CN113392185A - Public opinion early warning method, device, equipment and storage medium - Google Patents
Public opinion early warning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113392185A CN113392185A CN202110649627.XA CN202110649627A CN113392185A CN 113392185 A CN113392185 A CN 113392185A CN 202110649627 A CN202110649627 A CN 202110649627A CN 113392185 A CN113392185 A CN 113392185A
- Authority
- CN
- China
- Prior art keywords
- data
- intention
- traffic data
- public opinion
- telephone traffic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application provides a public opinion early warning method, a device, equipment and a storage medium, the method obtains traffic data, and carries out data preprocessing on the traffic data to obtain effective traffic data; performing intention identification on the effective telephone traffic data according to a preset intention identification model to obtain intention telephone traffic data; normalizing the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data; if the first normalized intention data is larger than the preset intention threshold, the public sentiment is determined to be abnormal, public sentiment early warning information is generated, and the accuracy of public sentiment early warning is improved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a public opinion early warning method, device, equipment and storage medium.
Background
With the rapid development of the internet and information technology, especially new media such as network platforms and network media, have great influence on politics, economy, culture and social life due to the characteristics of rich form, high coverage rate and the like, the accompanying network public opinion problem also becomes an important factor influencing social stability, and public opinions need to be monitored, analyzed and early warned.
At present, keywords are usually captured by a natural language processing technology, and if the frequency of the keywords is too high, it is determined that an emergency occurs and public sentiment early warning needs to be performed.
However, in the prior art, the public sentiment misjudgment condition can be caused in a special time period, an accurate public sentiment early warning result cannot be obtained, and the accuracy of the public sentiment early warning is poor.
Disclosure of Invention
The application provides a public opinion early warning method, a device, equipment and a storage medium, thereby solving the technical problems that the public opinion misjudgment can be caused in a special time period, an accurate public opinion early warning result cannot be obtained, and the accuracy of public opinion early warning is poor in the prior art.
In a first aspect, an embodiment of the present application provides a public opinion early warning method, including:
acquiring telephone traffic data, and performing data preprocessing on the telephone traffic data to obtain effective telephone traffic data;
according to a preset intention identification model, carrying out intention identification on the effective telephone traffic data to obtain intention telephone traffic data;
normalizing the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data;
and if the first normalization intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
Here, in the embodiment of the application, data preprocessing is performed on traffic data, effective traffic data is screened out, only the effective data is reserved, and subsequent analysis is facilitated, in order to reduce maintenance cost of a keyword bank, word frequency is not used as a feature, intention recognition can be performed on the effective traffic data through a preset intention recognition model to obtain intention traffic data, then normalization processing is performed on the intention traffic data through a preset predicted traffic regression model, because the preset predicted traffic regression model is obtained through training according to historical traffic data and historical public opinion data, influences caused by phenomena of sharp increase of certain speech in a special period are eliminated, influences of traffic increased by an emergency on public opinion data analysis are eliminated, and accuracy of public opinion early warning is improved.
Optionally, before the performing intent recognition on the valid traffic data according to a preset intent recognition model to obtain the intended traffic data, the method further includes:
establishing an intention labeling training database;
and carrying out natural language processing model training on the intention labeling training data in the intention labeling training database to obtain a preset intention recognition model.
Here, the embodiment of the application does not use word frequency as a feature to perform intention recognition, so that the cost of maintaining a keyword library is reduced, and a preset intention recognition model can be established before intention recognition by establishing intention tagging training data tagged in advance in an intention tagging training database, so that intention recognition is performed according to the model, the cost of public opinion analysis early warning is reduced, and the efficiency is improved.
Optionally, before the normalizing the intended traffic data according to the preset predicted traffic regression model to obtain first normalized intended data, the method further includes:
acquiring historical telephone traffic data and historical public opinion data;
and establishing a preset predicted telephone traffic regression model according to the historical telephone traffic data and the historical public opinion data.
Here, in order to normalize the intended traffic data, the embodiment of the present application establishes a preset predicted traffic regression model in advance, and the establishment of the model combines the historical traffic data and the historical public opinion data, so that the traffic added by an emergency can be effectively removed, thereby obtaining an accurate traffic regression model matching with the actual traffic, and further improving the accuracy of public opinion early warning.
Optionally, before the determining that the public opinion is abnormal and generating public opinion warning information if the normalized intention data is greater than a preset intention threshold, the method further includes:
acquiring traffic data of a newly added service;
establishing a newly added service regression model according to the newly added service traffic data;
performing second normalization processing on the first normalization intention data according to the newly added service regression model to obtain second normalization intention data;
correspondingly, if the first normalization intention data is greater than a preset intention threshold, determining that the public opinion is abnormal, and generating public opinion early warning information, including:
and if the second normalized intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
Here, the embodiment of the present application may further establish an input system of a new service, embed the input system of the new service in the public opinion early warning process, and record a time point of the new service, that is, traffic data of the new service, which can be used to establish a regression model of the new service, thereby implementing a second normalization on the first normalization intention data, eliminating an influence of public opinion analysis caused by the new service data, and further improving accuracy of public opinion early warning.
Optionally, the data preprocessing the traffic data includes:
and classifying and screening invalid data of the telephone traffic data through a natural language processing technology.
Optionally, after the generating public opinion early warning information, further comprising:
and outputting a public opinion report.
Here, after determining that there is an abnormal public opinion, the embodiment of the present application may output a public opinion report, so as to facilitate grasping of public opinion information, and perform service adjustment and prediction of telephone traffic according to the public opinion information.
In a second aspect, an embodiment of the present application provides a public opinion early warning device, including:
the first acquisition module is used for acquiring the telephone traffic data and carrying out data preprocessing on the telephone traffic data to obtain effective telephone traffic data;
the first processing module is used for carrying out intention identification on the effective telephone traffic data according to a preset intention identification model to obtain intention telephone traffic data;
the second processing module is used for carrying out normalization processing on the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data; (ii) a
And the early warning module is used for determining that the public sentiment is abnormal and generating public sentiment early warning information if the first normalized intention data is greater than a preset intention threshold value.
Optionally, before the first processing module performs intent recognition on the valid traffic data according to a preset intent recognition model to obtain intent traffic data, the apparatus further includes:
the first establishing module is used for establishing an intention labeling training database;
and the training module is used for carrying out natural language processing model training on the intention labeling training data in the intention labeling training database to obtain a preset intention recognition model.
Optionally, before the second processing module normalizes the intended traffic data according to a preset regression model of predicted traffic to obtain first normalized intended data, the apparatus further includes:
the second acquisition module is used for acquiring historical telephone traffic data and historical public opinion data;
and the second establishing module is used for establishing a preset predicted telephone traffic regression model according to the historical telephone traffic data and the historical public opinion data.
Optionally, before the early warning module determines that the public opinion is abnormal and generates the public opinion early warning information if the normalized intention data is greater than a preset intention threshold, the apparatus further includes:
the third acquisition module is used for acquiring traffic data of the newly added service;
the third establishing module is used for establishing a newly added service regression model according to the newly added service telephone traffic data;
the third processing module is used for carrying out second normalization processing on the first normalization intention data according to the newly added service regression model to obtain second normalization intention data;
correspondingly, the early warning module is specifically configured to:
and if the second normalized intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
Optionally, the first obtaining module is specifically configured to:
and classifying and screening invalid data of the telephone traffic data through a natural language processing technology.
Optionally, after the warning module generates the public opinion warning information, the method further includes:
and the generating module is used for generating a public opinion report.
In a third aspect, an embodiment of the present application provides a public opinion early warning device, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the public opinion alerting method as described above in the first aspect and various possible designs of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the public opinion warning method according to the first aspect and various possible designs of the first aspect is implemented.
In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the public opinion warning method according to the first aspect and various possible designs of the first aspect is implemented.
The public opinion early warning method, the device, the equipment and the storage medium provided by the embodiment of the application are characterized in that the method firstly carries out data preprocessing aiming at telephone traffic data, screens out effective telephone traffic data, only retains the effective data for convenient subsequent analysis, reduces the maintenance cost of a keyword library, does not use word frequency as a characteristic, and identifies a model through preset intentions, the method can identify the intention of the effective telephone traffic data to obtain the intention telephone traffic data, and then through a preset regression model of the predicted telephone traffic, the intention traffic data is normalized, and the preset prediction traffic regression model is obtained by training according to the historical traffic data and the historical public opinion data, so that the influence caused by the phenomenon that a certain traffic is increased sharply in a special period is eliminated, the influence of the traffic increased by an emergency on public opinion data analysis is eliminated, and the accuracy of public opinion early warning is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic diagram of a public opinion warning system architecture according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart illustrating a public opinion warning method according to an embodiment of the present disclosure;
fig. 3 is a graph of actual traffic data of a regression model of preset predicted traffic according to an embodiment of the present disclosure;
fig. 4 is a graph of intended traffic data provided by an embodiment of the present application;
FIG. 5 is a graph of first normalized intention data after normalization processing;
fig. 6 is a flowchart illustrating another public opinion warning method according to an embodiment of the present application;
FIG. 7 is a 5-month traffic curve provided in the embodiments of the present application;
FIG. 8 is a 6-month traffic curve provided by an embodiment of the present application;
fig. 9 is a graph of traffic volume after 6 months of correction according to an embodiment of the present application;
fig. 10 is a graph of an unreduced traffic volume according to an embodiment of the present application;
fig. 11 is a graph illustrating a traffic volume after a new increase according to an embodiment of the present application;
fig. 12 is a schematic structural diagram of a public opinion warning device according to an embodiment of the present application;
fig. 13 is a schematic structural diagram of a public opinion warning device according to an embodiment of the present application.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terms "first," "second," "third," and "fourth," if any, in the description and claims of this application and the above-described figures are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The public opinion early warning in the communication industry is mainly used for monitoring emergencies, such as network abnormity, system abnormity, group complaint events and the like, a common method is adopted, the recall rate of the emergencies early warning can reach 99%, but the accuracy rate is less than 10%, the main reason is that the conversation content in the communication industry is related to time factors, such as account period at the end of the month, telephone charge problems can be increased rapidly, flow use problems can also be increased rapidly in the month, which are normal phenomena, and the conventional monitoring system can classify the situations into the emergencies, so that the accuracy rate is low, and a large amount of time is required for workers to check the accuracy of the emergencies.
The prior art has the technical problems that the public sentiment misjudgment can be caused in a special time period, an accurate public sentiment early warning result cannot be obtained, and the accuracy of public sentiment early warning is poor.
In order to solve the above problems, embodiments of the present application provide a public opinion early warning method, apparatus, device, and storage medium, where the method may identify an intention by using a natural language technology, count frequency of the intention, and construct a regression model by using big data, so as to eliminate an influence caused by a phenomenon that a certain intention is suddenly increased due to different periods in the industry.
Optionally, fig. 1 is a schematic diagram of a public opinion warning system architecture according to an embodiment of the present disclosure. In fig. 1, the above-described architecture includes an operator server 101 and an information supervision server 102.
The information monitoring server 102 can collect traffic data through the operator server 101, and performs public sentiment early warning according to the traffic data.
It is understood that the schematic structure of the embodiment of the present application does not constitute a specific limitation to the architecture of the public opinion warning system. In other possible embodiments of the present application, the foregoing architecture may include more or less components than those shown in the drawings, or combine some components, or split some components, or arrange different components, which may be determined according to practical application scenarios, and is not limited herein. The components shown in fig. 1 may be implemented in hardware, software, or a combination of software and hardware.
It should be understood that the processor may be implemented by reading instructions in the memory and executing the instructions, or may be implemented by a chip circuit.
In addition, the network architecture and the service scenario described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not constitute a limitation to the technical solution provided in the embodiment of the present application, and it can be known by a person skilled in the art that along with the evolution of the network architecture and the appearance of a new service scenario, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.
The technical scheme of the application is described in detail by combining specific embodiments as follows:
optionally, fig. 2 is a schematic flow chart of a public opinion warning method according to an embodiment of the present disclosure. The execution subject of the embodiment of the present application may be the information monitoring server 101 in fig. 1, and the specific execution subject may be determined according to an actual application scenario. As shown in fig. 2, the method comprises the steps of:
s201: and acquiring the traffic data, and performing data preprocessing on the traffic data to obtain effective traffic data.
Optionally, the data preprocessing is performed on the traffic data, and includes:
and classifying and screening invalid data of the traffic data by a natural language processing technology.
Alternatively, the pre-processing of traffic data may be accomplished by one or more of a crawler technique, a Chinese word segmentation technique, and a natural language processing technique.
S202: and performing intention identification on the effective telephone traffic data according to a preset intention identification model to obtain the intention telephone traffic data.
Optionally, before performing intent recognition on the valid traffic data according to a preset intent recognition model to obtain intent traffic data, the method further includes:
establishing an intention labeling training database; and carrying out natural language processing model training on the intention labeling training data in the intention labeling training database to obtain a preset intention recognition model.
In this case, a large amount of "content-intention" training data may be manually labeled to perform Natural Language Processing (NLP) model training, and then used for intention recognition of the effective data.
Here, the embodiment of the application does not use word frequency as a feature to perform intention recognition, so that the cost of maintaining a keyword library is reduced, and a preset intention recognition model can be established before intention recognition by establishing intention tagging training data tagged in advance in an intention tagging training database, so that intention recognition is performed according to the model, the cost of public opinion analysis early warning is reduced, and the efficiency is improved.
Alternatively, the intention recognition may be performed according to the word frequency.
S203: and normalizing the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data.
The preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data.
Exemplarily, fig. 3 is a graph of actual traffic data of a regression model of preset predicted traffic, fig. 4 is a graph of intention traffic data, and fig. 5 is a graph of normalized intention data, which can be used for public opinion warning according to fig. 5.
S204: and if the first normalized intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
It is understood that the preset intention threshold value can be determined according to actual conditions, and the embodiment of the application is not particularly limited.
Optionally, after generating the public opinion warning information, the method further includes:
and outputting a public opinion report.
Here, after determining that there is an abnormal public opinion, the embodiment of the present application may output a public opinion report, so as to facilitate grasping of public opinion information, and perform service adjustment and prediction of telephone traffic according to the public opinion information.
The embodiment of the application firstly carries out data preprocessing aiming at the traffic data, effective traffic data is screened out, only the effective data is reserved, and subsequent analysis is convenient to carry out, in order to reduce the maintenance cost of a keyword library, word frequency is not used as a characteristic, the effective traffic data can be subjected to intention identification through a preset intention identification model to obtain intention traffic data, then, the intention traffic data is subjected to normalization processing through a preset predicted traffic regression model, and the preset predicted traffic regression model is obtained through training according to historical traffic data and historical public opinion data, so that the influence caused by the phenomenon that a certain traffic sharply increases in a special period is eliminated, the influence of the traffic increased by an emergency on public opinion data analysis is eliminated, and the accuracy of public opinion early warning is improved.
In an optional implementation manner, in the embodiment of the present application, a preset regression model of predicted telephone traffic and a regression model of a newly added service may be further pre-established, and the intention telephone traffic data is normalized twice through the models, so that the influence of the special time and the newly added service on public opinion early warning can be effectively eliminated, and accordingly, fig. 6 is a schematic flow diagram of another public opinion early warning method provided in the embodiment of the present application, as shown in fig. 6, the method includes:
s601: and acquiring the traffic data, and performing data preprocessing on the traffic data to obtain effective traffic data.
S602: and performing intention identification on the effective telephone traffic data according to a preset intention identification model to obtain the intention telephone traffic data.
The implementation manners of steps S601 to S602 are similar to the implementation manners of steps S201 to S202, and are not described herein again.
S603: and acquiring historical telephone traffic data and historical public opinion data.
S604: and establishing a preset predicted telephone traffic regression model according to the historical telephone traffic data and the historical public opinion data.
In an exemplary case, if network failure occurs in a certain place in 6 months and 5 days, the regression model cannot be established by adopting data of 6 months and 5 days, and 6 months and 5 need to be replaced by normal data of 5 months and 5 months or 7 months and 5.
Exemplarily, fig. 7 is a 5-month traffic volume graph provided by the embodiment of the present application, fig. 8 is a 6-month traffic volume graph provided by the embodiment of the present application, wherein if traffic volume abnormality occurs in 5 days after 6 months, data replacement is performed according to 5 or 5 months after 7 months, and a corrected curve can be obtained, and fig. 9 is a 6-month traffic volume graph provided by the embodiment of the present application.
In order to normalize the intended traffic data, a preset predicted traffic regression model is pre-established in the embodiment of the application, and the establishment of the model combines the historical traffic data and the historical public opinion data, so that the traffic increased by an emergency can be effectively removed, an accurate traffic regression model matched with the actual traffic is obtained, and the accuracy of public opinion early warning is further improved.
S605: and normalizing the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data.
S606: and acquiring traffic data of the newly added service.
S607: and establishing a newly added service regression model according to the newly added service traffic data.
Exemplarily, fig. 10 is a graph of an unreduced traffic volume according to the embodiment of the present application, and fig. 11 is a graph of a post-added traffic volume according to the embodiment of the present application.
S608: and performing second normalization processing on the first normalization intention data according to the newly added service regression model to obtain second normalization intention data.
S609: and if the second normalized intention data is larger than the preset intention threshold, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
The embodiment of the application can also establish a newly-added service input system, the newly-added service input system is embedded in the public opinion early warning process, the time point of the newly-added service, namely the newly-added service traffic data, is recorded, and the data can be used for establishing a newly-added service regression model, so that the secondary normalization of the first normalization intention data is realized, the influence of public opinion analysis caused by the newly-added service data is eliminated, and the accuracy of public opinion early warning is further improved.
Fig. 12 is a schematic structural diagram of a public opinion warning device according to an embodiment of the present application, and as shown in fig. 12, the device according to the embodiment of the present application includes: the system comprises a first acquisition module 1201, a first processing module 1202, a second processing module 1203 and an early warning module 1204. The public opinion warning device may be the information monitoring server 102 itself, or a chip or an integrated circuit that implements the functions of the information monitoring server 102. It should be noted here that the division of the first obtaining module 1201, the first processing module 1202, the second processing module 1203 and the early warning module 1204 is only a division of logic functions, and the two modules may be integrated or independent physically.
The first acquisition module is used for acquiring the traffic data and carrying out data preprocessing on the traffic data to obtain effective traffic data;
the first processing module is used for carrying out intention identification on the effective telephone traffic data according to a preset intention identification model to obtain intention telephone traffic data;
the second processing module is used for carrying out normalization processing on the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data; (ii) a
And the early warning module is used for determining that the public sentiment is abnormal and generating public sentiment early warning information if the first normalized intention data is greater than a preset intention threshold value.
Optionally, before the first processing module performs intent recognition on the valid traffic data according to a preset intent recognition model to obtain the intent traffic data, the apparatus further includes:
the first establishing module is used for establishing an intention labeling training database;
and the training module is used for carrying out natural language processing model training on the intention labeling training data in the intention labeling training database to obtain a preset intention recognition model.
Optionally, before the second processing module normalizes the intended traffic data according to the preset regression model of predicted traffic to obtain the first normalized intended data, the apparatus further includes:
the second acquisition module is used for acquiring historical telephone traffic data and historical public opinion data;
and the second establishing module is used for establishing a preset predicted telephone traffic regression model according to the historical telephone traffic data and the historical public opinion data.
Optionally, before the early warning module determines that the public opinion is abnormal and generates the public opinion early warning information if the normalized intention data is greater than the preset intention threshold, the apparatus further includes:
the third acquisition module is used for acquiring traffic data of the newly added service;
the third establishing module is used for establishing a newly added service regression model according to the traffic data of the newly added service;
the third processing module is used for carrying out second normalization processing on the first normalization intention data according to the newly added service regression model to obtain second normalization intention data;
correspondingly, the early warning module is specifically configured to:
and if the second normalized intention data is larger than the preset intention threshold, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
Optionally, the first obtaining module is specifically configured to:
and classifying and screening invalid data of the traffic data by a natural language processing technology.
Optionally, after the public opinion early warning information is generated by the early warning module, the method further comprises:
and the generating module is used for generating a public opinion report.
Fig. 13 is a schematic structural diagram of a public opinion warning device according to an embodiment of the present application, where the public opinion warning device may be an information monitoring server 102. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not limiting to the implementations of the present application described and/or claimed herein.
As shown in fig. 13, the public opinion early warning apparatus includes: processor 1301 and memory 1302, the various components being interconnected using different buses, and may be mounted on a common motherboard or in other manners as desired. The processor 1301 may process instructions for execution within a public opinion alerting device, including instructions for graphical information stored in or on a memory for display on an external input/output apparatus (such as a display device coupled to an interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Fig. 13 illustrates an example of a processor 1301.
The memory 1302 may be used as a non-transitory computer readable storage medium to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method of the public opinion warning apparatus in the embodiment of the present application (for example, as shown in fig. 12, the first obtaining module 1201, the first processing module 1202, the second processing module 1203, and the warning module 1204). The processor 1301 executes various functional applications and data processing of the authentication platform by running non-transitory software programs, instructions and modules stored in the memory 1302, so as to implement the method of the public opinion warning apparatus in the above method embodiment.
Public opinion early warning equipment can also include: an input device 1303 and an output device 1304. The processor 1301, the memory 1302, the input device 1303 and the output device 1304 may be connected by a bus or other means, and fig. 13 illustrates the bus connection.
The input device 1303 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the public opinion warning apparatus, such as a touch screen, a keypad, a mouse, or a plurality of mouse buttons, a trackball, a joystick, and the like. The output device 1304 may be an output device such as a display device of a public opinion warning device. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Public opinion early warning equipment of this application embodiment can be used for carrying out the technical scheme in each above-mentioned method embodiment of this application, and its theory of realization and technological effect are similar, and it is no longer repeated here.
An embodiment of the present application further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is used to implement any one of the above public opinion early warning methods.
The embodiment of the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program is configured to implement any one of the above-mentioned public opinion early warning methods.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units 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, and can also be realized in a form of a software functional unit.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A public opinion early warning method is characterized by comprising the following steps:
acquiring telephone traffic data, and performing data preprocessing on the telephone traffic data to obtain effective telephone traffic data;
according to a preset intention identification model, carrying out intention identification on the effective telephone traffic data to obtain intention telephone traffic data;
normalizing the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data;
and if the first normalization intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
2. The method of claim 1, wherein before the performing intent recognition on the valid traffic data according to a preset intent recognition model to obtain intent traffic data, the method further comprises:
establishing an intention labeling training database;
and carrying out natural language processing model training on the intention labeling training data in the intention labeling training database to obtain a preset intention recognition model.
3. The method of claim 1, wherein before the normalizing the intended traffic data according to the preset regression model of predicted traffic to obtain the first normalized intended data, the method further comprises:
acquiring historical telephone traffic data and historical public opinion data;
and establishing a preset predicted telephone traffic regression model according to the historical telephone traffic data and the historical public opinion data.
4. The method of claim 3, wherein before determining that the public opinion is abnormal and generating the public opinion warning information if the normalized intention data is greater than a preset intention threshold, further comprising:
acquiring traffic data of a newly added service;
establishing a newly added service regression model according to the newly added service traffic data;
performing second normalization processing on the first normalization intention data according to the newly added service regression model to obtain second normalization intention data;
correspondingly, if the first normalization intention data is greater than a preset intention threshold, determining that the public opinion is abnormal, and generating public opinion early warning information, including:
and if the second normalized intention data is larger than a preset intention threshold value, determining that the public sentiment is abnormal, and generating public sentiment early warning information.
5. The method of any of claims 1 to 4, wherein the data pre-processing the traffic data comprises:
and classifying and screening invalid data of the telephone traffic data through a natural language processing technology.
6. The method of any one of claims 1 to 4, wherein after the generating the public opinion warning information, the method further comprises:
and generating a public opinion report.
7. The utility model provides a public opinion early warning device which characterized in that includes:
the first acquisition module is used for acquiring the telephone traffic data and carrying out data preprocessing on the telephone traffic data to obtain effective telephone traffic data;
the first processing module is used for carrying out intention identification on the effective telephone traffic data according to a preset intention identification model to obtain intention telephone traffic data;
the second processing module is used for carrying out normalization processing on the intention telephone traffic data according to a preset predicted telephone traffic regression model to obtain first normalized intention data, wherein the preset predicted telephone traffic regression model is obtained by training according to historical telephone traffic data and historical public opinion data;
and the early warning module is used for determining that the public sentiment is abnormal and generating public sentiment early warning information if the first normalized intention data is greater than a preset intention threshold value.
8. The utility model provides a public opinion early warning equipment which characterized in that includes:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the public opinion alerting method of any one of claims 1 to 6.
9. A computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are used for implementing the public opinion early warning method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the public opinion alerting method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649627.XA CN113392185B (en) | 2021-06-10 | 2021-06-10 | Public opinion early warning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110649627.XA CN113392185B (en) | 2021-06-10 | 2021-06-10 | Public opinion early warning method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392185A true CN113392185A (en) | 2021-09-14 |
| CN113392185B CN113392185B (en) | 2023-06-23 |
Family
ID=77620296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110649627.XA Active CN113392185B (en) | 2021-06-10 | 2021-06-10 | Public opinion early warning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392185B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070250362A1 (en) * | 2004-04-30 | 2007-10-25 | Olympus America Inc. | Method and system for valuing a venture |
| CN107203641A (en) * | 2017-06-19 | 2017-09-26 | 北京易华录信息技术股份有限公司 | A kind of method of the collection of Internet traffic public feelings information and processing |
| CN107516279A (en) * | 2017-08-15 | 2017-12-26 | 皑沐(上海)文化传媒有限公司 | A kind of method of network public-opinion automatic early-warning |
| US20180285892A1 (en) * | 2017-03-31 | 2018-10-04 | International Business Machines Corporation | Sentiment and analytics for predicting future legislation |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109325860A (en) * | 2018-08-29 | 2019-02-12 | 中国科学院自动化研究所 | Network public-opinion detection method and system for overseas investment Risk-warning |
| CN109388749A (en) * | 2018-09-29 | 2019-02-26 | 武汉烽火普天信息技术有限公司 | The detection of accurate high-efficiency network public sentiment and method for early warning based on multi-layer geography |
| CN109961368A (en) * | 2019-03-18 | 2019-07-02 | 京东数字科技控股有限公司 | Data processing method and device based on machine learning |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110659436A (en) * | 2019-08-22 | 2020-01-07 | 阿里巴巴集团控股有限公司 | Network public opinion monitoring method, device and equipment |
| CN111008896A (en) * | 2019-12-05 | 2020-04-14 | 中国银行股份有限公司 | Financial risk early warning method and device, electronic equipment and storage medium |
| CN111310014A (en) * | 2020-02-21 | 2020-06-19 | 深圳中兴网信科技有限公司 | Scenic spot public opinion monitoring system, method, device and storage medium based on deep learning |
| CN111581945A (en) * | 2020-04-09 | 2020-08-25 | 上海淇毓信息科技有限公司 | Public opinion analysis-based data analysis method, device and system |
| CN111738610A (en) * | 2020-06-29 | 2020-10-02 | 金电联行（北京）信息技术有限公司 | Public opinion data-based enterprise loss risk early warning system and method |
| CN111931027A (en) * | 2020-08-17 | 2020-11-13 | 深圳新闻网传媒股份有限公司 | Intelligent news public opinion early warning system |
-
2021
- 2021-06-10 CN CN202110649627.XA patent/CN113392185B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070250362A1 (en) * | 2004-04-30 | 2007-10-25 | Olympus America Inc. | Method and system for valuing a venture |
| US20180285892A1 (en) * | 2017-03-31 | 2018-10-04 | International Business Machines Corporation | Sentiment and analytics for predicting future legislation |
| CN107203641A (en) * | 2017-06-19 | 2017-09-26 | 北京易华录信息技术股份有限公司 | A kind of method of the collection of Internet traffic public feelings information and processing |
| CN107516279A (en) * | 2017-08-15 | 2017-12-26 | 皑沐(上海)文化传媒有限公司 | A kind of method of network public-opinion automatic early-warning |
| CN109325860A (en) * | 2018-08-29 | 2019-02-12 | 中国科学院自动化研究所 | Network public-opinion detection method and system for overseas investment Risk-warning |
| CN109299258A (en) * | 2018-09-18 | 2019-02-01 | 平安科技（深圳）有限公司 | A kind of public sentiment event detecting method, device and equipment |
| CN109388749A (en) * | 2018-09-29 | 2019-02-26 | 武汉烽火普天信息技术有限公司 | The detection of accurate high-efficiency network public sentiment and method for early warning based on multi-layer geography |
| CN109961368A (en) * | 2019-03-18 | 2019-07-02 | 京东数字科技控股有限公司 | Data processing method and device based on machine learning |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110659436A (en) * | 2019-08-22 | 2020-01-07 | 阿里巴巴集团控股有限公司 | Network public opinion monitoring method, device and equipment |
| CN111008896A (en) * | 2019-12-05 | 2020-04-14 | 中国银行股份有限公司 | Financial risk early warning method and device, electronic equipment and storage medium |
| CN111310014A (en) * | 2020-02-21 | 2020-06-19 | 深圳中兴网信科技有限公司 | Scenic spot public opinion monitoring system, method, device and storage medium based on deep learning |
| CN111581945A (en) * | 2020-04-09 | 2020-08-25 | 上海淇毓信息科技有限公司 | Public opinion analysis-based data analysis method, device and system |
| CN111738610A (en) * | 2020-06-29 | 2020-10-02 | 金电联行（北京）信息技术有限公司 | Public opinion data-based enterprise loss risk early warning system and method |
| CN111931027A (en) * | 2020-08-17 | 2020-11-13 | 深圳新闻网传媒股份有限公司 | Intelligent news public opinion early warning system |
Non-Patent Citations (4)
| Title |
|---|
| REN-DE LI 等: "Entity perception of Two-Step-Matching framework for public opinions", 《JOURNAL OF SAFETY SCIENCE AND RESILIENCE》, pages 36 - 43 * |
| 卢婷婷: "基于短文本的互联网用户意图识别方法及应用研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 138 - 6165 * |
| 尹俊: "政府治理现代化视角下社会网络舆情应对的策略研究", 《中共银川市委党校学报》, pages 76 - 80 * |
| 李芸: "基于爬虫和文本聚类分析的网络舆情分析***设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 138 - 3619 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392185B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021174694A1 (en) | Operation and maintenance monitoring method and apparatus based on data center, device, and storage medium | |
| CN109344170B (en) | Stream data processing method, system, electronic device and readable storage medium | |
| US9507946B2 (en) | Program vulnerability identification | |
| CN114185708A (en) | Data analysis method and device based on distributed link tracking and electronic equipment | |
| EP3916584A1 (en) | Information processing method and apparatus, electronic device and storage medium | |
| EP3968185A1 (en) | Method and apparatus for pushing information, device and storage medium | |
| CN110647523B (en) | Data quality analysis method and device, storage medium and electronic equipment | |
| CN108829716B (en) | Conference agenda generation method and device for conference to be held | |
| CN105354697A (en) | Financial account rule base based automatic online auditing method and system | |
| CN102073912A (en) | Data quality control method, device and system | |
| US20180329466A1 (en) | Per-Screen On Session Power Consumption Profiling | |
| US11776078B2 (en) | Systems and methods for generating strategic competitive intelligence data relevant for an entity | |
| US11250365B2 (en) | Systems and methods for utilizing compliance drivers to conserve system resources and reduce compliance violations | |
| US11587095B2 (en) | Semantic sweeping of metadata enriched service data | |
| CN111949490A (en) | JVM process monitoring method and device | |
| CN113392185A (en) | Public opinion early warning method, device, equipment and storage medium | |
| CN110677271A (en) | Big data alarm method, device, equipment and storage medium based on ELK | |
| CN115393128A (en) | Panoramic analysis method and device for intellectual property, computer equipment and medium | |
| CN112131090B (en) | Service system performance monitoring method, device, equipment and medium | |
| CN115309638A (en) | Method and device for assisting model optimization | |
| CN113961441A (en) | Alarm event processing method, auditing method, device, equipment, medium and product | |
| CN113934595A (en) | Data analysis method and system, storage medium and electronic terminal | |
| CN113450208A (en) | Loan risk change early warning and model training method and device | |
| CN117931635B (en) | Analysis method, device, equipment and medium for database test case execution result | |
| CN117172632B (en) | Enterprise abnormal behavior detection 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |