CN109409619A - Prediction technique, device, medium and the electronic equipment of public sentiment trend - Google Patents
Prediction technique, device, medium and the electronic equipment of public sentiment trend Download PDFInfo
- Publication number
- CN109409619A CN109409619A CN201811554723.0A CN201811554723A CN109409619A CN 109409619 A CN109409619 A CN 109409619A CN 201811554723 A CN201811554723 A CN 201811554723A CN 109409619 A CN109409619 A CN 109409619A
- Authority
- CN
- China
- Prior art keywords
- public sentiment
- target
- keyword
- industry
- network
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present embodiments relate to data processing fields, provide a kind of prediction technique of public sentiment trend, prediction meanss, computer-readable medium and the electronic equipment of public sentiment trend, this method comprises: according to history public sentiment data relevant to multiple industries, determine network of personal connections relevant to target industry, the network of personal connections includes multiple keywords；Based on the network of personal connections, the degree of correlation between target keyword public sentiment crisis corresponding with the target industry is obtained；According to the public sentiment trend of target industry described in the relevance predication between target keyword public sentiment crisis corresponding with the target industry.Technical solution through the embodiment of the present invention can be realized the prediction to the public sentiment trend of target industry; it can realize the prediction to public sentiment crisis potential, may occurring; so as to improve the accuracy for a possibility that estimation forms public sentiment crisis, be conducive to the pre-alerting ability for promoting public sentiment monitoring system.
Description
Technical field
The present invention relates to data processing field, in particular to the prediction technique of public sentiment trend a kind of, public sentiment trend
Prediction meanss, computer-readable medium and electronic equipment.
Background technique
With the continuous renewal of information propagation pattern, the public has to what hot spots certain in actual life, focal issue were held
The spread speed of stronger influence power, tendentious speech and viewpoint is getting faster.In order to avoid adverse effect caused by public sentiment, people
Generally obtained using public sentiment Risk-warning by the way of neutralizing, cope with adverse effect taken necessity, efficient action.
In the prior art, the method for carrying out Risk-warning according to public sentiment usually crawls the side such as network information using network
Formula obtains a large amount of real time information, public sentiment data, using technologies such as Keywords matching, retrieval, semantics recognitions, filter out and this
Company, the relevant public feelings information of industry, then according to the side such as Keywords matching quantity, manual analysis, artificial intelligence semantic analysis
Formula, and then judge the emotion degree of public feelings information, to provide the early warning of public sentiment.
However, the prediction effect of the prediction technique for the public sentiment trend that the prior art provides is to be improved.
It should be noted that information is only used for reinforcing the reason to background of the invention disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
A kind of prediction technique for being designed to provide public sentiment trend of the embodiment of the present invention, the prediction meanss of public sentiment trend,
Computer-readable medium and electronic equipment, and then the prediction for the public sentiment trend for overcoming the prior art to provide at least to a certain extent
The prediction effect of method disadvantage to be improved.
Other characteristics and advantages of the invention will be apparent from by the following detailed description, or partially by the present invention
Practice and acquistion.
According to a first aspect of the embodiments of the present invention, a kind of prediction technique of public sentiment trend is provided, comprising:
According to history public sentiment data relevant to multiple industries, network of personal connections relevant to target industry, the relationship are determined
Net includes multiple keywords；
Based on the network of personal connections, obtain related between target keyword public sentiment crisis corresponding to the target industry
Degree；
According to mesh described in the relevance predication between target keyword public sentiment crisis corresponding with the target industry
Mark the public sentiment trend of industry.
In some embodiments of the invention, aforementioned schemes are based on, according to history public sentiment data relevant to multiple industries,
Determine network of personal connections relevant to target industry, the network of personal connections includes multiple keywords, comprising:
According to the relevant history public sentiment data of multiple industries, multiple keywords relevant to the target industry are obtained；
According to the determination of the attribute information of relationship and each keyword between the multiple keyword and the target line
The relevant network of personal connections of industry.
In some embodiments of the invention, aforementioned schemes are based on, target keyword and the target industry pair are being obtained
Before the degree of correlation between public sentiment crisis answered, further includes:
Based on the relevant history public sentiment data of multiple industries, the attribute information, the multiple of the multiple keyword is extracted
It is related between relation information and the multiple keyword public sentiment crisis corresponding to the target industry between keyword
Degree is used as training sample；
Relevance predication model according to the training sample train classification models, and after being trained.
In some embodiments of the invention, aforementioned schemes are based on, the network of personal connections is based on, obtain target keyword and institute
State the degree of correlation between the corresponding public sentiment crisis of target industry, comprising:
Based on the network of personal connections, the attribute information and the target keyword for obtaining the target keyword are closed with other
Relation information between keyword；
By the target keyword, the attribute information of the target keyword and the target keyword and other keys
Relation information between word is input to the relevance predication model；
The phase between the target keyword and the target industry is determined according to the output of the relevance predication model
Guan Du.
In some embodiments of the invention, aforementioned schemes are based on, the attribute information includes: the frequency.
In some embodiments of the invention, aforementioned schemes are based on, the disaggregated model includes but is not limited to: decision tree,
One of random forest, artificial neural network and support vector machines.
In some embodiments of the invention, aforementioned schemes are based on, according to the target keyword and the target industry
The public sentiment trend of target industry described in relevance predication between corresponding public sentiment crisis, comprising:
Include according to the degree of correlation acquisition between target keyword public sentiment crisis corresponding with the target industry
The score value of the information of the keyword and the information；
Score value is greater than the information of early warning value as target information, with according to the target information to the target industry
Public sentiment trend predicted.
In some embodiments of the invention, aforementioned schemes are based on, the target industry is insurance industry.
According to a second aspect of the embodiments of the present invention, a kind of prediction meanss of public sentiment trend are provided, comprising:
Network of personal connections determining module, for according to history public sentiment data relevant to multiple industries, determination and target industry phase
The network of personal connections of pass, the network of personal connections include multiple keywords；
The degree of correlation obtains module, and for being based on the network of personal connections, it is corresponding with the target industry to obtain target keyword
The degree of correlation between public sentiment crisis；
Prediction module, for according to related between target keyword public sentiment crisis corresponding to the target industry
Degree predicts the public sentiment trend of the target industry.
According to a third aspect of the embodiments of the present invention, a kind of computer-readable medium is provided, computer is stored thereon with
Program realizes the public sentiment trend such as first aspect in above-described embodiment or as described in second aspect when described program is executed by processor
Prediction technique.
According to a fourth aspect of the embodiments of the present invention, a kind of electronic equipment is provided, comprising: one or more processors；
Storage device, for storing one or more programs, when one or more of programs are held by one or more of processors
When row, so that one or more of processors are realized first aspect in above-described embodiment or the public sentiment as described in second aspect are dynamic
To prediction technique.
Technical solution provided in an embodiment of the present invention can include the following benefits:
On the one hand, according to magnanimity history public sentiment data relevant to multiple industries, determine it is relevant to target industry including
The network of personal connections of multiple keywords, and according to the degree of correlation between keyword public sentiment crisis corresponding with target industry to the target
The public sentiment trend of industry is predicted.Divided in the technical program based on magnanimity history public sentiment data relevant to multiple industries
Analysis by analyzing current announced, processed public sentiment, and then is realized to the pre- of the public sentiment trend of target industry
It surveys, that is, the prediction to public sentiment crisis potential, may occurring is realized, so as to improve the possibility that estimation forms public sentiment crisis
Property accuracy, be conducive to promoted public sentiment monitoring system pre-alerting ability.
On the other hand, using any one keyword in above-mentioned relation net as target keyword, in the network of personal connections
Obtain the degree of correlation between target keyword and above-mentioned target industry, in turn, the corresponding correlation of the multiple target keywords of root
Degree predicts the public sentiment trend of the target industry, it is seen then that the keyword that user can be concerned about is as target critical
Word predicts the public sentiment trend of target industry, meets the individual demand of user, improves the prediction experience of user.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
It can the limitation present invention.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.It should be evident that the accompanying drawings in the following description is only the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 shows the flow diagram of the prediction technique of the public sentiment trend of embodiment according to the present invention；
Fig. 2 shows the processes of the determination method of the network of personal connections relevant to target industry of embodiment according to the present invention to show
It is intended to；
Fig. 3 shows the flow diagram of the determination method of the relevance predication model of embodiment according to the present invention；
Fig. 4 is shown between the target keyword public sentiment crisis corresponding with target industry of embodiment according to the present invention
The flow diagram of the determination method of the degree of correlation；
Fig. 5 shows the process signal of the prediction technique of the public sentiment trend of the target industry of embodiment according to the present invention
Figure；
Fig. 6 shows the structural schematic diagram of the prediction meanss of the public sentiment trend of embodiment according to the present invention；
Fig. 7 shows the structural schematic diagram for being suitable for the computer system for the electronic equipment for being used to realize the embodiment of the present invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the present invention will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to the embodiment of the present invention.However,
It will be appreciated by persons skilled in the art that technical solution of the present invention can be practiced without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy each aspect of the present invention.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
The prior art provide public sentiment trend prediction technique, can only to currently specific Keywords matching our company or
The information of the industry is merely able to carry out early warning, therefore, the prior art to public sentiment that is having occurred, issued or propagating
The prediction technique timeliness of the public sentiment trend of offer is poor, and the prediction effect so as to cause the prediction technique of public sentiment trend is poor.
Fig. 1 shows the flow diagram of the prediction technique of the public sentiment trend of embodiment according to the present invention.The present embodiment
The prediction technique for the public sentiment trend that the prediction technique of the public sentiment trend of offer overcomes the prior art to provide at least to a certain extent
Prediction effect disadvantage to be improved.Wherein, the executing subject of the prediction technique of public sentiment trend provided in this embodiment can be with
It is that there is equipment of calculation processing function, such as server etc..
Prediction technique with reference to Fig. 1, the public sentiment trend includes:
Step S101 determines network of personal connections relevant to target industry according to history public sentiment data relevant to multiple industries,
The network of personal connections includes multiple keywords；
Step S102 is based on the network of personal connections, obtain corresponding with the target industry public sentiment crisis of target keyword it
Between the degree of correlation；And
Step S103, it is pre- according to the degree of correlation between target keyword public sentiment crisis corresponding with the target industry
Survey the public sentiment trend of the target industry.
In technical solution provided by embodiment shown in Fig. 1, on the one hand, according to magnanimity history relevant to multiple industries
Public sentiment data determines networks of personal connections relevant to target industry, including multiple keywords, and according to keyword and target industry pair
The degree of correlation between public sentiment crisis answered predicts the public sentiment trend of the target industry.In the technical program based on it is more
The relevant magnanimity history public sentiment data of a industry is analyzed, by analyzing current announced, processed public sentiment,
And then prediction of the realization to the public sentiment trend of target industry, that is, realize the prediction to public sentiment crisis potential, may occurring, from
And can be improved the accuracy for a possibility that estimation forms public sentiment crisis, be conducive to the pre-alerting ability for promoting public sentiment monitoring system.
On the other hand, using any one keyword in above-mentioned relation net as target keyword, in the network of personal connections
Obtain the degree of correlation between target keyword and above-mentioned target industry, in turn, the corresponding correlation of the multiple target keywords of root
Degree predicts the public sentiment trend of the target industry, it is seen then that the keyword that user can be concerned about is as target critical
Word predicts the public sentiment trend of target industry, meets the individual demand of user, improves the prediction experience of user.
The specific implementation of each step of embodiment illustrated in fig. 1 is described in detail below:
In the exemplary embodiment, above-mentioned target industry can be insurance industry, can be in each embodiment below
It is predicted based on public sentiment trend of multiple industry datas to insurance industry.Specifically, in this example, it is based on and multiple industries
Relevant magnanimity history public sentiment data is analyzed, by analyzing current announced, processed public sentiment, Jin Ershi
Now to the prediction of the public sentiment trend of insurance industry, that is, realize the pre- of the public sentiment crisis to insurance industry potential, may occurring
It surveys, so as to improve the accuracy for a possibility that estimation insurance industry forms public sentiment crisis, is conducive to be promoted to insurance industry
The pre-alerting ability of public sentiment monitoring system
In the exemplary embodiment, Fig. 2 shows the relationships relevant to target industry of embodiment according to the present invention
The flow diagram of the determination method of net.It is introduced below in conjunction with specific embodiment of the Fig. 2 to step S101.With reference to Fig. 2,
The method comprising the steps of S201 and step S202.
In step s 201, it according to the relevant history public sentiment data of multiple industries, obtains relevant to the target industry
Multiple keywords；And
In step S202, determined according to the attribute information of relationship and each keyword between the multiple keyword
Network of personal connections relevant to the target industry.
Wherein, the relevant history public sentiment data of above-mentioned multiple industries refers to generation in multiple industries (including when being not limited to protect
Dangerous industry) the corresponding information and date of dependent event that has occurred and that.
It is illustrated by taking vehicle insurance as an example in the present embodiment, vehicle frequency of being in danger generally is much higher than other insurance kinds, and vehicle insurance is taken
Increasing has larger impact to the business development of insurance company.Illustratively, by network crawl in the way of in conglomerate phase
The relevant history public sentiment number of vehicle insurance is obtained in the network information (such as: microblogging, forum, blog, discussion bar, news and comment etc.) of pass
According to.These history public sentiment datas can be related news, the speed of expense reimbursement of the report that vehicle is in danger, vehicle insurance reimbursement service
And/or user submits an expense account the information such as the evaluation serviced to vehicle insurance to insurance company.
Further, multiple keywords relevant with vehicle insurance are determined according to history public sentiment data relevant to vehicle insurance.Such as:
The blue money vehicle public sentiment event increases in 2017 of the recent Chevrolet Ke Luzi in Yunnan in history public sentiment data, rate of being in danger is high, microblogging
There is more multipair Pingan Insurance and services complaint not in place.Keyword relevant to insurance industry, which can therefrom be extracted, to be had:
Vehicle insurance, Chevrolet, Ke Luzi, blue Ke Luzi, Ke Luzi money in 2017, Yunnan Pingan Insurance, Yunnan Chevrolet, the Zhaotong shop 4S
Service the keywords such as difference.
In the exemplary embodiment, between the key of above-described embodiment there are incidence relations, such as: " Yunnan safety protect
Danger ", " Yunnan Chevrolet " and " the Zhaotong shop 4S " belong to Yunnan, and " Yunnan Pingan Insurance " exists with " vehicle insurance " to be belonged to insure
Relationship, and " vehicle insurance " and " Chevrolet, Ke Luzi, blue Ke Luzi, Ke Luzi money in 2017 " the relevant association with " vehicle "
Relationship.Meanwhile there is also respective attribute informations for each keyword, comprising: the frequency etc. of each keyword in preset time period.
In turn, relationship relevant to vehicle insurance is determined according to the attribute information of relationship and each keyword between above-mentioned multiple keywords
Net.
In the exemplary embodiment, the prediction technique of public sentiment trend further include: the determination of relevance predication model.Fig. 3
Show the flow diagram of the determination method of the relevance predication model of embodiment according to the present invention.With reference to Fig. 3, this method
Including step S301 and step S302.
In step S301, it is based on the relevant history public sentiment data of multiple industries, extracts the attribute of the multiple keyword
Relation information and the multiple keyword public sentiment danger corresponding with the target industry between information, the multiple keyword
The degree of correlation between machine is as training sample；And
In step s 302, the relevance predication mould according to the training sample train classification models, and after being trained
Type.
In the exemplary embodiment, above-mentioned target industry still can be insurance industry, then above-mentioned relevance predication mould
Type can be used to predict keyword and the insurance industry degree of correlation.Wherein, also carry out history public sentiment data using multiple industries are relevant
Training data is extracted, the forecasting accuracy for improving machine learning model is conducive to.
In the exemplary embodiment, extracted in the history public sentiment data of magnanimity multiple keywords attribute information, on
State the relation information between multiple keywords and the phase between the public sentiment crisis corresponding with the target industry of multiple keywords
Guan Du is as training sample.In the case where history public sentiment data is information data, for each information, extraction and target
The relevant multiple keywords of public sentiment and keyword the frequency occurred in this information, the incidence relation between keyword and this
Information causes a possibility that public sentiment crisis (if having caused public sentiment crisis, use 100% is indicated), as this information pair
The sample information answered.The sample information for obtaining big data quantity can be extracted as training sample according to the information of big quantity.
In the exemplary embodiment, according to above-mentioned training sample train classification models, pass through training machine learning model
Mode obtain relevance predication model.
In the exemplary embodiment, the phase according to above-mentioned training sample data train classification models, and after being trained
Pass degree prediction model, for the public sentiment trend according to the Relationship Prediction target industry between the keyword frequency, keyword.Wherein,
Above-mentioned disaggregated model includes but is not limited to: one of decision tree, random forest, artificial neural network and support vector machines.
It continues to refer to figure 1, after determining network of personal connections relevant to target public sentiment, in step s 102, is based on the pass
It is net, obtains the degree of correlation between target keyword public sentiment crisis corresponding with the target industry.
In the exemplary embodiment, Fig. 4 shows the target keyword and target industry of embodiment according to the present invention
The flow diagram of the determination method of the degree of correlation between corresponding public sentiment crisis.Below in conjunction with Fig. 4 to the specific of step S102
Embodiment is introduced.With reference to Fig. 4, the method comprising the steps of S401- step S403.
In step S401, be based on the network of personal connections, obtain the target keyword attribute information and the target
Relation information between keyword and other keywords；
In step S402, the target keyword, the attribute information of the target keyword and the target are closed
Relation information between keyword and other keywords is input to the relevance predication model；And
In step S403, the target keyword and the target are determined according to the output of the relevance predication model
The degree of correlation between the corresponding public sentiment crisis of industry.
In the exemplary embodiment, if target industry is " insurance industry ", the target keyword determined for user
" cutaneum carcinoma ", then the determination method of the degree of correlation between cutaneum carcinoma public sentiment crisis corresponding with insurance industry, comprising: firstly, root
Determining according to above-described embodiment is " insurance industry " relevant network of personal connections to target industry, obtains above-mentioned target keyword " skin
The attribute information of cancer " and this target keyword " cutaneum carcinoma " and other keywords (such as: cutaneum carcinoma anti-cancer herb medicine, price,
Medical industry, medical insurance etc.) between relation information.Then, will acquire with above-mentioned all information inputs to above-mentioned reality
Apply the relevance predication model that example determines.Above-mentioned target keyword " skin can be then determined by the output of relevance predication model
The degree of correlation between skin cancer " public sentiment crisis corresponding with insurance industry.
In the exemplary embodiment, if target industry is still " insurance industry ", user can also obtain multiple targets
The degree of correlation between keyword public sentiment crisis corresponding with insurance industry.Specifically, multiple keywords are as follows: medical industry, special efficacy
Medicine, cutaneum carcinoma, cancer, high drug price, medical insurance are predicted by above-mentioned relevance predication model, obtain each key
The degree of correlation between word public sentiment crisis corresponding with insurance industry are as follows: medical industry (30%), specific drug (45%), cutaneum carcinoma
(20%), cancer (70%), high drug price (25%), medical insurance (66%).Wherein: " medical industry (30%) " indicates: closing
The degree of correlation between keyword " medical industry " public sentiment crisis corresponding with insurance industry is 30%；" specific drug (45%) " indicates:
The degree of correlation between keyword " specific drug " public sentiment crisis corresponding with insurance industry is 45%；And " medical insurance
(66%) " indicate: the degree of correlation between keyword " medical insurance " public sentiment crisis corresponding with insurance industry is 66%, etc..
It continues to refer to figure 1, after obtaining the degree of correlation between target keyword public sentiment crisis corresponding with target industry,
In step s 103, according to the relevance predication institute between target keyword public sentiment crisis corresponding with the target industry
State the public sentiment trend of target industry.
In the exemplary embodiment, Fig. 5 shows the public sentiment trend of the target industry feelings of embodiment according to the present invention
Prediction technique flow diagram.It is introduced below in conjunction with specific embodiment of the Fig. 5 to step S103.It, should with reference to Fig. 5
Method includes step S501 and step S502.
In step S501, according to related between target keyword public sentiment crisis corresponding to the target industry
It includes the information of the keyword and the score value of the information that degree, which obtains,；And
Information in step S502 using score value greater than early warning value is as target information, according to the target information pair
The public sentiment trend of the target industry is predicted.
In the exemplary embodiment, according to previous embodiment, if target industry is still " insurance industry ", user is directed to
Multiple target keywords: Yunnan Chevrolet, Ke Luzi money in 2017, vehicle insurance, Chevrolet, Ke Luzi, blue Ke Luzi, by upper
It states relevance predication model to be predicted, obtains the degree of correlation between the public sentiment crisis corresponding with insurance industry of each keyword
Are as follows: Yunnan Chevrolet (41%), Ke Luzi money (37%) in 2017, vehicle insurance (14%), Chevrolet (11%), Ke Luzi (8%),
Blue Ke Luzi (7.5%).Wherein: " Yunnan Chevrolet (41%) " indicates: keyword " Yunnan Chevrolet " and insurance industry pair
The degree of correlation between public sentiment crisis answered is 41%；" vehicle insurance (14%) " indicates: keyword " vehicle insurance " is corresponding with insurance industry
The degree of correlation between public sentiment crisis is 14%；And " Ke Luzi money (37%) in 2017 " indicates: keyword " Ke Luzi 2017
The degree of correlation between year money " public sentiment crisis corresponding with insurance industry is 37%, etc..
In the exemplary embodiment, for more comprising keyword, and keyword public sentiment danger corresponding with target industry
The bigger information of the degree of correlation between machine illustrates more to be conducive to improve forecasting accuracy, therefore is more suitable for target industry
Public sentiment trend is predicted.Illustratively, the degree of correlation between keyword public sentiment crisis corresponding with target industry can be turned
Turn to scoring form (such as: it is related between keyword " Ke Luzi money in 2017 " public sentiment crisis corresponding to insurance industry
Degree is 37%, can be converted are as follows: related between keyword " Ke Luzi money in 2017 " public sentiment crisis corresponding to insurance industry
Spending corresponding scoring is 37 points), in turn, the scoring for the keyword for including according to information determines the score value of information, similarly, information
Score value it is bigger, more be suitable for the public sentiment trend of target industry is predicted.
In the exemplary embodiment, according to the corresponding scoring of the above-mentioned degree of correlation or the degree of correlation got, acquisition includes
There are the information of these keywords, and the score value to obtain information according to the keyword that each information includes.Such as: information S includes
Keyword A (the corresponding scoring of the degree of correlation is a), keyword B (the corresponding scoring of the degree of correlation is b), (degree of correlation is corresponding by keyword C
Scoring be that c) and keyword D (degree of correlation corresponding scoring be d), and then the score value of available information S is a+b+c+
d。
In the exemplary embodiment, information score value is greater than the information of early warning value as target information.Such as one
In the information of entitled " Ke Luzi is called back again and again, and the more shops 4S are crowded with vehicles ", multiple keywords have been related to it: have avenged Buddhist in Yunnan
Blue (2 times), Ke Luzi money (2 times) in 2017, Chevrolet (4 times), Ke Luzi (1 time), blue Ke Luzi (2 times).According to above-mentioned
The degree of correlation between keyword and public sentiment crisis can calculate the score value of this information: 44*2+37*2+11*4+8+7.5*2=
229.Assuming that early warning value is 200 points, then this information can be used as target information, with dynamic according to public sentiment of this information to insurance industry
To being predicted.
The technical solution provided through this embodiment, which can be seen that, does not refer to insurance, vehicle insurance etc. inside this information
Word relevant to target public sentiment, but according to the method provided in this embodiment based on network of personal connections and relevance predication model, know
Do not go out in the recent target information that may be present for causing insurance industry public sentiment crisis occur, in time to give the message push
Public sentiment treatment people.Illustratively, after public sentiment treatment people receives the early warning of target information, the frequent thing of confirmation can be checked in time
Therefore vehicle, the shop 4S position, and manpower is organized to contact the correlation shop 4S, conferred and the maintenance and inspection expense for the vehicle that arranges that accidents happened
Calculation work, and carry out insurance company vehicle insurance publicity, can both increase vehicle insurance insurant, carry out propaganda work in time,
It is capable of the appearance for avoiding public sentiment crisis of maximum dynamics again.
In the exemplary embodiment, an information in relation to Mr. Yu's disease is propagated in network: treating the spy of skin cancer
It is significant to imitate medicine " anticancer jinx * * * * " drug effect, can contain that cancer cell is spread, adhering to taking for a long time can be no different with ordinary person, but should
Drug high drug price, the medical fee for causing cutaneum carcinoma cancer patient's financial insolvency high, so that most of patient can not effectively hold back
The information such as cancer cell diffusion processed, the death rate are still high ....
Wherein, be related to multiple keywords: medical industry (2 times), specific drug (2 times), cutaneum carcinoma (4 times), medicine valence are empty
High (1 time), medical insurance (2 times).According to the degree of correlation between above-mentioned keyword and public sentiment crisis, commenting for this information can be calculated
Score value: 30*2+45*2+20*4+25+66*2=387.Assuming that early warning value is 200 points, then this information can be used as target information,
To be predicted according to public opinion trend of this information to insurance industry.Having identified leads to insurance industry that may be present in the recent period
After the target information for public opinion crisis occur, the message push is given to public sentiment treatment people in time.Illustratively, public sentiment administrative staff
After analysis, the drug that discovery information is related to has been included in its insurance company " * * advanced medical " insurance kind, and only insurance is public
Publication is announced in time for department, is reminded everybody if it is intended to more comprehensively ensureing, can be bought " * * advanced medical " insurance kind, involved
A few money prices are high, curative effect but Serious Drug well, the disease of user can be provided safeguard.To effectively contain
Public opinion is panic, and has publicized " * * advanced medical " insurance kind, company and obtained everybody favor.
A kind of data analysis algorithm based on big data analysis is proposed in technical solution provided in an embodiment of the present invention,
By analyzing announced, processed history public sentiment current in multiple industries, collecting public sentiment propagating source and being propagated through
Each stage keyword in journey, by way of machine learning, each row of analytical calculation, each industry, each product are corresponding with insurance industry
A possibility that public sentiment crisis degree.And then while carrying out information, public sentiment data screening, it can also occur to potential, possible
Public sentiment crisis predicted, estimation a possibility that forming public sentiment crisis, then by continuous machine learning, to algorithm progress
Optimization, is reached accurate prediction, can be guided with early excise public sentiment, it would be possible to which the public sentiment crisis of generation is in budding period energy
Enough neutralizings.
The device of the invention embodiment introduced below can be used for executing the prediction side of the above-mentioned public sentiment trend of the present invention
Method.
Fig. 6 shows the structural schematic diagram of the prediction meanss of the public sentiment trend of embodiment according to the present invention, with reference to Fig. 6,
The prediction meanss 600 of public sentiment trend, comprising: network of personal connections determining module 601, the degree of correlation obtain module 602 and prediction module 603.
Wherein, network of personal connections determining module 601 is used for according to history public sentiment data relevant to multiple industries, determining and target
The relevant network of personal connections of industry, the network of personal connections include multiple keyword words；
The degree of correlation obtains module 602 and is used to be based on the network of personal connections, and it is corresponding with the target industry to obtain target keyword
Public sentiment crisis between the degree of correlation；And
Prediction module 603 is used for according to the phase between target keyword public sentiment crisis corresponding with the target industry
Guan Du predicts that the public sentiment trend of the target industry is surveyed.
In some embodiments of the invention, aforementioned schemes are based on, the network of personal connections determining module 601 includes: keyword
Acquiring unit and network of personal connections determination unit.
Wherein, the keyword acquiring unit is used for according to the relevant history public sentiment data of multiple industries, obtain with it is described
The relevant multiple keywords of target industry；And
The network of personal connections determination unit is used for the category according to relationship and each keyword between the multiple keyword
Property information determine relevant to target industry network of personal connections.
In some embodiments of the invention, aforementioned schemes, the prediction meanss 600 of the public sentiment trend are based on, further includes:
Relevance predication model determining module.
The relevance predication model determining module is used for:
Based on the relevant history public sentiment data of multiple industries, the attribute information, the multiple of the multiple keyword is extracted
It is related between relation information and the multiple keyword public sentiment crisis corresponding to the target industry between keyword
Degree is used as training sample；And
Relevance predication model according to the training sample train classification models, and after being trained.
In some embodiments of the invention, aforementioned schemes are based on, the degree of correlation obtains module 602, is specifically used for:
Based on the network of personal connections, the attribute information and the target keyword for obtaining the target keyword are closed with other
Relation information between keyword；
By the target keyword, the attribute information of the target keyword and the target keyword and other keys
Relation information between word is input to the relevance predication model；And
Target keyword carriage corresponding with the target industry is determined according to the output of the relevance predication model
The degree of correlation between feelings crisis.
In some embodiments of the invention, aforementioned schemes are based on, the attribute information includes: the frequency.
In some embodiments of the invention, aforementioned schemes are based on, the disaggregated model includes but is not limited to: decision tree,
One of random forest, artificial neural network and support vector machines.
In some embodiments of the invention, aforementioned schemes, the prediction module 603 are based on, comprising: score value obtains single
Member and public sentiment trend predicting unit.
Wherein, the score value acquiring unit is used for according to target keyword public sentiment corresponding with the target industry
It includes the information of the keyword and the score value of the information that the degree of correlation between crisis, which obtains,；And
The public sentiment trend predicting unit is used for the information using score value greater than early warning value as target information, according to institute
Target information is stated to predict the public sentiment trend of the target industry.
In some embodiments of the invention, aforementioned schemes are based on, the target industry can be insurance industry.
Since each functional module of the prediction meanss of the public sentiment trend of example embodiments of the present invention and above-mentioned public sentiment are dynamic
To prediction technique example embodiment the step of it is corresponding, therefore for undisclosed details in apparatus of the present invention embodiment, ask
Referring to the embodiment of the prediction technique of the above-mentioned public sentiment trend of the present invention.
Below with reference to Fig. 7, it illustrates the computer systems 700 for the electronic equipment for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.The computer system 700 of electronic equipment shown in Fig. 7 is only an example, should not be to the embodiment of the present invention
Function and use scope bring any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (CPU) 701, it can be read-only according to being stored in
Program in memory (ROM) 702 or be loaded into the program in random access storage device (RAM) 703 from storage section 708 and
Execute various movements appropriate and processing.In RAM 703, it is also stored with various programs and data needed for system operatio.CPU
701, ROM 702 and RAM 703 is connected with each other by bus 704.Input/output (I/O) interface 705 is also connected to bus
704。
I/O interface 705 is connected to lower component: the importation 706 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 707 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 708 including hard disk etc.；
And the communications portion 709 of the network interface card including LAN card, modem etc..Communications portion 709 via such as because
The network of spy's net executes communication process.Driver 710 is also connected to I/O interface 705 as needed.Detachable media 711, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 710, in order to read from thereon
Computer program be mounted into storage section 708 as needed.
Particularly, according to an embodiment of the invention, may be implemented as computer above with reference to the process of flow chart description
Software program.In such embodiment, which can be downloaded and installed from network by communications portion 709,
And/or it is mounted from detachable media 711.When the computer program is executed by central processing unit (CPU) 701, sheet is executed
The above-mentioned function of being limited in the system of application.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.
In this regard, each box in flowchart or block diagram can represent one of a module, program segment or code
Point, a part of above-mentioned module, program segment or code includes one or more for implementing the specified logical function executable
Instruction.It should also be noted that in some implementations as replacements, function marked in the box can also be to be different from attached drawing
The sequence marked occurs.For example, two boxes succeedingly indicated can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that each side in block diagram or flow chart
The combination of frame and the box in block diagram or flow chart can be based on hardware with the dedicated of defined functions or operations is executed
System realize, or can realize using a combination of dedicated hardware and computer instructions.
Being described in unit involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part realizes that described unit also can be set in the processor.Wherein, the title of these units is in certain situation
Under do not constitute restriction to the unit itself.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programs
When standby execution, so that the electronic equipment realizes the prediction technique such as above-mentioned public sentiment trend as described in the examples.
For example, each step as shown in any figure of Fig. 1 to Fig. 5 may be implemented in the electronic equipment.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims.
Claims (10)
1. a kind of prediction technique of public sentiment trend characterized by comprising
According to history public sentiment data relevant to multiple industries, network of personal connections relevant to target industry, the network of personal connections packet are determined
Include multiple keywords；
Based on the network of personal connections, the degree of correlation between target keyword public sentiment crisis corresponding with the target industry is obtained；
According to target line described in the relevance predication between target keyword public sentiment crisis corresponding with the target industry
The public sentiment trend of industry.
2. the prediction technique of public sentiment trend according to claim 1, which is characterized in that gone through according to relevant to multiple industries
History public sentiment data determines network of personal connections relevant to target industry, and the network of personal connections includes multiple keywords, comprising:
According to the relevant history public sentiment data of multiple industries, multiple keywords relevant to the target industry are obtained；
According to the determination of the attribute information of relationship and each keyword between the multiple keyword and the target industry phase
The network of personal connections of pass.
3. the prediction technique of public sentiment trend according to claim 1, which is characterized in that obtain target keyword with it is described
Before the degree of correlation between the corresponding public sentiment crisis of target industry, further includes:
Based on the relevant history public sentiment data of multiple industries, the attribute information of the multiple keyword, the multiple key are extracted
The degree of correlation between relation information and the multiple keyword public sentiment crisis corresponding with the target industry between word is made
For training sample；
Relevance predication model according to the training sample train classification models, and after being trained.
4. the prediction technique of public sentiment trend according to claim 3, which is characterized in that be based on the network of personal connections, obtain mesh
Mark the degree of correlation between keyword public sentiment crisis corresponding with the target industry, comprising:
Based on the network of personal connections, the attribute information and the target keyword and other keywords of the target keyword are obtained
Between relation information；
By the target keyword, the attribute information of the target keyword and the target keyword and other keywords it
Between relation information be input to the relevance predication model；
Target keyword public sentiment danger corresponding with the target industry is determined according to the output of the relevance predication model
The degree of correlation between machine.
5. the prediction technique of public sentiment trend according to claim 3 or 4, which is characterized in that the attribute information includes: frequency
It is secondary.
6. the prediction technique of public sentiment trend according to claim 3 or 4, which is characterized in that the disaggregated model include but
It is not limited to: one of decision tree, random forest, artificial neural network and support vector machines.
7. the prediction technique of public sentiment trend according to any one of claims 1 to 4, which is characterized in that according to the target
The public sentiment trend of target industry described in relevance predication between keyword public sentiment crisis corresponding with the target industry, packet
It includes:
It include described according to the degree of correlation acquisition between target keyword public sentiment crisis corresponding with the target industry
The score value of the information of keyword and the information；
Information using score value greater than early warning value is as target information, with the carriage according to the target information to the target industry
Feelings trend is predicted.
8. a kind of prediction meanss of public sentiment trend characterized by comprising
Network of personal connections determining module, for according to history public sentiment data relevant to multiple industries, determination to be relevant to target industry
Network of personal connections, the network of personal connections include multiple keywords；
The degree of correlation obtains module, for being based on the network of personal connections, obtains target keyword public sentiment corresponding with the target industry
The degree of correlation between crisis；
Prediction module, for pre- according to the degree of correlation between target keyword public sentiment crisis corresponding with the target industry
Survey the public sentiment trend of the target industry.
9. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is executed by processor
The prediction technique of public sentiment trend of the Shi Shixian as described in any one of claims 1 to 7.
10. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
When device executes, so that one or more of processors realize the pre- of the public sentiment trend as described in any one of claims 1 to 7
Survey method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554723.0A CN109409619A (en) | 2018-12-19 | 2018-12-19 | Prediction technique, device, medium and the electronic equipment of public sentiment trend |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554723.0A CN109409619A (en) | 2018-12-19 | 2018-12-19 | Prediction technique, device, medium and the electronic equipment of public sentiment trend |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109409619A true CN109409619A (en) | 2019-03-01 |
Family
ID=65460097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811554723.0A Pending CN109409619A (en) | 2018-12-19 | 2018-12-19 | Prediction technique, device, medium and the electronic equipment of public sentiment trend |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409619A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110156A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | Industry public sentiment monitoring method, device, computer equipment and storage medium |
| CN110134844A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | Subdivision field public sentiment monitoring method, device, computer equipment and storage medium |
| CN110175733A (en) * | 2019-04-01 | 2019-08-27 | 阿里巴巴集团控股有限公司 | A kind of public opinion information processing method and server |
| CN111104505A (en) * | 2019-12-30 | 2020-05-05 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN111222032A (en) * | 2019-12-17 | 2020-06-02 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
| CN112256974A (en) * | 2020-11-13 | 2021-01-22 | 泰康保险集团股份有限公司 | Public opinion information processing method and device |
| CN113689148A (en) * | 2021-09-26 | 2021-11-23 | 支付宝(杭州)信息技术有限公司 | Text risk identification method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019399A1 (en) * | 2009-05-22 | 2014-01-16 | Step 3 Systems, Inc. | System and method for automatically predicting the outcome of expert forecasts |
| CN105808722A (en) * | 2016-03-08 | 2016-07-27 | 苏州大学 | Information discrimination method and system |
| CN108023768A (en) * | 2017-12-01 | 2018-05-11 | 中国联合网络通信集团有限公司 | Network event chain establishment method and network event chain establish system |
-
2018
- 2018-12-19 CN CN201811554723.0A patent/CN109409619A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019399A1 (en) * | 2009-05-22 | 2014-01-16 | Step 3 Systems, Inc. | System and method for automatically predicting the outcome of expert forecasts |
| CN105808722A (en) * | 2016-03-08 | 2016-07-27 | 苏州大学 | Information discrimination method and system |
| CN108023768A (en) * | 2017-12-01 | 2018-05-11 | 中国联合网络通信集团有限公司 | Network event chain establishment method and network event chain establish system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175733A (en) * | 2019-04-01 | 2019-08-27 | 阿里巴巴集团控股有限公司 | A kind of public opinion information processing method and server |
| CN110175733B (en) * | 2019-04-01 | 2023-07-11 | 创新先进技术有限公司 | Public opinion information processing method and server |
| CN110110156A (en) * | 2019-04-04 | 2019-08-09 | 平安科技（深圳）有限公司 | Industry public sentiment monitoring method, device, computer equipment and storage medium |
| CN110134844A (en) * | 2019-04-04 | 2019-08-16 | 平安科技（深圳）有限公司 | Subdivision field public sentiment monitoring method, device, computer equipment and storage medium |
| CN111222032A (en) * | 2019-12-17 | 2020-06-02 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
| CN111222032B (en) * | 2019-12-17 | 2024-04-30 | 中国平安人寿保险股份有限公司 | Public opinion analysis method and related equipment |
| CN111104505A (en) * | 2019-12-30 | 2020-05-05 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN111104505B (en) * | 2019-12-30 | 2023-08-25 | 浙江阿尔法人力资源有限公司 | Information prompting method, device, equipment and storage medium |
| CN112256974A (en) * | 2020-11-13 | 2021-01-22 | 泰康保险集团股份有限公司 | Public opinion information processing method and device |
| CN112256974B (en) * | 2020-11-13 | 2023-11-17 | 泰康保险集团股份有限公司 | Public opinion information processing method and device |
| CN113689148A (en) * | 2021-09-26 | 2021-11-23 | 支付宝(杭州)信息技术有限公司 | Text risk identification method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409619A (en) | Prediction technique, device, medium and the electronic equipment of public sentiment trend | |
| Rodríguez-Ibánez et al. | A review on sentiment analysis from social media platforms | |
| Fan et al. | Heronian mean operators of linguistic neutrosophic multisets and their multiple attribute decision-making methods | |
| Cheng et al. | Adapting large language models via reading comprehension | |
| Lee et al. | Using Mahalanobis–Taguchi system, logistic regression, and neural network method to evaluate purchasing audit quality | |
| CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
| Grupac et al. | Virtual navigation and augmented reality shopping tools, immersive and cognitive technologies, and image processing computational and object tracking algorithms in the metaverse commerce | |
| Iddrisu et al. | A sentiment analysis framework to classify instances of sarcastic sentiments within the aviation sector | |
| CN109559242A (en) | Processing method, device, equipment and the computer readable storage medium of abnormal data | |
| Qiu et al. | Data mining–based disturbances prediction for job shop scheduling | |
| Liu et al. | Comparison of administrative and regulatory green technologies development between China and the US based on patent analysis | |
| Tao et al. | Can online consumer reviews signal restaurant closure: A deep learning-based time-series analysis | |
| CN115292594A (en) | Service recommendation method, system, electronic device and storage medium | |
| Xia et al. | Knowledge graph of mobile payment platforms based on deep learning: Risk analysis and policy implications | |
| Xue et al. | Identifying abnormal riding behavior in urban rail transit: a survey on “in-out” in the same subway station | |
| Gozuacik et al. | Technological forecasting based on estimation of word embedding matrix using LSTM networks | |
| CN109636648A (en) | Social security violation detection method, device, equipment and computer storage medium | |
| Liu et al. | Analysis of Beijing Tianjin Hebei regional credit system from the perspective of big data credit reporting | |
| Morrow et al. | A case for developing domain-specific vocabularies for extracting suicide factors from healthcare notes | |
| Guan et al. | Information extraction and application for constructing guidance corpus of welding fabrication | |
| CN109615538A (en) | Social security violation detection method, device, equipment and computer storage medium | |
| CN115620886A (en) | Data auditing method and device | |
| CN109636627A (en) | Insurance products management method, device, medium and electronic equipment based on block chain | |
| CN115048487A (en) | Artificial intelligence-based public opinion analysis method, device, computer equipment and medium | |
| CN114372892A (en) | Payment data monitoring method, device, equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |
|
| RJ01 | Rejection of invention patent application after publication |