Dynamic quantitative evaluation method and device for network public opinion comprehensive risk

Abstract

The invention discloses a dynamic quantitative evaluation method and device for comprehensive risks of network public opinions, and the method comprises the steps: constructing an index system of network public opinion risk symptoms, the index system comprising a public opinion symptom index set and a public opinion symptom index association graph; based on an actually occurring public opinion risk event sequence, matching a public opinion symptom index set, generating an incidence matrix according to the public opinion symptom index association graph, and quantifying an association risk value of each public opinion risk event through risk intensity; based on a risk time sequence attenuation model, performing time attenuation calculation on the associated risk value of each public opinion risk event to obtain a real-time risk value; on the basis of all real-time risk values, the comprehensive risk index of the network public opinions is calculated through an improved logistic model, factors in multiple aspects are considered, mathematical modeling is combined to simulate a real scene, and a wait index association diagram, a risk time sequence attenuation model and the improved logistic model are introduced in the calculation process, so that the evaluation result tends to the real situation more.

Description

Technical Field

[0001] This invention relates to the field of online public opinion assessment technology, specifically to a dynamic quantitative assessment method and apparatus for comprehensive online public opinion risk. Background Technology

[0002] In recent years, with the rapid development of internet technology, people's activity space has gradually expanded from traditional physical space to cyberspace. Cyberspace data content has become richer, and various internet platforms such as social media, news websites, forums, blogs, and short videos are filled with a large amount of event information. This event information constantly influences online public opinion security. Online public opinion security risks are a public opinion situation formed by the combined effects of multiple fields of content and factors. Its scope includes factors in multiple fields such as public safety, social welfare, economy and finance, and culture and entertainment. Comprehensively understanding the online public opinion situation, effectively assessing the comprehensive risks of online public opinion, and grasping the current state of public opinion risks are important cornerstones for maintaining national cybersecurity.

[0003] In related technologies, there is already a large amount of research on public opinion risk assessment. It mainly focuses on the perception and monitoring of public opinion on a certain type of theme event in a single field. It assesses the public opinion risk of a single event from the aspects of dissemination power, influence, and degree of harm, or relies on the experience of experts in the field to make risk judgments. Its advantage is that it can handle complex risk situations, but it is more of a subjective qualitative description and cannot fully and accurately understand and grasp the comprehensive risk situation of online public opinion under the intertwining of multiple field factors.

[0004] Therefore, it is urgent to find a scientific assessment method for the comprehensive risk quantification of online public opinion. Summary of the Invention

[0005] In view of the above problems, the present invention provides a dynamic quantitative assessment method and device for comprehensive risk assessment of online public opinion. It comprehensively considers multiple factors, simulates real-world scenarios through mathematical modeling, and introduces a symptom indicator correlation diagram, a risk time series decay model, and an improved logistic model to make the assessment results more closely resemble the actual situation.

[0006] In a first aspect, embodiments of the present invention provide a dynamic quantitative assessment method for comprehensive online public opinion risk, the method comprising: A system of indicators for online public opinion risk symptoms is constructed, which includes a set of public opinion symptom indicators and a correlation diagram of public opinion symptom indicators; Based on the actual sequence of public opinion risk events, the set of public opinion symptom indicators is matched, a correlation matrix is ​​generated according to the correlation graph of the public opinion symptom indicators, and the correlation risk value of each public opinion risk event is quantified by risk intensity. Based on the risk time-series decay model, the associated risk value of each public opinion risk event is calculated to obtain the real-time risk value. Based on all real-time risk values, a comprehensive risk index for online public opinion is calculated using an improved logistic model, wherein the improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

[0007] In some embodiments, the step of matching the set of public opinion symptom indicators based on the actual sequence of public opinion risk events, and generating a correlation matrix according to the correlation graph of the public opinion symptom indicators, includes: Based on the sequence and intensity of public opinion risk events, the correlation between events is calculated using the first formula, and a correlation matrix is ​​generated. The first formula is:

[0008] Where k represents a public opinion symptom indicator, i and j are the sequence numbers of all public opinion symptom indicators connected by the shortest path in the public opinion symptom indicator correlation graph, and the public opinion risk event sequence is... The risk intensity is ; The expression for the correlation matrix is:

[0009] in, The correlation matrix M represents the degree of correlation between public opinion risk events, where m is the number of public opinion risk events at the time of assessment, and all elements on the diagonal of the correlation matrix M are zero.

[0010] In some embodiments, quantifying the associated risk value of each public opinion risk event by risk intensity includes: The associated risk value of each public opinion risk event is calculated using the second formula through the public opinion risk event association risk value calculation operator. The second formula is as follows:

[0011] The method for calculating the associated risk value is as follows:

[0012] in, For calculating the associated risk value of public opinion risk events, Let be the associated risk value of the j-th public opinion risk event.

[0013] In some embodiments, the risk time-series decay model is constructed based on the Ebbinghaus forgetting curve theory, and the expression of the risk time-series decay model is:

[0014] in, The associated risk value for public opinion risk events. As the attenuation factor, This represents the time interval between the initial assessment of a public opinion risk event and the current assessment.

[0015] In some embodiments, the expression for the improved logistic model is:

[0016] Where Z represents the comprehensive risk quantification value of online public opinion. Here, d represents the real-time risk value of a public opinion risk event, and d is a sliding adjustment factor with a value of [value missing]. The value is the time interval between the latest public opinion risk event and the previous public opinion risk event.

[0017] In some embodiments, the set of public opinion indicators includes public opinion indicators in the fields of public safety, social welfare, economic and financial affairs, and cultural and entertainment affairs, and each public opinion indicator is defined by risk intensity and attenuation factor.

[0018] In some embodiments, the public opinion indicator correlation graph is a directed graph structure, and its expression is: ,in, For a set of public opinion indicator sets, Let be a set of directed edges, representing the risk impact relationship between preceding indicators and subsequent indicators.

[0019] Secondly, embodiments of the present invention provide a dynamic quantitative assessment device for comprehensive online public opinion risk, the device comprising: The module is used to construct an indicator system for online public opinion risk symptoms. The indicator system includes a set of public opinion symptom indicators and a correlation diagram of public opinion symptom indicators. The quantification module is used to match the set of public opinion symptom indicators based on the actual sequence of public opinion risk events, generate a correlation matrix according to the correlation graph of the public opinion symptom indicators, and quantify the correlation risk value of each public opinion risk event through risk intensity measurement. The calculation module is used to calculate the time decay of the associated risk value of each public opinion risk event based on the risk time series decay model, so as to obtain the real-time risk value. The evaluation module is used to calculate the comprehensive risk index of online public opinion based on all real-time risk values ​​using an improved logistic model, wherein the improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

[0020] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores program code that can run on the processor, and when the program code is executed by the processor, it implements a dynamic quantitative assessment method for comprehensive network public opinion risk as described in any embodiment of the first aspect.

[0021] Fourthly, embodiments of this application provide a computer storage medium storing one or more programs, which can be executed by an electronic device as described in the third aspect, to implement a dynamic quantitative assessment method for comprehensive network public opinion risk as described in any embodiment of the first aspect.

[0022] This invention provides a dynamic quantitative assessment method and apparatus for comprehensive online public opinion risk, comprising: constructing an indicator system for online public opinion risk symptoms, the indicator system including a set of public opinion symptom indicators and a correlation graph of public opinion symptom indicators; matching the set of public opinion symptom indicators based on actual public opinion risk event sequences, generating a correlation matrix according to the correlation graph of public opinion symptom indicators, and quantifying the associated risk value of each public opinion risk event through risk intensity measurement; calculating the time decay of the associated risk value of each public opinion risk event based on a risk time-series decay model to obtain a real-time risk value; and calculating the comprehensive online public opinion risk index based on all real-time risk values ​​using an improved logistic model. The improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk value, and comprehensively considers multiple factors combined with mathematical modeling to simulate real-world scenarios. In the processes of quantifying the associated risk value of online public opinion and calculating comprehensive public opinion risk, technical means such as the symptom indicator correlation graph, the risk time-series decay model, and the improved logistic model are introduced to make the assessment results more closely resemble the actual situation.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] The invention will now be described in more detail with reference to embodiments and the accompanying drawings.

[0025] Figure 1 The diagram illustrates an exemplary dynamic quantitative assessment method for comprehensive online public opinion risk proposed in one embodiment of the present invention. Figure 2 This diagram illustrates an exemplary process for quantitative assessment of comprehensive online public opinion risks, as proposed in one embodiment of the present invention. Figure 3This diagram illustrates an exemplary correlation diagram of online public opinion risk indicator proposed in one embodiment of the present invention. Figure 4 This diagram illustrates an exemplary network public opinion risk indicator system proposed in one embodiment of the present invention. Figure 5 The diagram shows a structural block diagram of a dynamic quantitative assessment device for comprehensive online public opinion risk proposed in one embodiment of the present invention. Figure 6 A structural block diagram of an electronic device for performing a dynamic quantitative assessment method for comprehensive network public opinion risk according to an embodiment of this application is shown. Figure 7 This application illustrates a computer-readable storage medium for storing or carrying a dynamic quantitative assessment method for comprehensive online public opinion risk according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0027] Existing technologies include a large number of studies on public opinion risk assessment, which mainly focus on the perception and monitoring of public opinion on a specific type of event in a single field. These studies assess the public opinion risk of a single event from the aspects of dissemination power, influence, and degree of harm, or rely on the experience of experts in the field to make risk judgments. The advantage is that it can handle complex risk situations, but it is more of a subjective qualitative description and cannot fully and accurately understand and grasp the comprehensive risk situation of online public opinion under the intertwining of multiple field factors.

[0028] Based on this, the present invention uses open-source multi-domain public opinion risk data to quickly calculate the current comprehensive public opinion risk value and locate key risk points based on real-time cyberspace public opinion events.

[0029] According to the applicant's research, the comprehensive risk of online public opinion is characterized by multi-domain interweaving and dynamic evolution. These characteristics bring three challenges to the comprehensive risk assessment of online public opinion. First, it is necessary to consider the complex correlation and mutual influence of risks in multiple fields such as public safety, social welfare, economy and finance, and culture and entertainment, which jointly affect the overall risk of online public opinion. How to quantitatively characterize this correlation and mutual influence is the key. Second, it is necessary to continuously assess the decay of each type of public opinion risk event over time from a long-term perspective. Establishing a reasonable time-series decay model is the key. Third, it is necessary to comprehensively and quantitatively calculate the comprehensive risk value of online public opinion based on various types of public opinion risk events.

[0030] To address the above challenges, this invention introduces a correlation graph of public opinion symptom indicators. Based on the network structure of the correlation graph, it deeply reveals the influence of the correlation between public opinion risk events on their risk. Based on the Ebbinghaus forgetting theory, it constructs a risk time-series decay model. Finally, it uses an improved logistic model to comprehensively quantify and calculate the comprehensive risk value of online public opinion. By adjusting the factor, the calculation results are made to approximate the dynamic evolution process of real public opinion risk.

[0031] One of the methods for dynamic quantitative assessment of comprehensive risks in online public opinion will be described in detail in subsequent embodiments.

[0032] The following describes an application scenario of a dynamic quantitative assessment method for comprehensive online public opinion risk provided by an embodiment of the present invention: Please see Figure 1 , Figure 1 This is a flowchart illustrating a dynamic quantitative assessment method for comprehensive online public opinion risk provided in this embodiment of the invention. In this embodiment, the dynamic quantitative assessment method for comprehensive online public opinion risk can be applied to, for example... Figure 5 The dynamic quantitative assessment device 300 for comprehensive risk assessment of online public opinion shown is neutralizing... Figure 6 In the electronic device 200 shown, the following is specifically for... Figure 1 The process shown is described in detail. A dynamic quantitative assessment method for comprehensive risks of online public opinion can include S110 to S140.

[0033] S110: Construct an indicator system for online public opinion risk indicators, which includes a set of public opinion indicator sets and a correlation diagram of public opinion indicator sets.

[0034] In this embodiment of the application, the network public opinion risk indicator system includes two parts: the construction of a set of public opinion indicator sets and the construction of a correlation graph of public opinion indicator sets.

[0035] Among them, public opinion indicator sets are multi-level sets of public opinion indicator sets that summarize and generalize risk events in various fields. Each public opinion indicator set influences the overall risk of online public opinion to a certain extent. By peeling away the layers of online public opinion risk factors, the set of public opinion indicator sets is constructed as follows: The areas of public opinion risk include: public safety, which can include public opinion related to accidents and disasters, public health, social order, urban operations, and natural disasters.

[0036] The area of ​​public opinion risk is: The cultural and entertainment sector, which may include: Public opinion on cultural and entertainment products and cultural heritage.

[0037] Among them, the aforementioned public safety public opinion events correspond to typical event cases in turn, which may include: Controversial incidents involving film, television, and gaming content, as well as incidents of cultural and educational loss / abuse.

[0038] The above content may also be not limited to this, and this application will not elaborate on it.

[0039] See Figure 3 As shown, this application can conduct public opinion risk assessments in the following areas: Public safety risks refer to risk factors related to public safety that affect online public opinion, mainly including public opinion risk indicator items related to accidents and disasters, public health, social order, urban operation, and natural disasters; Social and livelihood risks: These refer to risk factors affecting online public opinion related to social and livelihood issues, mainly including public opinion risk indicators related to education equity, employment security, social security, housing security, and public services. Economic and financial risks refer to risk factors in the economic and financial spheres that affect online public opinion, mainly including risk indicators related to financial markets, the real economy, consumer markets, and foreign trade. Cultural and entertainment risks: These refer to risk factors in the cultural and entertainment sector that affect online public opinion, mainly including public opinion risk indicators related to cultural and entertainment products and cultural heritage.

[0040] In some implementations, in S110, the set of public opinion indicator sets includes public opinion indicator sets in the fields of public safety, social welfare, economic and financial, and cultural and entertainment, and each public opinion indicator is defined by risk intensity and attenuation factor.

[0041] For example, the set of public opinion indicator sets is represented as follows: Each symptom indicator is represented as , where r and These represent the risk intensity and attenuation factor of the public opinion symptom indicator, respectively. Risk intensity represents the severity of the risk posed by the public opinion symptom indicator, ranging from [0,10]. A higher value indicates a higher risk intensity and a stronger potential public opinion risk. The attenuation factor refers to the degree to which the public opinion risk caused by the event represented by the public opinion symptom indicator decays over time, ranging from [0,1]. A higher value indicates a faster decay over time. r and They were all initialized based on the historical experience and knowledge of experts in their respective fields.

[0042] In some implementations, the correlation graph of public opinion indicator is a directed graph structure, and its expression is: ,in, For a set of public opinion indicator sets, Let be a set of directed edges, representing the risk impact relationship between preceding indicators and subsequent indicators.

[0043] In this embodiment, the public opinion indicator correlation graph is constructed by inferring and identifying the risk impact relationships between events based on a large number of historical online public opinion risk events. The risk impact relationships between public opinion risk events are mapped to the correlation relationships between public opinion indicator symptom graphs, as shown in the attached figure. Figure 4 As shown. Figure 4 In a directed graph, nodes represent public opinion indicators, and directed edges represent the degree to which preceding indicators affect the risk of subsequent indicators. This is a correlation diagram of public opinion indicator indicators, in which... For a set of public opinion indicator sets, It is a set of directed edges.

[0044] S120: Based on the actual sequence of public opinion risk events, match the set of public opinion symptom indicators, generate a correlation matrix according to the correlation diagram of public opinion symptom indicators, and quantify the correlation risk value of each public opinion risk event through risk intensity measurement.

[0045] Specifically, S120 matches a set of public opinion symptom indicators based on actual public opinion risk event sequences, and generates a correlation matrix based on the correlation diagram of public opinion symptom indicators, including: S121: Based on the sequence and intensity of public opinion risk events, the correlation between events is calculated using the first formula, and a correlation matrix is ​​generated. The first formula is:

[0046] Where k represents a public opinion symptom indicator, i and j are the sequence numbers of all public opinion symptom indicators connected by the shortest path in the public opinion symptom indicator correlation graph, and the public opinion risk event sequence is... The risk intensity is ; The expression for the correlation matrix is:

[0047] in, The correlation matrix M represents the degree of correlation between public opinion risk events, where m is the number of public opinion risk events at the time of assessment, and all elements on the diagonal of the correlation matrix M are zero.

[0048] In this embodiment of the application, in order to quantify the associated risk value of public opinion risk events, it is necessary to first calculate the risk correlation degree between public opinion symptom indicators based on the correlation diagram of public opinion symptom indicators and the risk intensity of symptom indicators. The risk correlation degree between public opinion symptom indicators refers to the degree of mutual response of symptom indicators, that is, the risk impact of preceding public opinion symptom indicators on subsequent symptom indicators. The calculation formula is the first calculation formula mentioned above.

[0049] Specifically, S120 quantifies the associated risk value of each public opinion risk event through risk intensity measurement, including: The associated risk value of each public opinion risk event is calculated using the second formula through the public opinion risk event association risk value calculation operator. The second formula is as follows:

[0050] When j=1, it means that there is only one initial public opinion risk event during the evaluation, and no preceding public opinion risk events have an impact on it. .

[0051] The method for calculating the associated risk value is as follows:

[0052] in, For calculating the associated risk value of public opinion risk events, Let be the associated risk value of the j-th public opinion risk event.

[0053] In this embodiment of the application, since various public opinion risk events are rampant on the Internet each time the comprehensive risk of online public opinion is assessed, and these public opinion risk events influence each other, in order to accurately assess the risk value of each public opinion risk event under such influence, the present invention generates a correlation matrix based on the correlation diagram of symptom indicators and the degree of risk correlation, and quantifies and calculates its correlation risk value based on the actual public opinion risk events that occur.

[0054] The sequence of public opinion risk events is denoted as The risk intensity is The correlation between public opinion risk events is calculated based on the symptom indicators corresponding to the risk events, thereby generating a correlation matrix M.

[0055] S130: Based on the risk time-series decay model, the associated risk value of each public opinion risk event is calculated to obtain the real-time risk value.

[0056] In this embodiment, the risk time-series decay model is constructed based on the Ebbinghaus forgetting curve theory, and the expression of the risk time-series decay model is:

[0057] in, The associated risk value for public opinion risk events. As the attenuation factor, This represents the time interval between the initial assessment of a public opinion risk event and the current assessment.

[0058] In this embodiment, the risk value of a real-world public opinion risk event will decrease over time. This decay process is similar to the forgetting rate curve derived by German psychologist H. Ebbinghaus through systematic experiments and in-depth analysis of the forgetting patterns of the human brain when exposed to new information. Based on this, this application combines and constructs a decay function between the risk value of a public opinion risk event and time.

[0059] S140: Based on all real-time risk values, the comprehensive risk index of online public opinion is calculated using an improved logistic model. The improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

[0060] In this embodiment of the application, the expression of the improved logistic model is:

[0061] Where Z represents the comprehensive risk quantification value of online public opinion. Here, d represents the real-time risk value of a public opinion risk event, and d is a sliding adjustment factor with a value of [value missing]. The value is the time interval between the latest public opinion risk event and the previous public opinion risk event.

[0062] It should be noted that the risk values ​​of all public opinion risk events at the current assessment time are comprehensively superimposed and calculated. This superposition is not a simple, unlimited upward process, but rather a curved process involving incubation, development, climax, and decline. This change curve is similar to a logistic curve. Therefore, this invention uses the logistic equation as the basis for superposition calculation and introduces a sliding adjustment factor to control the rate of increase and inflection point of the comprehensive public opinion risk in real time, making it more closely resemble the real-world scenario.

[0063] See Figure 2 As shown in the flowchart, the specific implementation process of the dynamic quantitative assessment method for comprehensive public opinion risk in this application may include the following stages: S1: Construction of an Indicator System for Online Public Opinion Risk Signs The comprehensive risk of online public opinion is the overall result of the intertwining and mutual influence of multiple fields. First, it is necessary to reveal the influence relationship between risk events in each field layer by layer. In order to digitally represent this relationship for subsequent quantitative assessment, the public opinion risk events in each field are first abstracted into public opinion symptom indicators. Then, a public opinion symptom indicator correlation diagram is introduced to structurally represent the inherent risk correlation between indicators, thereby quantitatively calculating the degree of risk impact of a certain type of risk event on its type of risk event.

[0064] S2: Calculate the associated risk value of public opinion risk events. Building upon the established system of public opinion risk indicator systems, it is necessary to match real-world risk events with these indicator systems. Here, indicator systems and risk events are relative concepts; indicator systems are abstract, theoretical constructs, while risk events are concrete, real-world occurrences. For example, a food safety incident in the public safety sector is an indicator system, and excessive lead content in food at a kindergarten in a certain city is a concrete public opinion risk event resulting from a food safety incident. Based on the indicator system correlation diagram, a correlation matrix of public opinion risk events is calculated for each assessment, thereby quantifying the associated risk value of each public opinion risk event.

[0065] S3: Calculate the real-time risk value of public opinion risk events. In reality, the risk level of public opinion events decreases over time. Events with stronger influence and higher risk levels experience a slower decline in risk value, while countermeasures decrease more rapidly. Therefore, a risk time-series decay model is established to calculate the real-time risk value of each public opinion event after its decay.

[0066] S4: Comprehensive quantitative assessment of online public opinion risks Finally, by using the real-time risk value of each public opinion risk event, a comprehensive quantitative model of strategic security risk with a sliding adjustment factor is constructed through an improved logistic equation to calculate the current comprehensive risk index of online public opinion.

[0067] In summary, this application comprehensively considers multiple factors and designs a dynamic quantitative assessment process for the comprehensive risk of online public opinion. Through mathematical modeling to simulate real-world scenarios, it introduces technical means such as symptom indicator correlation diagrams, risk time-series decay models, and improved logistic models in the processes of quantifying the risk value associated with online public opinion and calculating the comprehensive risk of public opinion. This establishes a scientific and reasonable method for the quantitative assessment of the comprehensive risk of online public opinion, making the assessment results more closely resemble the actual situation.

[0068] Please see Figure 5 , Figure 5 This invention provides a structural block diagram of a dynamic quantitative assessment device for comprehensive online public opinion risk. The device includes: a construction module 310, a quantification module 320, a calculation module 330, and an assessment module 340, wherein: Module 310 is used to construct an indicator system for online public opinion risk symptoms. The indicator system includes a set of public opinion symptom indicators and a correlation diagram of public opinion symptom indicators. The quantification module 320 is used to match a set of public opinion symptom indicators based on the actual sequence of public opinion risk events, generate a correlation matrix according to the correlation diagram of public opinion symptom indicators, and quantify the correlation risk value of each public opinion risk event through risk intensity measurement. The calculation module 330 is used to calculate the time decay of the associated risk value of each public opinion risk event based on the risk time series decay model, so as to obtain the real-time risk value. The evaluation module 340 is used to calculate the comprehensive risk index of online public opinion based on all real-time risk values ​​using an improved logistic model. The improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

[0069] It should be noted that the device embodiments in this invention correspond to the aforementioned method embodiments. The specific principles in the device embodiments can be found in the content of the aforementioned method embodiments, and will not be repeated here.

[0070] In the several embodiments provided in this example, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0071] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0072] Please see Figure 6 , Figure 6 The present application provides a structural block diagram of an electronic device 200 that can perform the above-described dynamic quantitative assessment method for comprehensive network public opinion risk. The electronic device 200 may be a smartphone, tablet computer, computer, or portable computer.

[0073] The electronic device 200 also includes a processor 202 and a memory 204. The memory 204 stores programs that can execute the contents of the foregoing embodiments, and the processor 202 can execute the programs stored in the memory 204.

[0074] The processor 202 may include one or more cores for data processing and message matrix units. The processor 202 connects to various parts within the electronic device 200 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 204, and by calling data stored in the memory 204. Optionally, the processor 202 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 202 may integrate one or more of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem / decoder. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem / decoder handles wireless communication. It is understood that the modem / decoder may also be implemented separately as a communication chip, without being integrated into the processor.

[0075] Memory 204 may include random access memory (RAM) or read-only memory (ROM). Memory 204 can be used to store instructions, programs, code, code sets, or instruction sets. Memory 204 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., instructions for a user to obtain random numbers), instructions for implementing the various method embodiments described below, etc. The data storage area may also store data (e.g., random numbers) created by the terminal during use.

[0076] Electronic device 200 may also include a network module and a screen. The network module is used to receive and transmit electromagnetic waves, converting electromagnetic waves into electrical signals, thereby enabling communication with communication networks or other devices, such as audio playback devices. The network module may include various existing circuit elements used to perform these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, SIM cards, memory, etc. The network module can communicate with various networks such as the Internet, corporate intranets, and wireless networks, or communicate with other devices via wireless networks. The aforementioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. The screen can display interface content and facilitate data interaction.

[0077] Please refer to Figure 7 , Figure 7 This diagram illustrates a structural block diagram of a computer-readable storage medium according to an embodiment of this application. The computer-readable storage medium 400 stores program code 410, which can be called by a processor to execute the methods described in the above method embodiments.

[0078] The computer-readable storage medium 400 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium 400 has storage space for program code 410 that performs any of the method steps described above. This program code 410 can be read from or written to one or more computer program products. The program code 410 may be compressed, for example, in a suitable form.

[0079] This application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a dynamic quantitative assessment method for comprehensive online public opinion risk as described in the various optional implementations above.

[0080] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic quantitative assessment method for comprehensive online public opinion risk, characterized in that, The method includes: A system of indicators for online public opinion risk symptoms is constructed, which includes a set of public opinion symptom indicators and a correlation diagram of public opinion symptom indicators; Based on the actual sequence of public opinion risk events, the set of public opinion symptom indicators is matched, a correlation matrix is ​​generated according to the correlation graph of the public opinion symptom indicators, and the correlation risk value of each public opinion risk event is quantified by risk intensity. Based on the risk time-series decay model, the associated risk value of each public opinion risk event is calculated to obtain the real-time risk value. Based on all real-time risk values, a comprehensive risk index for online public opinion is calculated using an improved logistic model, wherein the improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

2. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 1, characterized in that, The process involves matching the sequence of actual public opinion risk events with the set of public opinion symptom indicators, and generating a correlation matrix based on the correlation graph of the public opinion symptom indicators, including: Based on the sequence and intensity of public opinion risk events, the correlation between events is calculated using the first formula, and a correlation matrix is ​​generated. The first formula is: Where k represents a public opinion symptom indicator, i and j are the sequence numbers of all public opinion symptom indicators connected by the shortest path in the public opinion symptom indicator correlation graph, and the public opinion risk event sequence is... The risk intensity is ; The expression for the correlation matrix is: in, The correlation matrix M represents the degree of correlation between public opinion risk events, where m is the number of public opinion risk events at the time of assessment, and all elements on the diagonal of the correlation matrix M are zero.

3. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 2, characterized in that, The method of quantifying the associated risk value of each public opinion risk event through risk intensity includes: The associated risk value of each public opinion risk event is calculated using the second formula through the public opinion risk event association risk value calculation operator. The second formula is as follows: The method for calculating the associated risk value is as follows: in, For calculating the associated risk value of public opinion risk events, Let be the associated risk value of the j-th public opinion risk event.

4. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 1, characterized in that, The risk time-series decay model is constructed based on the Ebbinghaus forgetting curve theory, and the expression of the risk time-series decay model is: in, The associated risk value for public opinion risk events. As the attenuation factor, This represents the time interval between the initial assessment of a public opinion risk event and the current assessment.

5. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 1, characterized in that, The expression for the improved logistic model is: Where Z represents the comprehensive risk quantification value of online public opinion. Here, d represents the real-time risk value of a public opinion risk event, and d is a sliding adjustment factor with a value of [value missing]. The value is the time interval between the latest public opinion risk event and the previous public opinion risk event.

6. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 1, characterized in that, The set of public opinion indicators includes indicators in the fields of public safety, social welfare, economy and finance, and culture and entertainment. Each public opinion indicator is defined by risk intensity and attenuation factor.

7. The dynamic quantitative assessment method for comprehensive online public opinion risk according to claim 6, characterized in that, The correlation graph of the public opinion indicator is a directed graph structure, and its expression is: ,in, For a set of public opinion indicator sets, Let be a set of directed edges, representing the risk impact relationship between preceding indicators and subsequent indicators.

8. A dynamic quantitative assessment device for comprehensive online public opinion risk, characterized in that, The device includes: The module is used to construct an indicator system for online public opinion risk symptoms. The indicator system includes a set of public opinion symptom indicators and a correlation diagram of public opinion symptom indicators. The quantification module is used to match the set of public opinion symptom indicators based on the actual sequence of public opinion risk events, generate a correlation matrix according to the correlation graph of the public opinion symptom indicators, and quantify the correlation risk value of each public opinion risk event through risk intensity measurement. The calculation module is used to calculate the time decay of the associated risk value of each public opinion risk event based on the risk time series decay model, so as to obtain the real-time risk value. The evaluation module is used to calculate the comprehensive risk index of online public opinion based on all real-time risk values ​​using an improved logistic model, wherein the improved logistic model introduces a sliding adjustment factor to dynamically control the evolution curve of the risk values.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores program code that can run on the processor. When the program code is executed by the processor, it implements a dynamic quantitative assessment method for comprehensive network public opinion risk as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be called by one or more processors to execute a dynamic quantitative assessment method for comprehensive online public opinion risk as described in any one of claims 1-7.

Images