Online public opinion risk monitoring and early warning system and method based on artificial intelligence
Through the network public opinion risk monitoring and early warning system based on artificial intelligence, using ontology modeling, entropy weight method and system dynamics modeling and other technologies, real-time intelligent monitoring and early warning of network public opinion risks is achieved, and the timeliness and accuracy of existing systems is solved. The problem of sexual inadequacy has improved the ability to manage online public opinion risks.
Patent Information
- Application Number
- CN202411233527.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The current online public opinion risk monitoring and early warning system is insufficient in timeliness and accuracy, and cannot effectively respond to challenges such as large amount of information, strong timeliness and high professional requirements, resulting in difficulties in the governance of online public opinion risk.
Adopt a network public opinion risk monitoring and early warning system based on artificial intelligence, including network public opinion risk ontology construction module, index system construction and prediction module, intelligent monitoring module, scene modeling and simulation module, risk level determination module, impact assessment generation module and automatic early warning The module realizes real-time intelligent monitoring and early warning through ontology modeling, entropy weight method, system dynamics model, large language model and other technologies.
It improves the timeliness and accuracy of online public opinion risk monitoring and early warning, can quickly respond and accurately evaluate online public opinion risks, and provides strong risk governance support.
Smart Images

Figure CN119026916A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of network public opinion risk monitoring, and more specifically to an artificial intelligence-based network public opinion risk monitoring and early warning system and method. Background Art
[0002] Online public opinion is generated by the occurrence of an event. With the help of the Internet platform, it contains netizens' specific cognition, attitude, and emotional behavior tendencies towards the event. With the development of technologies such as the Internet and artificial intelligence, online public opinion has the characteristics of richer content, faster dissemination, more confusing topics, and mutual reflection with real life.
[0003] Although there are many studies and solutions for online public opinion analysis and early warning, they still mainly rely on manual tracking by public opinion analysts to judge the status and influence of online public opinion. However, in the intelligent era, online public opinion has problems such as large amount of information, strong timeliness, and high professional requirements. The timeliness and accuracy of risk monitoring and early warning solutions need to be further improved. In order to avoid the impact of online public opinion, more attention needs to be paid to real-time monitoring, in-depth evaluation, timely early warning and rapid response of online public opinion risks. Therefore, real-time intelligent and accurate monitoring and early warning of online public opinion risks has become a problem that must be solved nowadays. Summary of the invention
[0004] In view of this, the present invention provides an artificial intelligence-based network public opinion risk monitoring and early warning system and method that solves at least some of the above-mentioned technical problems, facilitates the real-time intelligent monitoring and early warning of network public opinion risks, improves the timeliness and accuracy of network public opinion risk monitoring and early warning, and copes with challenges such as large amount of monitoring data, strong timeliness, and high professional requirements, providing strong support for network public opinion risk governance.
[0005] To achieve the above object, the technical solution adopted by the present invention is:
[0006] In a first aspect, the present invention provides an artificial intelligence-based network public opinion risk monitoring and early warning system, the system comprising: an application subsystem, a client terminal and a storage subsystem, wherein:
[0007] The application subsystem includes: network public opinion risk ontology construction module, indicator system construction and prediction module, intelligent monitoring module, scenario modeling and simulation module, risk level determination module, impact assessment generation module and automatic warning module; among which:
[0008] The network public opinion risk ontology construction module is used to construct a network public opinion risk ontology model using an ontology modeling auxiliary method, and formally express the concepts and relationships of the subject, type, propagation law, influencing factors and response strategies of network public opinion;
[0009] The indicator system construction and prediction module is used to construct an indicator system for network public opinion risk assessment based on the network public opinion risk ontology and in combination with network public opinion evaluation related data obtained from the Internet; at the same time, the obtained data is preprocessed, and the network public opinion risk assessment indicator measurement value of each data is obtained by combining the entropy weight method; and the future trend of the indicator is predicted based on the measurement data;
[0010] The intelligent monitoring module is used to monitor network public opinion risk information, and based on the monitoring information, automatically capture hot spot risk events in real time, and determine the field, related indicators and related events to which the hot spot risk events belong;
[0011] The scenario modeling and simulation module is used to classify network public opinion risk scenarios, identify typical risk scenarios, and construct a network public opinion risk scenario model through a system dynamics model; it is also used to simulate the risk scenario model, analyze the impact of risk events on related indicators, and the impact of response strategies on network public opinion;
[0012] The risk level determination module is used to determine the risk level of related indicators under the influence of hot spot risk events based on risk scenario model simulation, and determine the event risk level through the risk level of related indicators;
[0013] The impact assessment generation module is used to generate an assessment text of the impact of the network public opinion hot spot risk event based on the description of the hot spot risk event, the impact on the related indicators, and the information of the event risk level, using a large language model;
[0014] The automatic warning module is used to automatically analyze the fields and event contents of hot spot risk events, generate a hot spot risk event warning report in combination with the assessment text of the impact of the hot spot risk events, and send the warning report to the client terminal in real time;
[0015] The client terminal is used to receive the warning report sent by the automatic warning module and push the warning information to the client;
[0016] The storage subsystem includes: an ontology library for storing network public opinion risk ontology models, an indicator library for storing network public opinion risk assessment indicator systems, a scenario model library for storing network public opinion risk scenario models, an event library for storing network public opinion typical hot spot risk events, a database for storing network public opinion risk information data, and a large language model storage library.
[0017] Furthermore, in the network public opinion risk ontology construction module, the ontology modeling auxiliary method for constructing the network public opinion risk ontology model includes: data capture, term extraction, relationship extraction and text analysis.
[0018] Furthermore, in the indicator system construction and prediction module, preprocessing of the acquired data includes: data cleaning, indicator positive orientation and normalization.
[0019] Furthermore, in the indicator system construction and prediction module, the entropy weight method is combined to calculate the network public opinion risk assessment indicator measurement value of each data, and the calculation formula includes:
[0020]
[0021] Among them, i represents the i-th indicator, with a total of n indicators, j represents the j-th evaluation sample of the indicator, with a total of m evaluation samples, and e i represents the i-th index X i The entropy value of p ij represents the jth evaluation sample x of the i-th indicator after normalization ij The specific gravity, ω i represents the weight value of the i-th indicator, k j Represents the target measurement value after the j-th evaluation sample indicator is fused.
[0022] Furthermore, in the intelligent monitoring module, data crawlers and multimodal data analysis methods are used to automatically discover and capture hot risk events in online public opinion, and the monitoring information includes text and pictures.
[0023] Furthermore, in the scenario modeling and simulation module, the system dynamics model is:
[0024]
[0025] Among them, x i (k) represents the risk level of the kth stage of indicator i, It represents the comprehensive effect of all risk levels of indicators directly related to indicator i on it, N i(k) represents the set of all indicators that directly affect indicator i, α ji It represents the transmission coefficient of the effect of the associated index j on the index i, R ji (k) represents the influence of index i on index i, ΔR ji (k) represents the interaction strength between indicators, ΔE i (k) represents the comprehensive intervention effect of the intervention strategy on the indicator, β i is the impact intensity of the event on the indicator, S i(k) represents the set of all strategies directly associated with indicator i, = γ li x i (k) represents the risk effect of the suppression indicator, γ li is the impact of the strategy on the indicator, noise i (k) represents the noise value.
[0026] Furthermore, the application subsystem also includes: an expert analysis module, which is used to provide experts with a real-time window for receiving and viewing hot risk events, selecting typical hot risk events, entering the network public opinion risk scenario modeling and simulation module, improving the network public opinion risk scenario model, modifying and improving the risk level and impact assessment of typical hot event, and forming an early warning report on the response strategies proposed by experts for typical hot risk events.
[0027] In a second aspect, the present invention further provides an artificial intelligence-based network public opinion risk monitoring and early warning method, which is applied to the above-mentioned artificial intelligence-based network public opinion risk monitoring and early warning system to perform network public opinion risk monitoring and early warning, and the method comprises:
[0028] Using the ontology modeling auxiliary method, we construct the network public opinion risk ontology model, and formally express the concepts and relationships of the subject, type, propagation law, influencing factors and response strategies of network public opinion;
[0029] Based on the network public opinion risk ontology, combined with the network public opinion evaluation related data obtained from the Internet, a network public opinion risk assessment index system is constructed; at the same time, the obtained data is preprocessed, and the network public opinion risk assessment index measurement value of each data is calculated by combining the entropy weight method; the ARIMA method is used to automatically predict the future trend of the indicator based on the measured historical data;
[0030] Monitor online public opinion risk information, and based on the monitoring information, automatically capture hot risk events in real time, and determine the areas, related indicators, and related events to which the hot risk events belong;
[0031] Classify online public opinion risk scenarios, identify typical risk scenarios, and build online public opinion risk scenario models through system dynamics models; also used to simulate risk scenario models, analyze the impact of risk events on related indicators and the impact of response strategies on online public opinion;
[0032] Based on the simulation of risk scenario models, determine the risk level of related indicators under the influence of hot risk events, and determine the risk level of events through the risk level of related indicators;
[0033] Based on the description of hot risk events, the impact on related indicators, and the information on event risk levels, a large language model is used to generate an assessment text of the impact of hot risk events on online public opinion;
[0034] Automatically analyze the fields and content of hot spot risk events, generate hot spot risk event warning reports based on the assessment text of the impact of hot spot risk events, and send the warning reports to customer terminals in real time;
[0035] The client terminal receives the sent warning report and pushes the warning information to the client;
[0036] The network public opinion risk ontology model, network public opinion risk assessment indicator system, network public opinion risk scenario model, network public opinion typical hot risk events, network public opinion risk information data and large language model are stored.
[0037] Compared with the prior art, the present invention has at least the following beneficial technical effects:
[0038] The present invention provides an artificial intelligence-based network public opinion risk monitoring and early warning system and method, which facilitates the real-time intelligent monitoring and early warning of network public opinion risks, improves the timeliness and accuracy of network public opinion risk monitoring and early warning, and copes with challenges such as large amounts of monitoring data, strong timeliness, and high professional requirements, providing strong support for network public opinion risk governance.
[0039] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.
[0040] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0042] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.
[0043] Figure 1 A schematic diagram of the structure of an artificial intelligence-based network public opinion risk monitoring and early warning system provided in an embodiment of the present invention.
[0044] Figure 2 A schematic flow chart of a network public opinion risk monitoring and early warning method based on artificial intelligence provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings below, and the technical solution of the present invention will be clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
[0046] See also Figure 1 As shown, the embodiment of the present invention provides a network public opinion risk monitoring and early warning system based on artificial intelligence, which includes three parts: an application subsystem, a client terminal and a storage subsystem; wherein:
[0047] In the embodiment of the present invention, the application subsystem includes: a network public opinion risk ontology construction module, an indicator system construction and prediction module, an intelligent monitoring module, a scenario modeling and simulation module, a risk level determination module, an impact assessment generation module and an automatic warning module;
[0048] The storage subsystem includes: an ontology library for storing network public opinion risk ontology models, an indicator library for storing network public opinion risk assessment indicator systems, a scenario model library for storing network public opinion risk scenario models, an event library for storing network public opinion typical hot spot risk events, a database for storing network public opinion risk information data, and a large language model repository.
[0049] The module functions of the application subsystem of the present invention are introduced below:
[0050] 1. Ontology building module
[0051] It has ontology modeling auxiliary functions such as online public opinion information capture, term extraction, relationship extraction, etc. It can carry out visual modeling of online public opinion risk ontology and support model analysis and verification.
[0052] 2. Index system construction and prediction module
[0053] It is used to visualize the structure of the indicator system and the relationship between indicators and measurement data. It combines methods such as indicator information entropy quantification and expert evaluation to automatically predict future trends of indicators. It supports dynamic updating of measurement data and can store information such as evaluation indicators, measurements, data, and sources.
[0054] 3. Intelligent monitoring module
[0055] It is used to customize network public opinion risk monitoring information, and can automatically capture hot risk events in real time based on the monitoring information, and automatically determine the field, related indicators and related events to which the hot risk events belong.
[0056] 4. Scene modeling and simulation module
[0057] Based on modeling methods such as system dynamics, a visual network public opinion risk scenario model is constructed. Through the simulation of the risk scenario model, the impact of hot risk events on related indicators and the impact of response strategies on network public opinion can be analyzed. The network public opinion risk model is stored to form a network public opinion risk scenario model library.
[0058] 5. Risk level determination module
[0059] Intelligently match the online public opinion scenario model of hot risk events, vectorize the title and content of hot event, calculate the distance with the feature vector in the scenario model feature library, obtain the similarity evaluation index, and use the scenario model with the highest similarity index as the simulation calculation model of the event. Then, based on the simulation of the risk scenario model, analyze the impact of hot risk events on their core related indicators, compare the impact of events on indicators and the results of automated indicator trend prediction, determine the risk level of related indicators under the influence of hot risk events, and determine the risk level of events in combination with the risk level of related indicators.
[0060] 6. Impact Assessment Intelligent Generation Module
[0061] Based on the description of hot risk events, the impact on related indicators, event risk level and other information, a large language model is used to generate an impact assessment text for hot risk events in online public opinion.
[0062] 7. Automatic warning module
[0063] Conduct automated analysis on the fields and content of hot risk events, determine the recipients of warnings, and send hot risk event warning reports to customer terminals in real time.
[0064] In a preferred embodiment, the application subsystem of the system also includes: an expert analysis module, which is used to provide experts with a real-time window for receiving and viewing hot risk events, selecting typical hot risk events, entering the network public opinion risk scenario modeling and simulation module, improving the network public opinion risk scenario model, modifying and improving the risk level and impact assessment of typical hot events, and forming an early warning report on the response strategies proposed by experts for typical hot risk events.
[0065] The specific implementation modes of the present invention are described in detail below:
[0066] (1) Construction of Internet public opinion risk ontology.
[0067] In this embodiment, using online public opinion risk, public opinion risk, network opinion risk and the like as keywords, based on data capture, term extraction, relationship extraction, text analysis and other technologies, we obtain and analyze literature, reports and other materials related to online public opinion analysis methods and practices on the web of science and CNKI, identify the core concepts of online public opinion such as types, subjects, propagation laws, risk management, influencing factors, response strategies and their relationships, and construct a network public opinion risk ontology model in the ontology construction module.
[0068] (2) Construction of an online public opinion risk assessment indicator system.
[0069] 2.1: Based on the topic analysis of online public opinion risks, it is found that online public opinion risks involve different fields such as economy and technology, so they can be defined as primary indicators of economy and technology.
[0070] 2.2: Through a detailed analysis of the risks of online public opinion under the first-level indicators, clarify the second-level evaluation indicators. For example, the second-level indicators under the first-level economic evaluation indicators include: industry scale benefits, capital market activity, industrial development vitality, corporate competitiveness, R&D funding investment, etc.
[0071] 2.3: Based on the collected evaluation data, clarify the measurement name and measurement value of the secondary evaluation indicators, such as enterprise competitiveness, including: enterprise market value, product market share, product quantity, number of employees and other measurements. In addition, some measurements need to be calculated based on data. At this time, the underlying data is first cleaned, the indicators are positively oriented, normalized and other data preprocessing work is carried out, and then the weight of each data on the indicator measurement is estimated through methods such as entropy weight method, and the weight is determined after correction, integrated and calculated into the measurement value, and the data source, update cycle, etc. are clarified.
[0072] Among them, data normalization refers to mapping the data into a specified range to remove the large numerical differences caused by the dimension or dimensional unit of different data. The present invention uses Min-Max normalization (also known as deviation standardization, as shown in the following formula) to perform linear transformation on the original data and map the result to between 0 and 1.
[0073]
[0074] Among them, X' represents the dimensionless data, X represents the observed data, and X min Indicates the minimum value of the data, X max Indicates the data maximum value.
[0075] Data normalization is to determine whether the larger the data value, the better. If so, it is positive data, otherwise it is negative data. For positive data, the above formula is used for measurement normalization, and the negative data normalization is shown in the following formula.
[0076]
[0077] For the index measurement calculated from multiple data, the present invention mainly adopts the entropy weight method to determine the weight of each data, mainly based on the objective weighting method, and modified by the subjective weighting method. The weight is determined according to the information entropy of each data. According to information theory, entropy is a measure of the degree of disorder of the system. The i-th data X i The entropy value e i The calculation is shown in the following formula.
[0078]
[0079] Among them, i represents the i-th indicator, with a total of n indicators, j represents the j-th evaluation sample of the indicator, with a total of m evaluation samples, and e i represents the i-th index X i The entropy value of p ij represents the jth evaluation sample x of the i-th indicator after normalization ij proportion.
[0080]
[0081] Further entropy normalization of all data, if the entropy value of a certain data is large, it means that the data is more discrete, which can be regarded as the richer the information contained in the data. Therefore, when comprehensively evaluating the measurement, the greater the influence (i.e., weight) of the data, the greater the weight of each indicator ω i The objective calculation formula is as follows:
[0082]
[0083] Furthermore, the underlying data is preprocessed by forward and normalization, and the data is calculated according to the following formula to obtain the target measurement k after the jth evaluation sample index is fused: j Value:
[0084]
[0085] 2.4: Analyze the relationship between the secondary evaluation indicators and clarify their positive or negative impacts. For example, the more active the capital market is, the more active the industry development is. In the indicator system construction and prediction module, construct the indicator system.
[0086] 2.5: Store evaluation indicators, measurements, and data.
[0087] (3) Trend prediction of online public opinion risk assessment indicators.
[0088] In the indicator system construction and prediction module, based on the measured values of the network public opinion risk assessment indicators, methods such as ARIMA (Auto Rearessive Integrated Moving Average) can be used to automatically predict the future trend of the indicators based on the measured historical data, and give the valuation range of the confidence interval.
[0089] (4) Intelligent monitoring of online public opinion.
[0090] 4.1: In the intelligent monitoring module, based on the network public opinion risk ontology and risk assessment indicator system, determine the field, subject, keyword, language, and main source of network public opinion risk monitoring. Among them, the monitoring fields include economy, science and technology, etc. Each field has a subject of concern.
[0091] 4.2: Use data crawlers, multimodal data analysis and other technologies to automatically discover and capture hot risk events in online public opinion, including text and images, and based on large language model technology, realize language translation and intelligently generate risk event profiles; the above-mentioned large language model technology is an existing mature technology and will not be elaborated on.
[0092] 4.3: Based on technologies such as neural network models, event feature extraction and classification are realized to determine the field to which the hot risk events belong.
[0093] 4.4: Retrieve the network public opinion risk assessment index system and determine the core correlation indicators of hot risk events based on text similarity calculation.
[0094] 4.5: Based on text similarity calculation, automatically capture hot risk event related events.
[0095] (5) Construction of a network public opinion risk scenario model library.
[0096] 5.1: Based on the analysis of online public opinion risk monitoring events, classify online public opinion risk scenarios and identify typical risk scenarios.
[0097] 5.2: In the network public opinion risk scenario modeling and simulation module, based on the network public opinion risk ontology, risk assessment indicator system, etc., combined with modeling methods such as system dynamics, a visual network public opinion risk scenario model is constructed.
[0098] For example, we regard the risk of online public opinion as a complex system, the risk assessment indicator system as the system state, the risk event as the external disturbance, and the intervention strategy as the system input. Finally, we transform the original problem into a control problem and construct a system dynamics model for the general risk assessment of online public opinion. The total set of equations is as follows:
[0099]
[0100] Among them, x i (k) represents the risk level of the kth stage of indicator i, and its value is obtained by comprehensively calculating its underlying data sources. It represents the comprehensive effect of all risk levels of indicators directly related to indicator i on it, N i(k) Represents the set of all indicators that directly affect indicator i, α ji It represents the transmission coefficient of the effect of correlation index j on index i. The higher the coefficient, the higher the correlation between the two indexes. ji (k) represents the influence of indicator i on indicator i. Its value is positively correlated with the risk level of indicator i itself. That is, the higher the risk of indicator i, the higher the additional risk it transfers to indicator i. ΔR ji (k) = x i (k)(x j (k)-x j _base) / x j _base represents the interaction strength between indicators, ΔE i (k) = e -θk β i x i (k), represents the comprehensive intervention effect of the intervention strategy on the indicator, β i is the impact intensity of the event on the indicator, S i(k) represents the set of all strategies directly associated with indicator i, ΔS li (k) = γ li x i The effect of (k) is to suppress the indicator risk, γ li is the impact of the strategy on the indicator, noise i (k) represents the noise value.
[0101] Furthermore, various network public opinion risk scenario models form a network public opinion risk scenario model library.
[0102] (6) Intelligent determination of the risk level of hot events in online public opinion. In the intelligent determination module of the risk level of hot events:
[0103] 6.1: Intelligently match the online public opinion scenario model of hot risk events, vectorize the title and content of the hot event, calculate the distance with the feature vector in the scenario model feature library, obtain the similarity evaluation index, and use the scenario model with the highest similarity index as the simulation calculation model of the event.
[0104] 6.2: Analyze the impact of hot risk events on its core related indicators through risk scenario model simulation.
[0105] 6.3: Compare the impact of hot spot risk events on indicators and the indicator trend forecast results, and determine the risk level of related indicators under the influence of hot spot risk events.
[0106] 6.4: Determine the event risk level by combining the risk level of the associated indicators with the risk level of similar events in the event database.
[0107] (7) Intelligent generation of impact assessment of hot events in online public opinion. In the intelligent generation module of impact assessment of hot risk events:
[0108] Based on the description of hot risk events, the impact on related indicators, the risk level, the impact assessment of similar events in the event library and other information, a large language model is used to generate the impact assessment of hot risk events in online public opinion.
[0109] (8) Human-machine collaborative analysis of typical hot topics in online public opinion.
[0110] 8.1: In the expert judgment module, it is used to provide experts with a window for receiving and viewing hot risk events in real time and display the event list; experts can receive and view the intelligent risk level evaluation and impact assessment results of hot risk events in real time, which is convenient for selecting typical hot risk events. Event ID, title, field, event introduction, event time, update event, original link, status, online time, edit link and other information are displayed in the event list.
[0111] 8.2: Based on the analysis of typical hot risk events and their related events, modify and improve the network public opinion risk scenario model.
[0112] 8.3: In the details of hot spot risk events, confirm the risk level of typical hot spot risk events and complete the impact assessment text of hot spot risk events.
[0113] 8.4: In the details of hot spot risk events, corresponding response strategy suggestions are proposed for the impact of typical hot spot risk events;
[0114] 8.5: In the details of hot spot risk events, a typical hot spot risk event warning report is formed.
[0115] (9) Automatically warn of typical hot topics in online public opinion.
[0116] 9.1: Determine the recipients of warnings based on automated analysis of the fields and content of typical hot spot risk events.
[0117] 9.2: With the help of the early warning function and the client terminal, the early warning information of typical hot spot risk events is sent to the client in real time, supporting the client to grasp the public opinion situation in real time. The automatic early warning module records the number of the latest dynamic events every day, the distribution of candidate event fields every day, and the trend of the number of typical hot spot events that have been pushed, and displays the candidate event and pushed event ID, title, field, event introduction, event time, update event, original link, status, online time, edit link, push terminal and other information.
[0118] 9.3: Customers can provide real-time feedback on suggestions for public opinion risk monitoring and early warning work through the early warning customer terminal to continuously improve the quality of online public opinion risk monitoring and early warning work.
[0119] (10) Construction of online public opinion event database.
[0120] Based on typical hot risk events in network public opinion risk monitoring and early warning, a network public opinion risk event database is constructed to record hot risk events of network public opinion, including event time, introduction, subject, field, related indicators, related events, risk level, impact assessment, response strategies, etc., to provide a reference for continuous intelligent monitoring and early warning of hot risk events of network public opinion.
[0121] From the description of the above embodiments, those skilled in the art can know that the present invention provides an artificial intelligence-based network public opinion risk monitoring and early warning system, which includes: an application subsystem, a client terminal and a storage subsystem. The present invention is based on Internet information, and integrates ontology construction, large language models, generative artificial intelligence, system modeling, expert judgment and other methods and technologies to build a network public opinion risk ontology and risk assessment indicator system, support network public opinion risk intelligent monitoring, risk scenario modeling, professional risk judgment and impact assessment and real-time early warning, improve the timeliness and accuracy of network public opinion risk monitoring and early warning, in order to cope with the challenges of large amount of monitoring data, strong timeliness, high professional requirements, etc., and provide strong support for network public opinion risk governance. The specific advantages are as follows:
[0122] ①. In order to cope with the challenges of large amount of data in the field of online public opinion and low efficiency of manual ontology construction, a network public opinion risk ontology model is constructed based on ontology modeling auxiliary technology to formally express the core concepts and their relationships in this field. This is not only conducive to the communication and understanding of knowledge in the field of online public opinion risk, but also provides important support for the construction of risk assessment indicator system, risk scenario modeling, large language model construction, risk event monitoring, etc. in this field.
[0123] ②. Classify and evaluate online public opinion risks through the online public opinion risk assessment index system, comprehensively and quickly measure the online public opinion risk situation, assist in accurately locating and analyzing problems, and support online public opinion risk assessment.
[0124] ③. Through customized real-time intelligent monitoring of online public opinion risks, we can quickly and accurately capture hot risk events of online public opinion, reduce labor costs, and improve information monitoring efficiency.
[0125] ④. Through the modeling and simulation of online public opinion risk scenarios, the visualization modeling, mechanism analysis and evolutionary reasoning of complex risk scenarios of online public opinion are realized, supporting the in-depth analysis of typical risk scenarios and risk events of online public opinion.
[0126] ⑤. Intelligent determination of risk levels and intelligent generation of impact assessments of hot events based on event libraries and large language models will effectively improve the efficiency of risk determination and impact assessments of hot events, and provide important references for expert research and judgment.
[0127] ⑥. Through automatic early warning and customer terminals, early warning information is sent in real time to support customers' rapid response. At the same time, customer feedback information is received in real time to promote the continuous update of the risk monitoring and early warning system.
[0128] Furthermore, the embodiment of the present invention also provides an artificial intelligence-based network public opinion risk monitoring and early warning method, which is applied to an artificial intelligence-based network public opinion risk monitoring and early warning system in the above embodiment to perform artificial intelligence-based human-machine collaborative network public opinion risk monitoring and early warning. For the specific process, see Figure 2 As shown, the method includes:
[0129] S1. Use the ontology modeling auxiliary method to construct the network public opinion risk ontology model, and formally express the concepts and relationships of the subject, type, propagation law, influencing factors and response strategies of network public opinion;
[0130] S2. Based on the network public opinion risk ontology and combined with the network public opinion evaluation related data obtained from the Internet, a network public opinion risk assessment index system is constructed; at the same time, the obtained data is preprocessed, and the network public opinion risk assessment index measurement value of each data is obtained by combining the entropy weight method; the ARIMA method is used to automatically predict the future trend of the indicator based on the measured historical data;
[0131] S3. Monitor online public opinion risk information, and based on the monitoring information, automatically capture hot risk events in real time, and determine the areas, related indicators, and related events to which the hot risk events belong;
[0132] S4. Classify network public opinion risk scenarios, identify typical risk scenarios, and construct network public opinion risk scenario models through system dynamics models; also used to simulate risk scenario models, analyze the impact of risk events on related indicators and the impact of response strategies on network public opinion;
[0133] S5. Based on the simulation of the risk scenario model, determine the risk level of the associated indicators under the influence of the hot risk event, and determine the event risk level through the risk level of the associated indicators;
[0134] S6. Based on the description of hot risk events, the impact on related indicators, and the information on event risk levels, a large language model is used to generate an assessment text of the impact of hot risk events on online public opinion;
[0135] S7. Automated analysis of the fields and content of hotspot risk events is performed, combined with the assessment text of the impact of hotspot risk events, to generate a hotspot risk event warning report, and the warning report is sent to the client terminal in real time;
[0136] S8. The client terminal receives the sent warning report and pushes the warning information to the client;
[0137] S9. Store the network public opinion risk ontology model, network public opinion risk assessment indicator system, network public opinion risk scenario model, network public opinion typical hot spot risk events, network public opinion risk information data and large language model.
[0138] The embodiment of the present invention provides an artificial intelligence-based network public opinion risk monitoring and early warning method, whose implementation principle and technical effects are the same as those of the aforementioned system embodiment. For the sake of brief description, for parts not mentioned in this embodiment, please refer to the corresponding content in the aforementioned system embodiment, and no further details will be given here.
[0139] In addition, an embodiment of the present invention also provides a storage medium on which one or more programs readable by a computing device are stored, and the one or more programs include instructions. When the instructions are executed by the computing device, the computing device executes the artificial intelligence-based network public opinion risk monitoring and early warning method in the above embodiment.
[0140] In the embodiment of the present invention, the storage medium may be, for example, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples of storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, and any suitable combination thereof.
[0141] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as systems, methods or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0142] It should be noted that the word "comprising" does not exclude the presence of components not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several distinct components, and by means of a suitably programmed computer.
[0143] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0144] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An artificial intelligence-based network public opinion risk monitoring and early warning system. It is characterized in that The system includes: an application subsystem, a client terminal and a storage subsystem, wherein: The application subsystem includes: network public opinion risk ontology construction module, indicator system construction and prediction module, intelligent monitoring module, scenario modeling and simulation module, risk level determination module, impact assessment generation module and automatic warning module; among which: The network public opinion risk ontology construction module is used to construct a network public opinion risk ontology model using an ontology modeling auxiliary method, and formally express the concepts and relationships of the subject, type, propagation law, influencing factors and response strategies of network public opinion; The indicator system construction and prediction module is used to construct an indicator system for network public opinion risk assessment based on the network public opinion risk ontology and in combination with network public opinion evaluation related data obtained from the Internet; at the same time, the obtained data is preprocessed, and the network public opinion risk assessment indicator measurement value of each data is obtained by combining the entropy weight method; and the future trend of the indicator is predicted based on the measurement data; The intelligent monitoring module is used to monitor network public opinion risk information, and based on the monitoring information, automatically capture hot spot risk events in real time, and determine the field, related indicators and related events to which the hot spot risk events belong; The scenario modeling and simulation module is used to classify network public opinion risk scenarios, identify typical risk scenarios, and construct a network public opinion risk scenario model through a system dynamics model; it is also used to simulate the risk scenario model, analyze the impact of risk events on related indicators, and the impact of response strategies on network public opinion; The risk level determination module is used to determine the risk level of related indicators under the influence of hot spot risk events based on risk scenario model simulation, and determine the event risk level through the risk level of related indicators; The impact assessment generation module is used to generate an assessment text of the impact of the network public opinion hot spot risk event based on the description of the hot spot risk event, the impact on the related indicators, and the information of the event risk level, using a large language model; The automatic warning module is used to automatically analyze the fields and event contents of hot spot risk events, generate a hot spot risk event warning report in combination with the assessment text of the impact of the hot spot risk events, and send the warning report to the client terminal in real time; The client terminal is used to receive the warning report sent by the automatic warning module and push the warning information to the client; The storage subsystem includes: an ontology library for storing network public opinion risk ontology models, an indicator library for storing network public opinion risk assessment indicator systems, a scenario model library for storing network public opinion risk scenario models, an event library for storing network public opinion typical hot spot risk events, a database for storing network public opinion risk information data, and a large language model storage library.
2. According to claim 1, an artificial intelligence-based network public opinion risk monitoring and early warning system, It is characterized in that In the network public opinion risk ontology construction module, the ontology modeling auxiliary method for constructing the network public opinion risk ontology model includes: data capture, term extraction, relationship extraction and text analysis.
3. According to claim 1, an artificial intelligence-based network public opinion risk monitoring and early warning system, It is characterized in that In the indicator system construction and prediction module, preprocessing of the acquired data includes: data cleaning, indicator positive orientation and normalization.
4. According to claim 1, an artificial intelligence-based network public opinion risk monitoring and early warning system, It is characterized in that In the indicator system construction and prediction module, the entropy weight method is combined to calculate the network public opinion risk assessment indicator measurement value of each data, and the calculation formula includes: Among them, i represents the i-th indicator, with a total of n indicators, j represents the j-th evaluation sample of the indicator, with a total of m evaluation samples, and e i represents the i-th index X i The entropy value of p ij represents the jth evaluation sample x of the i-th indicator after normalization ij The specific gravity, ω i represents the weight value of the i-th indicator, k j Represents the target measurement value after the j-th evaluation sample indicator is fused.
5. According to claim 1, an artificial intelligence-based network public opinion risk monitoring and early warning system, It is characterized in that In the intelligent monitoring module, data crawlers and multimodal data analysis methods are used to automatically discover and capture hot risk events in online public opinion, and the monitoring information includes text and pictures.
6. According to claim 1, a network public opinion risk monitoring and early warning system based on artificial intelligence, It is characterized in that In the scenario modeling and simulation module, the system dynamics model is: Among them, x i (k) represents the risk level of the kth stage of indicator i, It represents the comprehensive effect of all risk levels of indicators directly related to indicator i on it, N i(k) represents the set of all indicators that directly affect indicator i, α ji It represents the transmission coefficient of the effect of the associated index j on the index i, R ji (k) represents the influence of index i on index i, ΔR ji (k) represents the interaction strength between indicators, ΔE i (k) represents the comprehensive intervention effect of the intervention strategy on the indicator, β i is the impact intensity of the event on the indicator, S i(k) represents the set of all strategies directly associated with indicator i, ΔS li (k) = γ li x i (k) represents the risk effect of the suppression indicator, γ li is the impact of the strategy on the indicator, noise i (k) represents the noise value.
7. According to claim 1, a network public opinion risk monitoring and early warning system based on artificial intelligence, It is characterized in that The application subsystem also includes: an expert analysis module, which is used to provide experts with a real-time window for receiving and viewing hot risk events, selecting typical hot risk events, entering the network public opinion risk scenario modeling and simulation module, improving the network public opinion risk scenario model, modifying and improving the risk level and impact assessment of typical hot event, and forming an early warning report on the response strategies proposed by experts for typical hot risk events.
8. A network public opinion risk monitoring and early warning method based on artificial intelligence, It is characterized in that Applied to an artificial intelligence-based network public opinion risk monitoring and early warning system as described in any one of claims 1 to 7, to perform network public opinion risk monitoring and early warning, the method comprising: Using the ontology modeling auxiliary method, we construct the network public opinion risk ontology model, and formally express the concepts and relationships of the subject, type, propagation law, influencing factors and response strategies of network public opinion; Based on the network public opinion risk ontology, combined with the network public opinion evaluation related data obtained from the Internet, a network public opinion risk assessment index system is constructed; at the same time, the obtained data is preprocessed, and the network public opinion risk assessment index measurement value of each data is calculated by combining the entropy weight method; based on the measurement data, the future trend of the indicator is predicted; Monitor online public opinion risk information, and based on the monitoring information, automatically capture hot risk events in real time, and determine the areas, related indicators, and related events to which the hot risk events belong; Classify online public opinion risk scenarios, identify typical risk scenarios, and build online public opinion risk scenario models through system dynamics models; also used to simulate risk scenario models, analyze the impact of risk events on related indicators and the impact of response strategies on online public opinion; Based on the simulation of risk scenario models, determine the risk level of related indicators under the influence of hot risk events, and determine the risk level of events through the risk level of related indicators; Based on the description of hot risk events, the impact on related indicators, and the information on event risk levels, a large language model is used to generate an assessment text of the impact of hot risk events on online public opinion; Automatically analyze the fields and content of hot spot risk events, generate hot spot risk event warning reports based on the assessment text of the impact of hot spot risk events, and send the warning reports to customer terminals in real time; The client terminal receives the sent warning report and pushes the warning information to the client; The network public opinion risk ontology model, network public opinion risk assessment indicator system, network public opinion risk scenario model, network public opinion typical hot risk events, network public opinion risk information data and large language model are stored.
Citation Information
Patent Citations
College online public opinion risk assessment method
CN110866126A
Online public opinion real-time monitoring system and method based on artificial intelligence
CN112528197A
Online public opinion risk event monitoring, studying and judging method
CN117910575A
