CN112785146B - Method and system for evaluating network public sentiment - Google Patents
Method and system for evaluating network public sentiment Download PDFInfo
- Publication number
- CN112785146B CN112785146B CN202110073905.1A CN202110073905A CN112785146B CN 112785146 B CN112785146 B CN 112785146B CN 202110073905 A CN202110073905 A CN 202110073905A CN 112785146 B CN112785146 B CN 112785146B
- Authority
- CN
- China
- Prior art keywords
- information
- obtaining
- time
- evaluation
- obtaining unit
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 125
- 238000013210 evaluation model Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 21
- 238000007477 logistic regression Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 12
- 238000003062 neural network model Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000005056 compaction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 241000931705 Cicada Species 0.000 description 1
- 241000282806 Rhinoceros Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an assessment method and system of network public sentiment, which are used for obtaining first event information; obtaining a first event occurrence time; obtaining a first time difference, and taking the first time difference as first input information; detecting vocabularies of the first file to obtain a first risk level; obtaining a first browsing volume of a first file from a first publishing time to a second time, and obtaining a first incremental index according to the first browsing volume; performing risk assessment on the first incremental index according to a first assessment instruction to obtain a second risk level; obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information; and inputting the first input information and the second input information into the first public opinion evaluation model to obtain first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result. The technical problem that assessment of network public sentiment is not intelligent and accurate enough in the prior art is solved.
Description
Technical Field
The invention relates to the field of network public opinion evaluation, in particular to a method and a system for evaluating network public opinions.
Background
With the rapid development of microblogs, weChat and social networks, the great power of network public sentiment promotes the rapid development of the whole public sentiment industry. Internet public sentiment enters a high-speed development period. Due to the openness and the virtualization of the network, the characteristics of directness, burstiness and deviation of network public sentiment are determined. The internet has more and more netizens spreading expression viewpoints through related channels, so that effective real-time monitoring and guidance of public opinions have positive significance for maintaining social stability and creating a harmonious society.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problem that assessment of network public sentiment is not intelligent and accurate enough exists in the prior art.
Disclosure of Invention
The embodiment of the application provides the method and the system for evaluating the network public sentiment, solves the technical problem that the evaluation of the network public sentiment is not intelligent and accurate enough in the prior art, and achieves the technical effect of intelligent and accurate evaluation of the network public sentiment.
In view of the foregoing problems, the present invention provides a method and a system for assessing internet public sentiment.
In a first aspect, an embodiment of the present application provides an online public opinion evaluation method, where the method is applied to an online public opinion evaluation system, and the online public opinion evaluation system is communicatively connected to an information receiving module and a first public opinion evaluation model, where the method includes: obtaining first event information through the information receiving module; performing information analysis on the first event information to obtain first event occurrence time; obtaining a first time difference, wherein the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information; performing vocabulary detection on the first file, and acquiring a first risk level according to a vocabulary detection result; obtaining a first browsing volume of the first file from a first publishing time to a second time, and obtaining a first incremental index according to the first browsing volume; obtaining a first evaluation instruction, and performing risk evaluation on the first incremental index according to the first evaluation instruction to obtain a second risk level; obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information; inputting the first input information and the second input information into the first public opinion assessment model, wherein the first public opinion assessment model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result.
On the other hand, this application still provides an evaluation system of online public opinion, the system includes: a first obtaining unit, configured to obtain first event information through an information receiving module; a second obtaining unit, configured to perform information analysis on the first event information to obtain a first event occurrence time; a third obtaining unit, configured to obtain a first time difference, where the first time difference is a time difference between a first issue time of a first pattern and a first event occurrence time, and the first time difference is used as first input information; a fourth obtaining unit, configured to perform vocabulary detection on the first document, and obtain a first risk level according to the vocabulary detection result; a fifth obtaining unit, configured to obtain a first browsing volume of the first document from a first publishing time to a second publishing time, and obtain a first incremental index according to the first browsing volume; a sixth obtaining unit, configured to obtain a first evaluation instruction, perform risk evaluation on the first incremental index according to the first evaluation instruction, and obtain a second risk level; a seventh obtaining unit, configured to obtain a third risk level according to the first risk level and the second risk level, and use the third risk level as second input information; a first input unit, configured to input the first input information and the second input information into a first public opinion evaluation model, where the first public opinion evaluation model is obtained through training of multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result; an eighth obtaining unit, configured to obtain first output information of the first public opinion evaluation model, where the first output information includes a first evaluation result.
In a third aspect, the present invention provides an online public opinion assessment system, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method of the first aspect.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the technical effect of accurately and intelligently evaluating whether the first event and the public opinion guidance are misled or not according to the first evaluation result is achieved by using the first time difference as first input information, carrying out vocabulary detection on the vocabulary of the first document, obtaining a first risk grade according to a vocabulary detection result, obtaining a first incremental index according to a first browsing amount of the first document from the first publishing time to a second time, evaluating the incremental index according to a first evaluation instruction, obtaining a second risk grade, obtaining a third risk grade according to the first risk grade and the second risk grade, using the third risk grade as second input information, inputting the first input information and the second input information into a first public opinion evaluation model, obtaining a first evaluation result of the first public opinion evaluation model, and obtaining a technical effect of accurately and intelligently evaluating whether the first event and the public opinion guidance are misled or not according to the first evaluation result.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
Fig. 1 is a flowchart illustrating an evaluation method of internet public sentiment according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an evaluation system for internet public opinion according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of the reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a sixth obtaining unit 16, a seventh obtaining unit 17, a first input unit 18, an eighth obtaining unit 19, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, a bus interface 306.
Detailed Description
The embodiment of the application provides the method and the system for evaluating the network public opinion, solves the technical problem that the evaluation of the network public opinion is not intelligent and accurate enough in the prior art, and achieves the technical effect of intelligently and accurately evaluating the network public opinion. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Summary of the application
With the rapid development of microblogs, weChat and social networks, the great power of network public sentiment promotes the rapid development of the whole public sentiment industry. Internet public sentiment enters a high-speed development period. Due to the openness and the virtualization of the network, the characteristics of immediacy, burstiness and deviation of the network public opinion are determined. The internet has more and more netizens to spread expression viewpoints through related channels, so that effective real-time monitoring and guidance of public opinion have positive significance for maintaining social stability and creating a harmonious society. But the prior art has the technical problem that the evaluation of the network public sentiment is not intelligent and accurate enough.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an evaluation method of network public sentiment, the method is applied to a network public sentiment evaluation system, the network public sentiment evaluation system is in communication connection with an information receiving module and a first public sentiment evaluation model, and the method comprises the following steps: obtaining first event information through the information receiving module; performing information analysis on the first event information to obtain first event occurrence time; obtaining a first time difference, wherein the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information; performing vocabulary detection on the first file, and obtaining a first risk level according to the vocabulary detection result; obtaining a first browsing volume of the first file from a first publishing time to a second time, and obtaining a first increment index according to the first browsing volume; obtaining a first evaluation instruction, and performing risk evaluation on the first incremental index according to the first evaluation instruction to obtain a second risk level; obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information; inputting the first input information and the second input information into the first public opinion assessment model, wherein the first public opinion assessment model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result.
Having described the principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present invention provides a method for online public opinion evaluation, the method being applied to an online public opinion evaluation system, the online public opinion evaluation system being communicatively connected to an information receiving module and a first public opinion evaluation model, wherein the method comprises:
step S100: obtaining first event information through the information receiving module;
specifically, the internet public opinion evaluation system is a system for evaluating internet public opinions, the evaluation content includes but is not limited to public opinion guidance, malicious comments, malicious attacks, etc., the information receiving module is a module for collecting and integrating information, the first public opinion evaluation model is a model which can be obtained through training of multiple sets of training data and can carry out public opinion evaluation according to related parameters, and the information receiving module integrates the information of the first event to obtain the origin, the passing, the result, the time, the place, the related person information, etc. of the first event known up to now.
Step S200: performing information analysis on the first event information to obtain the occurrence time of the first event;
specifically, the first time is the occurrence time of the first event, where the occurrence time is the occurrence time of the first event with evidence, i.e. without other changes of the state.
Step S300: obtaining a first time difference, wherein the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information;
specifically, the first scripture is scripture information related to the first event, and the first scripture is published scripture information obtained through capturing by a plurality of network platforms, wherein the plurality of scriptures include, but are not limited to, micro blogs, micro letters, cicada, BBS, post, news comments, news syndication, and the like. And obtaining a first time difference according to the release time of the first file and the occurrence time of the first event, and taking the first time difference as first input information.
Step S400: performing vocabulary detection on the first file, and obtaining a first risk level according to the vocabulary detection result;
specifically, the vocabulary detection is to recognize vocabulary and semantics of the content of the first document, specifically, to recognize sensitive vocabulary, guide vocabulary, attention-attracting vocabulary, and the like of the document in a targeted manner based on the property of the first event, specifically, to evaluate the rhinoceros degree, the value of expression, and the like of the first document based on the property of the first event, and to obtain the first risk level based on the evaluation result.
Step S500: obtaining a first browsing volume of the first file from a first publishing time to a second time, and obtaining a first incremental index according to the first browsing volume;
specifically, the second time is after the first publishing time, the first publishing time is publishing time of the first file on a relevant platform, total browsing amount information of the first file in a time period from the first publishing time to the second time is obtained according to internal data statistics of the relevant platform from the first publishing time to the second time, the total browsing amount is the first browsing amount, the first increment index is a parameter reflecting an increase condition of the number of times the first file is browsed in a unit time, and the first increment index is obtained through a time difference from the first publishing time to the second time and the first browsing amount.
Step S600: obtaining a first evaluation instruction, and performing risk evaluation on the first incremental index according to the first evaluation instruction to obtain a second risk level;
step S700: obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information;
specifically, the first evaluation instruction is an instruction for evaluating the first incremental index, and the first incremental index obtained by calculation is evaluated according to the first evaluation instruction, wherein the evaluation includes an evaluation of whether the first incremental index exceeds the degree of attention of the first event, and an evaluation of whether the incremental index has abnormal increase, and a second risk level is obtained according to the evaluation result. And comprehensively considering the first risk level representing the vocabulary situation of the first file and the second risk level of the growth assessment of the first incremental index to obtain a third risk level, and taking the third risk level as second input information.
Step S800: inputting the first input information and the second input information into the first public opinion evaluation model, wherein the first public opinion evaluation model is obtained through training of multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result;
step S900: obtaining first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result.
Specifically, the first public opinion evaluation model is a Neural network model in machine learning, and Neural Networks (NN) are complex Neural network systems formed by widely connecting a large number of simple processing units (called neurons), reflect many basic features of human brain functions, and are highly complex nonlinear dynamical learning systems. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (Artificial Neural Networks) are a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And inputting the first input information and the second input information into a neural network model through training of a large amount of training data, and outputting a first evaluation result.
Furthermore, the training process further includes a supervised learning process, each group of supervised data includes the first input information, the second input information, and identification information identifying a first result, the first input information and the second input information are input into a neural network model, the neural network model performs continuous self-correction and adjustment according to the identification information identifying the first result, and the present group of supervised learning is ended until the obtained output result is consistent with the identification information, and the next group of supervised learning is performed; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through supervised learning of the neural network model, the neural network model can process the input information more accurately, so that a more accurate evaluation result of network public opinions is obtained, and the technical effect of accurately and intelligently evaluating whether the first event and public opinion guidance are misled or not is achieved.
Further, the obtaining a browsing volume of the first pattern from a first publishing time to a second publishing time, and obtaining a first incremental index according to the browsing volume, in step S500 of this embodiment of the present application, further includes:
step S510: obtaining a third time, wherein the third time is within the first time to the second time;
step S520: obtaining second browsing volume information from the first publishing time to the third time;
step S530: obtaining third browsing volume information from the third time to the second time;
step S540: obtaining a second time difference according to the first distribution time and the third time, and obtaining a third time difference according to the third time and the second time;
step S550: obtaining a second incremental index according to the second browsing volume information and the second time difference, and obtaining a third incremental index according to the third browsing volume information and the third time difference;
step S560: obtaining an average of the second incremental index and the third incremental index, and taking the average as the first incremental index.
Specifically, the third time is a certain time within a time period between the first publishing time and the second time, the third time is determined by a time point at which the browsing volume has a significant trend change between the first publishing time and the second time, when a turning point of the significant trend change of the browsing volume occurs, the time point at which the turning point occurs is obtained, the time point is a third time, a time interval from the first publishing time to the third time is obtained, the time interval is a second time difference, and second browsing volume information within the second time difference is obtained; and obtaining a time interval from the third time to the second time, wherein the time interval is a third time difference, obtaining third browsing volume information in the third time difference, obtaining a second incremental index according to the second browsing volume information and the second time difference, obtaining a third incremental index according to the third browsing volume information and the third time difference, and obtaining a first incremental index according to an average value of the second incremental index and the third incremental index. The incremental index is calculated by cutting the time point from the first publishing time to the second publishing time, so that the first incremental index which can more accurately reflect the trend of the change of the browsing volume can be obtained, and a foundation is laid for accurate and intelligent evaluation and compaction of the subsequent network public sentiment.
Further, the embodiment of the present application further includes:
step S561: obtaining a first incremental exponential threshold;
step S562: determining whether the third incremental index meets the first incremental index threshold;
step S563: obtaining first comment information for the third time when the third incremental index does not satisfy the first incremental index threshold;
step S564: obtaining first sensitive vocabulary information of the first comment information;
step S565: acquiring the first comment information to acquire first account information, taking the first sensitive vocabulary information as an abscissa and the first account information as an ordinate, and constructing a coordinate system;
step S566: and constructing a logistic regression line based on the coordinate system through a logistic regression model, and obtaining a second evaluation result through the logistic regression line.
Specifically, the first incremental index threshold is a threshold determined by the related information of the first event, that is, the expected total attention and the growth condition of the first event are obtained according to the time when the event occurs, the popularity of the main character of the event, and the nature of the event, the growth condition and the total attention are adjusted according to the social condition at that time, whether the third incremental index meets the first incremental index threshold is judged, when the third incremental index does not meet the first incremental index threshold, first comment information of the first document at the third time is obtained, the sensitivity of a first sensitive word of the first comment information is used as a horizontal coordinate, the account information condition of the first comment is used as a vertical coordinate, a rectangular coordinate system is constructed, a logical regression line is obtained through the rectangular coordinate system based on a logical regression model, wherein one side of the logical regression line represents a first result, wherein the first result is the other side of the first comment with an abnormality, the logical regression line represents a second result, the second result represents the first result of the sensitivity of the first event, the logical regression line and the sensitivity of the first comment is obtained based on the logical regression model, and the second result is obtained by inputting the first sensitive word into the logical comment model. And further judging the first comment information through the logistic regression line to obtain more accurate analysis results of whether the public sentiment is influenced and misled, thereby laying a foundation for accurate and intelligent evaluation of the network public sentiment in the follow-up process.
Further, the embodiment of the present application further includes:
step S5661: obtaining a first user according to the first account information, wherein the first user is a real-name authentication user of the first account information;
step S5662: judging whether the login equipment of the first account information is the common equipment of the first user or not, and obtaining a first index according to the judgment result;
step S5663: obtaining second account information of the first user, judging whether the second account information has abnormal remittance or not, and obtaining a second index according to the judgment result;
step S5664: and obtaining a third evaluation result according to the first index and the second index.
Specifically, the method includes obtaining real-name authentication information of a first account through registration information of the first account, and obtaining a first user according to the real-name authentication information, where the first user is an owner of the first account, determining, by a login device of the first account, whether the device is a common device for logging in the first account, and obtaining a first evaluation index according to a determination result, and further, obtaining the first evaluation index is further determined according to whether a login location of the first account is abnormal, where a second account of the first user includes an account that the second user can receive a transfer, and the method includes, but is not limited to: the method comprises the steps that a QQ account number, a WeChat account number, a Paibao account number, a bank card account number, a telephone number and the like are used for judging whether abnormal remittance exists in the second account number recently or not according to the information of the second account number, the remittance comprises single large-amount remittance and multiple small-amount remittance, a second evaluation index is obtained according to whether abnormal remittance exists or not, whether the first account is abnormal or not is evaluated according to the first index and the second index, whether public opinion is guided maliciously or not can be judged according to the evaluation result, and then accurate and intelligent evaluation of network public opinions is achieved.
Further, the determining whether the login device of the first account is a frequently-used device of the first user and obtaining a first index according to the determination result, in step S5662 of this embodiment of the present application, further includes:
step S56621: obtaining a second file of the first account information;
step S56622: performing semantic recognition on the second case to obtain a first semantic recognition result;
step S56623: judging whether the second file and the first comment information have a first degree of association according to the first semantic recognition result;
step S56624: when the second file and the first comment have the first relevance degree, obtaining a first identification instruction;
step S56625: identifying published contents of the first account information according to the first identification instruction to obtain a first identification result;
step S56626: obtaining a first attention degree of the first account;
step S56627: and taking the first recognition result and the first attention as the first index.
Specifically, the obtaining of the first index further includes analyzing other documents issued by the first account, where the analyzing includes obtaining second document information, performing semantic recognition on the second document, obtaining a first recognition result, and determining, according to the first recognition result, whether the second document and the first comment have a first degree of association, where the first degree of association is a name of a person, a name of a place, a time, or a content of an event itself where the first event occurs, and when the second document and the first comment have a first degree of attention, it indicates that the first user has too high degree of attention to the first event and a potential threat of malicious guidance may exist, at this time, obtaining a first recognition instruction, performing overall recognition on the documents issued by the first account information according to the first recognition instruction, obtaining a first recognition result, and taking the first degree of attention and the first recognition result of the first account as the first index.
Further, the embodiment of the present application further includes:
step S1010: obtaining second event information through the information receiving module, wherein the second event information has a second degree of association with the first event information;
step S1020: evaluating the first case according to the second event information to obtain a first public opinion guide grade;
step S1030: and obtaining a fourth evaluation result according to the first opinion guide level.
Specifically, the second event information with the second relevance is an event related to the first event, for example, when the first event involves two hands, the first event is a hand-separating statement issued by a first person, and the second event with the second relevance is a hand-separating statement issued by a second person, the content of the first case is evaluated according to the second event information, further, the second event may also be a change of the first event or an official statement, the first case is evaluated according to the second event, whether the first case has a malicious public opinion guidance and marketing effect is judged, a first public opinion guidance grade is obtained, and a fourth evaluation result is obtained according to the first public opinion guidance grade.
Further, the embodiment of the present application further includes:
step S1040: obtaining a first analysis instruction;
step 1050: analyzing the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result according to the first analysis instruction;
step S1060: obtaining a first analysis result, wherein the first analysis result comprises a fifth evaluation result.
Specifically, a first analysis instruction is obtained, wherein the first analysis instruction is an instruction for analyzing and processing the evaluation result, the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result are analyzed and processed in a summary manner according to the first analysis instruction, the result of the analysis is used as a fifth evaluation result, and the fifth evaluation result includes evaluation of public opinion guidance of the document after the first event occurs, evaluation of public opinion guidance of comment information, evaluation of whether malicious public opinion guidance exists or not, and the like, so that the technical effect of accurately and intelligently evaluating the network public opinion is achieved.
To sum up, the method and the system for evaluating internet public sentiment provided by the embodiment of the application have the following technical effects:
1. the technical effect of accurately and intelligently evaluating whether the first event and the public opinion guide are misled or not according to the first evaluation result is achieved by adopting the technical scheme that the first time difference is used as first input information, vocabulary detection is carried out on the vocabulary of the first case, the first risk level is obtained according to the vocabulary detection result, the first increment index is obtained according to the first browsing volume of the first case from the first publishing time to the second time, the increment index is evaluated according to a first evaluation instruction, the second risk level is obtained, the third risk level is used as second input information, the first input information and the second input information are input into a first public opinion evaluation model, the first evaluation result of the first public opinion evaluation model is obtained, and the first event and the public opinion guide are evaluated intelligently according to the first evaluation result.
2. Due to the adoption of the mode of supervising and learning the neural network model, the input information processed by the neural network model is more accurate, so that a more accurate evaluation result of network public opinions is obtained, and the technical effect of accurately and intelligently evaluating whether the first event and the public opinion guide are misled is achieved.
3. Due to the fact that the incremental index is calculated by cutting the time point from the first publishing time to the second publishing time, the first incremental index capable of reflecting the trend of the change of the browsing volume more accurately can be obtained, and a basis is laid for accurate and intelligent evaluation and compaction of the follow-up network public opinion.
4. Due to the fact that the first comment information is further judged through the logistic regression line, more accurate analysis results of whether public opinions are affected and misled are obtained, and a foundation is laid for accurate and intelligent evaluation of follow-up network public opinions.
Example two
Based on the same inventive concept as the method for evaluating internet public sentiment in the foregoing embodiment, the present invention further provides an evaluation system for internet public sentiment, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first event information through an information receiving module;
a second obtaining unit 12, where the second obtaining unit 12 is configured to perform information analysis on the first event information to obtain a first event occurrence time;
a third obtaining unit 13, configured to obtain a first time difference, where the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to perform vocabulary detection on the first document, and obtain a first risk level according to the vocabulary detection result;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to obtain a first browsing volume of the first file from a first publishing time to a second publishing time, and obtain a first incremental index according to the first browsing volume;
a sixth obtaining unit 16, where the sixth obtaining unit 16 is configured to obtain a first evaluation instruction, perform risk evaluation on the first incremental index according to the first evaluation instruction, and obtain a second risk level;
a seventh obtaining unit 17, where the seventh obtaining unit 17 is configured to obtain a third risk level according to the first risk level and the second risk level, and use the third risk level as second input information;
a first input unit 18, where the first input unit 18 is configured to input the first input information and the second input information into a first public opinion evaluation model, where the first public opinion evaluation model is obtained through training of multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result;
an eighth obtaining unit 19, where the eighth obtaining unit 19 is configured to obtain first output information of the first public opinion evaluation model, where the first output information includes a first evaluation result.
Further, the system further comprises:
a ninth obtaining unit, configured to obtain a third time, wherein the third time is within the first distribution time to the second time;
a tenth obtaining unit, configured to obtain second browsing volume information from the first distribution time to the third time;
an eleventh obtaining unit configured to obtain third browsing amount information from the third time to the second time;
a twelfth obtaining unit, configured to obtain a second time difference according to the first distribution time and the third time, and obtain a third time difference according to the third time and the second time;
a thirteenth obtaining unit, configured to obtain a second increment index according to the second browsing amount information and the second time difference, and obtain a third increment index according to the third browsing amount information and the third time difference;
a fourteenth obtaining unit configured to obtain an average value of the second incremental index and the third incremental index, the average value being a first incremental index.
Further, the system further comprises:
a fifteenth obtaining unit for obtaining a first incremental exponent threshold;
a first judgment unit configured to judge whether the third incremental index satisfies the first incremental index threshold;
a sixteenth obtaining unit configured to obtain first comment information at the third time when the third incremental index does not satisfy the first incremental index threshold;
a seventeenth obtaining unit, configured to obtain first sensitive vocabulary information of the first comment information;
an eighteenth obtaining unit, configured to obtain the first comment information to obtain first account information, use the first sensitive vocabulary information as a horizontal coordinate, and use the first account information as a vertical coordinate, and construct a coordinate system;
a nineteenth obtaining unit, configured to construct a logistic regression line based on the coordinate system through a logistic regression model, and obtain a second evaluation result through the logistic regression line.
Further, the system further comprises:
a twentieth obtaining unit, configured to obtain a first user according to the first account information, where the first user is a real-name authenticated user of the first account information;
a second judging unit, configured to judge whether a login device of the first account information is a common device of the first user, and obtain a first index according to a judgment result;
a twenty-first obtaining unit, configured to obtain second account information of the first user, determine whether the second account information has an abnormal remittance, and obtain a second indicator according to the determination result;
a twenty-second obtaining unit configured to obtain a third evaluation result according to the first index and the second index.
Further, the system further comprises:
a twenty-third obtaining unit, configured to obtain a second case of the first account information;
a twenty-fourth obtaining unit, configured to perform semantic recognition on the second pattern, and obtain a first semantic recognition result;
a third judging unit, configured to judge whether the second document and the first comment information have a first degree of association according to the first semantic recognition result;
a twenty-fifth obtaining unit, configured to obtain a first identification instruction when the second pattern and the first comment have the first association degree;
a twenty-sixth obtaining unit, configured to identify published content of the first account information according to the first identification instruction, and obtain a first identification result;
a twenty-seventh obtaining unit, configured to obtain a first attention degree of the first account;
a twenty-eighth obtaining unit that is configured to use the first recognition result and the first degree of attention as the first index.
Further, the system further comprises:
a twenty-ninth obtaining unit, configured to obtain second event information through the information receiving module, where the second event information has a second degree of association with the first event information;
a thirtieth obtaining unit, configured to evaluate the first document according to the second event information, and obtain a first opinion guide level;
a thirty-first obtaining unit configured to obtain a fourth evaluation result according to the first opinion guide level.
Further, the system further comprises:
a thirty-second obtaining unit to obtain a first analysis instruction;
a first analysis unit configured to analyze the first evaluation result, the second evaluation result, the third evaluation result, and the fourth evaluation result according to the first analysis instruction;
a thirty-third obtaining unit for obtaining a first analysis result, wherein the first analysis result comprises a fifth evaluation result.
Various variations and embodiments of the method for evaluating internet public opinion in the first embodiment of fig. 1 are also applicable to the system for evaluating internet public opinion of the present embodiment, and those skilled in the art can clearly understand the method for implementing the method for evaluating internet public opinion in the present embodiment through the detailed description of the method for evaluating internet public opinion, so that the detailed description is omitted here for the sake of brevity.
Exemplary electronic device
An electronic apparatus of an embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the application.
Based on the inventive concept of the method for evaluating internet public sentiment in the foregoing embodiments, the present invention further provides an evaluation system of internet public sentiment, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of any one of the methods for evaluating internet public sentiment described above.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides an evaluation method of network public sentiment, which is applied to a network public sentiment evaluation system, wherein the network public sentiment evaluation system is in communication connection with an information receiving module and a first public sentiment evaluation model, and the method comprises the following steps: obtaining first event information through the information receiving module; performing information analysis on the first event information to obtain first event occurrence time; obtaining a first time difference, wherein the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information; performing vocabulary detection on the first file, and obtaining a first risk level according to the vocabulary detection result; obtaining a first browsing volume of the first file from a first publishing time to a second time, and obtaining a first incremental index according to the first browsing volume; obtaining a first evaluation instruction, and performing risk evaluation on the first incremental index according to the first evaluation instruction to obtain a second risk level; obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information; inputting the first input information and the second input information into the first public opinion assessment model, wherein the first public opinion assessment model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result. The technical problem that the assessment of the network public sentiment is not intelligent and accurate enough in the prior art is solved, and the technical effect of intelligently and accurately assessing the network public sentiment is achieved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (4)
1. An assessment method of network public opinion is applied to a network public opinion assessment system, the network public opinion assessment system is in communication connection with an information receiving module and a first public opinion assessment model, wherein the method comprises the following steps:
obtaining first event information through the information receiving module;
performing information analysis on the first event information to obtain first event occurrence time;
obtaining a first time difference, wherein the first time difference is a time difference between a first publishing time of a first pattern and a first event occurrence time, and the first time difference is used as first input information;
performing vocabulary detection on the first file, and obtaining a first risk level according to the vocabulary detection result;
obtaining a first browsing volume of the first file from a first publishing time to a second time, and obtaining a first increment index according to the first browsing volume;
obtaining a third time, wherein the third time is within the first time to the second time;
obtaining second browsing volume information from the first publishing time to the third time;
obtaining third browsing volume information from the third time to the second time;
obtaining a second time difference according to the first distribution time and the third time, and obtaining a third time difference according to the third time and the second time;
obtaining a second incremental index according to the second browsing volume information and the second time difference, and obtaining a third incremental index according to the third browsing volume information and the third time difference;
obtaining an average value of the second incremental index and the third incremental index, and taking the average value as a first incremental index;
obtaining a first incremental exponential threshold;
determining whether the third incremental index meets the first incremental index threshold;
obtaining first comment information for the third time when the third incremental index does not satisfy the first incremental index threshold;
obtaining first sensitive vocabulary information of the first comment information;
acquiring the first comment information to acquire first account information, taking the first sensitive vocabulary information as a horizontal coordinate and the first account information as a vertical coordinate, and constructing a coordinate system;
constructing a logistic regression line based on the coordinate system through a logistic regression model, and obtaining a second evaluation result through the logistic regression line;
obtaining a first user according to the first account information, wherein the first user is a real-name authentication user of the first account information;
judging whether the login equipment of the first account information is the common equipment of the first user, and obtaining a first index according to a judgment result, wherein the judgment result comprises the following steps: obtaining a second file of the first account information; performing semantic recognition on the second case to obtain a first semantic recognition result; judging whether the second file and the first comment information have a first degree of association according to the first semantic recognition result; when the second file and the first comment have the first relevance degree, obtaining a first identification instruction; identifying published contents of the first account information according to the first identification instruction to obtain a first identification result; obtaining a first attention degree of the first account; using the first recognition result and the first attention as the first index, further comprising: obtaining second event information through the information receiving module, wherein the second event information has a second degree of association with the first event information; evaluating the first case according to the second event information to obtain a first public opinion guide grade; obtaining a fourth evaluation result according to the first public opinion guide level;
obtaining second account information of the first user, judging whether the second account information has abnormal remittance or not, and obtaining a second index according to a judgment result;
obtaining a third evaluation result according to the first index and the second index;
obtaining a first evaluation instruction, and performing risk evaluation on the first incremental index according to the first evaluation instruction to obtain a second risk level;
obtaining a third risk level according to the first risk level and the second risk level, and using the third risk level as second input information;
inputting the first input information and the second input information into the first public opinion assessment model, wherein the first public opinion assessment model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises the first input information, the second input information and identification information for identifying a first result;
obtaining first output information of the first public opinion evaluation model, wherein the first output information comprises a first evaluation result.
2. The method of claim 1, wherein the method further comprises:
obtaining a first analysis instruction;
analyzing the first evaluation result, the second evaluation result, the third evaluation result and the fourth evaluation result according to the first analysis instruction;
obtaining a first analysis result, wherein the first analysis result comprises a fifth evaluation result.
3. An evaluation system of network public opinion, wherein the system comprises:
a first obtaining unit, configured to obtain first event information through an information receiving module;
a second obtaining unit, configured to perform information analysis on the first event information to obtain a first event occurrence time;
a third obtaining unit, configured to obtain a first time difference, where the first time difference is a time difference between a first issue time of a first pattern and a first event occurrence time, and the first time difference is used as first input information;
a fourth obtaining unit, configured to perform vocabulary detection on the first case, and obtain a first risk level according to the vocabulary detection result;
a fifth obtaining unit, configured to obtain a first browsing volume of the first document from a first publishing time to a second publishing time, and obtain a first incremental index according to the first browsing volume;
a ninth obtaining unit, configured to obtain a third time, wherein the third time is within the first time to the second time;
a tenth obtaining unit, configured to obtain second browsing volume information from the first publishing time to the third time;
an eleventh obtaining unit configured to obtain third browsing amount information from the third time to the second time;
a twelfth obtaining unit, configured to obtain a second time difference according to the first distribution time and the third time, and obtain a third time difference according to the third time and the second time;
a thirteenth obtaining unit, configured to obtain a second increment index according to the second browsing amount information and the second time difference, and obtain a third increment index according to the third browsing amount information and the third time difference;
a fourteenth obtaining unit configured to obtain an average value of the second incremental index and the third incremental index, the average value being a first incremental index;
a fifteenth obtaining unit for obtaining a first incremental exponent threshold;
a first judgment unit configured to judge whether the third incremental index satisfies the first incremental index threshold;
a sixteenth obtaining unit configured to obtain first comment information at the third time when the third incremental index does not satisfy the first incremental index threshold;
a seventeenth obtaining unit, configured to obtain first sensitive vocabulary information of the first comment information;
an eighteenth obtaining unit, configured to obtain the first comment information to obtain first account information, use the first sensitive vocabulary information as a horizontal coordinate, and use the first account information as a vertical coordinate, and construct a coordinate system;
a nineteenth obtaining unit, configured to construct a logistic regression line based on the coordinate system through a logistic regression model, and obtain a second evaluation result through the logistic regression line;
a twentieth obtaining unit, configured to obtain a first user according to the first account information, where the first user is a real-name authenticated user of the first account information;
a second judging unit, configured to judge whether a login device of the first account information is a frequently-used device of the first user, and obtain a first index according to a judgment result;
a twenty-third obtaining unit, configured to obtain a second case of the first account information;
a twenty-fourth obtaining unit, configured to perform semantic recognition on the second pattern, and obtain a first semantic recognition result;
a third judging unit, configured to judge whether the second document and the first comment information have a first degree of association according to the first semantic recognition result;
a twenty-fifth obtaining unit, configured to obtain a first identification instruction when the second pattern and the first comment have the first association degree;
a twenty-sixth obtaining unit, configured to identify published content of the first account information according to the first identification instruction, and obtain a first identification result;
a twenty-seventh obtaining unit, configured to obtain a first attention degree of the first account;
a twenty-eighth obtaining unit configured to take the first recognition result and the first degree of attention as the first index;
a twenty-ninth obtaining unit, configured to obtain second event information through the information receiving module, where the second event information has a second degree of association with the first event information;
a thirtieth obtaining unit, configured to evaluate the first literature according to the second event information, and obtain a first opinion guide level;
a thirty-first obtaining unit, configured to obtain a fourth evaluation result according to the first opinion guide level;
a twenty-first obtaining unit, configured to obtain second account information of the first user, determine whether the second account information has an abnormal remittance, and obtain a second indicator according to a determination result;
a twenty-second obtaining unit, configured to obtain a third evaluation result according to the first index and the second index;
a sixth obtaining unit, configured to obtain a first evaluation instruction, perform risk evaluation on the first incremental index according to the first evaluation instruction, and obtain a second risk level;
a seventh obtaining unit, configured to obtain a third risk level according to the first risk level and the second risk level, and use the third risk level as second input information;
a first input unit, configured to input the first input information and the second input information into a first public opinion evaluation model, where the first public opinion evaluation model is obtained through training of multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result;
an eighth obtaining unit, configured to obtain first output information of the first public opinion evaluation model, where the first output information includes a first evaluation result.
4. An evaluation system for internet public opinion, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110073905.1A CN112785146B (en) | 2021-01-20 | 2021-01-20 | Method and system for evaluating network public sentiment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110073905.1A CN112785146B (en) | 2021-01-20 | 2021-01-20 | Method and system for evaluating network public sentiment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112785146A CN112785146A (en) | 2021-05-11 |
| CN112785146B true CN112785146B (en) | 2022-12-13 |
Family
ID=75757902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110073905.1A Active CN112785146B (en) | 2021-01-20 | 2021-01-20 | Method and system for evaluating network public sentiment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112785146B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114862171A (en) * | 2022-04-24 | 2022-08-05 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device for emergency event |
| CN117196293A (en) * | 2023-08-16 | 2023-12-08 | 平安科技（深圳）有限公司 | Public opinion risk determination method, device, server and medium based on artificial intelligence |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108021651B (en) * | 2017-11-30 | 2020-07-28 | 中科金联（北京）科技有限公司 | Network public opinion risk assessment method and device |
| CN110191113B (en) * | 2019-05-24 | 2021-09-24 | 新华三信息安全技术有限公司 | User behavior risk assessment method and device |
| CN111026940A (en) * | 2019-10-24 | 2020-04-17 | 中国电力科学研究院有限公司 | Network public opinion and risk information monitoring system and electronic equipment for power grid electromagnetic environment |
| CN111428113B (en) * | 2020-03-27 | 2022-07-01 | 华侨大学 | Network public opinion guiding effect prediction method based on fuzzy comprehensive evaluation |
| CN111581945B (en) * | 2020-04-09 | 2024-05-03 | 上海淇毓信息科技有限公司 | Public opinion analysis-based data analysis method, device and system |
| CN111753093A (en) * | 2020-07-02 | 2020-10-09 | 东北电力大学 | Method and device for evaluating level of network public opinion crisis |
| CN111859074B (en) * | 2020-07-29 | 2023-12-29 | 东北大学 | Network public opinion information source influence evaluation method and system based on deep learning |
-
2021
- 2021-01-20 CN CN202110073905.1A patent/CN112785146B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112785146A (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112785146B (en) | Method and system for evaluating network public sentiment | |
| CN112258093A (en) | Risk level data processing method and device, storage medium and electronic equipment | |
| CN107229689B (en) | Microblog public opinion risk studying and judging method | |
| CN114879613A (en) | Industrial control system information security attack risk assessment method and system | |
| CN113313479A (en) | Payment service big data processing method and system based on artificial intelligence | |
| CN110619535A (en) | Data processing method and device | |
| CN110162958A (en) | For calculating the method, apparatus and recording medium of the synthesis credit score of equipment | |
| CN116701130A (en) | Dynamic baseline optimization method and device based on index portrait and electronic equipment | |
| CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
| CN114625406A (en) | Application development control method, computer equipment and storage medium | |
| CN111275453A (en) | Industry identification method and system of Internet of things equipment | |
| CN113643127A (en) | Risk guarantee circle determination method and device, electronic equipment and readable storage medium | |
| CN109117352B (en) | Server performance prediction method and device | |
| CN113269378A (en) | Network traffic processing method and device, electronic equipment and readable storage medium | |
| CN102195814B (en) | Method and device for forecasting and predicting by using relevant IT (Information Technology) operation and maintenance indexes | |
| CN113256432B (en) | Intelligent management method and system based on financial investment project | |
| CN112798955B (en) | Fault detection method and device for special motor | |
| CN103560925A (en) | IT operation and maintenance index forecasting method utilizing relevance | |
| CN113435691B (en) | Building quality standard assessment method and system based on BIM | |
| CN111882135B (en) | Internet of things equipment intrusion detection method and related device | |
| CN114462861A (en) | Enterprise positioning industry chain data analysis method and system | |
| CN115278757A (en) | Method and device for detecting abnormal data and electronic equipment | |
| CN112464218B (en) | Model training method and device, electronic equipment and storage medium | |
| CN113627551A (en) | Multi-model-based certificate classification method, device, equipment and storage medium | |
| CN112668899A (en) | Contract risk identification method and device based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221124 Address after: No. 956, Yingkou Road, Changchun Economic Development Zone, 130,000 Jilin Province Applicant after: Jilin Province Internet Media Co.,Ltd. Address before: B05, enterprising Park, Nankai Science Park, No.3 Weishui Road, Nankai District, Tianjin Applicant before: Zhonghui lvlang Technology (Tianjin) Group Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |