind of combination dictionary and the text mining method of syntactic analysis, it is possible to quickly, accurately identify affair character mark
Property the vocabulary such as strong place name, name, institution term, and the public sentiment event described in it is carried out more deeply, careful quarter
Draw.
(3) for existing public sentiment text analyzing method to focus incident identification and the problem of early warning difficulty, it is proposed that a kind of
Focus incident based on semantic similitude cluster finds and the method for analysis, it is possible to Intelligent Recognition goes out the heat contained in network public-opinion text
The kind of some event, and predict its possible development trend.
Below with reference to accompanying drawing, the technique effect of design, concrete structure and the generation of the present invention is described further, with
It is fully understood from the purpose of the present invention, feature and effect.
Accompanying drawing explanation
Fig. 1 is the flow chart of the public sentiment intelligent supervision method according to one embodiment of the present invention.
Fig. 2 is the display page of the passing newsletter archive relevant to city emergency event according to the concrete example of the present invention.
Fig. 3 is the network public-opinion real-time text display page according to the concrete example of the present invention.
Fig. 4 is the focus incident text case library display page according to the concrete example of the present invention.
It should be noted that accompanying drawing is used for illustrating the present invention, and the unrestricted present invention.Note, represent that the accompanying drawing of structure can
Can be not necessarily drawn to scale.Further, in accompanying drawing, same or like element indicates same or like label.
Detailed description of the invention
In order to overcome existing text analyzing method, the efficiency occurred during network public-opinion text is low, of poor quality etc. asks resolving
Topic, the present invention provides a kind of focus incident identification and the analysis method of language processing techniques of unified with nature targetedly.
Fig. 1 is the flow chart of the public sentiment intelligent supervision method according to one embodiment of the present invention.
As it is shown in figure 1, include according to the public sentiment intelligent supervision method of one embodiment of the present invention:
Step S1: utilize lists of keywords and network public-opinion site list that city emergency event is relevant, obtain network carriage
Feelings text；In the present embodiment, obtain that network public-opinion text can (simple information be gathered based on web crawlers technology and/or RSS
Close, be also Really Simple Syndication) subscription technology, it is possible to use other technologies, the most not
Make concrete restriction.
Such as, network public-opinion text includes: the passing newsletter archive relevant to city emergency event and network public-opinion are real-time
Text.Wherein, relevant to city emergency event passing newsletter archive be typically derived from Baidu's news, Sohu's news, must be new
Domestic each big door news websites such as news, by configuring emergency event key word and search site list, utilize web crawlers skill
Art is disposable, batch type obtains.On the other hand, network public-opinion real-time text derives from the public such as Sina's microblogging, Tengxun's microblogging ginseng
The website higher with degree, by configuring propelling movement site list, utilize RSS subscription technology in real time, increment type obtains.
Step S2: utilize natural language processing technique, carries out deep analysis to public sentiment text, obtains in emergency event main
Body, object object and emergency event signature identification (such as, affair character mark includes place name, name, mechanism's name etc.)；
For in step S2 towards the natural language processing technique of magnanimity public sentiment text library, for the media event collected
Text, first Chinese text to public sentiment text can carry out word segmentation processing, then utilizes part of speech to analyze method and syntactic analysis
Method, extracts the key message in the subject composition of every, text words, predicate composition, object component respectively, and classified finishing is
Event body, event behavior and event object.
For the content information of the abundantest event, the present invention also uses name Entities Matching technology based on dictionary, logical
Cross comparison ground thesaurus, people's thesaurus, mechanism's thesaurus, the place name accurately mentioned in extraction newsletter archive, name, organization
Name, and arrange the signature identification for event.
Concrete, above-mentioned information is carried out formalization, can arrange as event model, i.e. event=< event flag code, thing
Part classification, event body, event object, event behavior, affair character >.
It is also preferred that the left after affair character mark being detected, combined with context secondary judgement can be carried out, clearly extract
Out whether word is affair character mark.Because dividing when, it is possible to occur that ambiguity divides.Such as " in White Cloud Mountain
In the east " in this case, it is possible to mistake can be divided, using this word of Shandong as key word.The function judged by secondary, it is possible to
Avoid the generation of analogue.
Step S3: by main body, object object and emergency event signature identification in emergency event are carried out semantic similitude
Degree analysis and assessment, carry out clustering processing, and determine the focus incident classification belonging to network public-opinion text public sentiment text；
In step s3, public sentiment text is carried out clustering processing to include: the passing news literary composition relevant to city emergency event
This cluster and the cluster of network public-opinion real-time text.
Specifically, the cluster of relevant to city emergency event passing newsletter archive can directly be entered by search key word
OK, the text case library of all kinds of focus incident is built.
For the network public-opinion real-time text without key word, by calculating the language of text and each focus incident text case library
Justice similarity, and filtering rule is set, clustered to most like focus incident case library, and with the keyword pair of case library
Network public-opinion real-time text carries out classification mark.The method using case-based reasioning, to network public-opinion real-time text and passing
Incidence relation between media event text is identified and evaluates such that it is able to identify from network public-opinion real-time text in time
City focus incident also makes rational trend prediction.
Step S4: the result exporting clustering processing and the focus incident classification belonging to network public-opinion text determined.Example
As, in step S4, the result exporting clustering processing in the way of the semantic model statement of specification and the network public-opinion literary composition determined
Focus incident classification belonging to Ben.
In concrete example, such as, build have the relevant passing newsletter archive storehouse of the city emergency event of keyword (as
Shown in Fig. 2) and without the network public-opinion real-time text (as shown in Figure 3) of keyword.Then utilize that the present invention proposes towards sea
The natural language processing technique of amount public sentiment text library, carries out information extraction and whole with the canonical form of event model to every text
Reason.The focus incident based on semantic similitude cluster proposed further according to the present invention finds and the method for analysis, builds as shown in Figure 4
Focus incident text case library, and judge whether network public-opinion real-time text contains the focus incident of respective classes.If identifying
Obtain focus incident, then public sentiment management system sends alarm, reminds supervisor to take Supervision Measures.
Described above illustrate and describes the preferred embodiment of the present invention, as previously mentioned, it should be understood that the present invention is not
It is confined to form disclosed herein, is not to be taken as the eliminating to other embodiments, and can be used for other combinations various, repair
Change and environment, and can be entered by above-mentioned teaching or the technology of association area or knowledge in invention contemplated scope described herein
Row is changed.And the change that those skilled in the art are carried out and change are without departing from the spirit and scope of the present invention, the most all should be in the present invention
In the protection domain of claims.
Claims (10)
1. a public sentiment intelligent supervision method, it is characterised in that comprise the following steps:
S1: utilize lists of keywords and network public-opinion site list that city emergency event is relevant, obtain network public-opinion text；
S2: resolve public sentiment text, obtains main body, object object and emergency event signature identification in emergency event；
S3: main body, object object and emergency event signature identification in emergency event are carried out semantic similarity analysis and assessment is right
Public sentiment text carries out clustering processing, and determines the focus incident classification belonging to network public-opinion text；
S4: the result exporting clustering processing and the focus incident classification belonging to network public-opinion text determined.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that described network public-opinion text includes: with
Passing newsletter archive that city emergency event is relevant and network public-opinion real-time text；Wherein
The passing newsletter archive relevant to city emergency event is based on web crawlers technical limit spacing；Network public-opinion real-time text based on
RSS subscribes to technical limit spacing.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that described affair character mark includes ground
Name, name and mechanism's name.
Public sentiment intelligent supervision method the most according to claim 3, it is characterised in that use name entity based on dictionary
Technology of joining is extracted described affair character and is identified:
By comparison ground thesaurus, people's thesaurus, mechanism's thesaurus, the place name mentioned in extraction newsletter archive, name, tissue machine
Structure name.
Public sentiment intelligent supervision method the most according to claim 4, it is characterised in that after affair character mark being detected,
Combined with context carry out secondary judgement, specify affair character mark.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that in described step S2, to public sentiment literary composition
This Chinese text carries out word segmentation processing, then utilizes part of speech to analyze method and syntactic analysis method, extracts every, text respectively
The subject composition of words, predicate composition, key message in object component, and classified finishing is event body, event behavior and thing
Part object.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that in described step S3, to public sentiment literary composition
Originally carry out clustering processing to comprise the following steps:
S3.1: the passing newsletter archive cluster relevant to city emergency event；
S3.2: network public-opinion real-time text is compared with each key word clustered and differentiates；
S3.3: network public-opinion real-time text is ranged each cluster.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that in described step S3, by search
Key word carries out the cluster of the passing newsletter archive relevant to city emergency event, and builds the text case of all kinds of focus incident
Example storehouse.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that in described step S3, for unrelated
The cluster of the network public-opinion real-time text of keyword, by calculating network public-opinion real-time text and each focus incident text case library
Semantic similarity, arranges filtering rule, by network public-opinion real-time text cluster to most like focus incident case library, and with case
The keyword in example storehouse carries out classification mark to network public-opinion real-time text.
Public sentiment intelligent supervision method the most according to claim 1, it is characterised in that in step s 4, with the semanteme of specification
The mode of model formulation exports the focus incident classification belonging to the result of clustering processing and network public-opinion text.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610621688.4A CN106294619A (en) | 2016-08-01 | 2016-08-01 | Public sentiment intelligent supervision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610621688.4A CN106294619A (en) | 2016-08-01 | 2016-08-01 | Public sentiment intelligent supervision method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106294619A true CN106294619A (en) | 2017-01-04 |
Family
ID=57664046
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610621688.4A Pending CN106294619A (en) | 2016-08-01 | 2016-08-01 | Public sentiment intelligent supervision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294619A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203641A (en) * | 2017-06-19 | 2017-09-26 | 北京易华录信息技术股份有限公司 | A kind of method of the collection of Internet traffic public feelings information and processing |
| CN107784083A (en) * | 2017-09-30 | 2018-03-09 | 北京合力智联科技有限公司 | A kind of automatic identification processing method of network public sentiment information validity |
| CN108804501A (en) * | 2018-04-08 | 2018-11-13 | 深圳市腾讯计算机系统有限公司 | A kind of method and device of detection effective information |
| CN109241438A (en) * | 2018-09-27 | 2019-01-18 | 国家计算机网络与信息安全管理中心 | Across channel focus incident discovery method, apparatus and storage medium based on element |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109446409A (en) * | 2018-09-19 | 2019-03-08 | 杭州安恒信息技术股份有限公司 | A kind of recognition methods of the target object of doubtful multiple level marketing behavior |
| CN109460475A (en) * | 2018-12-13 | 2019-03-12 | 北京百分点信息科技有限公司 | A kind of merging method of similar clue |
| CN109710918A (en) * | 2018-11-26 | 2019-05-03 | 平安科技（深圳）有限公司 | Public sentiment relation recognition method, apparatus, computer equipment and storage medium |
| CN110020052A (en) * | 2017-12-15 | 2019-07-16 | 联易软件有限公司 | Food and medicine data processing method and device |
| CN110889274A (en) * | 2018-08-17 | 2020-03-17 | 北大方正集团有限公司 | Information quality evaluation method, device, equipment and computer readable storage medium |
| CN111160019A (en) * | 2019-12-30 | 2020-05-15 | 中国联合网络通信集团有限公司 | Public opinion monitoring method, device and system |
| US10747771B2 (en) * | 2017-11-30 | 2020-08-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining hot event |
| CN111639183A (en) * | 2020-05-19 | 2020-09-08 | 民生科技有限责任公司 | Financial industry consensus public opinion analysis method and system based on deep learning algorithm |
| CN112199585A (en) * | 2020-09-29 | 2021-01-08 | 黑龙江省网络空间研究中心 | Network public opinion emergent hotspot event discovery method based on data mining technology |
| CN112749269A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Entity public opinion calculation method and system |
| CN114692593A (en) * | 2022-03-21 | 2022-07-01 | 中国刑事警察学院 | Network information safety monitoring and early warning method |
| CN115062107A (en) * | 2022-06-10 | 2022-09-16 | 浙江嘉兴数字城市实验室有限公司 | Social scene automatic identification and inspection plan dynamic generation method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117283A (en) * | 2009-12-30 | 2011-07-06 | 安世亚太科技（北京）有限公司 | Semantic indexing-based data retrieval method |
| CN102207947A (en) * | 2010-06-29 | 2011-10-05 | 天津海量信息技术有限公司 | Direct speech material library generation method |
| CN102207948A (en) * | 2010-07-13 | 2011-10-05 | 天津海量信息技术有限公司 | Method for generating incident statement sentence material base |
| CN102654866A (en) * | 2011-03-02 | 2012-09-05 | 北京百度网讯科技有限公司 | Method and device for establishing example sentence index and method and device for indexing example sentences |
| CN102708096A (en) * | 2012-05-29 | 2012-10-03 | 代松 | Network intelligence public sentiment monitoring system based on semantics and work method thereof |
| CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| KR20150053313A (en) * | 2013-11-07 | 2015-05-18 | 이근직 | Method for a customized information collection and efficient communication |
| CN104820629A (en) * | 2015-05-14 | 2015-08-05 | 中国电子科技集团公司第五十四研究所 | Intelligent system and method for emergently processing public sentiment emergency |
-
2016
- 2016-08-01 CN CN201610621688.4A patent/CN106294619A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117283A (en) * | 2009-12-30 | 2011-07-06 | 安世亚太科技（北京）有限公司 | Semantic indexing-based data retrieval method |
| CN102207947A (en) * | 2010-06-29 | 2011-10-05 | 天津海量信息技术有限公司 | Direct speech material library generation method |
| CN102207948A (en) * | 2010-07-13 | 2011-10-05 | 天津海量信息技术有限公司 | Method for generating incident statement sentence material base |
| CN102654866A (en) * | 2011-03-02 | 2012-09-05 | 北京百度网讯科技有限公司 | Method and device for establishing example sentence index and method and device for indexing example sentences |
| CN102708096A (en) * | 2012-05-29 | 2012-10-03 | 代松 | Network intelligence public sentiment monitoring system based on semantics and work method thereof |
| CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
| CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
| KR20150053313A (en) * | 2013-11-07 | 2015-05-18 | 이근직 | Method for a customized information collection and efficient communication |
| CN104820629A (en) * | 2015-05-14 | 2015-08-05 | 中国电子科技集团公司第五十四研究所 | Intelligent system and method for emergently processing public sentiment emergency |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203641A (en) * | 2017-06-19 | 2017-09-26 | 北京易华录信息技术股份有限公司 | A kind of method of the collection of Internet traffic public feelings information and processing |
| CN107784083A (en) * | 2017-09-30 | 2018-03-09 | 北京合力智联科技有限公司 | A kind of automatic identification processing method of network public sentiment information validity |
| US10747771B2 (en) * | 2017-11-30 | 2020-08-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining hot event |
| CN110020052A (en) * | 2017-12-15 | 2019-07-16 | 联易软件有限公司 | Food and medicine data processing method and device |
| CN108804501A (en) * | 2018-04-08 | 2018-11-13 | 深圳市腾讯计算机系统有限公司 | A kind of method and device of detection effective information |
| CN108804501B (en) * | 2018-04-08 | 2020-12-11 | 深圳市腾讯计算机系统有限公司 | Method and device for detecting effective information |
| CN110889274B (en) * | 2018-08-17 | 2022-02-08 | 北大方正集团有限公司 | Information quality evaluation method, device, equipment and computer readable storage medium |
| CN110889274A (en) * | 2018-08-17 | 2020-03-17 | 北大方正集团有限公司 | Information quality evaluation method, device, equipment and computer readable storage medium |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109299258B (en) * | 2018-09-18 | 2023-07-21 | 平安科技（深圳）有限公司 | Public opinion event detection method, device and equipment |
| CN109446409A (en) * | 2018-09-19 | 2019-03-08 | 杭州安恒信息技术股份有限公司 | A kind of recognition methods of the target object of doubtful multiple level marketing behavior |
| CN109241438A (en) * | 2018-09-27 | 2019-01-18 | 国家计算机网络与信息安全管理中心 | Across channel focus incident discovery method, apparatus and storage medium based on element |
| CN109241438B (en) * | 2018-09-27 | 2022-06-24 | 国家计算机网络与信息安全管理中心 | Element-based cross-channel hot event discovery method and device and storage medium |
| CN109710918A (en) * | 2018-11-26 | 2019-05-03 | 平安科技（深圳）有限公司 | Public sentiment relation recognition method, apparatus, computer equipment and storage medium |
| CN109460475A (en) * | 2018-12-13 | 2019-03-12 | 北京百分点信息科技有限公司 | A kind of merging method of similar clue |
| CN112749269A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Entity public opinion calculation method and system |
| CN111160019A (en) * | 2019-12-30 | 2020-05-15 | 中国联合网络通信集团有限公司 | Public opinion monitoring method, device and system |
| CN111160019B (en) * | 2019-12-30 | 2023-08-15 | 中国联合网络通信集团有限公司 | Public opinion monitoring method, device and system |
| CN111639183A (en) * | 2020-05-19 | 2020-09-08 | 民生科技有限责任公司 | Financial industry consensus public opinion analysis method and system based on deep learning algorithm |
| CN111639183B (en) * | 2020-05-19 | 2023-11-28 | 民生科技有限责任公司 | Financial co-industry public opinion analysis method and system based on deep learning algorithm |
| CN112199585A (en) * | 2020-09-29 | 2021-01-08 | 黑龙江省网络空间研究中心 | Network public opinion emergent hotspot event discovery method based on data mining technology |
| CN114692593A (en) * | 2022-03-21 | 2022-07-01 | 中国刑事警察学院 | Network information safety monitoring and early warning method |
| CN115062107A (en) * | 2022-06-10 | 2022-09-16 | 浙江嘉兴数字城市实验室有限公司 | Social scene automatic identification and inspection plan dynamic generation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106294619A (en) | Public sentiment intelligent supervision method | |
| US10275407B2 (en) | Apparatus and method for executing an automated analysis of data, in particular social media data, for product failure detection | |
| CN106055541B (en) | A kind of news content filtering sensitive words method and system | |
| Srinivasa et al. | Crime base: Towards building a knowledge base for crime entities and their relationships from online news papers | |
| McMinn et al. | Real-time entity-based event detection for twitter | |
| Wang et al. | DUET: Data-driven approach based on latent Dirichlet allocation topic modeling | |
| CN108776671A (en) | A kind of network public sentiment monitoring system and method | |
| CN105389354B (en) | Unsupervised event extraction and sorting technique towards social media text | |
| CN104462053A (en) | Inner-text personal pronoun anaphora resolution method based on semantic features | |
| Alsaedi et al. | Arabic event detection in social media | |
| Tonon et al. | ArmaTweet: detecting events by semantic tweet analysis | |
| CN101751458A (en) | Network public sentiment monitoring system and method | |
| CN103853744B (en) | Deceptive junk comment detection method oriented to user generated contents | |
| Alami et al. | Cybercrime profiling: Text mining techniques to detect and predict criminal activities in microblog posts | |
| CN109408804A (en) | The analysis of public opinion method, system, equipment and storage medium | |
| CN107885883A (en) | A kind of macroeconomy field sentiment analysis method and system based on Social Media | |
| Sharma et al. | Detecting hate speech and insults on social commentary using nlp and machine learning | |
| CN110263169A (en) | A kind of focus incident detection method based on convolutional neural networks and keyword clustering | |
| CN102508830A (en) | Method and system for extracting social network from news document | |
| CN110324273A (en) | A kind of Botnet detection method combined based on DNS request behavior with domain name constitutive characteristic | |
| CN103176984A (en) | Detection method of deceptive rubbish suggestions in user generated contents | |
| CN112883286A (en) | BERT-based method, equipment and medium for analyzing microblog emotion of new coronary pneumonia epidemic situation | |
| CN109543410A (en) | One kind being based on the associated malicious code detecting method of Semantic mapping | |
| CN109857869A (en) | A kind of hot topic prediction technique based on Ap increment cluster and network primitive | |
| CN103679034A (en) | Computer virus analyzing system based on body and virus feature extraction method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |