Information propagation prediction method, system and medium

Abstract

The present invention belongs to the technical field of network information processing, and discloses an information propagation prediction method, system and medium. The prediction method includes: constructing entity attributes and state variables based on topic propagation data in social networks; constructing corresponding differential propagation dynamics equations and cellular automata based on entity attributes and state variables respectively; performing stability and parameter sensitivity analysis of the propagation state vector field according to the propagation dynamics equation, and performing propagation network structure and entity difference analysis through cellular automata simulation. The present invention solves the challenges existing in traditional information propagation dynamics simulation, that is, while ensuring the grasp of the propagation trend at the macro level and the effective mapping of the individual propagation behavior characteristics at the micro level, it realizes the stability analysis of the macro group propagation state and the difference analysis of the micro entity propagation ability, providing a reliable tool for accurately analyzing the evolution trend of information propagation.

Description

Technical Field

[0001] The present invention belongs to the technical field of network information processing, and in particular relates to an information propagation prediction method, system and medium. Background Art

[0002] With the development of information dissemination technology, the dynamics and complexity of information dissemination are increasing, which puts higher requirements on information dissemination simulation. Existing information dissemination dynamics models often have difficulty in achieving effective connection between micro and macro levels when simulating individual behavior and the overall state of the system, that is, it is difficult to ensure effective mapping between individual behavior simulation and overall system state simulation. This inconsistency makes it difficult for model predictions to effectively achieve both macro group dissemination state stability analysis and micro entity difference analysis of the same system, limiting its effectiveness in practical applications.

[0003] The kinetic equation model provides a mature mathematical theoretical basis for simulating the overall state of information propagation, such as describing continuous-time models by differential equations and describing discrete-time models by difference equations. There are abundant theoretical tools and methods for analysis. The kinetic equation is usually directly related to macroscopic phenomena and is easy to explain and apply. However, the kinetic equation usually focuses on the overall behavior of the system and may not capture the details of individual behavior or small-scale dynamics.

[0004] Cellular automata simulate complex systems by defining local rules that are intuitive and easy to understand and implement. However, although cellular automata can simulate local interactions, it can be very difficult to predict the global behavior of the entire system, especially for complex initial conditions and rules. In addition, there may be a lack of direct correspondence between the microscopic simulation of cellular automata and the dynamic equations at the macroscopic level, making the combination and analysis of the two complicated.

[0005] Through the above analysis, the problems and defects of the existing information propagation simulation method are as follows:

[0006] (1) The dynamic equations focus on the overall behavior of the system and cannot capture the details of individual behaviors or small-scale dynamics;

[0007] (2) It can be very difficult to use cellular automata simulations to predict the global behavior of the entire system, especially for complex initial conditions and rules;

[0008] (3) There may be a lack of direct and effective mapping between the microscopic simulation of cellular automata and the dynamic equations at the macroscopic level, which makes it challenging to simultaneously and effectively implement the stability analysis of the macroscopic group propagation state and the analysis of the differences in the microscopic entity propagation capabilities of the same system.

[0009] The combination of cellular automata and dynamic equations is a cross-scale simulation method. This method associates cellular automata with dynamic equations, and performs dynamic modeling from both specific entity indicators and overall statistical indicators. On the premise of ensuring effective mapping between individual behavior simulation and overall system state simulation, macro-group communication state stability analysis and micro-entity communication ability difference analysis are performed respectively. In this way, the dynamic behavior of information dissemination in the communication system can be explored and understood more deeply, providing more accurate solutions for communication trend prediction and communication strategy formulation. The present invention can solve the following problems:

[0010] 1. Integrated micro and macro perspectives: When used together, both micro-level entity attributes to define individual behaviors and macro-level overall trends can be considered, analyzing system behaviors at different scales, from individuals to groups to the entire system, providing multi-scale insights and a more comprehensive understanding of the system.

[0011] 2. Enhanced prediction capabilities: Through global analysis of dynamic equations and local detail simulation of cellular automata, the behavior and development trends of propagation systems can be predicted more accurately.

[0012] 3. Stability and Difference Analysis: The combined use of these two methods can provide more data points and methods for stability analysis of macro-group propagation states and difference analysis of micro-entity propagation capabilities, thereby providing a deeper understanding of the system’s response to changes in different parameters. Summary of the invention

[0013] In order to address the challenges existing in traditional information propagation dynamics simulation, namely, achieving macro-stability analysis and micro-difference analysis while ensuring the grasp of macro-level trends and effective mapping of micro-level individual behavior characteristics, information propagation prediction methods, systems and media are disclosed to achieve macro-stability analysis and micro-difference analysis, and then accurately predict the entity behavior in the cognitive domain.

[0014] The technical solution is as follows: an information propagation prediction method, the method comprising the following specific steps:

[0015] Construct entity attributes and state variables based on relevant data such as platform environment and communication data in social networks to complete data preprocessing;

[0016] The entity attributes and state variables are transformed into parameters of differential dynamics equations by using the method of transforming cellular automata state variables into differential operators and integrating them.

[0017] The method of using the parameters of the dynamics equation as differential operators is adopted to transform the parameters of the differential dynamics equation into entity attributes and state variables;

[0018] The differential propagation dynamics equation is used to construct the propagation state vector field to analyze the stability of macro variables and the sensitivity of propagation parameters. At the same time, the differential operator is used to construct cells to perform entity difference simulation analysis of cellular automata.

[0019] Steps to complete data preprocessing include:

[0020] Define state variables for each entity;

[0021] Define the propagation environment state variables;

[0022] Combine the environment state variables with the entity state variables to define related entity attributes.

[0023] The steps define the state variables of each entity, including but not limited to:

[0024] For the purpose of defining information dissemination, collect information interaction relationships between entities through multi-level dissemination analysis ,in, Represents the entity involved in the propagation , Representing Entities and entities The information interaction between Representing Entities A collection of information interaction relationships with other entities involved in communication;

[0025] Calculate the topic forwarding rate of each entity ,in, Indicates the time after the topic starts to spread , Indicates the time from when the topic started to spread to when Time Entity Total number of reposts;

[0026] Define entity state variable collection , where the information interaction relationship set between entities Topic forwarding rate with entity is a collection of entity state variables subvariables of .

[0027] The steps define the environment state variables, including but not limited to:

[0028] Give different weights to various information transmissions on social platforms ,in, Represents different weight sets of information transmission, Indicates the weights corresponding to different delivery methods;

[0029] Give different weights to different interaction methods on social platforms ,in, represents a set of weights with different interaction modes, Indicates the weights corresponding to different interaction modes;

[0030] Define a collection of environment state variables , where information transfer has different weights Different weights for interaction A collection of environment state variables subvariables of .

[0031] The steps combine the environment state variables and the entity state variables to define the relevant entity attributes, including:

[0032] Defining Entities The entity attributes are ,in, Represents the entity attributes in the form of differential operators, Represents entity State variable collection and the set of environment state variables Jointly designated entities The entity attributes are as follows:

[0033] ,

[0034] in: Represents macro variables used to describe the state of the circled information dissemination, including but not limited to the total number of entities in the susceptible state and the total number of entities in the forwarding state; Represents each macro variable Corresponding to entity The sub-variables of Indicates the time after the topic starts to spread ; Indicates that Describe the macro variables corresponding to the entity The sub-variable The differential equations of the rate of change include but are not limited to the entity information receiving rate and the entity topic forwarding rate.

[0035] In the step, the method of transforming the state variables of the cellular automaton into differential operators and integrating them is adopted to transform the entity attributes and state variables into the parameters of the differential dynamics equation, including:

[0036] Differential operator integral, according to the differential operator , define the differential dynamics equation as follows:

[0037] ,

[0038] in, represents the sum of entities affected by the dissemination of circled information, Represents an entity attribute that can be viewed as a continuous variable , The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the time after the topic starts to spread ;

[0039] Normalization of the kinetic equation variables is based on mapping all kinetic equation variables to The dynamic equations are treated in an interval manner.

[0040] In the step, the method of using the dynamic equation parameters as differential operators to transform the differential dynamic equation parameters into entity attributes and state variables includes:

[0041] Definition of differential dynamics equations. Based on the propagation statistical characteristics, differential dynamics equations are defined. as follows:

[0042] ,

[0043] in, The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables used to describe the propagation state, Indicates the time after the topic starts to spread ;

[0044] right Derivative calculation differential operator , the specific calculation method is as follows:

[0045] ,

[0046] in, represents the sum of entities affected by the dissemination of circled information, Represents an entity attribute that can be viewed as a continuous variable , The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the time after the topic starts to spread ,like Known, then there is ;

[0047] Normalization of differential operator parameters is based on mapping all differential operator parameters to The differential operator is processed in an interval manner;

[0048] Through the differential operator Construct the cell.

[0049] In the step, the method of constructing the propagation state vector field by using the differential propagation dynamics equation is used to analyze the stability of macro variables and the sensitivity of propagation parameters. At the same time, the method of constructing cells by using differential operators is used to perform the simulation analysis of the entity difference of cellular automata, including:

[0050] Build dimensional space, where the dimension Corresponding to the differential dynamics equations Parameters in ;

[0051] According to the differential dynamics equation calculate Vectors of points in dimensional space , build dimensional vector field;

[0052] The topological structure of the vector field is used to analyze the macroscopic variable stability of the propagation state and the properties related to the sensitivity of the propagation parameters;

[0053] According to the differential dynamics equation Corresponding differential operator Construct cells and use cellular automata to simulate and analyze the properties related to entity differences, including but not limited to the structure of the communication network, entity differences in communication capabilities, and individual differences in information acceptance.

[0054] Another object of the present invention is to provide an information propagation prediction system, comprising:

[0055] A data collection unit, used to collect topic propagation data in social networks;

[0056] A data preprocessing unit, connected to the data acquisition unit, for completing data preprocessing;

[0057] An entity attribute and state variable construction unit, connected to the data preprocessing unit, for constructing entity attributes and state variables according to the preprocessed data;

[0058] A cellular automaton simulation unit, connected to the entity attribute and state variable construction unit, is used to perform cellular automaton simulation;

[0059] A differential propagation dynamics equation building unit is connected to the entity attribute and state variable building unit and is used to build the differential propagation dynamics equation according to the entity attribute and the state variable;

[0060] Vector field analysis unit, used to perform vector field analysis based on differential propagation dynamics equations;

[0061] Visualization unit, used to present simulation results and analyze data.

[0062] Combining all the above technical solutions, the advantages and positive effects of the present invention are as follows:

[0063] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving the problems, this paper closely combines the technical solutions to be protected by the present invention and the results and data in the research and development process, and analyzes in detail and in depth how the technical solutions of the present invention solve the technical problems, as well as some creative technical effects brought about after solving the problems.

[0064] Second, the method combines the subject model and differential equations to simulate individual behavior and group dynamics more accurately, improving the accuracy of predictions. The system can better evaluate the impact of different information dissemination methods and provide a scientific basis for adjusting the dissemination method.

[0065] Third, as auxiliary evidence of the inventiveness of the present invention, it is also reflected in the following important aspects:

[0066] (1) Multi-scale modeling capability: The ability to model at both the micro (individual) and macro (group) scales helps to understand dynamic processes at different scales.

[0067] (2) Flexibility and adaptability: The system can adjust according to new data or conditions and has high flexibility and adaptability to cope with the ever-changing environment.

[0068] In the information dissemination simulation scenario, the present invention can simulate the tendency change of information dissemination from different scales. The following are the steps for use in the information dissemination simulation scenario:

[0069] 1. Entity attribute definition (micro level): Define the entity attributes of each entity in the form of differential operators, including the scope of propagation influence, topic immunity rate, etc.

[0070] 2. Differential equation transformation (macro level): transform the differential operators representing entity properties into differential dynamics equations representing the overall dynamic characteristics.

[0071] 3. Definition of differential equations (macro level): Construct differential dynamics equations based on the overall dynamic characteristics of the propagation system.

[0072] 4. Entity attribute transformation (micro level): transform the differential dynamics equations representing the overall dynamic characteristics into differential operators representing entity attributes.

[0073] 5. Vector field analysis (macro level): Analyze the macroscopic variable stability of the propagation state and the properties related to the sensitivity of the propagation parameters through the topological structure of the vector field.

[0074] 6. Cellular automaton analysis (micro level): Analyze the properties related to entity differences through cellular automaton simulation, such as communication network structure, entity differences in communication capabilities, individual differences in information acceptance, etc.

[0075] Output simulation results: perform propagation simulation, and output the cellular automaton simulation process and the vector field analysis results of the dynamic equation. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 A schematic diagram of the flow of the information propagation prediction method described in this application;

[0077] Figure 2 Schematic diagram of the program running steps in the embodiment of the present application. DETAILED DESCRIPTION

[0078] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0079] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0080] The innovation of the information propagation prediction method provided by the embodiment of the present invention is that the method performs dynamic effective mapping from two aspects: specific entity indicators and overall statistical indicators, and realizes macro stability analysis and micro difference analysis at the same time. In this way, it is possible to take into account the content that is difficult to analyze with a single subject model or dynamic equation, making the analysis result more accurate.

[0081] Example 1: The information propagation prediction method provided by the embodiment of the present invention combines the differential dynamics equations at the macro level and the entity attributes and state variables at the micro level to simulate the system state and entity behavior of the information propagation evolution at different levels, thereby achieving macro stability analysis and micro difference analysis while ensuring the grasp of the propagation trend at the macro level and the effective mapping of the individual propagation behavior characteristics at the micro level. Figure 1 and Figure 2 As shown: The method comprises the following specific steps:

[0082] Step S01, constructing entity attributes and state variables according to topic propagation data in the social network, and completing data preprocessing, including:

[0083] Step S011, defining the state variables of each entity;

[0084] Step S012, defining the propagation environment state variables;

[0085] Step S013, defining relevant entity attributes by combining the environment state variables and the entity state variables.

[0086] Exemplarily, in step S011, the state variables of each entity are defined, including but not limited to:

[0087] For the purpose of defining information dissemination, collect information interaction relationships between entities through multi-level dissemination analysis ,in, Represents the entity involved in the propagation , Representing Entities and entities The information interaction between Representing Entities A collection of information interaction relationships with other entities involved in communication;

[0088] Calculate the forwarding rate of each entity to enhance the prediction ability ,in, Indicates the time after the topic starts to spread , Indicates the time from when the topic started to spread to when Time Entity Total number of reposts;

[0089] Define entity state variable collection , where the information interaction relationship set between entities Topic forwarding rate with entity is a collection of entity state variables subvariables of .

[0090] Exemplarily, in step S012, the environment state variable is defined , including but not limited to:

[0091] Give different weights to various information transmission and interaction methods on social platforms ;

[0092] is a set of environment state sub-variables, specifically .

[0093] Exemplarily, in step S013, the related entity attributes are defined in combination with the environment state variables and the entity state variables, including:

[0094] Defining Entities The entity attributes are ,in, Represents the entity attributes in the form of differential operators, Represents entity State variable collection and the set of environment state variables Jointly designated entities The entity attributes are as follows:

[0095] ,

[0096] in: Represents macro variables used to describe the state of the circled information dissemination, including but not limited to the total number of entities in the susceptible state and the total number of entities in the forwarding state; Represents each macro variable Corresponding to entity The sub-variables of Indicates the time after the topic starts to spread ; Indicates that Describe the macro variables corresponding to the entity The sub-variable The differential equations of the rate of change include but are not limited to the entity information receiving rate and the entity topic forwarding rate.

[0097] Step S02, in order to effectively map the entity attributes and state variables at the micro level to the differential dynamics equation at the macro level, the entity attributes and state variables are transformed into the differential dynamics equation parameters by using the method of transforming the cellular automaton state variables into differential operators and integrating, including:

[0098] Differential operator integral, according to the differential operator , define the differential dynamics equation as follows:

[0099] ,

[0100] in, represents the sum of entities affected by the dissemination of circled information, Represents an entity attribute that can be viewed as a continuous variable , The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the time after the topic starts to spread ;

[0101] Normalization of the kinetic equation variables is based on mapping all kinetic equation variables to The dynamic equations are treated in an interval manner.

[0102] Step S03, in order to effectively map the macro-level differential dynamics equation to the micro-level entity attributes and state variables, the method of using the dynamics equation parameters as differential operators to transform the differential dynamics equation parameters into entity attributes and state variables includes:

[0103] Definition of differential dynamics equations. Based on the propagation statistical characteristics, differential dynamics equations are defined. as follows:

[0104] ,

[0105] in, The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables used to describe the propagation state, Indicates the time after the topic starts to spread ;

[0106] right Derivative calculation differential operator , the specific calculation method is as follows:

[0107] ,

[0108] in, represents the sum of entities affected by the dissemination of circled information, Represents an entity attribute that can be viewed as a continuous variable , The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the time after the topic starts to spread ,like Known, then there is ;

[0109] Normalization of differential operator parameters is based on mapping all differential operator parameters to The differential operator is processed in an interval manner;

[0110] Through the differential operator Construct the cell.

[0111] Step S04, in order to simultaneously realize macroscopic stability analysis and microscopic difference analysis, a method of constructing a propagation state vector field using differential propagation dynamics equations is used to perform macroscopic variable stability and propagation parameter sensitivity analysis, and a method of constructing cells using differential operators is used to perform cellular automaton entity difference simulation analysis, including:

[0112] Build dimensional space, where the dimension Corresponding to the differential dynamics equations Parameters in ;

[0113] According to the differential dynamics equation calculate Vectors of points in dimensional space , build dimensional vector field;

[0114] The topological structure of the vector field is used to analyze the macroscopic variable stability of the propagation state and the properties related to the sensitivity of the propagation parameters;

[0115] According to the differential dynamics equation Corresponding differential operator Construct cells and use cellular automata to simulate and analyze the properties related to entity differences, including but not limited to the structure of the communication network, entity differences in communication capabilities, and individual differences in information acceptance.

[0116] An embodiment of the present invention also provides a computer-readable storage medium, on which computer program instructions are stored and which implement the steps of the method when executed.

[0117] The embodiment of the present invention also provides a computer device configured with software for executing the method.

[0118] The embodiment of the present invention further provides an information propagation prediction system, including:

[0119] A data collection unit, used to collect topic propagation data in social networks;

[0120] A data preprocessing unit, connected to the data acquisition unit, for completing data preprocessing;

[0121] An entity attribute and state variable construction unit, connected to the data preprocessing unit, for constructing entity attributes and state variables according to the preprocessed data;

[0122] A cellular automaton simulation unit, connected to the entity attribute and state variable construction unit, is used to perform cellular automaton simulation;

[0123] A differential propagation dynamics equation building unit is connected to the entity attribute and state variable building unit and is used to build the differential propagation dynamics equation according to the entity attribute and the state variable;

[0124] Vector field analysis unit, used to perform vector field analysis based on differential propagation dynamics equations.

[0125] The embodiment of the present invention also provides an information dissemination and display system, including a user interface for displaying simulation results and analysis data.

[0126] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. A person of ordinary skill in the art will appreciate that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0127] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for predicting information propagation, characterized in that: The specific steps include: Construct entity attributes and state variables based on the platform environment and propagation data in the social network to complete data preprocessing; The entity attributes and state variables are transformed into parameters of differential dynamics equations by using the method of transforming cellular automata state variables into differential operators and integrating them. The method of using the parameters of the dynamics equation as differential operators is adopted to transform the parameters of the differential dynamics equation into entity attributes and state variables; The differential propagation dynamics equation is used to construct the propagation state vector field to analyze the stability of macro variables and the sensitivity of propagation parameters. The differential operator is used to construct cells to simulate the entity difference of cellular automata. The method of constructing the propagation state vector field by using differential propagation dynamics equations to analyze the stability of macro variables and the sensitivity of propagation parameters, and the method of constructing cells by using differential operators to perform entity difference simulation analysis of cellular automata, include: Build The dimension space is , , where the dimension Corresponding to the differential dynamics equations represents the macro variables describing the propagation state; According to the differential dynamics equation calculate Vectors of points in dimensional space , build dimensional vector field; The topological structure of the vector field is used to analyze the macroscopic variable stability of the propagation state and the properties related to the sensitivity of the propagation parameters; According to the differential dynamics equation Corresponding differential operator Construct cells and use cellular automata to simulate and analyze properties related to entity differences, including communication network structure, entity differences in communication capabilities, and individual differences in information acceptance.

2. The information propagation prediction method according to claim 1, characterized in that: The data preprocessing is completed, including: Define state variables for each entity; Define the propagation environment state variables; Combine the environment state variables with the entity state variables to define related entity attributes.

3. The information propagation prediction method according to claim 2, characterized in that: The state variables of each entity are defined as follows: Targeting information dissemination, through multi-level dissemination analysis, collect information interaction relationships between entities ,in, Represents the entity involved in the propagation , Representing Entities and entities The information interaction between Representing Entities A collection of information interaction relationships with other entities involved in communication; Calculate the topic forwarding rate of each entity ,in, Indicates the time after the topic starts to spread. Indicates the time from when the topic started to spread to when Time Entity Total number of reposts; Define entity state variable collection , where the information interaction relationship set between entities Topic forwarding rate with entity is a collection of entity state variables subvariables of .

4. The information propagation prediction method according to claim 2, characterized in that: The definition of the propagation environment state variable specifically includes: Give different weights to various information transmissions on social platforms ,in, Represents different weight sets of information transmission, Indicates the weights corresponding to different delivery methods; Give different weights to different interaction methods on social platforms ,in, represents a set of weights with different interaction modes, Indicates the weights corresponding to different interaction modes; Define a collection of environment state variables , where information transfer has different weights Different weights for interaction A collection of environment state variables subvariables of .

5. The information propagation prediction method according to claim 2, characterized in that: The combining of the environment state variables and the entity state variables to define the related entity attributes includes: Defining Entities The entity attributes are ,in, Represents entity State variable collection and the set of environment state variables Jointly designated entities The entity attributes are as follows: ， in: Represents macro variables describing the propagation state, including the total number of entities in the susceptible state and the total number of entities in the forwarding state; Represents each macro variable Corresponding to entity The sub-variables of Indicates the moment after the topic starts to spread; Indicates that Describe the macro variables corresponding to the entity The sub-variable The differential equation group of the change rate includes the entity information receiving rate and the entity topic forwarding rate.

6. The information propagation prediction method according to claim 1, characterized in that: The method of transforming the state variables of cellular automata into differential operators and integrating them to transform the entity attributes and state variables into parameters of differential dynamics equations includes: Differential operator integral, according to the differential operator , define the differential dynamics equation as follows: ， in, represents the sum of entities affected by the dissemination of circled information, represents entity attributes treated as continuous variables, The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the moment after the topic starts to spread; Normalization of the kinetic equation variables is based on mapping all kinetic equation variables to The dynamic equations are treated in an interval manner.

7. The information propagation prediction method according to claim 6, characterized in that: The method of using the dynamic equation parameters as differential operator transformation to transform the differential dynamic equation parameters into entity attributes and state variables includes: Define the differential dynamics equation. According to the propagation statistics, define the differential dynamics equation as follows: ， in, The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the moment after the topic starts to spread; right Derivative calculation differential operator , the specific calculation method is as follows: ， in, represents the total number of entities affected by the circled information, represents entity attributes treated as continuous variables, The system of differential equations representing the rate of change of macroscopic variables describing the propagation state, represents the macro variables describing the propagation state, Indicates the time after the topic starts to spread. If Known, then there is ; Normalization of differential operator parameters is based on mapping all differential operator parameters to The differential operator is processed in an interval manner; Through the differential operator Construct the cell.

8. A readable storage medium for executing the information propagation prediction method according to any one of claims 1 to 7, characterized in that: The readable storage medium comprises computer program instructions, which are stored on the computer readable storage medium and implement the steps of the information propagation prediction method according to any one of claims 1 to 7 when executed.

9. A system using the information propagation prediction method according to any one of claims 1 to 7, characterized in that: include: A data collection unit, wherein the data collection unit is used to collect topic propagation data in the social network; A data preprocessing unit, the data preprocessing unit is connected to the data acquisition unit and is used to complete data preprocessing; An entity attribute and state variable construction unit, which is connected to the data preprocessing unit and is used to construct entity attributes and state variables according to the preprocessed data; A cellular automaton simulation unit, wherein the cellular automaton simulation unit is connected to the entity attribute and state variable construction unit and is used for performing cellular automaton simulation; A differential propagation dynamics equation construction unit, wherein the differential propagation dynamics equation construction unit is connected to the entity attribute and state variable construction unit and is used to construct the differential propagation dynamics equation according to the entity attribute and the state variable; A vector field analysis unit, wherein the vector field analysis unit is used to perform vector field analysis according to differential propagation dynamics equations; A visualization unit is used to display simulation results and analyze data.

Images