CN117076751A - Public opinion event development trend judging system based on multidimensional feature analysis - Google Patents
Public opinion event development trend judging system based on multidimensional feature analysis Download PDFInfo
- Publication number
- CN117076751A CN117076751A CN202311304646.4A CN202311304646A CN117076751A CN 117076751 A CN117076751 A CN 117076751A CN 202311304646 A CN202311304646 A CN 202311304646A CN 117076751 A CN117076751 A CN 117076751A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- event
- emotion
- development
- target public
- 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.)
- Granted
Links
- 238000011161 development Methods 0.000 title claims abstract description 162
- 238000004458 analytical method Methods 0.000 title claims abstract description 57
- 230000008451 emotion Effects 0.000 claims abstract description 140
- 238000004891 communication Methods 0.000 claims description 68
- 230000005540 biological transmission Effects 0.000 claims description 30
- 230000000694 effects Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 23
- 230000008909 emotion recognition Effects 0.000 claims description 21
- 230000007935 neutral effect Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000007667 floating Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 230000007480 spreading Effects 0.000 claims description 5
- 230000002996 emotional effect Effects 0.000 claims description 4
- 230000000644 propagated effect Effects 0.000 claims description 4
- 101100391172 Dictyostelium discoideum forA gene Proteins 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of public opinion event development trend judgment, and particularly discloses a public opinion event development trend judgment system based on multidimensional feature analysis. Through analyzing emotion acceptance consistency coefficients of professional fields and masses, information such as the degree of support and objection of the public to the event is comprehensively solved, so that the atmosphere and public opinion movement of the society can be better mastered, corresponding measures can be timely taken, negative influences can be actively responded, the public opinion risk is effectively controlled, public opinion opportunities can be timely captured, and reputation and influence of enterprises or organizations can be improved.
Description
Technical Field
The invention belongs to the field of public opinion event development trend judgment, and relates to a public opinion event development trend judgment system based on multidimensional feature analysis.
Background
Along with the development of the Internet, the number and complexity of public opinion events are continuously increased, and positive or negative information is easily and continuously amplified through a network platform to form public hot events, so that how to rapidly and accurately predict the development trend of the public opinion events is of great significance to various aspects of enterprises, media and the like.
By analyzing the development of the public opinion event, the public opinion and attitude of the event can be better known, so that a better coping strategy is formulated. For example, if the public's attitude towards a brand or company changes, then the business or customs personnel may take timely action to change the public's opinion and avoid negative effects. In addition, through analyzing the development of the public opinion event, future public opinion trend can be predicted, and a better decision basis is provided for enterprises or public officers.
The public opinion event development trend judging system can help us to know the development situation of the public opinion event so as to better deal with and process, however, the existing public opinion event development trend judging system has the following defects: 1. the existing public opinion event development trend judgment lacks in analyzing network relation characteristics among professional fields in terms of multidimensional characteristic analysis. The development of public opinion events often involves expertise in different domains, and lack of analysis of network relationship features between the specialized domains can limit our understanding of the development trend in the crossing domains, prevent cross-domain collaboration and innovation, affect resource utilization efficiency, and increase evolution of potential risks.
2. The existing public opinion event development trend judgment lacks in analyzing the consistency of the emotion tendencies of the public users in the aspect of multidimensional feature analysis. The emotion characteristics are important indexes for knowing the emotion tendency of the public to the event, and can help us to predict the positive and negative development trend of the event better. Without analysis of the consistency of public emotion tendencies, public opinion analysis may be subjectively affected by some opinion leaders or active users with greater impact. This may result in a biased or misleading judgment of the public opinion event, which may not objectively reflect the general emotional tendency of the public. Decision makers may not be able to timely learn and cope with changes in public emotions, leading to crisis expansion or adverse consequences.
Disclosure of Invention
In view of this, in order to solve the problems set forth in the background art, a public opinion event development trend judging system based on multidimensional feature analysis is proposed.
The aim of the invention can be achieved by the following technical scheme: the invention provides a public opinion event development trend judging system based on multidimensional feature analysis, which comprises: public opinion event data collection module: the method is used for acquiring related information of the target public opinion event, and the related information comprises network relation characteristic information and time sequence characteristic information.
A network relation analysis module: the method is used for analyzing the transmission activity index of the target public opinion event in each professional field based on the network relation characteristic information.
Time floating trend analysis module: and the method is used for analyzing the propagation depth influence factor of the target public opinion event based on the time sequence characteristic information.
Public opinion event heat development trend judging module: the method is used for calculating the current activity index of the target public opinion event based on the transmission activity index of the target public opinion event in each professional field, and judging the heat development trend of the target public opinion event by combining the transmission depth influence factor of the target public opinion event.
Information base: the method is used for storing each historical event corresponding to each professional field and the historical development time length of each historical event, and storing the development fluctuation rate change curve of each historical event in the historical development time length and the propagation density and propagation breadth change curve of each historical event in the corresponding professional field in the historical development time length.
Emotion analysis module: the emotion recognition consistency coefficient of each professional field is evaluated according to the emotion tendency expressed in the text content of each communication post, which is obtained by the text content of each communication post issued by the corresponding relevant user of each professional field.
Public opinion event emotion development trend judging module: the method is used for acquiring comment text contents of comment users corresponding to each communication post issued by each associated user in each professional field, analyzing emotion recognition consistency coefficients of masses, and judging emotion tendency development trend of target public opinion events by combining the emotion recognition consistency coefficients of each professional field.
In one embodiment, the network relationship characteristic information includes propagation density and propagation breadth within each area of expertise.
The time series characteristic information includes the predicted development duration and development fluctuation rate of the target public opinion event.
In a specific embodiment, the step of analyzing the spreading activity index of the target public opinion event in each professional field includes: and classifying and screening all user identities in the multimedia platform based on the user ID authentication information to obtain corresponding associated users in each professional field.
Acquiring the occurrence time period of a target public opinion event, and counting the number of communication posts related to the target public opinion event, which are issued by corresponding associated users in each professional field in the occurrence time period，/>Indicates the professional field number,/-, and>，/>number representing associated user->。
Extracting forwarding quantity and comment quantity corresponding to each communication post related to the target public opinion event and issued by each relevant user in each professional field, and respectively marking the forwarding quantity and comment quantity as，/>Representing the number of the communication post>。
From the calculation formulaObtaining the transmission density of the target public opinion event in each professional field, < ->The number of the reference ac posts, the reference forwarding amount and the reference comment amount are respectively set.
Extracting geographic positions of forwarding users and comment users corresponding to the communication posts related to the target public opinion event and issued by the relevant users in the professional fields, and performing de-duplication processing to obtain the number of geographic positions of the target public opinion event propagated in the professional fieldsBy->Obtaining the spread breadth of the target public opinion event in each professional field, < >>Influence correction factor for the set propagation breadth, +.>For a set number of reference geographic locations.
Weight setting is carried out on the propagation density to obtain the corresponding weight of the propagation density of the target public opinion event in each professional fieldFurther analyze the spreading activity index of the target public opinion event in each professional field>Wherein->To set constant +.>。
In a specific embodiment, the corresponding analyzing step for analyzing the propagation depth influence factor of the target public opinion event includes: (41) Dividing the occurrence time period of the target public opinion event according to the set duration to obtain each sub-time stage, and recording the transmission density and the transmission breadth of the target public opinion event in each professional field in real time.
(42) Extracting the propagation density and propagation breadth of the target public opinion event in each professional field in each sub-time stage, and calculating to obtain the propagation activity index of the target public opinion event in each professional field in each sub-time stage，/>Representing the sub-time phase number,/->Further analyzing and obtaining the development fluctuation rate of the target public opinion event，/>Is the number of sub-time periods>Is the number of professional fields.
(43) The professional field corresponding to the target public opinion event is used as the appointed professional field, each historical event corresponding to the appointed professional field and the historical development time length of each historical event are extracted from the information base, the reference event is screened, and the predicted development time length of the target public opinion event is analyzed according to the historical development time length of the reference event。
(44) Substituting the predicted development duration and the development fluctuation rate of the target public opinion event into a formulaObtaining the transmission depth influence factor of the target public opinion event>Wherein->For a set reference development time period.
In a specific embodiment, the historical development time length obtaining manner of each historical event is as follows: and monitoring the development fluctuation rate of each historical event in real time, and when the development fluctuation rate of a certain historical event is smaller than a set development fluctuation rate threshold value in a set monitoring time period, marking the starting time corresponding to the set monitoring time period as the ending time of the historical event, and further taking the time interval between the starting time and the ending time of each historical event as the historical development time of each historical event.
In a specific embodiment, the step of determining the popularity development trend of the target public opinion event includes: to be used forAs the current active index of the target public opinion event, combining the transmission depth influence factor of the target public opinion event +.>Calculating to obtain the heat development ductility index of the target public opinion event>，/>Corresponding duty ratio weights of the set current activity index and the propagation depth influence factor respectively
And demarcating the range of the heat development ductility index of the public opinion event according to a set principle to obtain the range of the heat development ductility index of the public opinion event corresponding to each heat development trend, wherein the heat development trend comprises an ascending trend, a gentle trend and a descending trend, and the heat development trends corresponding to the heat development ductility index of the target public opinion event are obtained by matching.
In one specific embodiment, the step of determining the emotion tendencies expressed in the text content of each communication post includes: (71) And removing repeated words and part of speech labeling processing is carried out on the text contents of each communication post by adopting a language text processing mode, and then emotion analysis is carried out on the processed text contents of the communication post by using an emotion classification algorithm, so that each emotion vocabulary corresponding to the text contents of each communication post is obtained.
(72) Classifying and summarizing emotion vocabularies in each professional field according to a preset principle to obtain emotion tendency vocabulary libraries corresponding to each professional field, wherein emotion tendency comprises positive emotion tendency, negative emotion tendency and neutral emotion tendency.
(73) According to the professional field corresponding to each communication post, comparing each emotion vocabulary corresponding to each communication post text content with each emotion tendency vocabulary library corresponding to the professional field to obtain each emotion tendency vocabulary corresponding to each communication post text content, and taking the emotion tendency corresponding to the maximum emotion tendency vocabulary in each communication post text content as the emotion tendency expressed in each communication post text content.
In a specific embodiment, the evaluation mode for evaluating the emotion recognition consistency coefficient of each professional field is as follows: and judging and obtaining the emotion tendencies expressed in the text contents of the communication posts issued by the corresponding associated users in the professional fields based on the emotion tendencies corresponding judging step expressed in the text contents of the communication posts.
Collecting corresponding release time of each communication post released by each associated user in each professional field, and counting to obtain the number of positive emotion tendency communication posts released by each associated user in each professional field in each sub-time periodFrom the calculation formulaAnd obtaining the consistency coefficient of the positive emotion tendencies of the professional fields.
The uniformity coefficient of the negative emotion tendencies and the uniformity coefficient of the neutral emotion tendencies in each professional field are obtained by the same analysis and respectively marked as。
In a specific embodiment, the method for analyzing the emotion recognition consistency coefficient of the crowd personnel is as follows: judging emotion tendencies of comment text contents of comment users corresponding to the positive emotion tendencies of corresponding associated users in each professional field and corresponding to each comment user in each sub-time period, and counting to obtain the number of comment users corresponding to positive acceptance of the positive emotion tendencies of corresponding associated users in each professional field and corresponding to each associated user in each sub-time periodAnd then by the calculation formulaAnd obtaining the consistency coefficient of the positive emotion tendencies of the masses.
The same analysis is carried out to obtain a coefficient of consistency of the negative emotion tendencies of the masses and a coefficient of consistency of the neutral emotion tendencies of the masses, which are respectively recorded as。
In a specific embodiment, the specific content of the emotional tendency development trend of the judgment target public opinion event is: will beSubstitution formula->Obtaining the positive emotion tendency development consistency index of the target public opinion event, the same asAnd obtaining a negative emotion tendency development consistency index and a neutral emotion tendency development consistency index of the target public opinion event, comparing the negative emotion tendency development consistency index and the neutral emotion tendency development consistency index to obtain emotion tendency corresponding to the maximum value of the emotion tendency development consistency index of the target public opinion event, and taking the emotion tendency as the development emotion tendency of the target public opinion event.
Compared with the prior art, the invention has the following beneficial effects: (1) Based on the network relation characteristic information and the time sequence characteristic information, the invention judges the heat development trend of the public opinion event through analyzing the transmission activity index of the target public opinion event in each professional field. The network relation feature analysis among the professional fields is beneficial to understanding the mutual dependence, cooperation and influence relation among different fields, so that the decision maker can be helped to know the possible influence range and development direction of the public opinion event in advance based on the heat development trend judgment result obtained by the network relation feature analysis method of the professional fields, and further help the decision maker to make a corresponding public opinion event heat regulation decision in time.
(2) According to the method, emotion tendencies and development trends of target public opinion events are judged by analyzing emotion recognition consistency coefficients of various professional fields and emotion recognition consistency coefficients of people. The analysis of the emotion recognition consistency coefficient can be used as a basis for public opinion risk early warning, and when the emotion recognition consistency coefficient is lower than a certain threshold value, the meaning that the development trend of the target public opinion event possibly has public opinion crisis. Therefore, through analyzing emotion recognition consistency coefficients of professional fields and masses, the information such as the degree of support and objection of the public to the event can be comprehensively known, so that the atmosphere and the public opinion trend of the society can be better mastered, corresponding measures can be timely taken, the public opinion can be actively responded, negative influence can be effectively controlled, the public opinion risk is reduced, meanwhile, the public opinion opportunity can be timely captured, and the reputation and influence of enterprises or organizations are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the system module connection of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a public opinion event development trend judging system based on multidimensional feature analysis, the system comprises: the system comprises a public opinion event data collection module, a network relation analysis module, a time floating trend analysis module, a public opinion event heat development trend judgment module, an information base, an emotion analysis module and a public opinion event emotion development trend judgment module. The public opinion data collection module is respectively connected with the network relation analysis module and the time floating trend analysis module, the public opinion event heat development trend judgment module is respectively connected with the network relation analysis module and the time floating trend analysis module, the information base is connected with the time floating trend analysis module, and the emotion analysis module is connected with the public opinion event emotion development trend judgment module.
The public opinion event data collection module is used for obtaining related information of target public opinion events, wherein the related information comprises network relation characteristic information and time sequence characteristic information.
Illustratively, the network relationship characteristic information includes a propagation density and a propagation breadth within each of the specialized fields.
The time series characteristic information includes the predicted development duration and development fluctuation rate of the target public opinion event.
The network relation analysis module is used for analyzing the transmission activity index of the target public opinion event in each professional field based on the network relation characteristic information.
Illustratively, the specific steps of analyzing the spreading activity index of the target public opinion event in each professional field are as follows: and classifying and screening all user identities in the multimedia platform based on the user ID authentication information to obtain corresponding associated users in each professional field. The user ID authentication information comprises a professional field and a geographic position, the professional field comprises culture, society, science and technology, environment, education, entertainment and sports corresponding fields, and the associated user comprises expert authoritative users, official media users and public personnel users.
Acquiring the occurrence time period of a target public opinion event, and counting the number of communication posts related to the target public opinion event, which are issued by corresponding associated users in each professional field in the occurrence time period，/>Indicates the professional field number,/-, and>，/>number representing associated user->。
The time period of the target public opinion event is a time period corresponding to the time period from the start of the target public opinion event to the current time, and the start of the target public opinion event refers to a time point when the target public opinion event is greatly propagated on the multimedia platform.
Specifically, the method for acquiring the starting occurrence time of the target public opinion event is as follows: and analyzing the text contents of the communication paste issued by all users of the multimedia platform in real time by adopting a language text processing mode to obtain the posting quantity of the multimedia platform to each public opinion event at each time point, and when detecting that the posting quantity of the multimedia platform to a public opinion event at a certain time point exceeds a preset posting quantity threshold value, marking the time point as the occurrence time of the event, and marking the public opinion event as a target public opinion event.
The statistical mode of the number of the communication posts related to the target public opinion event, which are issued by the corresponding associated users in each professional field in the occurrence time period, is as follows: extracting all the communication post titles issued by the corresponding associated users in each professional field in the occurrence time period from the multimedia platform, matching the communication post titles with the corresponding titles of the target public opinion events, and counting to obtain the number of the communication posts issued by the corresponding associated users in each professional field in the occurrence time period, wherein the titles can be successfully matched, namely the number of the communication posts related to the target public opinion events issued by the corresponding associated users in each professional field in the occurrence time period.
Extracting forwarding quantity and comment quantity corresponding to each communication post related to the target public opinion event and issued by each relevant user in each professional field, and respectively marking the forwarding quantity and comment quantity as，/>Representing the number of the communication post>。
From the calculation formulaObtaining the transmission density of the target public opinion event in each professional field, < ->The number of the reference ac posts, the reference forwarding amount and the reference comment amount are respectively set.
Extracting geographic positions of forwarding users and comment users corresponding to the communication posts related to the target public opinion event and issued by the relevant users in the professional fields, and performing de-duplication processing to obtain the number of geographic positions of the target public opinion event propagated in the professional fieldsBy->Obtaining the spread breadth of the target public opinion event in each professional field, < >>Influence correction factor for the set propagation breadth, +.>For a set number of reference geographic locations.
Weight setting is carried out on the propagation density to obtain the corresponding weight of the propagation density of the target public opinion event in each professional fieldFurther analyze the spreading activity index of the target public opinion event in each professional field>Wherein->To set constant +.>。
The time floating trend analysis module is used for analyzing the propagation depth influence factor of the target public opinion event based on the time sequence characteristic information.
Illustratively, the analyzing the propagation depth influence factor of the target public opinion event includes: (41) Dividing the occurrence time period of the target public opinion event according to the set duration to obtain each sub-time stage, and recording the transmission density and the transmission breadth of the target public opinion event in each professional field in real time.
(41) Extracting the propagation density and propagation breadth of the target public opinion event in each professional field in each sub-time stage, and calculating the propagation activity index of the target public opinion event in each professional field in the occurrence time periodThe same theory calculates to obtain the transmission activity index of the target public opinion event in each professional field in each sub-time stage，/>Representing the sub-time phase number,/->Further analyzing and obtaining the development fluctuation rate of the target public opinion event，/>Is the number of sub-time periods>Is the number of professional fields.
And the propagation density and the propagation breadth of the target public opinion event in each professional field corresponding to each sub-time stage are the propagation density and the propagation breadth of the target public opinion event in each professional field corresponding to the corresponding ending time of each sub-time stage.
(42) The professional field corresponding to the target public opinion event is used as the appointed professional field, each historical event corresponding to the appointed professional field and the historical development time length of each historical event are extracted from the information base, the reference event is screened, and the predicted development time length of the target public opinion event is obtained through analysis according to the historical development time length of the reference eventWherein->For reference to the time length of the historical development of the event, +.>For the occurrence time period of the target public opinion event, < +.>A deviation compensation time length for the set estimated development time length;
(43) Substituting the predicted development duration and the development fluctuation rate of the target public opinion event into a formulaObtaining the transmission depth influence factor of the target public opinion event>Wherein->For a set reference development time period.
The historical development time length of each historical event is obtained by the following steps: and monitoring the development fluctuation rate of each historical event in real time, and when the development fluctuation rate of a certain historical event is smaller than a set development fluctuation rate threshold value in a set monitoring time period, marking the starting time corresponding to the set monitoring time period as the ending time of the historical event, and further taking the time interval between the starting time and the ending time of each historical event as the historical development time of each historical event.
The method for acquiring the starting time of each historical event is the same as the method for acquiring the starting time of the target public opinion event.
The method for screening the reference event is as follows: (51) Extracting a development fluctuation rate change curve of each historical event in the historical development time from an information base, taking the corresponding time of the occurrence time period of the target public opinion event as the reference time, and extracting the corresponding development fluctuation rate of each historical event at the ending time of the historical event in the reference time，/>The number of the historical event is given,。
(52) And screening the maximum value of the transmission active indexes of the target public opinion event in each sub-time stage from the transmission active indexes of the target public opinion event in each corresponding professional field in each sub-time stage, and extracting the corresponding professional field number.
(53) Extracting the propagation density and propagation breadth change curve of each historical event in each professional field in the historical development time period from an information base, and screening to obtain the corresponding reference field number of the maximum value of the propagation activity index of each historical event in each sub-time period in the reference time period according to the calculation mode of the propagation activity index of the target public opinion event in each professional field in each sub-time period.
(54) Sequentially comparing the professional domain numbers corresponding to the maximum value of the propagation active indexes of the target public opinion events in each sub-time stage with the corresponding reference domain numbers corresponding to the maximum value of the propagation active indexes of the history events in the sub-time stages corresponding to the reference duration according to the sequencing order of each sub-time stage to obtain the domain number matching quantity of the history events and the target public opinion events。
(55) Calculating the comprehensive similarity of each historical event and the target public opinion event，/>Wherein->Setting reference values corresponding to the event development fluctuation rate and the number matching number respectively, +.>The set event development fluctuation rate and the number matching quantity respectively correspond to the influence weight ratio, and e is natural normalAnd acquiring a historical event corresponding to the maximum value of the comprehensive similarity, and recording the historical event as a reference event.
The public opinion event heat development trend judging module is used for calculating the current activity index of the target public opinion event based on the transmission activity index of the target public opinion event in each professional field and judging the heat development trend of the target public opinion event by combining the transmission depth influence factor of the target public opinion event.
The step of judging the heat development trend of the target public opinion event is as follows: to be used forAs the current active index of the target public opinion event, combining the transmission depth influence factor of the target public opinion event +.>Calculating to obtain the heat development ductility index of the target public opinion event>，/>And respectively setting the current activity index and the propagation depth influence factor to correspond to the duty ratio weights.
The method comprises the steps of defining the range of the heat development ductility index of the public opinion event according to a set principle to obtain the range of the heat development ductility index of the public opinion event corresponding to each heat development trend, wherein the heat development trend comprises an ascending trend, a gentle trend and a descending trend, and further matching the heat development ductility index of the target public opinion event with the range of the heat development ductility index of the public opinion event corresponding to each heat development trend to obtain the heat development trend corresponding to the heat development ductility index of the target public opinion event.
Based on the network relation characteristic information and the time sequence characteristic information, the invention judges the heat development trend of the public opinion event through analyzing the transmission activity index of the target public opinion event in each professional field. The network relation feature analysis among the professional fields is beneficial to understanding the mutual dependence, cooperation and influence relation among different fields, so that the decision maker can be helped to know the possible influence range and development direction of the public opinion event in advance based on the heat development trend judgment result obtained by the network relation feature analysis method of the professional fields, and further help the decision maker to make a corresponding public opinion event heat regulation decision in time.
The information base is used for storing each historical event corresponding to each professional field and the historical development time length of each historical event, and storing the development fluctuation rate change curve of each historical event in the historical development time length and the propagation density and propagation breadth change curve of each historical event in the corresponding professional field in the historical development time length.
The emotion analysis module is used for acquiring text contents of each communication post issued by corresponding relevant users in each professional field, judging emotion tendencies expressed in the text contents of each communication post, and accordingly evaluating emotion acceptance consistency coefficients in each professional field.
Illustratively, the step of determining the emotion tendencies expressed in the text content of each communication post includes: (71) And removing repeated words and part of speech labeling processing is carried out on the text contents of each communication post by adopting a language text processing mode, and then emotion analysis is carried out on the processed text contents of the communication post by using an emotion classification algorithm, so that each emotion vocabulary corresponding to the text contents of each communication post is obtained.
(72) Classifying and summarizing emotion vocabularies in each professional field according to a preset principle to obtain emotion tendency vocabulary libraries corresponding to each professional field, wherein emotion tendency comprises positive emotion tendency, negative emotion tendency and neutral emotion tendency.
(73) According to the professional field corresponding to each communication post, comparing each emotion vocabulary corresponding to each communication post text content with each emotion tendency vocabulary library corresponding to the professional field to obtain each emotion tendency vocabulary corresponding to each communication post text content, and taking the emotion tendency corresponding to the maximum emotion tendency vocabulary in each communication post text content as the emotion tendency expressed in each communication post text content.
Illustratively, the evaluation mode for evaluating the emotion recognition consistency coefficient of each professional field is as follows: and judging and obtaining the emotion tendencies expressed in the text contents of the communication posts issued by the corresponding associated users in the professional fields based on the emotion tendencies corresponding judging step expressed in the text contents of the communication posts.
Collecting corresponding release time of each communication post released by each associated user in each professional field, and counting to obtain the number of positive emotion tendency communication posts released by each associated user in each professional field in each sub-time periodFrom the calculation formulaAnd obtaining the consistency coefficient of the positive emotion tendencies of the professional fields.
The uniformity coefficient of the negative emotion tendencies and the uniformity coefficient of the neutral emotion tendencies in each professional field are obtained by the same analysis and respectively marked as。
Illustratively, the means for analyzing the emotion recognition consistency coefficient of the crowd is as follows: based on the emotion tendency corresponding step expressed in the text content of each communication post, the same theory carries out emotion tendency judgment on comment text content of each comment user corresponding to the positive emotion tendency communication post issued by each associated user in each time period in each professional field, and statistics is carried out to obtain the number of comment users positively agreed to corresponding to the positive emotion tendency communication post issued by each associated user in each time period in each professional fieldFurther, by the calculation formula->And obtaining the consistency coefficient of the positive emotion tendencies of the masses.
The uniformity coefficient of the negative emotion tendencies of the masses is obtained through the same analysis, and the uniformity coefficient of the negative emotion tendencies of the masses is identical with the uniformity coefficient of the neutral emotion tendencies of the massesSex coefficients, respectively noted as。
The public opinion event emotion development trend judging module is used for acquiring comment text contents, corresponding to comment users, of each communication post issued by each associated user in each professional field, analyzing emotion acceptance consistency coefficients of people according to the comment text contents, and judging emotion trend development trend of a target public opinion event by combining the emotion acceptance consistency coefficients of each professional field.
The specific content of the emotional tendency development trend of the judgment target public opinion event is as follows: will beSubstitution formula->And obtaining the positive emotion tendency development consistency index of the target public opinion event, and similarly obtaining the negative emotion tendency development consistency index and the neutral emotion tendency development consistency index of the target public opinion event, comparing the positive emotion tendency development consistency index and the neutral emotion tendency development consistency index to obtain the emotion tendency corresponding to the maximum value of the emotion tendency development consistency index of the target public opinion event, and taking the emotion tendency as the development emotion tendency of the target public opinion event.
According to the method, emotion tendencies and development trends of target public opinion events are judged by analyzing emotion recognition consistency coefficients of various professional fields and emotion recognition consistency coefficients of people. The analysis of the emotion recognition consistency coefficient can be used as a basis for public opinion risk early warning, and when the emotion recognition consistency coefficient is lower than a certain threshold value, the meaning that the development trend of the target public opinion event possibly has public opinion crisis. Therefore, through analyzing emotion recognition consistency coefficients of professional fields and masses, the information such as the degree of support and objection of the public to the event can be comprehensively known, so that the atmosphere and the public opinion trend of the society can be better mastered, corresponding measures can be timely taken, the public opinion can be actively responded, negative influence can be effectively controlled, the public opinion risk is reduced, meanwhile, the public opinion opportunity can be timely captured, and the reputation and influence of enterprises or organizations are improved.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (10)
1. A public opinion event development trend judging system based on multidimensional feature analysis is characterized in that: the system comprises:
public opinion event data collection module: the method comprises the steps that related information of a target public opinion event is obtained, wherein the related information comprises network relation characteristic information and time sequence characteristic information;
a network relation analysis module: the method is used for analyzing the transmission activity index of the target public opinion event in each professional field based on the network relation characteristic information;
time floating trend analysis module: the method comprises the steps of analyzing a propagation depth influence factor of a target public opinion event based on time sequence characteristic information;
public opinion event heat development trend judging module: the method comprises the steps of calculating the current activity index of a target public opinion event based on the transmission activity index of the target public opinion event in each professional field, and judging the heat development trend of the target public opinion event by combining the transmission depth influence factor of the target public opinion event;
information base: the method is used for storing each historical event corresponding to each professional field and the historical development time length of each historical event, and storing the development fluctuation rate change curve of each historical event in the historical development time length and the propagation density and propagation breadth change curve of each historical event in the corresponding professional field in the historical development time length;
emotion analysis module: the emotion recognition consistency coefficient of each professional field is evaluated according to the emotion tendency expressed in the text content of each communication post;
public opinion event emotion development trend judging module: the method is used for acquiring comment text contents of comment users corresponding to each communication post issued by each associated user in each professional field, analyzing emotion recognition consistency coefficients of masses, and judging emotion tendency development trend of target public opinion events by combining the emotion recognition consistency coefficients of each professional field.
2. The system for judging the development trend of a public opinion event based on multidimensional feature analysis according to claim 1, wherein the system comprises: the network relation characteristic information comprises propagation density and propagation breadth in each professional field;
the time series characteristic information includes the predicted development duration and development fluctuation rate of the target public opinion event.
3. The system for judging the development trend of the public opinion event based on the multidimensional feature analysis according to claim 2, wherein the system is characterized in that: the specific steps of analyzing the transmission activity index of the target public opinion event in each professional field are as follows:
classifying and screening all user identities in the multimedia platform based on the user ID authentication information to obtain corresponding associated users in each professional field;
acquiring the occurrence time period of a target public opinion event, and counting the number of communication posts related to the target public opinion event, which are issued by corresponding associated users in each professional field in the occurrence time period，/>Indicates the professional field number,/-, and>，/>number representing associated user->；
Extracting forwarding quantity and comment quantity corresponding to each communication post related to the target public opinion event and issued by each relevant user in each professional field, and respectively marking the forwarding quantity and comment quantity as，/>Representing the number of the communication post>；
From the calculation formulaObtaining the transmission density of the target public opinion event in each professional field, < ->The method comprises the steps of respectively setting the number of the reference alternating-current posts, the reference forwarding quantity and the reference comment quantity;
extracting geographic positions of forwarding users and comment users corresponding to the communication posts related to the target public opinion event and issued by the relevant users in the professional fields, and performing de-duplication processing to obtain the number of geographic positions of the target public opinion event propagated in the professional fieldsBy->Obtaining the spread breadth of the target public opinion event in each professional field, < >>Influence correction factor for the set propagation breadth, +.>To be set upReferring to the number of geographic locations;
weight setting is carried out on the propagation density to obtain the corresponding weight of the propagation density of the target public opinion event in each professional fieldFurther analyze the spreading activity index of the target public opinion event in each professional field>Wherein->To set constant +.>。
4. The public opinion event development trend judging system based on multidimensional feature analysis of claim 3, wherein: the corresponding analysis step of analyzing the propagation depth influence factor of the target public opinion event comprises the following steps:
(41) Dividing the occurrence time period of the target public opinion event according to the set duration to obtain each sub-time stage, and recording the transmission density and the transmission breadth of the target public opinion event in each professional field in real time;
(42) Extracting the propagation density and propagation breadth of the target public opinion event in each professional field in each sub-time stage, and calculating to obtain the propagation activity index of the target public opinion event in each professional field in each sub-time stage，/>Representing the sub-time phase number,/->Further analyze and obtain target public opinionRate of progression fluctuation of emotional events，/>Is the number of sub-time periods>Is the number of professional fields;
(43) The professional field corresponding to the target public opinion event is used as the appointed professional field, each historical event corresponding to the appointed professional field and the historical development time length of each historical event are extracted from the information base, the reference event is screened, and the predicted development time length of the target public opinion event is analyzed according to the historical development time length of the reference event；
(44) Substituting the predicted development duration and the development fluctuation rate of the target public opinion event into a formulaObtaining the transmission depth influence factor of the target public opinion event>Wherein->For a set reference development time period.
5. The system for judging the trend of public opinion events based on multidimensional feature analysis of claim 4, wherein: the historical development time length of each historical event is obtained by the following steps: and monitoring the development fluctuation rate of each historical event in real time, and when the development fluctuation rate of a certain historical event is smaller than a set development fluctuation rate threshold value in a set monitoring time period, marking the starting time corresponding to the set monitoring time period as the ending time of the historical event, and further taking the time interval between the starting time and the ending time of each historical event as the historical development time of each historical event.
6. The system for judging the trend of public opinion events based on multidimensional feature analysis of claim 4, wherein: the step of judging the heat development trend of the target public opinion event comprises the following steps:
to be used forAs the current active index of the target public opinion event, combining the transmission depth influence factor of the target public opinion event +.>Calculating to obtain the heat development ductility index of the target public opinion event>，/>The corresponding duty ratio weights of the set current activity index and the propagation depth influence factor are respectively set;
and demarcating the range of the heat development ductility index of the public opinion event according to a set principle to obtain the range of the heat development ductility index of the public opinion event corresponding to each heat development trend, wherein the heat development trend comprises an ascending trend, a gentle trend and a descending trend, and the heat development trends corresponding to the heat development ductility index of the target public opinion event are obtained by matching.
7. The public opinion event development trend judging system based on multidimensional feature analysis of claim 3, wherein: the emotion tendency corresponding step expressed in the text content of each communication post is judged as follows:
(71) Removing repeated words and part of speech labeling processing is carried out on the text contents of each communication post by adopting a language text processing mode, and emotion analysis is carried out on the processed text contents of each communication post by using an emotion classification algorithm, so that each emotion vocabulary corresponding to the text contents of each communication post is obtained;
(72) Classifying and summarizing emotion vocabularies in each professional field according to a preset principle to obtain emotion tendency vocabulary libraries corresponding to each professional field, wherein emotion tendency comprises positive emotion tendency, negative emotion tendency and neutral emotion tendency;
(73) According to the professional field corresponding to each communication post, comparing each emotion vocabulary corresponding to each communication post text content with each emotion tendency vocabulary library corresponding to the professional field to obtain each emotion tendency vocabulary corresponding to each communication post text content, and taking the emotion tendency corresponding to the maximum emotion tendency vocabulary in each communication post text content as the emotion tendency expressed in each communication post text content.
8. The system for judging the trend of public opinion events based on multidimensional feature analysis of claim 7, wherein: the evaluation mode for evaluating the emotion acceptance consistency coefficient of each professional field is as follows:
judging and obtaining emotion tendencies expressed in the text contents of each communication post issued by corresponding relevant users in each professional field based on the emotion tendencies corresponding judging and expressing in the text contents of each communication post;
collecting corresponding release time of each communication post released by each associated user in each professional field, and counting to obtain the number of positive emotion tendency communication posts released by each associated user in each professional field in each sub-time periodFrom the calculation formulaObtaining the consistency coefficient of the positive emotion tendencies of each professional field;
the uniformity coefficient of the negative emotion tendencies and the uniformity coefficient of the neutral emotion tendencies in each professional field are obtained by the same analysis and respectively marked as。
9. The system for judging the trend of public opinion events based on multidimensional feature analysis of claim 8, wherein: the method for analyzing the emotion recognition consistency coefficient of the masses comprises the following steps:
judging emotion tendencies of comment text contents of comment users corresponding to the positive emotion tendencies of corresponding associated users in each professional field and corresponding to each comment user in each sub-time period, and counting to obtain the number of comment users corresponding to positive acceptance of the positive emotion tendencies of corresponding associated users in each professional field and corresponding to each associated user in each sub-time periodFurther, by the calculation formula->Obtaining a consistency coefficient of positive emotion tendencies acceptance of the masses;
the same analysis is carried out to obtain a coefficient of consistency of the negative emotion tendencies of the masses and a coefficient of consistency of the neutral emotion tendencies of the masses, which are respectively recorded as。
10. The system for judging the trend of public opinion events based on multidimensional feature analysis of claim 9, wherein: the specific content of the emotion tendency development trend of the judgment target public opinion event is as follows: will beSubstitution formulaObtaining the positive emotion tendency development consistency index of the target public opinion event, and obtaining the sameThe negative emotion tendency development consistency index and the neutral emotion tendency development consistency index of the target public opinion event are compared with each other to obtain emotion tendency corresponding to the maximum value of the emotion tendency development consistency index of the target public opinion event, and the emotion tendency is taken as the development emotion tendency of the target public opinion event. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311304646.4A CN117076751B (en) | 2023-10-10 | 2023-10-10 | Public opinion event development trend judging system based on multidimensional feature analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311304646.4A CN117076751B (en) | 2023-10-10 | 2023-10-10 | Public opinion event development trend judging system based on multidimensional feature analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117076751A true CN117076751A (en) | 2023-11-17 |
| CN117076751B CN117076751B (en) | 2024-01-16 |
Family
ID=88711936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311304646.4A Active CN117076751B (en) | 2023-10-10 | 2023-10-10 | Public opinion event development trend judging system based on multidimensional feature analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117076751B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776841A (en) * | 2016-11-28 | 2017-05-31 | 福建亿榕信息技术有限公司 | The acquisition methods and system of a kind of internet public feelings event propagation index |
| CN108549957A (en) * | 2018-04-11 | 2018-09-18 | 中译语通科技股份有限公司 | Internet topic trend auxiliary prediction technique and system, information data processing terminal |
| CN109508416A (en) * | 2018-11-09 | 2019-03-22 | 四川大学 | Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN110705288A (en) * | 2019-09-29 | 2020-01-17 | 武汉海昌信息技术有限公司 | Big data-based public opinion analysis system |
| CN111461553A (en) * | 2020-04-02 | 2020-07-28 | 上饶市中科院云计算中心大数据研究院 | System and method for monitoring and analyzing public sentiment in scenic spot |
| CN111538888A (en) * | 2020-06-05 | 2020-08-14 | 国网山东省电力公司检修公司 | Network public opinion intensity evolution analysis system based on active monitoring engine and big data |
| CN113535899A (en) * | 2021-07-07 | 2021-10-22 | 西安康奈网络科技有限公司 | Automatic studying and judging method for internet information emotion tendentiousness |
| CN114742281A (en) * | 2022-03-21 | 2022-07-12 | 西北工业大学 | Public event network public opinion popularity prediction method based on grey model |
| WO2023050652A1 (en) * | 2021-09-28 | 2023-04-06 | 平安科技（深圳）有限公司 | Text recognition-based method for determining esg index in region, and related product |
| CN116450924A (en) * | 2022-09-09 | 2023-07-18 | 深圳市生态环境智能管控中心 | Analysis module and method of intelligent environment-friendly platform ecological environment public opinion monitoring system |
-
2023
- 2023-10-10 CN CN202311304646.4A patent/CN117076751B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776841A (en) * | 2016-11-28 | 2017-05-31 | 福建亿榕信息技术有限公司 | The acquisition methods and system of a kind of internet public feelings event propagation index |
| CN108549957A (en) * | 2018-04-11 | 2018-09-18 | 中译语通科技股份有限公司 | Internet topic trend auxiliary prediction technique and system, information data processing terminal |
| CN109508416A (en) * | 2018-11-09 | 2019-03-22 | 四川大学 | Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews |
| CN110245792A (en) * | 2019-06-03 | 2019-09-17 | 北京清博大数据科技有限公司 | A kind of network public opinion prediction method, device, terminal and storage medium |
| CN110705288A (en) * | 2019-09-29 | 2020-01-17 | 武汉海昌信息技术有限公司 | Big data-based public opinion analysis system |
| CN111461553A (en) * | 2020-04-02 | 2020-07-28 | 上饶市中科院云计算中心大数据研究院 | System and method for monitoring and analyzing public sentiment in scenic spot |
| CN111538888A (en) * | 2020-06-05 | 2020-08-14 | 国网山东省电力公司检修公司 | Network public opinion intensity evolution analysis system based on active monitoring engine and big data |
| CN113535899A (en) * | 2021-07-07 | 2021-10-22 | 西安康奈网络科技有限公司 | Automatic studying and judging method for internet information emotion tendentiousness |
| WO2023050652A1 (en) * | 2021-09-28 | 2023-04-06 | 平安科技（深圳）有限公司 | Text recognition-based method for determining esg index in region, and related product |
| CN114742281A (en) * | 2022-03-21 | 2022-07-12 | 西北工业大学 | Public event network public opinion popularity prediction method based on grey model |
| CN116450924A (en) * | 2022-09-09 | 2023-07-18 | 深圳市生态环境智能管控中心 | Analysis module and method of intelligent environment-friendly platform ecological environment public opinion monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117076751B (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992968B (en) | Electric energy meter metering error prediction method based on integrated time series analysis technology | |
| CN112035658B (en) | Enterprise public opinion monitoring method based on deep learning | |
| CN109359137B (en) | User growth portrait construction method based on feature screening and semi-supervised learning | |
| CN111309864B (en) | User group emotional tendency migration dynamic analysis method for microblog hot topics | |
| CN110472256B (en) | Machine translation engine evaluation optimization method and system based on chapters | |
| WO2017071474A1 (en) | Method and device for processing language data items and method and device for analyzing language data items | |
| CN111966878A (en) | Public sentiment event reversal detection method based on machine learning | |
| CN111415131A (en) | Big data talent resume analysis method based on natural language processing technology | |
| CN115396389A (en) | Internet of things information technology customer service system based on emotion energy perception | |
| CN109543041A (en) | A kind of generation method and device of language model scores | |
| CN110958472A (en) | Video click rate rating prediction method and device, electronic equipment and storage medium | |
| CN117076751B (en) | Public opinion event development trend judging system based on multidimensional feature analysis | |
| CN116342074B (en) | Engineering project consultation expert base talent matching service system | |
| CN111221915B (en) | Online learning resource quality analysis method based on CWK-means | |
| CN111078859B (en) | Author recommendation method based on reference times | |
| CN109460474B (en) | User preference trend mining method | |
| CN116307792B (en) | Urban physical examination subject scene-oriented evaluation method and device | |
| Siregar | Application of the Naive Bayes classifier method in the sentiment analysis of Twitter user about the capital city relocation | |
| Yan et al. | User recommendation with tensor factorization in social networks | |
| CN112541010A (en) | User gender prediction method based on logistic regression | |
| CN113641918B (en) | Regional air environment quality monitoring system and method based on big data | |
| CN113961818B (en) | Group demand prediction method based on long-short-period interests and social influence | |
| CN111178982B (en) | Customer satisfaction analysis method, storage medium and computer device | |
| CN108805458A (en) | A kind of enterprise technology Competitiveness Assessment method and device | |
| CN113590673A (en) | Data heat degree statistical method based on block chain deep learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |