CN109460922A - A kind of Internet public opinion analysis and aid decision-making system with power industry feature - Google Patents
A kind of Internet public opinion analysis and aid decision-making system with power industry feature Download PDFInfo
- Publication number
- CN109460922A CN109460922A CN201811347367.5A CN201811347367A CN109460922A CN 109460922 A CN109460922 A CN 109460922A CN 201811347367 A CN201811347367 A CN 201811347367A CN 109460922 A CN109460922 A CN 109460922A
- Authority
- CN
- China
- Prior art keywords
- public
- information
- analysis
- opinion
- feelings information
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 77
- 238000012544 monitoring process Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 8
- 238000007405 data analysis Methods 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 5
- 230000004048 modification Effects 0.000 claims description 5
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000003442 weekly effect Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 claims 1
- 238000007418 data mining Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 11
- 238000007726 management method Methods 0.000 description 10
- 238000000034 method Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 241000408659 Darpa Species 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Internet public opinion analysis and aid decision-making system with power industry feature, database server, the analysis of public opinion server for being analyzed collected public feelings information, the storage equipment for storing high risk keyword and public sentiment application module including the information acquisition module for acquiring the public feelings information in power industry related web site and forum, the public feelings information for storing acquisition；Database server is connected with information acquisition module and the analysis of public opinion server respectively, and the analysis of public opinion server is connected with public sentiment application module and storage equipment respectively.The present invention is able to solve the range problem of acquisition information, it solves to press subject classification in terms of the analysis of public opinion, determines the difficulty problem of public opinion distributor information, it is ensured that the accuracy and timeliness of public sentiment, public feelings information is acquired in real time, analyze and is studied and judged, ensure that the depth and range of data mining.
Description
Technical field
It is applied to filter the research field of unrelated webpage, in particular to a kind of tool the present invention relates to best-first search technology
There are the Internet public opinion analysis and aid decision-making system of power industry feature.
Background technique
Strategic requirement with national grid towards " three collection five are big " starts to make the transition, and Guo Wang company will gradually move towards intensive
Change, standardization, scale." three collection five are big " is that the deep summary of development of company and height instruct, and is that company moves towards internationalization one
Flow the only way of enterprise.However, any one change be not it is stranghtforward, all experience is explored, summarizes, improves these
Stage necessarily involves institutional adjustment, function adjustment, specification adjustment, industry in the implementation process of " three collection five are big " development strategy
The comprehensive reforms such as process of being engaged in adjustment, electric power enterprise will draw as the closely bound up enterprise of national lifeblood, big variation
The public opinion reaction for playing social every aspect, especially meet difficulty in change, bottleneck when, it is various suspect, negative will be confused
To, therefore monitor in time, collect, study and judge online public sentiment, it is the important prerequisite correctly to guide public opinion.Only carry out public sentiment work
Work could be that " three collection five are big " smooth carry out of significant development strategy escorts.Current Internet public opinion analysis some on the market are soft
Part has search and analytic function to the public opinion on extensive internet, but be all it is unilateral, it is not deep to go for row
Industry is studied.
Foreign countries are more early to the research starting in terms of natural language processing, have some related scholars and expert all certainly in succession
A series of more effective theory and methods are proposed in terms of grammer, syntax and semantic analysis in right Language Processing.Current ratio
More important meeting and forum has: text retrieval conference, the meeting of information retrieval special interest group, topic detection and tracking meeting etc..Its
In the technology based on Statistical Analysis of Key Words method it is relatively mature, but also have greatly improved sky in terms of validity
Between.A research project from the U.S.: topic detection and tracking (Topic Detection and Tracking, TDT) mentions
A kind of demand that news data stream theme can be judged automatically in the case where no manual intervention is developed out.Researcher starts this
Demand carries out Primary Study, and achieves some initial achievements, including establishing a beforehand research corpus for TDT research,
The content of research includes finding the consistent text fragment of inherent theme, that is, provide one section of continuous data flow (text or language
Sound), allow system to judge the boundary between two events, and the appearance of new events and the reproduction of old affair part can be judged automatically.
Under DARPA support, American National Standard technical research institute (NIST) will hold topic detection and tracking international conference every year,
And carry out corresponding system evaluation.
The main body of country's public sentiment research at present is mainly governmental investigations department, University Scientific Research unit, news media's public sentiment clothes
Business mechanism, software service company and fact-finding organ.The researcher of Peking University and the Computer Department of the Chinese Academy of Science has also carried out this respect
Tracking and research.Multivariate characteristics are presented in public sentiment study on monitoring, and foundation is respectively to the understanding of public sentiment and emphasis, respectively in carriage
There is differentiation in feelings excavation, public sentiment application etc..Common main technology include text cluster, classification, orientation identification,
The content of text messages identification technologies and dynamic chart displaying, business intelligence, database mining etc. such as automatic selection.Subsequent center of gravity
Five basic Tasks are transferred to, including the segmentation task reported towards news broadcast class；Towards oneself know topic with
Track task；Detection task towards unknown topic；To unknown topic correlation between the Detection task and report of relevant report for the first time
Detection task.In recent years, natural language Intelligent treatment is more and more is applied to search and data acquisition, how quickly to have
Effect identification natural language, makes human-computer interaction more smooth, more natural, makes search more intelligent, be it is following need further to explore mesh and
Research.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of ranges for being able to solve acquisition information to ask
Topic, solve the analysis of public opinion in terms of press subject classification, determine the difficulty problem of public opinion distributor information, it is ensured that the accuracy of public sentiment and
The Internet public opinion analysis and aid decision-making system with power industry feature of timeliness.
The purpose of the present invention is achieved through the following technical solutions: a kind of network public-opinion with power industry feature
Analysis and aid decision-making system, including the information collection mould for acquiring the public feelings information in power industry related web site and forum
Block, the database server for storing the public feelings information acquired, the public sentiment for being analyzed collected public feelings information
Analysis server, the storage equipment for storing high risk keyword and public sentiment application module；
Database server is connected with information acquisition module and the analysis of public opinion server respectively, the analysis of public opinion server difference
It is connected with public sentiment application module and storage equipment；
The analysis of public opinion server can automatically generate hot spot public sentiment event according to the temperature of network public-opinion event, and right
The hot spot public sentiment event of generation is tracked；The analysis of public opinion server comprises the following modules:
Fundamental analysis module: webpage is determined according to default rule；
Advanced analysis module: depth analysis is carried out for the model of emphasis website and forum, seeks identical and similar note
Relevance between son, hyperlink and emphasis forum to user name and webpage, carry out emphasis acquisition and related urls all-links are deep
Degree excavates；
TOP analysis module:, provincialism portal website more to website visiting number, industrial sustainability and popular website
It is excavated with forum, is acquired and analyzes for the forum and discussion bar for posting most；For more, the active netizen of number that posts
Emphasis tracking is carried out, for its propagation condition on the internet of the tracking of information of its publication, according to reply, deletion, reprints and closes
System, establishes netizen's public feelings information library, and the information of its publication is paid close attention to；
The public sentiment application module includes following submodule:
Public sentiment monitors portal and manages submodule, for carrying out work navigation, monitoring and statistics, public sentiment monitoring, negative information pipe
Reason, hot information management and information update；
Public feelings information monitoring management submodule carries out early warning to negative public feelings information for identifying to public feelings information；
For extracting keyword and article element in public feelings information automatically, the autoabstract of public feelings information is formed；For public feelings information
Reprinting；The relevant report of public sentiment is analyzed in the form of picture；For carrying out snapshot evidence obtaining；
Public sentiment of classifying manages submodule, and English analyzes public feelings information source, issuing time, type, to emphasis carriage
Feelings information forms public sentiment specialist paper, analyzes its development trend and update status on the internet；
Public sentiment bulletin work management submodule, for automatically generating public sentiment weekly, monthly magazine, bulletin, to acquisition public feelings information
Medium type, publisher, region count, then carry out statistical graph analysis, and export statistical result；
Public feelings information tracks submodule, for the information that public sentiment monitors to be tracked and handled；
System administration submodule, for being managed to classifying rules, user information, user role, user right；
Public sentiment early warning submodule: the rank occurred for public sentiment carries out Classification Management, is higher than pre-set level to risk class
Public feelings information notify public sentiment manager in time；The content and rank of public sentiment early warning are according to the event property and public sentiment of network public-opinion
The real work of manager is preset；Early warning is using the publisher of public feelings information, reply people, distributional region and specified net
Stand and first close keyword frequency of occurrence threshold value, once be more than the threshold value i.e. carry out early warning.
Further, the network public-opinion early warning includes the early warning based on content analysis and the early warning based on numerical analysis；
Early warning based on content analysis: when Early-warning Model is established, forming concern public sentiment and identifiable keyword, into
When row magnanimity public feelings information is searched for, each public feelings information is judged, early warning is issued if there is preset keyword, it is no
Then automatic jump to next public feelings information；
Early warning based on numerical analysis: collected mass data disappear again, after denoising, calculates the heat of public feelings information
Degree and susceptibility, temperature and susceptibility are compared with preset temperature and susceptibility respectively, if the temperature of public feelings information and
Susceptibility is identical as preset value, determines that the public feelings information belongs to hot information, issues early warning；Otherwise it does not operate.
Further, the information acquisition module includes acquiring host for acquiring the text information of text information, is used for
The sound for acquiring the audio-video collection host of audio/video information and the audio/video information of audio-video collection host acquisition being decoded
Video Decoder.
Further, the information acquisition module includes operation layer and data analysis layer double-layer structure；
Operation layer uses three-level thread structure；Level-one thread is master control thread, controls website collecting thread and Meta Search Engine line
The operation of journey, while the configuration modification content of keyword and website is obtained, existing active thread is adjusted at any time；Second level line
Journey is divided into two kinds: one kind is site search thread, is responsible for the webpage information of acquisition and filtering appointed website；Second is Meta Search Engine
Thread is responsible for obtaining related web page by Baidu and Google search；Three-level thread is webpage capture thread, is responsible for passing through network
All the elements of named web page are grabbed in local data base；
Data analysis layer uses Hibernate, is that object is directly handled by Database Mapping, for third level thread dispatching,
Operate correspondence database table.
Further, system further include for show public feelings information public sentiment show equipment, public sentiment show equipment respectively with
The analysis of public opinion server is connected with database server.
Further, the public sentiment early warning submodule is connected with external alert device, and the warning device includes acousto-optic report
Alert device and SMS alarming device, SMS alarming device include wireless communication module and the antenna that is connected on wireless communication module.
The beneficial effects of the present invention are: the present invention can carry out phase according to the information source website and thematic information that user provides
The acquisition of open source information data is closed, and the web data that will acquire is stored to local；The web data of acquisition can be analyzed,
Diversified internet information is normalized by relevant calculating, and is stored；It can be pressed according to user demand
Preset related algorithm may also be combined with manual mode of operation and analyze normalization data, provide and special topic for user
The relevant analysis result of information；The interface of browser mode can be provided for all types of user, in order to which user information is inquired and is operated
And complete relevant system maintenance and audit work.It is able to solve the range problem of acquisition information, solves to press in terms of the analysis of public opinion
Subject classification determines the difficulty problem of public opinion distributor information, it is ensured that the accuracy and timeliness of public sentiment, in real time to public feelings information
It is acquired, analyzes and studies and judges, ensure that the depth and range of data mining.
Detailed description of the invention
Fig. 1 is Internet public opinion analysis and aid decision-making system structural schematic diagram of the invention.
Specific embodiment
Network public-opinion monitoring system of the system architecture based on power industry includes including data acquisition, the analysis of public opinion and public sentiment application
Three main modules, including data acquisition are to utilize the realization pair such as search engine technique, data mining technology and web crawlers technology
The acquisition of data；The analysis of public opinion system is realized by the relevant just negative keyword allusion quotation of power industry, the judgement of public sentiment emotion etc.
Screening and judgement to valuable information are completed in the analysis of public feelings information；Public sentiment application is to pass through useful public feelings information
Web interface and portal website show, and include the analysis of public opinion statistics, public sentiment early warning and Classification Management etc..Pair of public sentiment monitoring
As for media and websites such as webpage, news, forum, discussion bar, blog, microbloggings in internet.With reference to the accompanying drawing furtherly
Bright technical solution of the present invention.
It is based on MVC in terms of technological frame, system is developed under the framework of J2EE more mature at present
Struts framework.Web services are by establishing access and the request mechanism of client, after receiving the service request of user, according to
Different demands calls different processes, to realize the processing to different demands database access.Finally, again by processing result
Back to the page, user is showed, completes the request of user.
Request results are returned by Servlet and JSP technology in presentation layer and show user.In system design,
In order to facilitate the modification in later period, using modular design pattern.When modifying the page, it is only necessary to be carried out to corresponding html
Modification does not need to call Servlet and JSP program again.
This system is developed on the basis of based on Object -Oriented Model tool, MVC pattern and Java technology.
System include and three data application layer, middle layer and user interface layer parts, ensure that system stability and maintain easily.
As shown in Figure 1, a kind of Internet public opinion analysis and aid decision-making system with power industry feature, including for adopting
The information acquisition module of collection power industry related web site and the public feelings information in forum, the number for storing the public feelings information acquired
According to library server, the analysis of public opinion server for being analyzed collected public feelings information, for storing high risk key
The storage equipment and public sentiment application module of word；
Database server is connected with information acquisition module and the analysis of public opinion server respectively, the analysis of public opinion server difference
It is connected with public sentiment application module and storage equipment；
The analysis of public opinion server can automatically generate hot spot public sentiment event according to the temperature of network public-opinion event, and right
The hot spot public sentiment event of generation is tracked；The analysis of public opinion server comprises the following modules:
Fundamental analysis module: webpage is determined according to default rule；For example, analyzing some topic if necessary
The webpage number that occurs in for a period of time in this website, the within a certain period of time the number of visiting people in the region, reply note
Subnumber, the model number selected reply people and access the address ip and the time of people.Since this method is the method based on keyword,
Therefore, it has stronger mining ability to the model and news of keyword appearance, but lacks to the depth of the content of model itself
Weary enough analyses.
Advanced analysis module: depth analysis is carried out for the model of emphasis website and forum, seeks identical and similar note
Relevance between son, hyperlink and emphasis forum to user name and webpage, carry out emphasis acquisition and related urls all-links are deep
Degree excavates；
TOP analysis module:, provincialism portal website more to website visiting number, industrial sustainability and popular website
It is excavated with forum, is acquired and analyzes for the forum and discussion bar for posting most；For more, the active netizen of number that posts
Emphasis tracking is carried out, for its propagation condition on the internet of the tracking of information of its publication, according to reply, deletion, reprints and closes
System, establishes netizen's public feelings information library, and the information of its publication is paid close attention to.
The analysis of public opinion server is mainly used for analyzing the web data that acquisition module obtains, and passes through relevant calculating
Diversified internet information is normalized, and is stored.Storage mode takes two kinds: first is that document form,
Second is that database form.Webpage data a large amount of for early period mainly use document form to store, after analysis
Correlated results carry out database purchase.Data analysis is i.e. according to user demand, by preset related algorithm, crucial moment
It may also be combined with manual mode of operation to analyze normalization data, provide analysis result relevant to thematic information for user.
The public sentiment application module includes following submodule:
Public sentiment monitors portal and manages submodule, for carrying out work navigation, monitoring and statistics, public sentiment monitoring, negative information pipe
Reason, hot information management and information update；
Work navigation: daily public sentiment monitoring is completed in guidance.
Monitoring and statistics: according to day, week, the moon, season statistical monitoring situation.
Public sentiment monitoring: browsing monitoring information.
Negative information management: it by establishing public feelings information susceptibility and just negative dictionary, is issued on automatic identification network
The risk of information.
Hot information: the temperature of public feelings information is automatically analyzed；Public feelings information real-time perfoming monitoring to hot spot, tracks it most
New dynamic.
Information update: updating the update status of forum's other information, and concern user is interested of the same trade or with area
Public feelings information is as reference.
Public feelings information monitoring management submodule carries out early warning to negative public feelings information for identifying to public feelings information；
For extracting keyword and article element in public feelings information automatically, the autoabstract of public feelings information is formed；For public feelings information
Reprinting；The relevant report of public sentiment is analyzed in the form of picture；For carrying out snapshot evidence obtaining；
Public sentiment of classifying manages submodule, and English analyzes public feelings information source, issuing time, type, to emphasis carriage
Feelings information forms public sentiment specialist paper, analyzes its development trend and update status on the internet；
Public sentiment bulletin work management submodule, for automatically generating public sentiment weekly, monthly magazine, bulletin, to acquisition public feelings information
Medium type, publisher, region count, then form the statistical graphs such as cake chart, histogram and analyzed, and to system
Result is counted with the export of the formats such as word, excel；
Public feelings information tracks submodule, for the information that public sentiment monitors to be tracked and handled；
System administration submodule, for being managed to classifying rules, user information, user role, user right；
Public sentiment early warning submodule: the rank occurred for public sentiment carries out Classification Management, is higher than pre-set level to risk class
Public feelings information notify public sentiment manager in time；The content and rank of public sentiment early warning are according to the event property and public sentiment of network public-opinion
The real work of manager is preset；Early warning is using the publisher of public feelings information, reply people, distributional region and specified net
Stand and first close keyword frequency of occurrence threshold value, once be more than the threshold value i.e. carry out early warning.The public sentiment early warning submodule with
External alert device is connected, and the warning device includes combined aural and visual alarm and SMS alarming device, and SMS alarming device includes nothing
Line communication module and the antenna being connected on wireless communication module.Information acquisition module is deposited after acquiring information data from internet
It stores up in database server, stores in equipment and be previously stored with high risk keyword, the analysis of public opinion server will be collected
The high risk keyword stored in data and storage equipment is compared, and is carried out after detecting public sentiment data by warning device
Alarm.
Public sentiment early warning should carry out the prediction and analysis of public feelings information under certain condition first, be herein by public feelings information by
Classify according to the different time, establishes public sentiment model respectively.By the public feelings information of the collected magnanimity of web crawlers, as with
The basic data source of public sentiment processing information.The network public-opinion early warning includes early warning based on content analysis and based on numerical analysis
Early warning；
Early warning based on content analysis: when Early-warning Model is established, forming concern public sentiment and identifiable keyword, into
When row magnanimity public feelings information is searched for, each public feelings information is judged, early warning is issued if there is preset keyword, it is no
Then automatic jump to next public feelings information；
Early warning based on numerical analysis: collected mass data disappear again, after denoising, calculates the heat of public feelings information
Degree and susceptibility, temperature and susceptibility are compared with preset temperature and susceptibility respectively, if the temperature of public feelings information and
Susceptibility is identical as preset value, determines that the public feelings information belongs to hot information, issues early warning；Otherwise it does not operate.
Further, the information acquisition module includes acquiring host for acquiring the text information of text information, is used for
The sound for acquiring the audio-video collection host of audio/video information and the audio/video information of audio-video collection host acquisition being decoded
Video Decoder.
Further, the information acquisition module includes operation layer and data analysis layer double-layer structure；
The information acquisition module uses My SQL database, and Java is aided with database company as basic fundamental
Pond is connect, thread pool, web crawlers, log system, HTML parsing, JAVA object persistence and embedded database re-scheduling carry out structure
At complete framework.Module, which is realized, uses J2EE framework, including operation layer and data analysis layer double-layer structure；
Operation layer uses three-level thread structure；Level-one thread is master control thread, controls website collecting thread and Meta Search Engine line
The operation of journey, while the configuration modification content of keyword and website is obtained, existing active thread is adjusted at any time；Second level line
Journey is divided into two kinds: one kind is site search thread, is responsible for the webpage information of acquisition and filtering appointed website；Second is Meta Search Engine
Thread is responsible for obtaining related web page by Baidu and Google search；Three-level thread is webpage capture thread, is responsible for passing through network
All the elements of named web page are grabbed in local data base；
Data analysis layer uses Hibernate, is that object is directly handled by Database Mapping, for third level thread dispatching,
Operate correspondence database table.
Electric power including data acquisition module is not only able to achieve the information collection to webpage, moreover it is possible to forum, discussion bar, microblogging, news
The acquisition of the related public feelings informations of media such as comment, collecting efficiency is higher, meets the needs of including data acquisition, power industry associated nets
It stands and forum includes electric power News Network, spicy community Sichuan forum, Electricity Information Network etc..
Further, system further include for show public feelings information public sentiment show equipment, public sentiment show equipment respectively with
The analysis of public opinion server is connected with database server.
Further, the public sentiment early warning submodule is connected with external alert device, and the warning device includes acousto-optic report
Alert device and SMS alarming device, SMS alarming device include wireless communication module and the antenna that is connected on wireless communication module.
In terms of overall system design, this system in order to facilitate the use of the user, and considers the software loop based on Windows
Border, takes B/S framework mode, and all operations of the graphical operation interface based on browser, system use graphical operation
Interface is interacted with user, easy to operate, is easy to grasp.Framework mode and network more popular at present in view of B/S
The open source and convenience of programming mode and programming software, the corresponding programming technology for being taken based on Java are realized.System is set
Meter should use modular design method, have certain independence between subsystems.Realize it is stronger it is readable with can
Maintainability is easy to use and safeguards.Part of data acquisition is encoded with java and is realized, Web service program is realized with .net.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill disclosed the technical disclosures can make according to the present invention and various not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (6)
1. a kind of Internet public opinion analysis and aid decision-making system with power industry feature, which is characterized in that including for adopting
The information acquisition module of collection power industry related web site and the public feelings information in forum, the number for storing the public feelings information acquired
According to library server, the analysis of public opinion server for being analyzed collected public feelings information, for storing high risk key
The storage equipment and public sentiment application module of word；
Database server is connected with information acquisition module and the analysis of public opinion server respectively, the analysis of public opinion server respectively with carriage
Feelings application module is connected with storage equipment；
The analysis of public opinion server can automatically generate hot spot public sentiment event according to the temperature of network public-opinion event, and to generation
Hot spot public sentiment event tracked；The analysis of public opinion server comprises the following modules:
Fundamental analysis module: webpage is determined according to default rule；
Advanced analysis module: for emphasis website and forum model carry out depth analysis, seek identical and similar model it
Between relevance, hyperlink and emphasis forum to user name and webpage, carry out emphasis acquisition and related urls all-links depth dig
Pick；
TOP analysis module:, provincialism portal website more to website visiting number, industrial sustainability and popular website and opinion
Altar is excavated, and is acquired and is analyzed for the forum and discussion bar for posting most；For posting, more, the active netizen of number is carried out
Emphasis tracking according to reply, deletion, is reprinted relationship, is built for its propagation condition on the internet of the tracking of information of its publication
Vertical netizen's public feelings information library, pays close attention to the information of its publication；
The public sentiment application module includes following submodule:
Public sentiment monitors portal and manages submodule, for carrying out work navigation, monitoring and statistics, public sentiment monitoring, negative information management, heat
Point information management and information update；
Public feelings information monitoring management submodule carries out early warning to negative public feelings information for identifying to public feelings information；For
The automatic keyword and article element extracted in public feelings information, forms the autoabstract of public feelings information；For turning for public feelings information
It carries；The relevant report of public sentiment is analyzed in the form of picture；For carrying out snapshot evidence obtaining；
Public sentiment of classifying manages submodule, and English analyzes public feelings information source, issuing time, type, believes emphasis public sentiment
Breath forms public sentiment specialist paper, analyzes its development trend and update status on the internet；
Public sentiment bulletin work management submodule, for automatically generating public sentiment weekly, monthly magazine, bulletin, to the matchmaker for obtaining public feelings information
Body type, publisher, region count, and then carry out statistical graph analysis, and export statistical result；
Public feelings information tracks submodule, for the information that public sentiment monitors to be tracked and handled；
System administration submodule, for being managed to classifying rules, user information, user role, user right；
Public sentiment early warning submodule: the rank occurred for public sentiment carries out Classification Management, and the carriage of pre-set level is higher than to risk class
Feelings information notifies public sentiment manager in time；Event property and public sentiment management of the content and rank of public sentiment early warning according to network public-opinion
The real work of person is preset；Early warning use the publisher of public feelings information, reply people, distributional region and appointed website with
And the frequency of occurrence threshold value of keyword is first closed, once it is more than that the threshold value carries out early warning.
2. a kind of Internet public opinion analysis and aid decision-making system with power industry feature according to claim 1,
It is characterized in that, the network public-opinion early warning includes the early warning based on content analysis and the early warning based on numerical analysis；
Early warning based on content analysis: when Early-warning Model is established, forming concern public sentiment and identifiable keyword, is carrying out sea
When measuring public feelings information search, each public feelings information is judged, early warning is issued if there is preset keyword, otherwise certainly
It is dynamic to jump to next public feelings information；
Early warning based on numerical analysis: disappear after weight, denoising to collected mass data, calculate public feelings information temperature and
Temperature and susceptibility are compared with preset temperature and susceptibility by susceptibility respectively, if the temperature and sensitivity of public feelings information
Degree is identical as preset value, determines that the public feelings information belongs to hot information, issues early warning；Otherwise it does not operate.
3. a kind of Internet public opinion analysis and aid decision-making system with power industry feature according to claim 1,
It is characterized in that, the information acquisition module includes acquiring host for acquiring the text information of text information, for acquiring sound view
The audio-video collection host of frequency information and the audio/video decoding that the audio/video information of audio-video collection host acquisition is decoded
Device.
4. a kind of Internet public opinion analysis and aid decision-making system with power industry feature according to claim 1,
It is characterized in that, the information acquisition module includes operation layer and data analysis layer double-layer structure；
Operation layer uses three-level thread structure；Level-one thread is master control thread, controls website collecting thread and Meta Search Engine thread
Operation, while the configuration modification content of keyword and website is obtained, existing active thread is adjusted at any time；Second level thread point
Be two kinds: one kind is site search thread, is responsible for the webpage information of acquisition and filtering appointed website；Second is Meta Search Engine line
Journey is responsible for obtaining related web page by Baidu and Google search；Three-level thread is webpage capture thread, and being responsible for will by network
All the elements of named web page grab in local data base；
Data analysis layer uses Hibernate, is that object is directly handled by Database Mapping, for third level thread dispatching, operation
Correspondence database table.
5. a kind of Internet public opinion analysis and aid decision-making system with power industry feature according to claim 1,
Be characterized in that, system further include for show public feelings information public sentiment show equipment, public sentiment show equipment respectively with the analysis of public opinion
Server is connected with database server.
6. a kind of Internet public opinion analysis and aid decision-making system with power industry feature according to claim 1,
It is characterized in that, the public sentiment early warning submodule is connected with external alert device, and the warning device includes combined aural and visual alarm and short
Believe that warning device, SMS alarming device include wireless communication module and the antenna that is connected on wireless communication module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811347367.5A CN109460922A (en) | 2018-11-13 | 2018-11-13 | A kind of Internet public opinion analysis and aid decision-making system with power industry feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811347367.5A CN109460922A (en) | 2018-11-13 | 2018-11-13 | A kind of Internet public opinion analysis and aid decision-making system with power industry feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109460922A true CN109460922A (en) | 2019-03-12 |
Family
ID=65610312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811347367.5A Pending CN109460922A (en) | 2018-11-13 | 2018-11-13 | A kind of Internet public opinion analysis and aid decision-making system with power industry feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109460922A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096636A (en) * | 2019-05-08 | 2019-08-06 | 上海泰豪迈能能源科技有限公司 | Search engine optimization method, apparatus and electronic equipment |
| CN110263237A (en) * | 2019-05-31 | 2019-09-20 | 精硕科技（北京）股份有限公司 | The acquisition methods and device of public sentiment data |
| CN110705288A (en) * | 2019-09-29 | 2020-01-17 | 武汉海昌信息技术有限公司 | Big data-based public opinion analysis system |
| CN111581500A (en) * | 2020-04-24 | 2020-08-25 | 贵州力创科技发展有限公司 | Network public opinion-oriented data distributed directional storage method and device |
| CN111984786A (en) * | 2020-08-17 | 2020-11-24 | 深圳新闻网传媒股份有限公司 | Intelligent whistle blowing early warning method based on news information and server |
| CN112000889A (en) * | 2020-08-31 | 2020-11-27 | 上海微趣网络科技有限公司 | Information gathering and presenting system |
| CN112214658A (en) * | 2019-07-10 | 2021-01-12 | 武汉朗立创科技有限公司 | Data analysis system based on web crawler |
| CN114357272A (en) * | 2022-01-17 | 2022-04-15 | 安徽恒科信息技术有限公司 | Public opinion handling decision method based on web crawler technology |
| CN114386422A (en) * | 2022-01-14 | 2022-04-22 | 淮安市创新创业科技服务中心 | Intelligent aid decision-making method and device based on enterprise pollution public opinion extraction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN105787064A (en) * | 2016-03-01 | 2016-07-20 | 广州铭诚计算机科技有限公司 | Mining platform establishment method based on big data |
| CN107958322A (en) * | 2017-10-09 | 2018-04-24 | 中国电子科技集团公司第二十八研究所 | A kind of urban network spatial synthesis governing system |
-
2018
- 2018-11-13 CN CN201811347367.5A patent/CN109460922A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408157A (en) * | 2014-12-05 | 2015-03-11 | 四川诚品电子商务有限公司 | Funnel type data gathering, analyzing and pushing system and method for online public opinion |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
| CN105787064A (en) * | 2016-03-01 | 2016-07-20 | 广州铭诚计算机科技有限公司 | Mining platform establishment method based on big data |
| CN107958322A (en) * | 2017-10-09 | 2018-04-24 | 中国电子科技集团公司第二十八研究所 | A kind of urban network spatial synthesis governing system |
Non-Patent Citations (1)
| Title |
|---|
| 冼敏婷: "网络舆情监测系统设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096636A (en) * | 2019-05-08 | 2019-08-06 | 上海泰豪迈能能源科技有限公司 | Search engine optimization method, apparatus and electronic equipment |
| CN110263237A (en) * | 2019-05-31 | 2019-09-20 | 精硕科技（北京）股份有限公司 | The acquisition methods and device of public sentiment data |
| CN112214658A (en) * | 2019-07-10 | 2021-01-12 | 武汉朗立创科技有限公司 | Data analysis system based on web crawler |
| CN110705288A (en) * | 2019-09-29 | 2020-01-17 | 武汉海昌信息技术有限公司 | Big data-based public opinion analysis system |
| CN111581500A (en) * | 2020-04-24 | 2020-08-25 | 贵州力创科技发展有限公司 | Network public opinion-oriented data distributed directional storage method and device |
| CN111984786A (en) * | 2020-08-17 | 2020-11-24 | 深圳新闻网传媒股份有限公司 | Intelligent whistle blowing early warning method based on news information and server |
| CN112000889A (en) * | 2020-08-31 | 2020-11-27 | 上海微趣网络科技有限公司 | Information gathering and presenting system |
| CN114386422A (en) * | 2022-01-14 | 2022-04-22 | 淮安市创新创业科技服务中心 | Intelligent aid decision-making method and device based on enterprise pollution public opinion extraction |
| CN114386422B (en) * | 2022-01-14 | 2023-09-15 | 淮安市创新创业科技服务中心 | Intelligent auxiliary decision-making method and device based on enterprise pollution public opinion extraction |
| CN114357272A (en) * | 2022-01-17 | 2022-04-15 | 安徽恒科信息技术有限公司 | Public opinion handling decision method based on web crawler technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460922A (en) | A kind of Internet public opinion analysis and aid decision-making system with power industry feature | |
| Mehmood et al. | Implementing big data lake for heterogeneous data sources | |
| CN104933093B (en) | The monitoring of regional public sentiment and decision support system (DSS) based on big data and method | |
| CN109658044A (en) | The long APP management system in river and method | |
| Nurwidyantoro et al. | Event detection in social media: A survey | |
| CN110533212A (en) | Urban waterlogging public sentiment monitoring and pre-alarming method based on big data | |
| CN101751458A (en) | Network public sentiment monitoring system and method | |
| CN107229708A (en) | A kind of personalized trip service big data application system and method | |
| CN106407278A (en) | Architecture design system of big data platform | |
| CN106815307A (en) | Public Culture knowledge mapping platform and its use method | |
| 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 | |
| CN110705288A (en) | Big data-based public opinion analysis system | |
| CN103049532A (en) | Method for creating knowledge base engine on basis of sudden event emergency management and method for inquiring knowledge base engine | |
| CN108417274A (en) | Forecast of epiphytotics method, system and equipment | |
| CN111967761A (en) | Monitoring and early warning method and device based on knowledge graph and electronic equipment | |
| CN109754219A (en) | A kind of big data management and analysis platform system based on city management | |
| CN105205048B (en) | A kind of hot word analytic statistics system and method | |
| CN112000929A (en) | Cross-platform data analysis method, system, equipment and readable storage medium | |
| CN117971606B (en) | Log management system and method based on elastic search | |
| Tong et al. | Multimedia network public opinion supervision prediction algorithm based on big data | |
| CN109345293A (en) | A kind of big data information service method and system towards brand electric business | |
| CN110889632B (en) | Data monitoring and analyzing system of company image lifting system | |
| CN111859108A (en) | Public opinion system search word recommendation system | |
| CN110059316A (en) | A kind of dynamic scientific and technological resources semantic analysis based on data perception |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |
|
| RJ01 | Rejection of invention patent application after publication |