Multi-scene simulation deduction method of network public opinion evolution law

Abstract

The invention relates to a multi-scenario simulation deduction method for a network public opinion evolution rule, and the method comprises the steps: constructing a multi-scenario simulation deduction system for the public opinion evolution rule, carrying out the simulation fitting of the public opinion evolution rule through the real public opinion data, and carrying out the scenario evolution of the public opinion evolution rule. A multi-scene simulation method based on system dynamics is adopted, in combination with exogenous intervention, a multi-scene simulation deduction system of a public opinion evolution rule is constructed, whether public opinion evolution can be effectively accelerated to enter a fading period or not is observed by adjusting the number of three types of public opinions with high, medium and low influence degree levels, the evolution period is shortened, and the evolution efficiency is improved. And technical support is provided for health guidance of public opinions.

Description

Technical Field

[0001] This invention relates to a multi-scenario simulation and deduction method for the evolution of online public opinion, belonging to the technical field of online public opinion data analysis and mining. Background Technology

[0002] Currently, there are numerous documents and patent applications regarding methods or systems for "simulation, prediction, and extrapolation of online public opinion evolution." However, most of the published literature is based on multi-agent systems, deep learning / large language models, impulse / control strategies, or hybrid methods. These methods all employ unique system frameworks of "single-layer public opinion propagation models" or "multi-agent diffusion models," offering a single perspective for extrapolation or prediction, resulting in inaccurate predictions. Therefore, finding a more accurate prediction and extrapolation method remains a pressing technical problem to be solved in this field. Summary of the Invention

[0003] To address the aforementioned problems, this invention discloses a multi-scenario simulation and deduction method for the evolution of online public opinion, the specific technical solution of which is as follows:

[0004] A multi-scenario simulation and deduction method for the evolution of online public opinion includes the following steps:

[0005] Step 1: The number of low, medium and high impact public opinion events are represented by L, M and H respectively, and defined as state variables L(t), M(t) and H(t) that change with time t respectively. The state variable of the total amount of public opinion events that changes with time t is represented by equation (1).

[0006] N(t) = L(t) + M(t) + H(t) (1)

[0007] Step 2: Define the growth rate IG(t) of each type of public opinion information at different times, as shown in equation (2). (2) in, The growth rates for low, medium, and high levels of public opinion are shown. This represents the carrying capacity of low, medium, and high levels of public opinion, i.e., the maximum allowable capacity of public opinion. X represents any one of L, M, and H, and X(t) represents any one of L(t), M(t), and H(t). Step 3: Pass through again This creates negative feedback, preventing growth from exceeding the upper limit. At the same time, the evolution of public opinion also involves the natural decay of information NA(t), which is defined as in equation (3). (3) in, The attenuation rate; Step 4: Next, quantify the "crowding-out effect" of any two different types of public opinion information selected from low, medium, and high impact levels. The two different types of public opinion information are represented as follows: The "squeeze-out effect" is shown in equation (4). (4) in, This is the competition inhibition coefficient; Step 5: Based on the above, add exogenous intervention. Thus, the state equation for the evolution of public opinion, as shown in equation (5), is obtained. (5) Step 6: Through iterative calculations using formulas (1) to (5) above, dynamically simulate the evolution trajectory of the number of public opinion events of low, medium, and high impact. , , The sum of them This is the evolution curve of the total amount of public opinion. By adjusting various parameters in formula (5), the feedback structure and exogenous intervention of the system can be changed. Input is used to achieve dynamic simulation of the evolution of public opinion.

[0008] Furthermore, the initial L(0), M(0) and H(0) are substituted into formula (5) to simulate the evolution of public opinion under different scenarios by adjusting the number of public opinion events at different times; the initial L(0), M(0) and H(0) refer to the first segment after dividing the entire public opinion period into several segments.

[0009] Furthermore, the process of obtaining the quantitative value of the dimension is as follows: 1.1: Determine the weights of influencing factors for each dimension: Assign weight values ​​to the influencing factors, and the sum of the weight values ​​of all influencing factors under each dimension is 1; 1.2: Quantitative calculation of quantitative values ​​for each dimension: Based on the weight values ​​of the influencing factors for each dimension, a weighted average is calculated to obtain the quantitative value for each dimension.

