CN107330613A - A kind of public sentiment monitoring method, equipment and computer-readable recording medium - Google Patents
A kind of public sentiment monitoring method, equipment and computer-readable recording medium Download PDFInfo
- Publication number
- CN107330613A CN107330613A CN201710514483.0A CN201710514483A CN107330613A CN 107330613 A CN107330613 A CN 107330613A CN 201710514483 A CN201710514483 A CN 201710514483A CN 107330613 A CN107330613 A CN 107330613A
- Authority
- CN
- China
- Prior art keywords
- public sentiment
- configuration
- data source
- clinic
- data
- 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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a kind of public sentiment monitoring method, equipment and computer-readable recording medium, data source is obtained by acquisition layer, then the processing such as page parsing, Chinese word segmentation, just negative identification, keyword extraction, automatic classification, autoabstract and data cleansing are carried out by analysis layer, appraisal result is shown by presentation layer afterwards.Pass through the just negative semantics recognition to network comment content, with reference to the essential information of clinic itself, give clinic and given a mark, while completing the examination ＆ verification auxiliary before reaching the standard grade, manual examination and verification workload can be reduced to a certain extent, while clinic quality of being reached the standard grade to raising company has certain help.
Description
Technical field
The present invention relates to public sentiment monitoring technology field, more particularly to a kind of public sentiment monitoring method, equipment and computer-readable
Storage medium.
Background technology
At present, increasing medical institutions add medical opening and shares service platform, but in order to ensure adding doctor
The service quality of each Xian Shang medical institutions in opening and shares service platform is treated, needs periodically to carry out examination ＆ verification scoring to it.
But, when carrying out examination ＆ verification scoring in each clinic to entering medical opening and shares service platform, all pass through
Manual examination and verification are completed.For different monitoring individuals（Monitoring individual adds each the examining of medical opening and shares service platform
Institute）Between can not make flexible comparative analysis, not for different monitoring individual score-system, it is impossible to in tens thousand of families
Line clinic carries out effective network public-opinion monitoring.
Therefore, prior art has yet to be improved and developed.
The content of the invention
In view of in place of above-mentioned the deficiencies in the prior art, it is an object of the invention to provide a kind of public sentiment monitoring method, equipment
And computer-readable recording medium, it is intended to solve in the prior art for that can not be done between the different monitoring individual in clinic on line
Go out flexible comparative analysis, not for the score-system of different monitoring individual, it is impossible to had for tens thousand of families clinic of reaching the standard grade
The problem of network public-opinion of effect is monitored.
In order to achieve the above object, this invention takes following technical scheme：
A kind of public sentiment monitoring method, wherein, it the described method comprises the following steps：
Data source is obtained by acquisition layer；
The analysis of public opinion is carried out to data source according to positive and negative semantics recognition by analysis layer, corresponding public sentiment score is obtained, and by public sentiment
Score basic score sum corresponding with clinic on line obtains clinic total score on line；
Clinic total score on the line is shown by presentation layer.
The public sentiment monitoring method, wherein, it is described by acquisition layer obtain data source the step of before also include：In configuration layer
Carry out the configuration of public sentiment data acquisition attributes and preserve；Wherein carrying out the configuration of public sentiment data acquisition attributes includes data source configuration, adopts
The regular configuration of collection, keyword configuration, early warning configuration, dimension configuration, distribution configuration and authority configuration.
The public sentiment monitoring method, wherein, it is described by acquisition layer obtain data source the step of include：
Keyword retrieval, data source after being searched for are carried out to data source according to designated key word；
The information gathered included in data source after search is fallen in automatic fitration, obtains automatic duplicate removal data source；
Key element collection is carried out to automatic duplicate removal data source according to designated key word key element, key element gathered data source is obtained；
Key element gathered data source is subjected to distribution storage in acquisition layer.
The public sentiment monitoring method, wherein, it is described that public sentiment point is carried out to data source according to positive and negative semantics recognition by analysis layer
Analysis, obtains corresponding public sentiment score, and it is total by public sentiment score basic score sum corresponding with clinic on line to obtain clinic on line
The step of score, includes：
Data source is carried out successively by analysis layer page parsing, Chinese word segmentation, keyword extraction, automatic classification, autoabstract and
After data cleansing, the first processing data source is obtained；
Positive and negative semantics recognition is carried out to the first processing data source according to text emotion parser, and according to positive and negative semantics recognition pair
Front comment accounting in result is answered to obtain public sentiment score；
Clinic total score on line is obtained by public sentiment score basic score sum corresponding with clinic on line.
The public sentiment monitoring method, wherein, it is described that the first processing data source is carried out just according to text emotion parser
Negative semantics recognition, and commented on according to front in positive and negative semantics recognition correspondence result in the step of accounting obtains public sentiment score, it is described
Text emotion parser includes：
First processing data is converted into vector data according to word frequency；
Weight model is obtained by the corpus for having mark in neural metwork training vector data；
According to the data not being marked in weight model predicted vector data, until completing positive and negative semantics recognition.
The public sentiment monitoring method, wherein, the corpus for having mark in the vector data by neural metwork training is obtained
To in the step of weight model, the corpus includes training set and test set, data total amount and the test of the training set
The ratio between data total amount of collection is more than 4:1.
The public sentiment monitoring method, wherein, it is described the step of show clinic total score on the line by presentation layer after also
Including：
By decision-making level according to public sentiment warning information, offline or comment will be carried out delete in clinic on line corresponding with public sentiment warning information
Remove.
A kind of public sentiment monitoring device, wherein, the public sentiment monitoring device includes processor, memory and communication bus；
The communication bus is used to realize the connection communication between processor and memory；
The processor is used to perform the public sentiment monitoring programme stored in memory, to realize the step of described public sentiment monitoring method
Suddenly.
The public sentiment monitoring device, wherein, it is described by acquisition layer obtain data source the step of before, the processor is also used
In performing the public sentiment monitoring programme to realize following steps：
The configuration of public sentiment data acquisition attributes is carried out in configuration layer and is preserved；Wherein carrying out the configuration of public sentiment data acquisition attributes includes number
Configured according to source, collection rule configuration, keyword configuration, early warning configuration, dimension configuration, distribution configuration and authority configuration.
A kind of computer-readable recording medium, wherein, the computer-readable recording medium storage has one or more
Program, one or more of programs can be by one or more computing device, to realize described public sentiment monitoring method
The step of.
Beneficial effect：Public sentiment monitoring method, equipment and computer-readable recording medium that the present invention is provided, pass through acquisition layer
Obtain data source, then by analysis layer carry out page parsing, Chinese word segmentation, just negative identification, keyword extraction, classify automatically,
Autoabstract and data cleansing etc. are handled, and show appraisal result by presentation layer afterwards.By to the just negative of network comment content
Semantics recognition, with reference to the essential information of clinic itself, gives clinic and is given a mark, while the examination ＆ verification auxiliary before reaching the standard grade is completed, can
To reduce manual examination and verification workload to a certain extent, while clinic quality of being reached the standard grade to raising company has certain help.
Brief description of the drawings
Fig. 1 is the flow chart of public sentiment monitoring method preferred embodiment of the present invention.
The flow chart that Fig. 2 is step S100 in public sentiment monitoring method preferred embodiment of the present invention.
The flow chart that Fig. 3 is step S200 in public sentiment monitoring method preferred embodiment of the present invention.
Fig. 4 is the running environment schematic diagram of public sentiment monitoring programme preferred embodiment of the present invention.
Fig. 5 is the functional block diagram of public sentiment monitoring programme preferred embodiment of the present invention.
Embodiment
The present invention provides a kind of public sentiment monitoring method, equipment and computer-readable recording medium, for make the purpose of the present invention,
Technical scheme and effect are clearer, clear and definite, and the present invention is described in more detail for the embodiment that develops simultaneously referring to the drawings.Should
Understand, specific embodiment described herein only to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 1, being the flow chart of public sentiment monitoring method preferred embodiment of the present invention.As shown in figure 1, described
Public sentiment monitoring method, comprises the following steps：
Step S100, data source obtained by acquisition layer.
In the present embodiment, the acquisition layer is provided in the virtual functions module in server end, and it is exactly from searching that it, which is acted on,
Index is held up（Such as Baidu, Google, 360 search）, microblogging（Such as Sina weibo, Tengxun's microblogging, Sohu's microblogging）, wechat（It is main
If wechat circle of friends, wechat public number etc.）, blog（Such as sina blog）, forum（Such as ends of the earth, cat are flutterred）, know, mhkc
（Mainly Baidu's mhkc）, obtain data source, and the data source to be obtained from these channels in news on internet and comment
It is used as the basis of the analysis of public opinion., it is necessary to which the data source obtained is examined on the line scored with needs in obvious the present embodiment
Related data source, rather than the mass data purposelessly obtained from internet.
For example in internet, related commentary is carried out to clinic A on line in a certain microblogging, then acquisition layer is obtained examines on the line
Institute A related commentary.If in internet, a certain news is referred to sports news and completely irrelevant with clinic A on line, then acquisition layer
The sports news will not be obtained.
Wherein, clinic, which is mainly, on the line that need to be scored adds medical platform on line（Such as ten thousand medical treatment of safety）Institute
Wired upper clinic, each clinic for adding medical platform on line need to be scored as monitoring individual.Certainly, in the present invention
Specific monitoring individual grammatically wrong sentence of the public sentiment monitoring method in application be confined to add the institute of medical platform on line it is wired on
Clinic, extends also to all clinics for being provided with Internet homepage.
Step S200, by analysis layer according to positive and negative semantics recognition to data source carry out the analysis of public opinion, obtain corresponding public sentiment
Score, and clinic total score on line is obtained by public sentiment score basic score sum corresponding with clinic on line.
In the present embodiment, it is positive and negative semantics recognition that topmost processing is carried out to data source by analysis layer, that is, first right
Data source carries out some pretreatments（Such as page analysis, participle, keyword extraction）Afterwards, further according to prestoring in analysis layer
Algorithm all carries out positive and negative semantics recognition to the data source obtained by acquisition layer, by the corresponding result conduct of positive and negative semantics recognition
The result of the analysis of public opinion.It will can more specifically be carried out by the corresponding result of positive and negative semantics recognition after score value conversion directly as carriage
Feelings score, and clinic total score on line is obtained by public sentiment score basic score sum corresponding with clinic on line.
Step S300, clinic total score on the line shown by presentation layer.
In the present embodiment, obtained on line corresponding with clinic on each line after the total score of clinic, not only may be used by analysis layer
Directly to show clinic total score on line by display layer, also rule and Strategic Proposals can be interfered according to the public sentiment early warning pre-set
Rule carries out commenting for clinic not up to standard in clinic in offline processing, or strikethrough to clinic not up to standard in clinic on line
By etc..
It is preferred that, as shown in figure 1, in the public sentiment monitoring method, also including before the step S100：
Step S10, carry out in configuration layer the configuration of public sentiment data acquisition attributes and preserving；Wherein, public sentiment data acquisition attributes are carried out
Configuration includes data source configuration, collection rule configuration, keyword configuration, early warning configuration, dimension configuration, distribution configuration and authority
Configuration.
More specifically, the auto-configuration data source in data source configuration, and can manually increasing and decreasing.
Collection rule configuration in configure public sentiment data collection rule, including collection the frequency, collection duration, the acquisition granularity,
Gather temperature.
Can human configuration news keyword and public sentiment comment keyword in keyword configuration.
Early warning configuration in can human configuration public sentiment early warning mode（Short message, system message, mail etc.）, scope, object
And the frequency.
Can the thematic dimension of human configuration public sentiment, brand influence dimension, strategic direction dimension in dimension configuration.
Can the different types of public sentiment distribution of human configuration in distribution configuration（Mail）Scope, object and the frequency.
In authority configuration can human configuration public sentiment monitoring system actor authority.
It can be seen that, carry out various with postponing, could accurately have been obtained by acquisition layer according to configuration information in configuration layer
Data source is taken, to realize the accurate monitoring to public sentiment.
It is preferred that, as shown in Fig. 2 in the public sentiment monitoring method, the step S100 includes：
Step S101, according to designated key word to data source carry out keyword retrieval, data source after being searched for；
The information gathered included in data source after search is fallen in step S102, automatic fitration, obtains automatic duplicate removal data
Source；
Step S103, according to designated key word key element to automatic duplicate removal data source carry out key element collection, obtain key element gathered data
Source；
Step S104, by key element gathered data source acquisition layer carry out distribution storage.
In the present embodiment, acquisition layer first obtains data according to the configuration of the public sentiment data acquisition attributes of configuration layer from internet
Source, performs following steps afterwards：
1）Keyword search：I.e. according to the automatic search summary in data source of the keyword of configuration or in full；
2）Automatic duplicate removal：Ignore the information gathered automatically；
3）Key element is gathered：Retrofit is carried out automatically according to key elements such as industry, address, mechanism name, brand name, ProductNames；
4）Distributed storage：Distribution storage is carried out to data, it is ensured that the efficiency that data are extracted.
Above-mentioned 1）Correspondence step S101,2）Correspondence step S102,3）Correspondence step S103,4）Correspondence step S104.Adopting
Carried out in collection layer after above-mentioned four step datas processing, data source just can be more accurately obtained from internet.
It is preferred that, as shown in Fig. 2 in the public sentiment monitoring method, the step S200 includes：
Step S201, by analysis layer data source is carried out successively page parsing, Chinese word segmentation, keyword extraction, automatic classification, from
After dynamic summary and data cleansing, the first processing data source is obtained；
Step S202, positive and negative semantics recognition carried out to the first processing data source according to text emotion parser, and according to positive and negative
Front comment accounting obtains public sentiment score in semantics recognition correspondence result；
Step S203, clinic total score on line obtained by public sentiment score basic score sum corresponding with clinic on line.
For example, the comment on clinic A on line that acquisition layer is obtained from internet there are 5 webpages, page parsing is carried out
After obtain following 5：
First：Clinic A doctor's level is very high；
Article 2：Clinic A medical level is pretty good；
Article 3：Clinic A doctor XXX is alive Huatuo；
Article 4：Remote diagnosis result inside the A of clinic is very accurate；
Article 5：Doctor's level inside the A of clinic is very poor.
Chinese word segmentation is carried out to above-mentioned five comments on clinic A on line and keyword extraction is respectively obtained：
First：Clinic A, level are very high；
Article 2：Clinic A, level are pretty good；
Article 3：Clinic A, alive Huatuo；
Article 4：Clinic A, remote diagnosis, result are accurate；
Article 5：Clinic A, level are very poor.
By above-mentioned five in clinic A comment on line, by level is very high, level is pretty good, alive Huatuo, result it is accurate
Automatically be divided into the first kind, by level it is very poor it is automatic be divided into Equations of The Second Kind, and to the autoabstract of first kind correspondence preferably, to second
Above-mentioned data are screened, merged and after privacy handles to be poor by class correspondence autoabstract again, obtain the first processing data
Source.
It can be assumed that level is very high, level is pretty good according to text emotion parser, alive Huatuo, result are accurately front
Comment, and it is negative reviews that level is very poor.Now the accounting 80% of front comment can be multiplied by 100 as public sentiment score, and will be with
The A corresponding summations of basic score 80 in clinic obtain clinic total score 160 on line on line.When it is implemented, can be set on a line
Clinic total score acceptance line（Such as 150 points）, and by clinic total score on line exceed make on line on the line of clinic total score acceptance line
Clinic, continuation holding, which is reached the standard grade, is runed.
More specifically, the text emotion parser in the step S202 includes following process step：
First processing data is converted into vector data according to word frequency；
Weight model is obtained by the corpus for having mark in neural metwork training vector data；
According to the data not being marked in weight model predicted vector data, until completing positive and negative semantics recognition.
For the ease of carrying out data mining, it is necessary to the first processing data is converted into vector data according to word frequency, by this
Vector data is to assess significance level of the word for a field file set in a file or a corpus.Tool
Body, being converted into vector data according to word frequency can be according to TFARC (term frequency-based ARC) this text classification
Algorithm is carried out.
By obtaining comment of the network user to clinic, commented on by a manual examination and verification processing part and mark just negative star
Level, is used as training, 3 stars and the above are taken as positive comment using the comment as tagged corpus（For example by level is very high, water
It is 3 stars to put down good, alive Huatuo, result accurate marker）, 1 star and 2 stars are taken as negative reviews（For example by the very poor mark of level
It is designated as 1 star or 2 stars）, that is to say and weight model is obtained by the corpus for having mark in neural metwork training vector data.
Wherein, tagged corpus is divided into training set and test set, training set is just negative each 5,000 comments, test set
For just negative each 1,000 comments.
The text emotion parser is to be based on Recognition with Recurrent Neural Network（RNN）And shot and long term memory models（LSTM）One
Plant algorithm.
In traditional neural network model, it, again to output layer from input layer to hidden layer, is to connect entirely between layers to be
Connect, and can just be connected between only adjacent layer, and the node between every layer is connectionless.This is being carried out at natural language
Reason（NLP）It is more weak during related task, for example, you will predict that what next word of sentence is, generally requires and uses
Word above, because word is not independent before and after in a sentence.
It is also relevant with output above why RNN is referred to as the output of circulation neural network, i.e., one sequence currently.Specifically
The form of expression information above can be remembered and be applied in the calculating currently exported for network, i.e., between hidden layer
Node is no longer connectionless but has connection, and not only the output including input layer also includes last moment for the input of hidden layer
The output of hidden layer.LSTM is a kind of RNN specific types, can learn long-term Dependency Specification.
In the text emotion parser, the corpus includes training set and test set, the training set
The ratio between data total amount and the data total amount of test set are more than 4:1.Tagged corpus is divided into training set and test set, training set is
Just negative each 5,000 comments, test set is just negative each 1,000 comments.By training, test accuracy rate reaches high level.
It is preferred that, in the public sentiment monitoring method, also include in the step S300：Shown and public sentiment point by presentation layer
Analyse corresponding hot news information, classification rating information, statistical graph information, public sentiment thematic information, public sentiment managing detailed catalogue, competition
Comparative information, industrial trend information, brand analysis information, public sentiment report information, public sentiment distribution information and public sentiment warning information.
Wherein, hot news information shows the hot news general view newest on clinic on line；
Classify rating information according to parser, the attributive classification of automatic mark public sentiment（Front, negative, neutrality）And rank；
Statistical graph information provides public sentiment statistics and ranks chart, including negative public sentiment seniority among brothers and sisters, positive public sentiment seniority among brothers and sisters, public sentiment are totally divided
Cloth, early warning public sentiment trend etc.；
Public sentiment thematic information is according to the thematic public sentiment of configuration displaying, tracking change；
Public sentiment managing detailed catalogue shows news public sentiment or comments on issuing time, summary, source of public sentiment etc., and can check original text；
Compete the news report volume contrast of comparative information displaying rival；
Industrial trend automatic acquisition of scientific information industrial hot spot information, and can human-edited, displaying trend analysis；
Brand analysis information is automatically analyzed according to configuration, and can human-edited, displaying brand influence radar map；
Public sentiment report information can human-edited's the analysis of public opinion, with reference to statistical graph, automatically generate public sentiment daily paper, weekly, monthly magazine；
Public sentiment distributes information and distributes different types of public feelings information according to configuration, automatically generates title, summary and links, and supports
Human-edited；
Public sentiment warning information shows early warning public sentiment general view, and carries out pre-alert notification according to configuration is automatic.
It is preferred that, in the public sentiment monitoring method, also include after step S300：
Step S400, by decision-making level according to public sentiment warning information, will on line corresponding with public sentiment warning information clinic carry out it is offline
Or comment is deleted.
Wherein, Strategic Proposals can be also carried out in step S400, i.e., strategic direction and realization are automatically analyzed according to configuration, and can
Human-edited advises.
It can be seen that, public sentiment monitoring method of the present invention by the just negative semantics recognition to data source, with reference to clinic from
The essential information of body, gives clinic and is given a mark, and manual examination and verification workload is reduced to a certain extent.And it is used as carriage by giving a mark
The index of feelings monitoring, realizes the network public-opinion monitoring to clinic on magnanimity line.
Based on above-mentioned public sentiment monitoring method, present invention also offers a kind of public sentiment monitoring device.As shown in figure 4, the carriage
Feelings monitoring device includes processor 11, memory 12 and communication bus；
The communication bus is used to realize the connection communication between processor and memory；
The processor is used to perform the public sentiment monitoring programme stored in memory, to realize following steps：
Data source is obtained by acquisition layer；
The analysis of public opinion is carried out to data source according to positive and negative semantics recognition by analysis layer, corresponding public sentiment score is obtained, and by public sentiment
Score basic score sum corresponding with clinic on line obtains clinic total score on line；
Clinic total score on the line is shown by presentation layer.
In the present embodiment, described public sentiment monitoring programme 10 is installed and run in electronic installation 1.The electronic installation
1 can be the computing devices such as desktop PC, notebook, palm PC and server.The electronic installation 1 may include, but not
It is only limitted to, memory 11, processor 12 and display 13.Fig. 4 illustrate only the electronic installation 1 with component 11-13, but should
What is understood is, it is not required that implement all components shown, the more or less component of the implementation that can be substituted.
The memory 11 can be the internal storage unit of the electronic installation 1, such as electricity in certain embodiments
The hard disk or internal memory of sub-device 1.The memory 11 can also be that the outside of the electronic installation 1 is deposited in further embodiments
Store up the plug-in type hard disk being equipped with equipment, such as described electronic installation 1, intelligent memory card（Smart Media Card, SMC）,
Secure digital（Secure Digital, SD）Card, flash card（Flash Card）Deng.Further, the memory 11 may be used also
With internal storage unit both including the electronic installation 1 or including External memory equipment.The memory 11, which is used to store, pacifies
Application software and Various types of data loaded on the electronic installation 1, such as the program code of the public sentiment monitoring programme 10.It is described
Memory 11 can be also used for temporarily storing the data that has exported or will export.
The processor 12 can be a central processing unit in certain embodiments（Central Processing Unit,
CPU）, microprocessor or other data processing chips, the program code stored for running in the memory 11 or processing number
According to such as performing the public sentiment monitoring programme 10.
The display 13 can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display in certain embodiments
And OLED（Organic Light-Emitting Diode, Organic Light Emitting Diode）Touch device etc..The display 13 is used
In being shown in the information that is handled in the electronic installation 1 and for showing visual user interface, such as application menu circle
Face, application icon interface etc..The part 11-13 of the electronic installation 1 is in communication with each other by system bus.
Referring to Fig. 5, being the functional block diagram that the present invention installs the preferred embodiment of public sentiment monitoring programme 10.In the present embodiment
In, described public sentiment monitoring programme 10 includes at least one computer program instructions section, and computer program instructions section is based on each
The function that part is realized is different, is segmented into one or more modules, and one or more of modules are stored in described deposit
In reservoir 11, and by one or more processors（The present embodiment is the processor 12）It is performed, to complete each reality of the application
Apply the public sentiment monitoring method of example.For example, in Figure 5, described public sentiment monitoring programme 10 includes acquisition layer module 21, analysis layer mould
Block 22 and presentation layer module 23；Wherein, acquisition layer module 21 is used to obtain data；Analysis layer module 22 is used for when according to positive and negative language
Justice identification carries out the analysis of public opinion to data source, obtains corresponding public sentiment score, and by public sentiment score base corresponding with clinic on line
Plinth score sum obtains clinic total score on line；Presentation layer module 23, for showing clinic total score on the line.
These modules are performed by processor 12, so as to realize following steps：
Data source is obtained by acquisition layer；
The analysis of public opinion is carried out to data source according to positive and negative semantics recognition by analysis layer, corresponding public sentiment score is obtained, and by public sentiment
Score basic score sum corresponding with clinic on line obtains clinic total score on line；
Clinic total score on the line is shown by presentation layer.Implement identical with embodiment above, will not be repeated here.
Also include before the step of acquisition data source by acquisition layer：Public sentiment data acquisition attributes are carried out in configuration layer to match somebody with somebody
Put and preserve；Wherein carry out the configuration of public sentiment data acquisition attributes include data source configuration, collection rule configuration, keyword configure,
Early warning configuration, dimension configuration, distribution configuration and authority configuration.Implement it is identical with embodiment above, herein no longer go to live in the household of one's in-laws on getting married
State.
The step of acquisition data source by acquisition layer, includes：
Keyword retrieval, data source after being searched for are carried out to data source according to designated key word；
The information gathered included in data source after search is fallen in automatic fitration, obtains automatic duplicate removal data source；
Key element collection is carried out to automatic duplicate removal data source according to designated key word key element, key element gathered data source is obtained；
Key element gathered data source is subjected to distribution storage in acquisition layer.Implement it is identical with embodiment above, herein no longer
Repeat.
It is described that the analysis of public opinion is carried out to data source according to positive and negative semantics recognition by analysis layer, corresponding public sentiment score is obtained,
And include the step of obtain clinic total score on line by public sentiment score basic score sum corresponding with clinic on line：
Data source is carried out successively by analysis layer page parsing, Chinese word segmentation, keyword extraction, automatic classification, autoabstract and
After data cleansing, the first processing data source is obtained；
Positive and negative semantics recognition is carried out to the first processing data source according to text emotion parser, and according to positive and negative semantics recognition pair
Front comment accounting in result is answered to obtain public sentiment score；
Clinic total score on line is obtained by public sentiment score basic score sum corresponding with clinic on line.Implement with above
Embodiment is identical, will not be repeated here.
It is described that positive and negative semantics recognition is carried out to the first processing data source according to text emotion parser, and according to positive and negative language
In the step of front comment accounting obtains public sentiment score in justice identification correspondence result, the text emotion parser includes：
First processing data is converted into vector data according to word frequency；
Weight model is obtained by the corpus for having mark in neural metwork training vector data；
According to the data not being marked in weight model predicted vector data, until completing positive and negative semantics recognition.Implement with
Embodiment above is identical, will not be repeated here.
It is described in the step of corpus for having mark in the vector data by neural metwork training obtains weight model
Corpus includes training set and test set, and the ratio between the data total amount of the training set and the data total amount of test set are more than 4:1.
Implement identical with embodiment above, will not be repeated here.
It is described the step of show clinic total score on the line by presentation layer after also include：
By decision-making level according to public sentiment warning information, offline or comment will be carried out delete in clinic on line corresponding with public sentiment warning information
Remove.Implement identical with embodiment above, will not be repeated here.
Based on above-mentioned public sentiment monitoring method, present invention also offers a kind of computer-readable recording medium.The computer
Readable storage medium storing program for executing is stored with one or more program, and one or more of programs can be by one or more processor
Perform, the step of to realize described public sentiment monitoring method.
In summary, a kind of public sentiment monitoring method provided by the present invention, equipment and computer-readable recording medium, pass through
Acquisition layer obtains data source, then carries out page parsing, Chinese word segmentation, just negative identification, keyword extraction, automatically by analysis layer
The processing such as classification, autoabstract and data cleansing, shows appraisal result by presentation layer afterwards.By to network comment content just
Negative semantics recognition, with reference to the essential information of clinic itself, gives clinic and is given a mark, while it is auxiliary to complete the examination ＆ verification before reaching the standard grade
Help, manual examination and verification workload can be reduced to a certain extent, while clinic quality of being reached the standard grade to raising company has certain help.
It is understood that for those of ordinary skills, can be with technique according to the invention scheme and this hair
Bright design is subject to equivalent substitution or change, and all these changes or replacement should all belong to the guarantor of appended claims of the invention
Protect scope.
Claims (10)
1. a kind of public sentiment monitoring method, it is characterised in that the described method comprises the following steps：
Data source is obtained by acquisition layer；
The analysis of public opinion is carried out to data source according to positive and negative semantics recognition by analysis layer, corresponding public sentiment score is obtained, and by public sentiment
Score basic score sum corresponding with clinic on line obtains clinic total score on line；
Clinic total score on the line is shown by presentation layer.
2. public sentiment monitoring method according to claim 1, it is characterised in that it is described the step of obtain data source by acquisition layer it
It is preceding also to include：The configuration of public sentiment data acquisition attributes is carried out in configuration layer and is preserved；Wherein carry out public sentiment data acquisition attributes configuration
Including data source configuration, collection rule configuration, keyword configuration, early warning configuration, dimension configuration, distribution configuration and authority configuration.
3. public sentiment monitoring method according to claim 1 or claim 2, it is characterised in that the step that data source is obtained by acquisition layer
Suddenly include：
Keyword retrieval, data source after being searched for are carried out to data source according to designated key word；
The information gathered included in data source after search is fallen in automatic fitration, obtains automatic duplicate removal data source；
Key element collection is carried out to automatic duplicate removal data source according to designated key word key element, key element gathered data source is obtained；
Key element gathered data source is subjected to distribution storage in acquisition layer.
4. public sentiment monitoring method according to claim 1 or claim 2, it is characterised in that described to be known by analysis layer according to positive and negative semanteme
It is other that the analysis of public opinion is carried out to data source, obtain corresponding public sentiment score, and by public sentiment score it is corresponding with clinic on line it is basic must
/ and include the step of obtain clinic total score on line：
Data source is carried out successively by analysis layer page parsing, Chinese word segmentation, keyword extraction, automatic classification, autoabstract and
After data cleansing, the first processing data source is obtained；
Positive and negative semantics recognition is carried out to the first processing data source according to text emotion parser, and according to positive and negative semantics recognition pair
Front comment accounting in result is answered to obtain public sentiment score；
Clinic total score on line is obtained by public sentiment score basic score sum corresponding with clinic on line.
5. public sentiment monitoring method according to claim 4, it is characterised in that it is described according to text emotion parser to first
Processing data source carries out positive and negative semantics recognition, and obtains public sentiment according to front comment accounting in positive and negative semantics recognition correspondence result and obtain
In the step of dividing, the text emotion parser includes：
First processing data is converted into vector data according to word frequency；
Weight model is obtained by the corpus for having mark in neural metwork training vector data；
According to the data not being marked in weight model predicted vector data, until completing positive and negative semantics recognition.
6. public sentiment monitoring method according to claim 5, it is characterised in that in the vector data by neural metwork training
In the step of corpus for having mark obtains weight model, the corpus includes training set and test set, the training set
Data total amount and the ratio between the data total amount of test set be more than 4:1.
7. public sentiment monitoring method according to claim 4, it is characterised in that described to show that clinic is total on the line by presentation layer
Also include after the step of score：
By decision-making level according to public sentiment warning information, offline or comment will be carried out delete in clinic on line corresponding with public sentiment warning information
Remove.
8. a kind of public sentiment monitoring device, it is characterised in that it is total that the public sentiment monitoring device includes processor, memory and communication
Line；
The communication bus is used to realize the connection communication between processor and memory；
The processor is used to perform the public sentiment monitoring programme stored in memory, to realize such as any one of claim 1-7 institutes
The step of public sentiment monitoring method stated.
9. public sentiment monitoring device according to claim 8, it is characterised in that it is described the step of obtain data source by acquisition layer it
Before, the processor is additionally operable to perform the public sentiment monitoring programme to realize following steps：
The configuration of public sentiment data acquisition attributes is carried out in configuration layer and is preserved；Wherein carrying out the configuration of public sentiment data acquisition attributes includes number
Configured according to source, collection rule configuration, keyword configuration, early warning configuration, dimension configuration, distribution configuration and authority configuration.
10. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be by one or more computing device, to realize that claim 1-7 such as appoints
The step of public sentiment monitoring method described in one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710514483.0A CN107330613A (en) | 2017-06-29 | 2017-06-29 | A kind of public sentiment monitoring method, equipment and computer-readable recording medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710514483.0A CN107330613A (en) | 2017-06-29 | 2017-06-29 | A kind of public sentiment monitoring method, equipment and computer-readable recording medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107330613A true CN107330613A (en) | 2017-11-07 |
Family
ID=60198266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710514483.0A Pending CN107330613A (en) | 2017-06-29 | 2017-06-29 | A kind of public sentiment monitoring method, equipment and computer-readable recording medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330613A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133017A (en) * | 2017-12-21 | 2018-06-08 | 广州市申迪计算机系统有限公司 | A kind of multi-data source acquisition configuration method and device |
| CN108256005A (en) * | 2018-01-02 | 2018-07-06 | 深圳壹账通智能科技有限公司 | Internet product monitoring method and terminal device |
| CN108304452A (en) * | 2017-12-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Article processing method and processing device, storage medium |
| CN108647249A (en) * | 2018-04-18 | 2018-10-12 | 平安科技（深圳）有限公司 | Public sentiment data prediction technique, device, terminal and storage medium |
| CN108846547A (en) * | 2018-05-06 | 2018-11-20 | 成都信息工程大学 | A kind of Enterprise Credit Risk Evaluation method of dynamic adjustment |
| CN108959479A (en) * | 2018-06-21 | 2018-12-07 | 成都睿码科技有限责任公司 | A kind of event sensibility classification method based on text similarity |
| CN109145216A (en) * | 2018-08-29 | 2019-01-04 | 中国平安保险(集团)股份有限公司 | Network public-opinion monitoring method, device and storage medium |
| CN109325161A (en) * | 2018-09-11 | 2019-02-12 | 五八有限公司 | Public sentiment data grasping means, device, equipment and storage medium |
| CN109376287A (en) * | 2018-09-21 | 2019-02-22 | 平安科技（深圳）有限公司 | House property map construction method, device, computer equipment and storage medium |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN109635072A (en) * | 2018-11-12 | 2019-04-16 | 平安科技（深圳）有限公司 | Public sentiment data distributed storage method, device, storage medium and terminal device |
| CN110134849A (en) * | 2019-05-20 | 2019-08-16 | 瑞森网安(福建)信息科技有限公司 | A kind of network public-opinion monitoring method and system |
| CN110134765A (en) * | 2019-05-05 | 2019-08-16 | 杭州师范大学 | A kind of dining room user comment analysis system and method based on sentiment analysis |
| CN110727850A (en) * | 2019-09-19 | 2020-01-24 | 浙江善政科技有限公司 | Network information filtering method, computer readable storage medium and mobile terminal |
| CN111080067A (en) * | 2019-11-18 | 2020-04-28 | 精硕科技（北京）股份有限公司 | Speaker commercial value evaluation method, storage medium and device |
| CN111078879A (en) * | 2019-12-09 | 2020-04-28 | 北京邮电大学 | Method and device for detecting text sensitive information of satellite internet based on deep learning |
| CN111125548A (en) * | 2019-12-31 | 2020-05-08 | 北京金堤科技有限公司 | Public opinion supervision method and device, electronic equipment and storage medium |
| CN111950717A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Public opinion quantification method based on neural network |
| CN113158669A (en) * | 2021-04-28 | 2021-07-23 | 河北冀联人力资源服务集团有限公司 | Method and system for identifying positive and negative comments of employment platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105373887A (en) * | 2015-11-12 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Quality evaluation method and system for terminal application |
| CN106127507A (en) * | 2016-06-13 | 2016-11-16 | 四川长虹电器股份有限公司 | A kind of commodity the analysis of public opinion method and system based on user's evaluation information |
| CN106777040A (en) * | 2016-12-09 | 2017-05-31 | 厦门大学 | A kind of across media microblogging the analysis of public opinion methods based on feeling polarities perception algorithm |
-
2017
- 2017-06-29 CN CN201710514483.0A patent/CN107330613A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105373887A (en) * | 2015-11-12 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Quality evaluation method and system for terminal application |
| CN106127507A (en) * | 2016-06-13 | 2016-11-16 | 四川长虹电器股份有限公司 | A kind of commodity the analysis of public opinion method and system based on user's evaluation information |
| CN106777040A (en) * | 2016-12-09 | 2017-05-31 | 厦门大学 | A kind of across media microblogging the analysis of public opinion methods based on feeling polarities perception algorithm |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304452A (en) * | 2017-12-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Article processing method and processing device, storage medium |
| CN108133017A (en) * | 2017-12-21 | 2018-06-08 | 广州市申迪计算机系统有限公司 | A kind of multi-data source acquisition configuration method and device |
| CN108256005A (en) * | 2018-01-02 | 2018-07-06 | 深圳壹账通智能科技有限公司 | Internet product monitoring method and terminal device |
| CN108647249A (en) * | 2018-04-18 | 2018-10-12 | 平安科技（深圳）有限公司 | Public sentiment data prediction technique, device, terminal and storage medium |
| WO2019200786A1 (en) * | 2018-04-18 | 2019-10-24 | 平安科技（深圳）有限公司 | Method for forecasting public sentiment data, device, terminal, and storage medium |
| CN108846547A (en) * | 2018-05-06 | 2018-11-20 | 成都信息工程大学 | A kind of Enterprise Credit Risk Evaluation method of dynamic adjustment |
| CN108959479A (en) * | 2018-06-21 | 2018-12-07 | 成都睿码科技有限责任公司 | A kind of event sensibility classification method based on text similarity |
| CN108959479B (en) * | 2018-06-21 | 2022-03-25 | 成都睿码科技有限责任公司 | Event emotion classification method based on text similarity |
| CN109145216A (en) * | 2018-08-29 | 2019-01-04 | 中国平安保险(集团)股份有限公司 | Network public-opinion monitoring method, device and storage medium |
| CN109145216B (en) * | 2018-08-29 | 2023-08-25 | 中国平安保险(集团)股份有限公司 | Network public opinion monitoring method, device and storage medium |
| CN109325161A (en) * | 2018-09-11 | 2019-02-12 | 五八有限公司 | Public sentiment data grasping means, device, equipment and storage medium |
| CN109376287B (en) * | 2018-09-21 | 2023-09-01 | 平安科技（深圳）有限公司 | House property map construction method, device, computer equipment and storage medium |
| CN109376287A (en) * | 2018-09-21 | 2019-02-22 | 平安科技（深圳）有限公司 | House property map construction method, device, computer equipment and storage medium |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN109635072A (en) * | 2018-11-12 | 2019-04-16 | 平安科技（深圳）有限公司 | Public sentiment data distributed storage method, device, storage medium and terminal device |
| CN110134765A (en) * | 2019-05-05 | 2019-08-16 | 杭州师范大学 | A kind of dining room user comment analysis system and method based on sentiment analysis |
| CN110134849A (en) * | 2019-05-20 | 2019-08-16 | 瑞森网安(福建)信息科技有限公司 | A kind of network public-opinion monitoring method and system |
| CN110727850B (en) * | 2019-09-19 | 2023-04-28 | 浙江善政科技有限公司 | Network information filtering method, computer readable storage medium and mobile terminal |
| CN110727850A (en) * | 2019-09-19 | 2020-01-24 | 浙江善政科技有限公司 | Network information filtering method, computer readable storage medium and mobile terminal |
| CN111080067A (en) * | 2019-11-18 | 2020-04-28 | 精硕科技（北京）股份有限公司 | Speaker commercial value evaluation method, storage medium and device |
| CN111078879A (en) * | 2019-12-09 | 2020-04-28 | 北京邮电大学 | Method and device for detecting text sensitive information of satellite internet based on deep learning |
| CN111125548A (en) * | 2019-12-31 | 2020-05-08 | 北京金堤科技有限公司 | Public opinion supervision method and device, electronic equipment and storage medium |
| CN111950717A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Public opinion quantification method based on neural network |
| CN111950717B (en) * | 2020-08-27 | 2022-07-19 | 桂林电子科技大学 | Public opinion quantification method based on neural network |
| CN113158669A (en) * | 2021-04-28 | 2021-07-23 | 河北冀联人力资源服务集团有限公司 | Method and system for identifying positive and negative comments of employment platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330613A (en) | A kind of public sentiment monitoring method, equipment and computer-readable recording medium | |
| WO2022141861A1 (en) | Emotion classification method and apparatus, electronic device, and storage medium | |
| KR101793222B1 (en) | Updating a search index used to facilitate application searches | |
| US10691770B2 (en) | Real-time classification of evolving dictionaries | |
| US9881037B2 (en) | Method for systematic mass normalization of titles | |
| US9311372B2 (en) | Product record normalization system with efficient and scalable methods for discovering, validating, and using schema mappings | |
| CN106682192A (en) | Method and device for training answer intention classification model based on search keywords | |
| US8825620B1 (en) | Behavioral word segmentation for use in processing search queries | |
| JP2023533475A (en) | Artificial intelligence for keyword recommendation | |
| US9110852B1 (en) | Methods and systems for extracting information from text | |
| US10628749B2 (en) | Automatically assessing question answering system performance across possible confidence values | |
| US10282678B2 (en) | Automated similarity comparison of model answers versus question answering system output | |
| US11809505B2 (en) | Method for pushing information, electronic device | |
| CN113886708A (en) | Product recommendation method, device, equipment and storage medium based on user information | |
| CN113919336A (en) | Article generation method and device based on deep learning and related equipment | |
| JPWO2019142345A1 (en) | Security information processing equipment, information processing methods and programs | |
| US20230394236A1 (en) | Extracting content from freeform text samples into custom fields in a software application | |
| CN113806492A (en) | Record generation method, device and equipment based on semantic recognition and storage medium | |
| Arafat et al. | Analyzing public emotion and predicting stock market using social media | |
| CN107688594A (en) | The identifying system and method for risk case based on social information | |
| US9705972B2 (en) | Managing a set of data | |
| CN113254623B (en) | Data processing method, device, server, medium and product | |
| CN113707302A (en) | Service recommendation method, device, equipment and storage medium based on associated information | |
| CN114780688A (en) | Text quality inspection method, device and equipment based on rule matching and storage medium | |
| CN115017200A (en) | Search result sorting method and device, electronic equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180720 Address after: 518000 Guangdong, Shenzhen, Futian District Futian street Fu'an community Yitian road 5033, Ping An financial center, 23 floor. Applicant after: Ping An Technology (Shenzhen) Co., Ltd. Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: Ping An Wanjia Medical Investment Management Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171107 |