CN114610980A - Network public opinion based black product identification method, device, equipment and storage medium - Google Patents
Network public opinion based black product identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114610980A CN114610980A CN202210278436.1A CN202210278436A CN114610980A CN 114610980 A CN114610980 A CN 114610980A CN 202210278436 A CN202210278436 A CN 202210278436A CN 114610980 A CN114610980 A CN 114610980A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- user
- opinion
- network
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 238000007477 logistic regression Methods 0.000 claims abstract description 54
- 238000012544 monitoring process Methods 0.000 claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 28
- 238000000611 regression analysis Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims description 98
- 238000013528 artificial neural network Methods 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 238000003064 k means clustering Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
- G06F16/953—Querying, e.g. by the use of web search engines
-
- 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
- G06F16/906—Clustering; Classification
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to an intelligent decision technology, and discloses a black product identification method based on network public sentiment, which comprises the following steps: carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing a historical public opinion monitoring record set to obtain a public opinion grade judgment model; judging the public sentiment grade of the public sentiment monitoring record of the target public sentiment by using a public sentiment grade judging model; determining the public sentiments with the public sentiment grade greater than or equal to the preset warning grade as suspected abnormal public sentiments, and acquiring a first user set for executing preset operation on the suspected abnormal public sentiments within preset time; extracting a black product user set from the first user set according to a preset black product user extraction rule; and querying a key opinion leader user associated with the information propagation path of the black product user set as a black product direct association user. The application also provides a network public opinion-based black product identification device, equipment and a storage medium. The method and the device can effectively position the black birth behavior and behavior income in the abnormal public opinion.
Description
Technical Field
The application relates to the technical field of intelligent decision, in particular to a black product identification method, device, equipment and storage medium based on network public sentiment.
Background
Along with the popularization of networks, the information transmission speed is greatly accelerated, and because the network users have different qualities, the network users are very easily influenced by true, true and false information on the network, so that the conditions of rumors, network violence and the like are caused.
With the increasing influence of the network on the reality, a network black production means is gradually generated to guide the trend of network public opinion. Aiming at the phenomenon, at present, a network supervision department can monitor the topic degree, time curve, ip distribution and the like of important public opinions, but when finding abnormal public opinions, an executor behind a black product behavior cannot be confirmed, at most, only a black product account can be blocked, and the right of an attacked enterprise is not greatly influenced. Therefore, a technical means capable of identifying the black products after the back of the abnormal public sentiment is urgently needed at present, and the network environment is supervised fundamentally.
Disclosure of Invention
The application provides a network public opinion-based black product identification method, device, equipment and storage medium, and mainly aims to update an activity product interface in real time for users with different roles.
In order to achieve the above object, the present application provides a black product identification method based on internet public sentiment, including:
carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing a historical public opinion monitoring record set to obtain a public opinion grade judgment model;
acquiring a public opinion monitoring record of a target public opinion according to a preset buried point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judgment model to obtain a public opinion grade of the target public opinion;
when the public opinion grade is larger than or equal to a preset warning grade, judging the target public opinion as suspected abnormal public opinion, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
inquiring the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity;
obtaining login addresses of all users in the low-level activity user set to obtain a login address set, and performing position clustering operation on the users in the login address set to obtain a clustering result;
extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and constructing an information propagation network of the key opinion leader set and the black product user set, inquiring key opinion leader users related to the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the inquired key opinion leader users as black product directly related users.
Optionally, the method for performing regression analysis on the pre-constructed initial logistic regression model by using the historical public opinion monitoring record set to obtain a public opinion grade judgment model includes:
performing data vectorization operation on the historical public opinion monitoring record set by using a one-hot model to obtain a historical public opinion sample record set;
sequentially extracting a historical public opinion recording sample from the historical public opinion sample recording set;
performing feature extraction on the historical public opinion sample record by using a feature recognition network in the initial logistic regression model to obtain a feature sequence;
carrying out forward propagation calculation on the characteristic sequence by using an operational neural network in the initial logistic regression model to obtain a prediction judgment result of the historical public opinion recording sample;
calculating a mixed network error of the feature recognition network and the operational neural network according to a real judgment result and a prediction judgment result of the historical public opinion recording sample;
according to a gradient descent method, minimizing the mixed network error to obtain a network updating parameter, and reversely updating the initial logistic regression model by using the network updating parameter to obtain an optimized initial logistic regression model;
judging whether the hybrid network error converges;
when the mixed network error is not converged, returning to the step of sequentially extracting a historical public opinion record sample from the historical public opinion sample record set, and further optimizing the optimized initial logistic regression model;
and when the mixed network error is converged, obtaining an optimized initial logistic regression model, and taking the optimized initial logistic regression model as a public opinion grade judgment model.
Optionally, the extracting features of the historical public opinion sample records by using a feature recognition network in the initial logistic regression model to obtain a feature sequence includes:
carrying out convolution on the historical public opinion sample record by utilizing the convolution layer of the feature recognition network to obtain a convolution matrix set;
performing maximum pooling operation on the convolution matrix set to obtain a pooled feature matrix set;
according to a preset splitting and connecting method, performing one-dimensional arrangement on each pooling feature matrix in the pooling feature matrix set to obtain a local feature sequence set;
and carrying out full connection operation on each local characteristic sequence in the local characteristic sequence set to obtain a characteristic sequence.
Optionally, the utilization the public opinion grade judges the model is right the public opinion monitoring record of target public opinion carries out grade judgment, obtains the public opinion grade of target public opinion includes:
identifying the public opinion monitoring record of the target public opinion by using a feature identification network of the public opinion grade judgment model to obtain a feature sequence of the public opinion monitoring record;
grouping the characteristic sequences of the public opinion monitoring records to obtain a propagation platform type characteristic sequence and a data change characteristic sequence;
and carrying out network configuration on the operational neural network of the public opinion grade judgment model according to the propagation platform type characteristic sequence, and carrying out public opinion type judgment on the data change characteristic sequence by using the configured operational neural network to obtain the public opinion grade of the target public opinion.
Optionally, the querying the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity, includes:
acquiring browsing activity, comment activity and forwarding activity of each user in the first user set;
according to preset weight configuration, the browsing activity, the comment activity and the forwarding activity, carrying out weighted summation calculation on each user in the first user set to obtain the user activity of each user in the first user set;
extracting users in a preset first interval of liveness as key opinion leaders to obtain a key opinion leader set;
and extracting the users in the preset second activity interval as the users with low activity to obtain a low-level activity user set.
Optionally, the performing a location clustering operation on the users in the login address set to obtain a clustering result includes:
carrying out longitude and latitude two-dimensional marking on each login address in the login address set to obtain a login coordinate cluster;
and carrying out position clustering on the login coordinate cluster by using a K-Means clustering algorithm to obtain a clustering result.
Optionally, before performing regression analysis on the pre-constructed initial logistic regression model by using the historical public opinion monitoring record set to obtain the public opinion grade judgment model, the method further includes:
acquiring a pre-constructed feature recognition network and an operational neural network containing a logistic regression activation function;
and connecting the characteristic recognition network serving as an input layer and the neural network serving as a processing judgment layer to obtain an initial logistic regression model.
In order to solve the above problem, the present application further provides a black product identification device based on internet public sentiment, the device includes:
the model acquisition module is used for carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing the historical public opinion monitoring record set to obtain a public opinion grade judgment model;
the public opinion grade judging module is used for acquiring a public opinion monitoring record of the target public opinion according to a preset embedding point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judging model to obtain a public opinion grade of the target public opinion;
the first user acquisition module is used for judging the target public opinion as a suspected abnormal public opinion when the public opinion grade is greater than or equal to a preset warning grade, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
the black product user query module is used for querying the user activity of each user in the first user set, extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity, acquiring a login address of each user in the low-level activity user set to obtain a login address set, performing position clustering operation on the users in the login address set to obtain a clustering result, and extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and the black product associated user query module is used for constructing an information propagation network of the key opinion leader set and the black product user set, querying key opinion leader users associated with the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the queried key opinion leader users as black product directly associated users.
In order to solve the above problem, the present application also provides an apparatus, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor, so that the at least one processor can execute the method for identifying black products based on internet public opinion.
In order to solve the above problem, the present application further provides a storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in a device to implement the network public opinion based black birth identification method.
The embodiment of the application carries out regression analysis on the initialized logistic regression model through the public opinion monitoring record set to obtain the public opinion grade judgment model, which is beneficial to quickly and accurately identifying whether the public opinion is abnormal or not and further convenient for identifying the black products; then, capturing users who perform preset operation in a first time period in suspected abnormal public sentiment, wherein the principle that information transmission needs time is utilized, extracting the users who respond at the first time, and increasing accuracy of detecting the black products; and finally, obtaining the key opinion leaders of the network black product service according to the incidence relation of the black product users and the key opinion leader sets in the information transmission process, thereby being used as an effective evidence related to the black product service. Therefore, the network public opinion-based black product identification method, device, equipment and storage medium provided by the embodiment of the application can effectively locate black product behaviors and behavior profits in the abnormal public opinion.
Drawings
Fig. 1 is a flowchart illustrating a black product identification method based on internet public sentiment according to an embodiment of the present application;
fig. 2 is a detailed flowchart illustrating a step of a black product identification method based on internet public sentiment according to an embodiment of the present application;
fig. 3 is a detailed flowchart illustrating a step of a method for identifying black products based on internet public sentiments according to an embodiment of the present application;
fig. 4 is a detailed flowchart illustrating a step of a black product identification method based on internet public opinion according to an embodiment of the present application;
fig. 5 is a detailed flowchart illustrating a step of a black product identification method based on internet public opinion according to an embodiment of the present application;
fig. 6 is a detailed flowchart illustrating a step of a method for identifying a black product based on internet public sentiment according to an embodiment of the present application;
fig. 7 is a flowchart illustrating a detailed procedure of a step in a method for identifying black products based on online public opinion according to an embodiment of the present application;
fig. 8 is a functional block diagram of a network public opinion-based black product identification device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an apparatus for implementing the network public opinion-based black birth identification method according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The embodiment of the application provides a black product identification method based on network public sentiment. In the embodiment of the present application, the implementation subject of the network public opinion-based black product identification method includes, but is not limited to, at least one of a server, a terminal, and other devices that can be configured to implement the method provided in the embodiment of the present application. In other words, the network public opinion-based black product identification method may be executed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Referring to fig. 1, a flow chart of a black product identification method based on internet public sentiment according to an embodiment of the present application is shown. In this embodiment, the network public opinion-based black product identification method includes the following steps S1-S9:
and S1, carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing the historical public opinion monitoring record set to obtain a public opinion grade judgment model.
In an embodiment of the present application, the initial logistic regression model is a neural network-based multi-class regression model, wherein the initial logistic regression model includes a feature extraction network and an operational neural network, and the feature extraction network includes a convolutional layer, a pooling layer, and a full connection layer; the operational neural network is a set of public opinion judgment networks corresponding to information transmission types of all information platforms (browsers, WeChat, microblog, knowns and the like).
In detail, referring to fig. 2, in the embodiment of the present application, the step S1 further includes the following steps S11-S18:
s11, carrying out data vectorization operation on the historical public opinion monitoring record set by using a one-hot model to obtain a historical public opinion sample record set;
s12, sequentially extracting a historical public opinion recording sample from the historical public opinion sample recording set;
s13, performing feature extraction on the historical public opinion sample record by using a feature recognition network in the initial logistic regression model to obtain a feature sequence;
s14, carrying out forward propagation calculation on the characteristic sequence by using an operational neural network in the initial logistic regression model to obtain a prediction judgment result of the historical public opinion recording sample;
s15, calculating a mixed network error of the feature recognition network and the operational neural network according to the real judgment result and the prediction judgment result of the historical public opinion recording sample;
s16, minimizing the mixed network error according to a gradient descent method to obtain a network updating parameter, and reversely updating the initial logistic regression model by using the network updating parameter to obtain an optimized initial logistic regression model;
s17, judging whether the mixed network error is converged;
when the mixed network error is not converged, returning to the step of sequentially extracting a historical public opinion record sample from the historical public opinion sample record set, and further optimizing the optimized initial logistic regression model;
and when the mixed network error is converged, S18, obtaining an optimized initial logistic regression model, and taking the optimized initial logistic regression model as a public opinion grade judgment model.
The one-hot model is a common preprocessing model in machine learning and is used for encoding sample data into a vector form in an encoding form, so that the input and calculation of a neural network are facilitated.
In the embodiment of the application, a one-hot model is used for carrying out data vectorization operation on a historical public opinion monitoring record set to obtain a vector-form historical public opinion sample record set, and then the historical public opinion sample records are input into an initial logistic regression model one by one according to a preset batch-size parameter for training, wherein a feature recognition network in the initial logistic regression model is used for carrying out feature extraction on the historical public opinion sample records to obtain a feature sequence; and the operational neural network in the initial logistic regression model is used for carrying out public opinion judgment on the characteristic sequence to obtain a prediction judgment result.
In detail, referring to fig. 3, in the embodiment of the present application, the step S13 further includes the following steps S131 to S134:
s131, convolving the historical public opinion sample record by utilizing the convolution layer of the feature recognition network to obtain a convolution matrix set;
s132, performing maximum pooling operation on the convolution matrix set to obtain a pooled feature matrix set;
s133, performing one-dimensional arrangement on each pooling feature matrix in the pooling feature matrix set according to a preset splitting and connecting method to obtain a local feature sequence set;
and S134, carrying out full connection operation on each local characteristic sequence in the local characteristic sequence set to obtain a characteristic sequence.
Specifically, a plurality of preset convolution kernels exist in the convolution layer, and each convolution kernel can perform a convolution operation on the historical public sentiment sample record to obtain a convolution matrix. Wherein, each convolution kernel is used for extracting different characteristics in the historical public opinion sample records.
The pooling layer replaces the maximum characteristic value in a preset neighborhood with the maximum characteristic value in the preset neighborhood, so that the dimensionality reduction of the matrix is completed, a pooling characteristic matrix set is obtained, and the data calculation amount can be reduced under the condition that the matrix characteristic is not influenced. Finally, the embodiment of the application performs full connection operation on each matrix in the pooled feature matrix set through a full connection layer to obtain a feature sequence, and then obtains a prediction judgment result through an operational neural network.
According to the embodiment of the application, the error of the prediction judgment result and the real judgment result of the historical public opinion recording sample is calculated according to a preset loss function L, and a network mixed error is obtained, wherein the network mixed error contains the error of whether the characteristic identification network identifies the correct platform type and the error of whether the operational neural network correctly predicts the public opinion grade. Wherein the loss function L of the initial logistic regression model is:
L=Lfeature identification+αLPublic opinion judgment
In the formula, the LFeature identificationIdentifying a loss function of the network for the feature, LPublic opinion judgmentAnd the alpha is a weight coefficient which is a loss function of the operational neural network.
Further, the gradient descent method is an optimization algorithm for solving, mainly solving the problem of solving the minimum value, and the basic idea is to continuously approach the optimal point, and the optimization direction of each step is the direction of the gradient.
In the embodiment of the application, by the gradient descent method, the mixed network error is minimized, so that weight parameters of each neuron in a network with the minimum mixed network error are obtained and collectively referred to as network update parameters, and the network update parameters are subjected to network back propagation through a preset activation function, so that the initial logistic regression model is updated, and an optimized initial logistic regression model is obtained.
In order to guarantee the training effect of the model, the embodiment of the application records the mixed network errors corresponding to the training process of each historical public opinion sample at any time, performs two-dimensional mapping and coordinate fitting on each mixed network error to obtain a mixed error change curve, and can judge whether the mixed network errors are converged by judging the derivative size of the mixed error change curve. And stopping the training process until the derivative is smaller than a preset threshold value, and taking the optimized initial logistic regression model as a public opinion grade judgment model.
In detail, referring to fig. 4, in the embodiment of the present application, before the step S1, the method further includes the following steps S01-S02:
s01, acquiring a pre-constructed feature recognition network and an operational neural network containing a logistic regression activation function;
and S02, connecting the feature recognition network serving as an input layer and the neural network serving as a processing fault layer to obtain an initial logistic regression model.
According to the operation, the initial logistic regression model is constructed and obtained.
S2, acquiring a public opinion monitoring record of the target public opinion according to a preset buried point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judgment model to obtain a public opinion grade of the target public opinion.
The embedded point is a common data acquisition method, and can automatically identify and store data according to a preset automatic program.
In detail, referring to fig. 5, in the embodiment of the present application, the performing a grade judgment on the target public opinion monitoring record by using the public opinion grade judgment model to obtain the public opinion grade of the target public opinion includes the following steps S21 to S23:
s21, identifying the public sentiment monitoring record of the target public sentiment by using the characteristic identification network of the public sentiment grade judgment model to obtain a characteristic sequence of the public sentiment monitoring record;
s22, grouping the feature sequences of the public opinion monitoring records to obtain a propagation platform type feature sequence and a data change feature sequence;
and S23, carrying out network configuration on the operational neural network of the public opinion grade judgment model according to the propagation platform type characteristic sequence, and carrying out public opinion type judgment on the data change characteristic sequence by using the configured operational neural network to obtain the public opinion grade of the target public opinion.
Specifically, in the embodiment of the application, the public opinion monitoring record of the target public opinion is identified by using the feature identification network of the public opinion grade judgment model, the feature sequence of the public opinion monitoring record is obtained, and the propagation platform type feature sequence and the data change feature sequence in the feature sequence are checked.
Due to the fact that each propagation platform such as a browser and WeChat is different in information propagation mechanism, control mode and fan group. The application needs to identify the propagation platform type characteristic sequence to judge a data source platform, so that a proper neuron is selected to judge the public sentiment level.
In the embodiment of the application, after obtaining the public opinion level, S3 is executed to determine whether the public opinion level is greater than or equal to a preset alert level.
And when the public opinion grade is less than the preset alert grade, executing S4 and judging the target public opinion to be normal public opinion.
And when the public opinion grade is greater than or equal to a preset warning grade, executing S5, judging the target public opinion to be suspected abnormal public opinion, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set.
In the embodiment of the application, when the public opinion grade is too high, the public opinion is a suspected abnormal public opinion, and an intervention check needs to be carried out. In addition, it should be noted that the black products and internet channels such as portal websites often agree on time to release information, the water army and the robot can synchronously follow up quickly without reaction time, and time is needed when the information is transmitted.
According to the embodiment of the application, the users who perform operations such as praise, comment and forwarding on suspected abnormal public opinions are extracted within a preset first time, such as ten minutes of information release, so that a first user set is obtained.
S6, inquiring the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity.
The network black product refers to an illegal behavior which takes the internet as a medium and a network technology as a main means and brings potential threats (major potential safety hazards) to the safety of a computer information system and the management order of network space, even the national safety and the social political stability. In the public opinion guiding process, the network black product mainly carries out automatic execution of specific operations (such as praise, forwarding, comment fixed statements and the like) on the account obtained by registration or illegal acquisition through a script program.
It should be known that, due to the nature of the black product account, the black product users are mainly used for executing fixed operations, the number of operations randomly browsed by each user is small, and the action purpose is strong, so that the users can be judged to be normal users or black product users by querying the activity.
In detail, referring to fig. 6, in the embodiment of the present application, the step of S6 further includes the following steps S61-S65:
s61, acquiring browsing activity, comment activity and forwarding activity of each user in the first user set;
s62, according to preset weight configuration, the browsing activity, the comment activity and the forwarding activity, performing weighted summation calculation on each user in the first user set to obtain the user activity of each user in the first user set;
s63, judging user activity intervals of each user;
s64, extracting users in a first preset activity interval as key opinion leaders to obtain a key opinion leader set;
and S65, extracting the users in the preset second activity interval as the users with low activity to obtain a low-level activity user set.
The first activity interval is an interval with extremely high activity, and the second activity interval is an interval with extremely low activity.
According to the embodiment of the application, the browsing activity, the comment activity and the forwarding activity are subjected to weighted summation according to the preset weight coefficient, and the user activity of each user is obtained. Wherein the weight of the browsing activity degree is greater than the weight of the comment activity degree and greater than the weight of the forwarding activity degree.
After the user activity of each user is obtained, user screening can be carried out according to the activity first interval and the activity second interval to obtain a key opinion leader set and a low-level activity user set. The key opinion leader is the existence of numerous vermicelli groups with extremely high adhesiveness, which is called KOL for short, and makes comments in various social hot spots after heavily participating in entertainment. The KOL plays a great role in public opinion guidance.
S7, obtaining login addresses of all users in the low-level activity user set to obtain a login address set, and carrying out position clustering operation on the users in the login address set to obtain a clustering result.
In this embodiment, the login address of each user in the low-level activity user set may be queried according to methods such as a preset PHP code.
In detail, referring to fig. 7, in this embodiment of the application, the performing location clustering operation on the users in the login address set to obtain a clustering result includes the following steps S71-S72:
s71, carrying out longitude and latitude two-dimensional marking on each login address in the login address set to obtain a login coordinate cluster;
and S72, carrying out position clustering on the login coordinate clusters by using a K-Means clustering algorithm to obtain a clustering result.
Wherein the K-Means clustering algorithm is a clustering method for partitioning.
According to the embodiment of the application, the login coordinate clusters are obtained by carrying out longitude and latitude two-dimensional marking on each login address, and the cluster part and the non-cluster part in the login address set are inquired through the K-Means clustering algorithm.
And S8, extracting the black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule.
In the embodiment of the application, the black product user extraction rule is formulated according to the normal cluster volume distribution obtained by big data statistics and is used for distinguishing the black product user from the normal user.
Specifically, according to the black product user extraction rule, the size of the cluster is inquired, the cluster part with the cluster volume larger than the preset value is extracted as an abnormal cluster, and each user in the abnormal cluster is extracted to obtain the black product user set.
S9, constructing an information propagation network of the key opinion leader set and the black product user set, inquiring key opinion leader users related to the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the inquired key opinion leader users as black product directly related users.
Because each platform information forwarding has forwarding records, an information propagation network is constructed according to the forwarding records of each key opinion leader set and the black user set, and whether the black user set is a direct leader or an indirect leader of each key opinion is judged, so that the associated KOL is used as an associated user of the black user as a solidification evidence, a crime and penalty subject is determined, and the network environment is supervised from the root.
The embodiment of the application carries out regression analysis on the initialized logistic regression model through the public opinion monitoring record set to obtain the public opinion grade judgment model, which is beneficial to quickly and accurately identifying whether the public opinion is abnormal or not and further convenient for identifying the black products; then, capturing users who perform preset operation in a first time period in suspected abnormal public sentiment, wherein the principle that information transmission needs time is utilized, extracting the users who respond at the first time, and increasing accuracy of detecting the black products; and finally, obtaining the key opinion leaders of the network black product service according to the incidence relation of the black product users and the key opinion leader sets in the information transmission process, thereby being used as an effective evidence related to the black product service. Therefore, the network public opinion-based black production identification method provided by the embodiment of the application can effectively locate black production behaviors and behavior incomes in the abnormal public opinion.
Fig. 8 is a functional block diagram of a network public opinion-based black product identification device according to an embodiment of the present application.
The network public opinion-based black product recognition device 100 can be installed in equipment. According to the implemented functions, the network public opinion-based black product identification device 100 may include a model obtaining module 101, a public opinion grade determining module 102, a first user obtaining module 103, a black product user querying module 104, and a black product associated user querying module 105. A module, also referred to as a unit in this application, refers to a series of computer program segments that can be executed by a processor of a device and that can perform a fixed function, and that are stored in a memory of the device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the model obtaining module 101 is configured to perform regression analysis on a pre-constructed initial logistic regression model by using a historical public opinion monitoring record set to obtain a public opinion grade judgment model;
the public opinion grade judging module 102 is configured to obtain a public opinion monitoring record of a target public opinion according to a preset embedding point, and perform grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judging model to obtain a public opinion grade of the target public opinion;
the first user obtaining module 103 is configured to, when the public opinion level is greater than or equal to a preset alert level, determine that the target public opinion is a suspected abnormal public opinion, and obtain a user who performs a preset operation on the suspected abnormal public opinion within a preset first time, so as to obtain a first user set;
the black product user query module 104 is configured to query the user activity of each user in the first user set, extract a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity, acquire a login address of each user in the low-level activity user set, obtain a login address set, perform location clustering on the users in the login address set, obtain a clustering result, and extract a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
the black product associated user query module 105 is configured to construct an information propagation network of the key opinion leader set and the black product user set, query key opinion leader users associated with an information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and output the queried key opinion leader users as black product directly associated users.
In detail, in the embodiment of the present application, when the modules in the network public opinion based black product identification apparatus 100 are used, the same technical means as the network public opinion based black product identification method described in fig. 1 to fig. 3 are adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 9 is a schematic structural diagram of an apparatus for implementing a network public opinion-based black product identification method according to an embodiment of the present application.
The device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a network consensus-based black birth identification program.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the device, connects various components of the entire device by using various interfaces and lines, and executes various functions of the device and processes data by running or executing programs or modules stored in the memory 11 (for example, executing a network consensus-based black product identification program, etc.), and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the device, for example a removable hard disk of the device. The memory 11 may also be an external storage device of the device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the device. Further, the memory 11 may also include both an internal storage unit of the device and an external storage device. The memory 11 may be used not only to store application software installed in the device and various data, such as a code of a network public opinion-based black product identification program, but also to temporarily store data that has been output or will be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the above-mentioned device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the device and other devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an Organic Light-Emitting Diode (OLED) touch panel, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the device and for displaying a visualized user interface.
Fig. 9 only shows the device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 9 does not constitute a limitation of the device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the apparatus may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions such as charge management, discharge management, and power consumption management are implemented through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The device may further include various sensors, a bluetooth module, a Wi-Fi module, etc., which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The network consensus-based black product identification program stored in the memory 11 of the device 1 is a combination of instructions, which when executed in the processor 10, can implement:
carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing a historical public opinion monitoring record set to obtain a public opinion grade judgment model;
acquiring a public opinion monitoring record of a target public opinion according to a preset buried point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judgment model to obtain a public opinion grade of the target public opinion;
when the public opinion grade is larger than or equal to a preset warning grade, judging the target public opinion as suspected abnormal public opinion, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
inquiring the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity;
obtaining login addresses of all users in the low-level activity user set to obtain a login address set, and performing position clustering operation on the users in the login address set to obtain a clustering result;
extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and constructing an information propagation network of the key opinion leader set and the black product user set, inquiring key opinion leader users related to the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the inquired key opinion leader users as black product directly related users.
Specifically, the specific implementation method of the instruction by the processor 10 may refer to the description of the relevant steps in the embodiment corresponding to the drawings, which is not described herein again.
Further, the integrated modules/units of the device 1 may be stored in a storage medium if they are implemented in the form of software functional units and sold or used as separate products. The storage medium may be volatile or nonvolatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present application also provides a storage medium, the readable storage medium storing a computer program that, when executed by a processor of a device, may implement:
carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing a historical public opinion monitoring record set to obtain a public opinion grade judgment model;
acquiring a public opinion monitoring record of a target public opinion according to a preset buried point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judgment model to obtain a public opinion grade of the target public opinion;
when the public opinion grade is larger than or equal to a preset warning grade, judging the target public opinion as suspected abnormal public opinion, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
inquiring the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity;
obtaining login addresses of all users in the low-level activity user set to obtain a login address set, and performing position clustering operation on the users in the login address set to obtain a clustering result;
extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and constructing an information propagation network of the key opinion leader set and the black product user set, inquiring key opinion leader users related to the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the inquired key opinion leader users as black product directly related users.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.
Claims (10)
1. A black product identification method based on network public sentiment is characterized by comprising the following steps:
carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing a historical public opinion monitoring record set to obtain a public opinion grade judgment model;
acquiring a public opinion monitoring record of a target public opinion according to a preset buried point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judgment model to obtain a public opinion grade of the target public opinion;
when the public opinion grade is larger than or equal to a preset warning grade, judging the target public opinion as suspected abnormal public opinion, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
inquiring the user activity of each user in the first user set, and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity;
obtaining login addresses of all users in the low-level activity user set to obtain a login address set, and performing position clustering operation on the users in the login address set to obtain a clustering result;
extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and constructing an information propagation network of the key opinion leader set and the black product user set, inquiring key opinion leader users related to the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the inquired key opinion leader users as black product directly related users.
2. The method for identifying black products based on internet public sentiment according to claim 1, wherein the performing regression analysis on the pre-constructed initial logistic regression model by using the historical public sentiment monitoring record set to obtain a public sentiment grade judgment model comprises:
performing data vectorization operation on the historical public opinion monitoring record set by using a one-hot model to obtain a historical public opinion sample record set;
sequentially extracting a historical public opinion recording sample from the historical public opinion sample recording set;
performing feature extraction on the historical public opinion sample record by using a feature recognition network in the initial logistic regression model to obtain a feature sequence;
carrying out forward propagation calculation on the characteristic sequence by using an operational neural network in the initial logistic regression model to obtain a prediction judgment result of the historical public opinion recording sample;
calculating a mixed network error of the feature recognition network and the operational neural network according to a real judgment result and a prediction judgment result of the historical public opinion recording sample;
according to a gradient descent method, minimizing the mixed network error to obtain a network updating parameter, and reversely updating the initial logistic regression model by using the network updating parameter to obtain an optimized initial logistic regression model;
judging whether the hybrid network error converges;
when the mixed network error is not converged, returning to the step of sequentially extracting a historical public opinion record sample from the historical public opinion sample record set, and further optimizing the optimized initial logistic regression model;
and when the mixed network error is converged, obtaining an optimized initial logistic regression model, and taking the optimized initial logistic regression model as a public opinion grade judgment model.
3. The method for identifying black products based on internet public sentiment according to claim 2, wherein the step of performing feature extraction on the historical public sentiment sample records by using the feature recognition network in the initial logistic regression model to obtain a feature sequence comprises:
carrying out convolution on the historical public opinion sample record by utilizing the convolution layer of the feature recognition network to obtain a convolution matrix set;
performing maximum pooling operation on the convolution matrix set to obtain a pooled feature matrix set;
according to a preset splitting connection method, performing one-dimensional arrangement on each pooling characteristic matrix in the pooling characteristic matrix set to obtain a local characteristic sequence set;
and carrying out full connection operation on each local characteristic sequence in the local characteristic sequence set to obtain a characteristic sequence.
4. The internet public opinion-based black product identification method according to claim 1, wherein the public opinion grade determination model is used for grade determination of the public opinion monitoring record of the target public opinion to obtain the public opinion grade of the target public opinion, comprising:
identifying the public opinion monitoring record of the target public opinion by using a feature identification network of the public opinion grade judgment model to obtain a feature sequence of the public opinion monitoring record;
grouping the characteristic sequences of the public opinion monitoring records to obtain a propagation platform type characteristic sequence and a data change characteristic sequence;
and carrying out network configuration on the operational neural network of the public opinion grade judgment model according to the propagation platform type characteristic sequence, and carrying out public opinion type judgment on the data change characteristic sequence by using the configured operational neural network to obtain the public opinion grade of the target public opinion.
5. The method as claimed in claim 1, wherein the step of querying the user activity of each user in the first user set and extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity comprises:
acquiring browsing activity, comment activity and forwarding activity of each user in the first user set;
according to preset weight configuration, the browsing activity, the comment activity and the forwarding activity, carrying out weighted summation calculation on each user in the first user set to obtain the user activity of each user in the first user set;
extracting users in a preset first interval of liveness as key opinion leaders to obtain a key opinion leader set;
and extracting the users in the preset second activity interval as the users with low activity to obtain a low-level activity user set.
6. The method for identifying black products based on internet public sentiment according to claim 1, wherein the performing location clustering operation on the users in the login address set to obtain a clustering result comprises:
carrying out longitude and latitude two-dimensional marking on each login address in the login address set to obtain a login coordinate cluster;
and carrying out position clustering on the login coordinate cluster by using a K-Means clustering algorithm to obtain a clustering result.
7. The method for identifying black products based on internet public sentiment according to claim 1, wherein before the regression analysis of the pre-constructed initial logistic regression model is performed by using the historical public sentiment monitoring record set to obtain the public sentiment grade judgment model, the method further comprises:
acquiring a pre-constructed feature recognition network and an operational neural network containing a logistic regression activation function;
and connecting the characteristic recognition network serving as an input layer and the neural network serving as a processing judgment layer to obtain an initial logistic regression model.
8. The utility model provides a black product recognition device based on network public opinion, its characterized in that, the device includes:
the model acquisition module is used for carrying out regression analysis on the pre-constructed initial logistic regression model by utilizing the historical public opinion monitoring record set to obtain a public opinion grade judgment model;
the public opinion grade judging module is used for acquiring a public opinion monitoring record of the target public opinion according to a preset embedding point, and performing grade judgment on the public opinion monitoring record of the target public opinion by using the public opinion grade judging model to obtain a public opinion grade of the target public opinion;
the first user acquisition module is used for judging the target public opinion as suspected abnormal public opinion when the public opinion grade is greater than or equal to a preset warning grade, and acquiring a user performing preset operation on the suspected abnormal public opinion within a preset first time to obtain a first user set;
the black product user query module is used for querying the user activity of each user in the first user set, extracting a key opinion leader set and a low-level activity user set from the first user set according to a preset extraction rule and the user activity, acquiring a login address of each user in the low-level activity user set to obtain a login address set, performing position clustering operation on the users in the login address set to obtain a clustering result, and extracting a black product user set from the low-level activity user set according to the clustering result and a preset black product user extraction rule;
and the black product associated user query module is used for constructing an information propagation network of the key opinion leader set and the black product user set, querying key opinion leader users associated with the information propagation path of the black product user set in the key opinion leader set according to the information propagation network, and outputting the queried key opinion leader users as black product directly associated users.
9. An apparatus, characterized in that the apparatus comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for identifying black products based on internet public opinion according to any one of claims 1 to 7.
10. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the network public opinion-based black product identification method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210278436.1A CN114610980A (en) | 2022-03-21 | 2022-03-21 | Network public opinion based black product identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210278436.1A CN114610980A (en) | 2022-03-21 | 2022-03-21 | Network public opinion based black product identification method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114610980A true CN114610980A (en) | 2022-06-10 |
Family
ID=81864635
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210278436.1A Pending CN114610980A (en) | 2022-03-21 | 2022-03-21 | Network public opinion based black product identification method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114610980A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111784492A (en) * | 2020-07-10 | 2020-10-16 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method, device, electronic equipment and storage medium |
CN111784492B (en) * | 2020-07-10 | 2024-08-02 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method and device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446394A (en) * | 2018-09-27 | 2019-03-08 | 武汉大学 | For network public-opinion event based on modular public sentiment monitoring method and system |
CN109525595A (en) * | 2018-12-25 | 2019-03-26 | 广州华多网络科技有限公司 | A kind of black production account recognition methods and equipment based on time flow feature |
CN110084395A (en) * | 2019-02-18 | 2019-08-02 | 天津科技大学 | Prediction technique, device, server and the storage medium of network public-opinion evolution result |
CN110995681A (en) * | 2019-11-25 | 2020-04-10 | 北京奇艺世纪科技有限公司 | User identification method and device, electronic equipment and storage medium |
CN111614690A (en) * | 2020-05-28 | 2020-09-01 | 上海观安信息技术股份有限公司 | Abnormal behavior detection method and device |
CN113742592A (en) * | 2021-09-08 | 2021-12-03 | 平安信托有限责任公司 | Public opinion information pushing method, device, equipment and storage medium |
-
2022
- 2022-03-21 CN CN202210278436.1A patent/CN114610980A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446394A (en) * | 2018-09-27 | 2019-03-08 | 武汉大学 | For network public-opinion event based on modular public sentiment monitoring method and system |
CN109525595A (en) * | 2018-12-25 | 2019-03-26 | 广州华多网络科技有限公司 | A kind of black production account recognition methods and equipment based on time flow feature |
CN110084395A (en) * | 2019-02-18 | 2019-08-02 | 天津科技大学 | Prediction technique, device, server and the storage medium of network public-opinion evolution result |
CN110995681A (en) * | 2019-11-25 | 2020-04-10 | 北京奇艺世纪科技有限公司 | User identification method and device, electronic equipment and storage medium |
CN111614690A (en) * | 2020-05-28 | 2020-09-01 | 上海观安信息技术股份有限公司 | Abnormal behavior detection method and device |
CN113742592A (en) * | 2021-09-08 | 2021-12-03 | 平安信托有限责任公司 | Public opinion information pushing method, device, equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111784492A (en) * | 2020-07-10 | 2020-10-16 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method, device, electronic equipment and storage medium |
CN111784492B (en) * | 2020-07-10 | 2024-08-02 | 讯飞智元信息科技有限公司 | Public opinion analysis and financial early warning method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111177714B (en) | Abnormal behavior detection method and device, computer equipment and storage medium | |
CN113592019A (en) | Fault detection method, device, equipment and medium based on multi-model fusion | |
CN112396547B (en) | Course recommendation method, device, equipment and medium based on unsupervised learning | |
CN111666415A (en) | Topic clustering method and device, electronic equipment and storage medium | |
CN111860377A (en) | Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium | |
CN115146865A (en) | Task optimization method based on artificial intelligence and related equipment | |
CN111767192B (en) | Business data detection method, device, equipment and medium based on artificial intelligence | |
CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
CN111985545A (en) | Target data detection method, device, equipment and medium based on artificial intelligence | |
CN114862140A (en) | Behavior analysis-based potential evaluation method, device, equipment and storage medium | |
CN115081016A (en) | Log desensitization method and device, electronic equipment and storage medium | |
CN115034315A (en) | Business processing method and device based on artificial intelligence, computer equipment and medium | |
CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
CN115037790B (en) | Abnormal registration identification method, device, equipment and storage medium | |
CN115099339A (en) | Fraud behavior identification method and device, electronic equipment and storage medium | |
CN115550077A (en) | Real-time online detection danger source data and trigger automatic defense method | |
CN114610980A (en) | Network public opinion based black product identification method, device, equipment and storage medium | |
CN115544566A (en) | Log desensitization method, device, equipment and storage medium | |
CN114662095A (en) | Safety monitoring method, device and equipment based on operation data and storage medium | |
CN115357666A (en) | Abnormal business behavior identification method and device, electronic equipment and storage medium | |
CN114996386A (en) | Business role identification method, device, equipment and storage medium | |
CN114662005A (en) | Message pushing method, device, equipment and storage medium for user behavior track | |
CN114818685A (en) | Keyword extraction method and device, electronic equipment and storage medium | |
CN114219367A (en) | User scoring method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |