CN112487188A - Public opinion monitoring method and device, electronic equipment and storage medium - Google Patents
Public opinion monitoring method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112487188A CN112487188A CN202011411226.2A CN202011411226A CN112487188A CN 112487188 A CN112487188 A CN 112487188A CN 202011411226 A CN202011411226 A CN 202011411226A CN 112487188 A CN112487188 A CN 112487188A
- Authority
- CN
- China
- Prior art keywords
- model
- public opinion
- monitoring
- training
- network structure
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 102
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 94
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 description 13
- 230000008451 emotion Effects 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000007935 neutral effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013526 transfer learning Methods 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
Abstract
The embodiment of the application discloses public opinion monitoring method, device, electronic equipment and storage medium, wherein the method comprises the following steps: acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task; modifying an output layer of the pre-training model into a text classification layer to obtain an initial model; aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model; and monitoring the acquired public opinion data based on a public opinion monitoring model. In the embodiment of the application, an initial model is directly constructed on the basis of the pre-training model, namely, the parameters of the pre-training model are reserved in the initial model, so that the model does not need to learn from zero, the efficiency of model training and the accuracy of model prediction are improved, and the accuracy of public opinion detection through the trained public opinion monitoring model is ensured.
Description
Technical Field
The application relates to the technical field of internet, in particular to a public opinion monitoring method, a public opinion monitoring device, electronic equipment and a storage medium.
Background
With the development of the internet, network media have permeated into the daily life of people, more and more users choose to announce their emotions on a social media platform, so how an enterprise can know the positive public sentiment and the negative public sentiment of the enterprise at the first time, and how to quickly master the problem types to which the negative public sentiment belongs after the negative public sentiment appears is an important ring for ensuring that the enterprise quickly starts a public affair emergency strategy at the first time, thereby improving the service quality and the customer satisfaction.
The existing online public opinion monitoring and analyzing method mainly comprises two types of manual monitoring and technical monitoring. The manual monitoring is a traditional information monitoring mode, mainly by means of some free public opinion monitoring tools or search engines, in-site navigation search of news portal websites and the like, and has the defects that the network information is always in dynamic change, the information quantity is huge, and the timeliness and the comprehensiveness of the information acquisition are difficult to guarantee; the technical monitoring method mostly adopts a machine system programming search or a machine learning method of traditional artificial characteristic engineering plus a shallow classification model, the text representation of the traditional machine learning method is high-latitude and high-sparsity, the characteristic expression capability is very weak, and a neural network is very poor in processing the data, so that the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word problem, difficult problems in different scenes and fields and the like are difficult to solve, and the accuracy of public opinion monitoring is low.
Disclosure of Invention
The embodiment of the application provides a public opinion monitoring method, a public opinion monitoring device, electronic equipment and a storage medium, so as to achieve the purpose of improving the public opinion monitoring accuracy.
In a first aspect, an embodiment of the present application provides a public opinion monitoring method, which includes:
acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
modifying an output layer of the pre-training model into a text classification layer to obtain an initial model;
aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model;
and monitoring the acquired public opinion data based on a public opinion monitoring model. In a second aspect, an embodiment of the present application provides a public opinion monitoring device, the device includes:
the model acquisition module is used for acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
the building module is used for modifying an output layer of the pre-training model into a text classification layer to obtain an initial model;
the training module is used for training the initial model by using public opinion sample data aiming at the text classification task to obtain a public opinion monitoring model;
and the monitoring module is used for monitoring the acquired public opinion data based on the public opinion monitoring model.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the public opinion monitoring method according to any embodiment of the present application.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the public opinion monitoring method according to any of the embodiments of the present application.
In the embodiment of the application, the pre-training model is obtained after the preset network structure is trained by using large-scale linguistic text data, so that the pre-training model can obtain word vector representation of each word, and semantic information and context information of the word are obtained. Therefore, the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word problems, different scenes and different fields in the prior art are solved; meanwhile, an initial model is directly constructed on the basis of the pre-training model, namely, the parameters of the pre-training model are reserved in the initial model, so that the model does not need to learn from zero, the efficiency of model training and the accuracy of model prediction are improved, and the accuracy of public opinion detection by using the trained public opinion monitoring model is further ensured.
Drawings
Fig. 1 is a flowchart illustrating a public opinion monitoring method according to a first embodiment of the present application;
fig. 2 is a flowchart illustrating a public opinion monitoring method according to a second embodiment of the present application;
fig. 3 is a schematic structural diagram of a public opinion monitoring device according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device for implementing a public opinion monitoring method according to a fourth embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Fig. 1 is a flowchart of a public opinion monitoring method according to a first embodiment of the present application, which is applicable to a situation where monitoring network public opinions is performed by a server or other devices, and the method can be performed by a public opinion monitoring device, which can be implemented in software and/or hardware, and can be integrated into an electronic device, such as an integrated server device.
Referring to fig. 1, the public opinion monitoring method specifically includes:
s101, obtaining a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task.
The existing public opinion monitoring method is difficult to solve the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word, difficult problems in different scenes and fields and the like. Based on the creative proposal of the inventor, the training of the public opinion monitoring model is divided into two stages, namely a pre-training stage and a transfer learning stage.
In the pre-training stage, a preset network structure is constructed, wherein the preset network structure is any one of the following structures: fully-connected network structures (e.g., word2vec, FastText), convolutional neural network structures (e.g., TextCNN), recurrent neural network structures (e.g., TextRNN, TextAttBliRNN, TextBiRNN, RCNNVariant), cyclic convolutional neural network structures (e.g., RCNNVariant), and attention models (e.g., BERT).
Further, the preset network structure is trained by using linguistic text data aiming at a language model task, wherein the linguistic text data can be selected as linguistic knowledge data in a text format, and the language model task is also a task for recognizing word vector representation of each word in the linguistic text data based on context. That is, the pre-trained model is used to identify context-based word vector representations of individual words in the linguistic text data. During specific training, a large amount of general linguistic knowledge can be extracted and coded into a preset network structure for training to obtain a pre-training model.
It should be noted here that the pre-training model is obtained by training a large amount of general linguistic knowledge data, so that the pre-training model can effectively obtain word vector representation based on context, and the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word problems, different scenes and fields are effectively solved.
The migration learning phase may proceed according to the process of S102-S103.
S102, modifying an output layer of the pre-training model into a text classification layer to obtain an initial model.
The pre-training model obtained in step S101 is a model with training weights (i.e., training parameters), and in order to avoid designing a complex model and training that takes a long time, in the migration learning stage, the output layer of the pre-training model may be directly modified to a text classification layer to obtain an initial model. That is, the training weight of the pre-training model is retained in the initial model, and only the output layer is changed into the text classification layer, so that the initial model can perform a text classification task.
In another alternative embodiment, a network structure identical to the pre-training model may be constructed, an output layer of the network structure is a text classification layer, and the training weights of the pre-training model are migrated to the network structure to obtain the initial model.
S103, aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model.
The public opinion sample data comprises positive public opinion data, negative public opinion data and neutral public opinion data, and besides a label for marking the positive and negative samples, the public opinion sample data is also provided with a label comprising at least one evaluation index. The evaluation index is determined according to a specific service, and may be selected from time limit, service quality, service attitude, price, and the like, and may also include other indexes, which are not specifically limited herein.
In an optional implementation manner, the monitoring the acquired public opinion data based on the public opinion monitoring analysis model includes: and inputting the acquired public opinion data into a public opinion monitoring model, and determining a public opinion monitoring result according to the output of the public opinion monitoring model.
Specifically, after a certain public opinion sample data is coded and input into a public opinion monitoring model, whether the public opinion sample data is positive public opinion data, negative public opinion data or neutral public opinion data is determined according to the output of the public opinion monitoring model, and an evaluation index of the public opinion sample data is determined. And comparing the determined result with the label of the public opinion data, and back-propagating the comparison result so as to adjust the weight of the model.
It should be noted that, because the training weight of the pre-training model is retained in the initial model, when public opinion sample data is utilized, only the training weight in the initial model needs to be fine-tuned, thereby improving the training efficiency of the model.
And S104, monitoring the acquired public opinion data based on a public opinion monitoring model.
After the public opinion monitoring model is obtained, the obtained public opinion data can be input into the model, and whether the public opinion data is positive evaluation, negative evaluation or neutral evaluation is determined according to the output of the model; and simultaneously, outputting the corresponding evaluation index.
Illustratively, the public opinion data obtained is: the XX express delivery is very weak, the express delivery is directly returned to … …', the express delivery is input into a public opinion monitoring model, the model outputs the probability of each evaluation index, and then the public opinion data can be determined to be negative evaluation according to the probability value, and the negative evaluation is mainly unsatisfactory to the time limit of the evaluation index. In the embodiment of the application, the pre-training model is obtained after the preset network structure is trained by using large-scale linguistic text data, so that the pre-training model can obtain word vector representation of each word, and semantic information and context information of the word are obtained. Therefore, the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word problems, different scenes and different fields in the prior art are solved; meanwhile, an initial model is directly constructed on the basis of the pre-training model, namely, the parameters of the pre-training model are reserved in the initial model, so that the model does not need to learn from zero, the efficiency of model training and the accuracy of model prediction are improved, and the accuracy of public opinion detection by using the trained public opinion monitoring model is further ensured.
Fig. 2 is a logic flow diagram of a public opinion monitoring method according to a second embodiment of the present application, which is optimized based on the above embodiments, and referring to fig. 2, the method logic includes:
s201, obtaining a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task.
S202, modifying an output layer of the pre-training model into a text classification layer to obtain an initial model.
S203, aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model.
And S204, monitoring the acquired public opinion data based on a public opinion monitoring model.
And S205, performing public opinion analysis in different dimensions according to the public opinion monitoring result.
The dimensionality at least comprises a public opinion propagation path, public opinion propagation user characteristics and public opinion overall situation. Aiming at the overall public opinion situation, the conditions such as complaint quantity, content and the like of different products on a platform can be benchmarked from the aspects of self and competitive products, so that enterprises can more intuitively and comprehensively master the overall public opinion situation; by analyzing public sentiment propagation paths, the public sentiment propagation rule can be mastered and the public sentiment fermentation can be effectively controlled through analyzing the influence of users transmitting the public sentiments, analyzing public sentiment forwarding time sequences and analyzing the public sentiment propagation; by analyzing the attributes of gender, region and the like of the user who issues the evaluation on the enterprise and the competitive products, the user characteristics of positive and negative evaluations can be known, so that data support is provided for targeted improvement of services.
Through the analysis to public opinion monitoring result in this application embodiment, can effectively grasp public opinion development, and then improve the not enough of enterprise self according to the public opinion.
Fig. 3 is a schematic structural diagram of a public opinion monitoring device according to a third embodiment of the present application, which is applicable to a situation of monitoring network public opinions through a server or other devices, referring to fig. 3, the device includes:
the model obtaining module 301 is configured to obtain a pre-training model, where the pre-training model is a language model obtained by training a preset network structure with linguistic text data for a language model task;
a building module 302, configured to modify an output layer of the pre-training model into a text classification layer to obtain an initial model;
the training module 303 is configured to train the initial model by using public opinion sample data to obtain a public opinion monitoring model for the text classification task;
and the monitoring module 304 is configured to monitor the obtained public opinion data based on a public opinion monitoring model.
In the embodiment of the application, the pre-training model is obtained after the preset network structure is trained by using large-scale linguistic text data, so that the pre-training model can obtain word vector representation of each word, and semantic information and context information of the word are obtained. Therefore, the problems of inaccurate word segmentation, lack of standard complete emotion word stock, negative word problems, different scenes and different fields in the prior art are solved; meanwhile, an initial model is directly constructed on the basis of the pre-training model, namely, the parameters of the pre-training model are reserved in the initial model, so that the model does not need to learn from zero, the efficiency of model training and the accuracy of model prediction are improved, and the accuracy of public opinion detection by using the trained public opinion monitoring model is further ensured.
On the basis of the above embodiment, optionally, the preset network structure is any one of the following: a fully connected network structure, a convolutional neural network structure, a cyclic convolutional neural network structure, and an attention model.
Based on the above embodiments, optionally, the pre-training model is used to identify context-based word vector representations of individual words in the linguistic text data.
On the basis of the foregoing embodiment, optionally, the monitoring module is specifically configured to:
and inputting the acquired public opinion data into a public opinion monitoring model, and determining a public opinion monitoring result according to the output of the public opinion monitoring model.
On the basis of the above embodiment, optionally, the method further includes:
and the analysis module is used for carrying out public opinion analysis in different dimensions according to a public opinion monitoring result after monitoring the acquired public opinion data based on the public opinion monitoring analysis model, wherein the dimensions at least comprise a public opinion propagation path, public opinion propagation user characteristics and the whole public opinion situation.
The public opinion monitoring device provided by the embodiment of the application can execute the public opinion monitoring method provided by any embodiment of the application, and has corresponding functional modules and beneficial effects of the execution method.
Fig. 4 is a schematic structural diagram of an electronic device provided in a fourth embodiment of the present application. As shown in fig. 4, the electronic device provided in the embodiment of the present application includes: one or more processors 402 and memory 401; the processor 402 in the electronic device may be one or more, and one processor 402 is taken as an example in fig. 4; the memory 401 is used to store one or more programs; the one or more programs are executed by the one or more processors 402, such that the one or more processors 402 implement the consensus monitoring method as any one of the embodiments herein.
The electronic device may further include: an input device 403 and an output device 404.
The processor 402, the memory 401, the input device 403 and the output device 404 in the electronic apparatus may be connected by a bus or other means, and fig. 4 illustrates an example of connection by a bus.
The storage device 401 in the electronic device is used as a computer-readable storage medium for storing one or more programs, which may be software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the public opinion monitoring method provided in the embodiments of the present application. The processor 402 executes various functional applications and data processing of the electronic device by running software programs, instructions and modules stored in the storage device 401, so as to implement the public opinion monitoring method in the above method embodiments.
The storage device 401 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 401 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 401 may further include memory located remotely from the processor 402, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 403 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus. The output device 404 may include a display device such as a display screen.
And, when one or more programs included in the above-mentioned electronic device are executed by the one or more processors 402, the programs perform the following operations:
acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
modifying an output layer of the pre-training model into a text classification layer to obtain an initial model;
aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model;
and monitoring the acquired public opinion data based on a public opinion monitoring model.
Of course, it can be understood by those skilled in the art that when the electronic device includes one or more programs executed by the one or more processors 402, the programs may also perform related operations in the public opinion monitoring method provided in any embodiment of the present application.
An embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program for performing a public opinion monitoring method when executed by a processor, the method comprising:
acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
modifying an output layer of the pre-training model into a text classification layer to obtain an initial model;
aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model;
and monitoring the acquired public opinion data based on a public opinion monitoring model.
Optionally, the program, when executed by a processor, may be further configured to perform the method provided in any of the embodiments of the present application.
The computer storage media of the embodiments of the present application may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. A computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take a variety of forms, including, but not limited to: an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including, for example, a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. A public opinion monitoring method is characterized in that the method comprises the following steps:
acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
modifying the output layer of the pre-training model into a text classification layer to obtain an initial model;
aiming at the text classification task, training the initial model by using public opinion sample data to obtain a public opinion monitoring model;
and monitoring the acquired public opinion data based on the public opinion monitoring model.
2. The method according to claim 1, wherein the predetermined network structure is any one of: a fully connected network structure, a convolutional neural network structure, a cyclic convolutional neural network structure, and an attention model.
3. The method of claim 1, wherein the pre-trained model is used to identify context-based word vector representations of individual words in linguistic text data.
4. The method of claim 1, wherein monitoring the acquired public opinion data based on the public opinion monitoring analysis model comprises:
and inputting the acquired public opinion data into the public opinion monitoring model, and determining a public opinion monitoring result according to the output of the public opinion monitoring model.
5. The method of claim 1, wherein after monitoring the acquired public opinion data based on the public opinion monitoring analysis model, the method further comprises:
and carrying out public opinion analysis in different dimensions according to the public opinion monitoring result, wherein the dimensions at least comprise a public opinion propagation path, public opinion propagation user characteristics and public opinion overall situation.
6. The utility model provides a public opinion monitoring devices which characterized in that includes:
the model acquisition module is used for acquiring a pre-training model, wherein the pre-training model is a language model obtained by training a preset network structure by using linguistic text data aiming at a language model task;
the building module is used for modifying the output layer of the pre-training model into a text classification layer to obtain an initial model;
the training module is used for training the initial model by using public opinion sample data aiming at the text classification task to obtain a public opinion monitoring model;
and the monitoring module is used for monitoring the acquired public opinion data based on the public opinion monitoring model.
7. The apparatus of claim 6, wherein the predetermined network structure is any one of: a fully connected network structure, a convolutional neural network structure, a cyclic convolutional neural network structure, and an attention model.
8. The apparatus of claim 6, wherein the monitoring module is specifically configured to:
and inputting the acquired public opinion data into the public opinion monitoring model, and determining a public opinion monitoring result according to the output of the public opinion monitoring model.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the consensus monitoring method of any one of claims 1-5.
10. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method of public opinion monitoring according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011411226.2A CN112487188A (en) | 2020-12-03 | 2020-12-03 | Public opinion monitoring method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011411226.2A CN112487188A (en) | 2020-12-03 | 2020-12-03 | Public opinion monitoring method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112487188A true CN112487188A (en) | 2021-03-12 |
Family
ID=74939513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011411226.2A Pending CN112487188A (en) | 2020-12-03 | 2020-12-03 | Public opinion monitoring method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112487188A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239290A (en) * | 2021-06-10 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Data analysis method and device for public opinion monitoring and electronic device |
| CN113269102A (en) * | 2021-05-28 | 2021-08-17 | 中邮信息科技(北京)有限公司 | Seal information identification method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829807A (en) * | 2018-06-07 | 2018-11-16 | 武汉斗鱼网络科技有限公司 | A kind of public sentiment merging method, device, server and storage medium |
| CN110008336A (en) * | 2019-01-14 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of public sentiment method for early warning and system based on deep learning |
| CN110263154A (en) * | 2019-05-17 | 2019-09-20 | 广州艾媒数聚信息咨询股份有限公司 | A kind of network public-opinion emotion situation quantization method, system and storage medium |
| CN110347830A (en) * | 2019-06-28 | 2019-10-18 | 阿里巴巴集团控股有限公司 | The implementation method and device of public sentiment early warning |
| US20200167419A1 (en) * | 2018-11-27 | 2020-05-28 | Sap Se | Exploiting document knowledge for aspect-level sentiment classification |
-
2020
- 2020-12-03 CN CN202011411226.2A patent/CN112487188A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829807A (en) * | 2018-06-07 | 2018-11-16 | 武汉斗鱼网络科技有限公司 | A kind of public sentiment merging method, device, server and storage medium |
| US20200167419A1 (en) * | 2018-11-27 | 2020-05-28 | Sap Se | Exploiting document knowledge for aspect-level sentiment classification |
| CN110008336A (en) * | 2019-01-14 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of public sentiment method for early warning and system based on deep learning |
| CN110263154A (en) * | 2019-05-17 | 2019-09-20 | 广州艾媒数聚信息咨询股份有限公司 | A kind of network public-opinion emotion situation quantization method, system and storage medium |
| CN110347830A (en) * | 2019-06-28 | 2019-10-18 | 阿里巴巴集团控股有限公司 | The implementation method and device of public sentiment early warning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269102A (en) * | 2021-05-28 | 2021-08-17 | 中邮信息科技(北京)有限公司 | Seal information identification method and device, computer equipment and storage medium |
| CN113239290A (en) * | 2021-06-10 | 2021-08-10 | 杭州安恒信息技术股份有限公司 | Data analysis method and device for public opinion monitoring and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7127106B2 (en) | Question answering process, language model training method, apparatus, equipment and storage medium | |
| CN112966712B (en) | Language model training method and device, electronic equipment and computer readable medium | |
| CN109145104B (en) | Method and device for dialogue interaction | |
| CN110597992A (en) | Semantic reasoning method and device based on knowledge graph and electronic equipment | |
| CN116127020A (en) | Method for training generated large language model and searching method based on model | |
| US20220358292A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
| CN112948534A (en) | Interaction method and system for intelligent man-machine conversation and electronic equipment | |
| US20230259712A1 (en) | Sound effect adding method and apparatus, storage medium, and electronic device | |
| US20230088445A1 (en) | Conversational recommendation method, method of training model, device and medium | |
| EP4134900A2 (en) | Method and apparatus for recommending content, method and apparatus for training ranking model, device, and storage medium | |
| CN112487188A (en) | Public opinion monitoring method and device, electronic equipment and storage medium | |
| CN113836925A (en) | Training method and device for pre-training language model, electronic equipment and storage medium | |
| CN115062617A (en) | Task processing method, device, equipment and medium based on prompt learning | |
| US11875125B2 (en) | System and method for designing artificial intelligence (AI) based hierarchical multi-conversation system | |
| CN113642324A (en) | Text abstract generation method and device, electronic equipment and storage medium | |
| CN117216393A (en) | Information recommendation method, training method and device of information recommendation model and equipment | |
| CN114417974B (en) | Model training method, information processing device, electronic equipment and medium | |
| CN114676227B (en) | Sample generation method, model training method and retrieval method | |
| CN115563281A (en) | Text classification method and device based on text data enhancement | |
| CN115129885A (en) | Entity chain pointing method, device, equipment and storage medium | |
| CN114254642A (en) | Entity information processing method, device, electronic equipment and medium | |
| CN113886543A (en) | Method, apparatus, medium, and program product for generating an intent recognition model | |
| CN113672699A (en) | Knowledge graph-based NL2SQL generation method | |
| CN114141236A (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN110990528A (en) | Question answering method and device and electronic equipment |
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 |