[0010] Furthermore, the process for obtaining the quantitative value of the influence is as follows: S1: Using the analytic hierarchy process (AHP) to determine the weights of different influence dimensions based on their quantitative values: S1.1: Establish a hierarchical model: The influence of the evolution of online public opinion is the target layer, and the five influence dimensions are the criteria layer. S1.2: Constructing the judgment matrix: Using the 1-9 scaling method, pairwise comparisons are performed on the influence dimensions of the criterion layer to form a judgment matrix. S1.3: Consistency Test: Calculate the eigenvectors and the largest eigenvalue of the judgment matrix, perform a consistency test, and if the test passes, obtain the final weight vector w, which is used as the weight of each influence dimension. , S2: Integrate the quantitative values ​​of each influence dimension, and use membership functions to construct a fuzzy relation matrix. Each influence dimension of public opinion information will obtain three membership degrees, ultimately forming a 5x3 fuzzy relation matrix U, as shown below. .

[0011] Furthermore, the process of obtaining the influence level is as follows: The five dimensions of influence were used to evaluate the influencing factors. ,in, These are quantitative values ​​for each influencing dimension. Then, the influence level set is recorded as [low, medium, high], and the influence value of each piece of public opinion information will eventually correspond to a certain level in the level set;

[0012] Multiplying the fuzzy relation matrix U by the eigenvector w yields the fuzzy comprehensive evaluation set S: in, For a value, , , ... These correspond to three levels of influence: low, medium, and high. According to the rules of fuzzy comprehensive evaluation, the maximum value among these three values ​​is the influence level, and the level corresponding to the maximum value is the influence level.

[0013] The beneficial effects of this invention are:

[0014] This invention is not simply an application of system dynamics models, but rather constructs a public opinion evolution simulation system with an innovative feedback mechanism by introducing a three-dimensional "influence level" public opinion subsystem, an intra-system competition term in the form of a "crowding-out effect," an exogenous intervention mechanism, and a multi-scenario dynamic simulation structure. These four elements combined form a unique system framework that differs from existing "single-layer public opinion propagation models" or "multi-agent diffusion models," enabling accurate simulation and deduction of public opinion evolution patterns. Attached Figure Description

[0015] Figure 1 This is a diagram illustrating the evolution of public opinion regarding events according to an embodiment of the present invention. Figure 2 This is a comparison diagram of the event simulation and evolution law and the actual evolution law in the embodiments of the present invention. Detailed Implementation

[0016] The present invention will be further illustrated below with reference to the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are for illustrative purposes only and are not intended to limit the scope of the invention.

[0017] The overall process of this invention's method for quantitatively calculating the influence of online public opinion evolution patterns is as follows: Natural language processing and mathematical statistics are used to calculate the quantitative values ​​of each influencing factor. To eliminate the quantitative differences in influencing factor values ​​between different methods, the influencing factor values ​​are standardized to ensure that each influencing factor value falls within the range of [0-1], and that its value is proportional to the level of influence, thus unifying the measurement of the influence of influencing factors and public opinion information. Next, the fuzzy comprehensive evaluation method is used to determine the weights of different influencing factors under the same influence dimension, thereby calculating the quantitative values ​​of each influence dimension. For each influence dimension value, the analytic hierarchy process (AHP) is used to determine the weights of different influence dimensions, and then the fuzzy comprehensive evaluation method is used to calculate the specific numerical value of the influence of online public opinion evolution patterns, classify the levels of influence, and then obtain the level evaluation of the influence of online public opinion evolution patterns based on the correspondence between the specific numerical value of the influence and the level of influence. The specific execution process of each step is explained in detail below:

[0018] Step 1: A framework for evaluating the impact of the evolution of online public opinion was constructed, comprising 5 impact dimensions and 13 influencing factors, as follows: Dimension 1: Objectivity: This includes influencing factors such as the proportion of vague words and the proportion of objective sentences. Dimension Two: Timeliness: This includes influencing factors such as release frequency and freshness. Dimension 3: Dissemination: This includes influencing factors such as the number of likes, comments, and dissemination rate. Dimension 4: Emotional Tendency: This includes influencing factors such as emotional intensity and emotional consistency. Dimension 5: Standardization: This includes influencing factors such as coherence, readability, similarity, and the proportion of sensitive words.

[0019] Step 2: Use natural language processing and mathematical statistics methods to calculate the quantitative value of each influencing factor, standardize the value of each influencing factor so that the quantitative value of each influencing factor falls within the range of [0-1], and the quantitative value of the influencing factor is directly proportional to the degree of influence.

[0020] (1) Objectivity

[0021] Objectivity refers to the degree of objectivity in the wording of online public opinion information. The higher the objectivity of a piece of public opinion information, the higher its credibility, and thus the greater its impact on the evolution of public opinion. Sub-influencing factors include: the proportion of vague words and the proportion of objective words.

[0022] ① The proportion of vague terms refers to the percentage of vague pronouns such as "it is said," "I heard," and "insider information" in public opinion information. To standardize vague pronouns, the research project constructed a vague pronoun database. Using this database, the proportion of vague pronouns in the total length of current public opinion was statistically analyzed. Since the more such words appear, the higher the proportion, and the lower the veracity of the events involved, the reciprocal of this ratio was taken as the final quantitative representation of the proportion of vague terms.

[0023] ② The proportion of objective sentences refers to the percentage of objective sentences in public opinion information. Subjective sentences are those with obvious emotions and subjective judgments. Objective sentences, on the other hand, are generally declarative sentences that objectively describe events without obvious emotional coloring. Because objective sentences are more credible than subjective sentences, the more objective sentences there are, the clearer the event description, and the greater the impact on the evolution of public opinion. Therefore, this study uses the proportion of objective sentences in public opinion information as the quantitative value of this influencing factor, that is, the percentage of objective sentences in public opinion information out of the total number of sentences in the public opinion information. Objective sentences generally use declarative statements, and whether a sentence is a declarative statement can be determined using the Natural Language Processing (NLTK) package.

[0024] (2) Timeliness

[0025] Timeliness refers to the measurement of the time interval between the release of public opinion information. Generally speaking, the shorter the interval, the greater the impact on the evolution pattern. Sub-influencing factors include: release frequency and freshness.

[0026] ① Release frequency refers to the relative rate at which public opinion information is released. It is calculated by comparing the interval between two public opinion messages that are adjacent to the current public opinion message in terms of release time. The calculation rule is as follows: Select two public opinion messages that are adjacent to the current public opinion message in terms of release time. Calculate the average of the time interval between the current public opinion message and these two public opinion messages in minutes, where the absolute value of the interval is taken. After obtaining the average value, take its reciprocal as the release frequency value, so that the smaller the interval, the greater the impact.

[0027] ② Freshness refers to the absolute rate at which public opinion information is released, calculated and compared with the release interval of the first piece of public opinion information. Also measured in minutes, the reciprocal of the time interval between the current public opinion and the first piece of public opinion is taken as the freshness value. The freshness of the first piece of public opinion is considered to be 1.

[0028] If the intervals mentioned above are all within the same minute, the interval is considered to be 1.

[0029] (3) Spread

[0030] Dissemination rate is a measure of the speed at which public opinion spreads; the higher the dissemination rate, the greater its impact on the evolutionary pattern. Sub-factors include: number of likes, number of comments, and dissemination rate.

[0031] ① The number of likes refers to the number of times users like public opinion information, and its value is a natural number.

[0032] ② The number of comments refers to the number of replies to the current public opinion information, and its value is a natural number.

[0033] ③ The propagation rate refers to the time interval between the spread of information from one online media to another. The calculation rule is as follows: calculate the interval between the time when the current public opinion information is published on the current platform and the time when that related information first appears on another platform. Also measured in minutes, the reciprocal of its absolute value is taken as the propagation rate.

[0034] The number of likes and comments may be relatively large, so for the same set of public opinion, they are normalized to convert their values ​​to [0-1], so as to keep them consistent with the value range of other influencing factors.

[0035] (4) Emotional Tendency

[0036] Sentiment bias is a measure of user emotions contained in public opinion information. The more pronounced the user emotions, the greater their influence on the evolution of public opinion. Sub-factors include: sentiment intensity and sentiment consistency.

[0037] ① Sentiment intensity refers to the degree of positive, negative, or neutral emotion expressed by users towards public opinion. The sentiment analysis tool TextBlob can be used to calculate sentiment intensity, which has a sentiment polarity value ranging from -1 to 1, where -1 represents extremely negative, 0 represents neutral, and 1 represents extremely positive. Here, we focus on intensity, so the absolute value is taken as the sentiment intensity value.

[0038] ② Emotional consistency refers to whether there is inconsistency in the emotions expressed within the content of public opinion. The calculation rule is as follows: Using TextBlob, the emotional polarity of each sentence is calculated, and the extreme values ​​are summed and the absolute value is taken. Since the summed value may exceed 1, the result is normalized to a range of [0-1]. 0 indicates completely opposite sentiments, i.e., complete inconsistency. 1 indicates that one emotion completely dominates, i.e., complete consistency.

[0039] (5) Normative

[0040] Standardization refers to the degree of standardization in the organization and expression of public opinion information. The higher the standardization, the greater the impact on the evolution of public opinion. Sub-factors include: coherence, readability, similarity, and the proportion of sensitive words.

[0041] ① Organizationality is a measure of whether public opinion information is logically organized in its text. Organizationality can be comprehensively evaluated from four aspects: logical connector density, semantic coherence analysis, topic concentration, and structural integrity. Logical connector density refers to the proportion of logical connectors such as "firstly," "secondly," "therefore," "however," and "for example" in the public opinion information. Semantic coherence analysis uses BERT to calculate the average similarity between adjacent sentences in the public opinion information. Topic concentration uses TextRank to extract keywords and calculates the topic distribution entropy as the concentration. Structural integrity checks for the existence of a general-specific-general structure; a complete structure scores 1 point, a partial structure scores 0.5 points, and no structure scores 0 points. The final organizationality score = 0.3 * logical connector density + 0.4 * semantic coherence + 0.2 * topic concentration + 0.1 * structural score.

[0042] ②Readability refers to the fluency of public opinion content. This study uses the readability method of the natural language processing tool cntext to calculate it directly, with a value ranging from 0 to 1. A higher value indicates greater readability.

[0043] ③ Similarity refers to the degree of similarity between a single piece of public opinion content and other public opinion information in the public opinion set. This project uses cosine similarity based on TF / IDF as the basic algorithm. The current public opinion information is compared pairwise with other public opinion information in the set, and the median is taken as the initial similarity. Since a higher similarity has a smaller impact on the pattern, the initial similarity is subtracted from 1 to obtain the final similarity.

[0044] ④ The percentage of sensitive words refers to the proportion of politically sensitive, stability-related, abusive, or personally attacking words in a given post. The calculation method for the percentage of sensitive words is similar to that for the percentage of vague words; it also requires constructing a sensitive word database and calculating the initial percentage of words in the database within the post. Since the more words in the database, the less compliant it is with current Chinese online information dissemination standards, the final percentage of sensitive words is obtained by subtracting the initial percentage from 1. A higher value indicates greater compliance and a stronger influence on the evolution of public opinion.

[0045] Applying the above calculation rules, the value of each influencing factor is a real number between 0 and 1, and the larger the value, the greater the impact on the evolution of public opinion.

[0046] The execution code for the above-mentioned influencing factors can be found in the code given in the specific implementation of the patent application filed by the inventor's team earlier (patent number 202411689716.7).

[0047] Step 3: Determine the weight values ​​of different influencing factors under the same influence dimension, and calculate the quantitative value of each influence dimension accordingly.

[0048] (1) Determine the weights of the influencing factors for each influencing dimension

[0049] This invention determines the weights of each influencing factor under different influence dimensions, as shown in Table 1. The weights shown in Table 1 are only examples.

[0050] Table 1 Weights of each influencing factor Influence Dimensions Influencing factor weights Objectivity The proportion of vague words was 59.5%, and the proportion of objective sentences was 40.5%. Timeliness Release frequency (22.7%), freshness (77.3%). Dissemination Likes (26.24%), comments (46.16%), and dissemination rate (27.6%). Emotional Tendency Emotional intensity (74.95%), emotional consistency (25.05%). Normative Organization (37.45%), readability (16.95%), similarity (16.52%), and percentage of sensitive words (29.08%).

[0051] (2) Calculation of quantified values ​​of each influencing dimension

[0052] Based on the weights shown in Table 1, the influencing factor values ​​are weighted and averaged according to the influencing dimension to obtain the quantitative value of each influencing dimension.

[0053] Step 4: For the quantitative values ​​of each influence dimension, determine the weight of different influence dimensions, and then use the fuzzy comprehensive evaluation method to calculate the specific numerical value of the influence of the evolution law of online public opinion.

[0054] 4.1 Calculate the weights of each influencing dimension using the AHP method. The steps are as follows:

[0055] ① Establish a hierarchical structure model: The influence of the evolution of online public opinion is the target layer, and the five influence dimensions are the criteria layer.

[0056] ② Constructing the judgment matrix: The influence dimensions of the criterion layer are compared pairwise using the 1-9 scaling method to form the judgment matrix, as shown in Table 2.

[0057] Table 2 Importance Judgment Matrix Influence Dimensions Objectivity Timeliness Dissemination Emotional Tendency Normative Objectivity 1 1 / 3 1 / 5 3 5 Timeliness 3 1 1 / 3 5 7 Dissemination 5 3 1 7 9 Emotional Tendency 1 / 3 1 / 5 1 / 7 1 3 Normative 1 / 5 1 / 7 1 / 9 1 / 3 1

[0058] ③ Consistency check: Calculate the eigenvectors and the largest eigenvalue of the matrix, perform a consistency check, and after passing the check, obtain the final weight vector w, which is used as the weight of each influence dimension.

[0059]

[0060] 4.2 Constructing the Fuzzy Relation Matrix

[0061] The fuzzy comprehensive evaluation method uses membership functions to construct a fuzzy relation matrix, representing the degree of conformity of each influence dimension to the influence level. This invention selects the trapezoidal function as the membership function, with the specific formula as follows: When the level of influence is [low], , When the level of influence is [Medium], , When the level of influence is [high], , Where x represents each influencing dimension V iThe value of the parameter is determined by the function, while parameters a, b, c, and d are used to divide the optimal interval. This means that by adjusting the parameter values, the influence dimension values ​​are made to fall within the range of [0-1]. This is precisely the important reason why this paper chooses [0-1] as the range of influence dimension values. The adjustment of this parameter also needs to be determined based on the actual influence value. According to this function, each influence dimension of public opinion information will obtain three membership degrees, ultimately forming a 5x3 fuzzy relation matrix U, as shown in the following formula:

[0062] Step 5: Classify the level of influence. Based on the correspondence between the specific numerical value of the influence and the level of influence, obtain the level of influence.

[0063] 5.1 Determine the influencing factors and their levels

[0064] The five dimensions of influence of regularity, namely the influencing factors, are denoted as follows: .in This refers to the quantitative value of the influence dimension. The level of influence is then denoted as [low, medium, high], with each level representing the magnitude of the impact on the evolution of public opinion. Through calculation, the influence value of each piece of public opinion information ultimately corresponds to a certain level in the evaluation set. The influence value of public opinion information is calculated from the fuzzy relation matrix and weights of the influencing factors.

[0065] 5.2 Calculate the fuzzy comprehensive evaluation set to evaluate the impact.

[0066] Multiplying the fuzzy relation matrix U by the eigenvector w yields the fuzzy comprehensive evaluation set S: , in, For a value, , , These correspond to three levels of influence: low, medium, and high. According to the rules of fuzzy comprehensive evaluation, the maximum value among these three values ​​is the influence level, and the level corresponding to the maximum value is the influence level.

[0067] The main process of this invention is as follows:

[0068] (1) Obtain public opinion information data.

[0069] (2) Construct a multi-scenario simulation and deduction system for the evolution of public opinion.

[0070] (3) Use real public opinion data to simulate and fit the evolution law of public opinion.

[0071] (4) Conduct scenario evolution of the public opinion evolution law.

[0072] Based on the outcome of the scenario evolution, reliable solutions can be provided for the healthy guidance or quelling of public opinion.

[0073] The specific solution of the present invention is as follows:

[0074] The public opinion evolution law constructed in this invention based on the time-series distribution statistics of influence can essentially be viewed as a complex system involving the interaction of three subsystems of public opinion with high, medium, and low influence levels. In real public opinion events, due to limited public attention and communication resources, there is inevitably a certain "crowding-out effect" among these three types of public opinion information. That is, the increase in the quantity of one type of public opinion will not only directly change the structure of the system, but also trigger dynamic changes in the quantity of the other two types of public opinion through competition and inhibition, ultimately reshaping the evolution trajectory and life cycle of the entire public opinion event. This nonlinear interaction and feedback relationship between the internal elements of the system is a typical application scenario of system dynamics methods. In addition, the evolution of public opinion is also subject to exogenous interventions such as the release of authoritative information, clarification of rumors by the parties involved, and reversals of topics, resulting in significant changes. This is also an important factor in the simulation and deduction of evolution laws. At the same time, the diversity of public opinion types determines the diversity of scenario simulations. Therefore, this invention adopts a multi-scenario simulation method based on system dynamics, combined with exogenous intervention, to construct a multi-scenario simulation and deduction system for the evolution of public opinion. By adjusting the number of the three types of public opinion, it can be observed whether the evolution of public opinion can be effectively accelerated to enter the decline period and the evolution cycle can be shortened.

[0075] First, the number of public opinion events with low, medium, and high impact are defined as core state variables L(t), M(t), and H(t) that change with time t, respectively. The total amount of public opinion events is shown in the following formula.

[0076] N(t) = L(t) + M(t) + H(t)

[0077] Secondly, we define the growth rate IG(t) of each type of public opinion information at different times, as shown in the following formula: , in, The growth rates for low, medium, and high levels of public opinion information are as follows: This refers to their respective carrying capacity, that is, the maximum capacity of the corresponding public opinion information, and then through... This creates negative feedback, preventing growth from exceeding the upper limit. Simultaneously, the evolution of public opinion also involves the natural decay of information NA(t), defined as shown in equation (3): (3) in, The decay rate was then used to quantify the "crowding-out effect" of two different types of public opinion information. As shown in equation (4): (4) in, For example, the competition inhibition coefficient, This indicates the strength of the suppression of low-impact public opinion information by high-impact public opinion information. The growth rate, decay rate, and competition inhibition coefficient all need to be obtained through analysis of actual public opinion data. Based on the above, exogenous intervention is added. Thus, we obtain the state equation for the evolution of public opinion as shown in equation (5): (5) Through iterative calculations of the above equations, the evolution trajectories of the three types of public opinion are dynamically simulated. , , The sum of them This represents the evolution curve of the total amount of public opinion. By adjusting various parameters in the equation, the feedback structure and exogenous input of the system are changed, thereby achieving dynamic simulation of multiple governance scenarios such as "suppressing noise," "strengthening authority," and "guiding the mainstream," providing a quantitative analytical basis for evaluating the effectiveness of different strategies in shortening the life cycle of public opinion.

[0078] In the multi-scenario simulation and deduction system of public opinion evolution law, the initial L(0), M(0) and H(0) are substituted into equation (5), and the public opinion evolution of different scenarios is simulated by adjusting the number of public opinion at different times.

[0079] This invention integrates a system dynamics model, a three-dimensional "influence level" public opinion ecosystem, intra-system competitive items in the form of "crowding-out effect", exogenous intervention mechanisms and multi-scenario dynamic simulation structures to construct a public opinion evolution prediction and simulation system.

[0080] This invention predicts the trend of public opinion by adjusting the parameters of a public opinion evolution simulation system, thereby providing decision support for public opinion emergency response.

[0081] The following is an example of the application of the present invention to a specific event: Taking the conflict at a Chinese restaurant in the United States as an example, based on the collected online public opinion information, the simulation system was first fitted and optimized. The fitting results are as follows: Figure 1 As shown.

[0082] like Figure 1 The two curve fitting evaluation indices are as follows: mean squared error (MSE) 330.69, root mean square error (RMSE) 18.18, and coefficient of determination (R²). 2The coefficient of determination (COP) reached 0.8366. With a maximum total number of public opinion events of 300, the average error of the simulation system was only about 6% of the data range, and the fitted curve was basically consistent with the actual observations. Furthermore, the COP exceeded 0.83, indicating that the simulation system could explain approximately 83.7% of the actual data variance, accurately reproducing the overall trend and fluctuation characteristics of public opinion evolution, and supporting necessary simulation deductions and strategy analysis. Based on this, simulation deductions were conducted to strengthen high-impact public opinion information, strengthen medium-impact public opinion information, and suppress low-impact public opinion information. The comparison results are as follows: Figure 2 As shown.

[0083] It is evident that, in this incident, strengthening high-impact public opinion information will help the public opinion subside as quickly as possible.

[0084] Those skilled in the art will understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as herein.

[0085] Based on the above-described preferred embodiments of the present invention, and through the above description, those skilled in the art can make various changes and modifications without departing from the technical concept of the present invention.

Claims

1. A multi-scenario simulation and deduction method for the evolution of online public opinion, characterized in that, Includes the following steps: Step 1: The number of low, medium and high impact public opinion events are represented by L, M and H respectively, and defined as state variables L(t), M(t) and H(t) that change with time t respectively. The state variable of the total amount of public opinion events that changes with time t is represented by equation (1). N(t) = L(t) + M(t) + H(t) (1) Step 2: Define the growth rate IG(t) of each type of public opinion information at different times, as shown in equation (2). （2） in, The growth rates for low, medium, and high levels of public opinion are shown. This represents the carrying capacity of low, medium, and high levels of public opinion, i.e., the maximum allowable capacity of public opinion. X represents any one of L, M, and H, and X(t) represents any one of L(t), M(t), and H(t). Step 3: Pass through again This creates negative feedback, preventing growth from exceeding the upper limit. At the same time, the evolution of public opinion also involves the natural decay of information NA(t), which is defined as in equation (3). （3） in, The attenuation rate; Step 4: Next, quantify the "crowding-out effect" of any two different types of public opinion information selected from low, medium, and high impact levels. The two different types of public opinion information are represented as follows: The "squeezing effect" is shown in equation (4). （4） in, This is the competition inhibition coefficient; Step 5: Based on the above, add exogenous intervention. Thus, the state equation for the evolution of public opinion, as shown in equation (5), is obtained. （5） Step 6: Through iterative calculations using formulas (1) to (5) above, dynamically simulate the evolution trajectory of the number of public opinion events of low, medium, and high impact. , , The sum of them This is the evolution curve of the total amount of public opinion. By adjusting various parameters in formula (5), the feedback structure and exogenous intervention of the system can be changed. Input is used to achieve dynamic simulation of the evolution of public opinion.

2. The multi-scenario simulation and deduction method for the evolution law of online public opinion according to claim 1, characterized in that, The initial L(0), M(0) and H(0) are substituted into formula (5) to simulate the evolution of public opinion under different scenarios by adjusting the number of public opinion events at different times; the initial L(0), M(0) and H(0) refer to the first segment after dividing the entire public opinion period into several segments.

3. The multi-scenario simulation and deduction method for the evolution law of online public opinion according to claim 1, characterized in that, The process of obtaining the quantitative value of the dimension is as follows: Determine the weights of influencing factors for each dimension: Assign weight values ​​to the influencing factors, and the sum of the weight values ​​of all influencing factors under each dimension is 1; Quantitative calculation of each dimension: Based on the weight values ​​of the influencing factors of each dimension, a weighted average is calculated to obtain the quantitative value of each dimension.

4. The multi-scenario simulation and deduction method for the evolution law of online public opinion according to claim 1, characterized in that, The process for obtaining the quantitative value of the influence is as follows: Step S1: For the quantitative values ​​of each influencing dimension, use the analytic hierarchy process (AHP) to determine the weights of different influencing dimensions: Step S1.1: Establish a hierarchical model: the influence of the evolution of online public opinion is the target layer, and the five influence dimensions are the criteria layer. Step S1.2: Construct the judgment matrix: Use the 1-9 scaling method to perform pairwise comparisons of the influence dimensions of the criterion layer to form a judgment matrix. Step S1.3: Consistency Check: Calculate the eigenvectors and the largest eigenvalue of the judgment matrix, perform a consistency check, and if the check passes, obtain the final weight vector w, which will be used as the weights for each influence dimension. , Step S2: Integrate the quantitative values ​​of each influence dimension, and use the membership function to construct a fuzzy relation matrix. Each influence dimension of public opinion information will obtain three membership degrees, ultimately forming a 5x3 fuzzy relation matrix U, as shown below. 。 5. The multi-scenario simulation and deduction method for the evolution law of online public opinion according to claim 1, characterized in that, The process of obtaining the influence level is as follows: The five dimensions of influence are used to evaluate the influencing factors, denoted as: ,in, These are quantitative values ​​for each influencing dimension. Then, the influence level set is recorded as [low, medium, high], and the influence value of each piece of public opinion information will eventually correspond to a certain level in the level set; Multiplying the fuzzy relation matrix U by the eigenvector w yields the fuzzy comprehensive evaluation set S: in, For a value, , , ... These correspond to three levels of influence: low, medium, and high. According to the rules of fuzzy comprehensive evaluation, the maximum value among these three values ​​is the influence level, and the level corresponding to the maximum value is the influence level.

Images