CN118410242A

CN118410242A - Method and device for tracing the source of public opinion, electronic device and storage medium

Info

Publication number: CN118410242A
Application number: CN202310156491.8A
Authority: CN
Inventors: 张欣; 王丽娟; 张悦欣; 刘道广; 沐雅琪
Original assignee: Xuzhou College of Industrial Technology
Current assignee: Xuzhou College of Industrial Technology
Priority date: 2023-02-23
Filing date: 2023-02-23
Publication date: 2024-07-30

Abstract

The present disclosure relates to a method and device for tracing the source of public opinion, an electronic device and a storage medium, and relates to the technical field of tracing the source of public opinion. The method for tracing the source of public opinion includes: obtaining the local social network corresponding to the public opinion, and generating an infection subgraph based on the local social network; establishing a search tree based on the infection subgraph; using the search tree to calculate the propagation center value corresponding to the node and the prior estimation value corresponding to the node; tracing the public opinion according to the propagation center value and the prior estimation value, and determining the source node of the public opinion propagation. The embodiments of the present disclosure can realize the tracing of public opinion.

Description

Public opinion tracing method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of public opinion tracing, in particular to a method and a device for public opinion tracing, electronic equipment and a storage medium.

Background

Along with the increasing popularization and rapid development of the Internet, the life of people is greatly changed, the time cost and social cost of the life of people are greatly reduced by the aid of the online communication function which is more convenient, and the dependence of people on social networks is gradually increased. Social networks were initially the only platform to acquire information and resources, and have now become a continuation of life and emotion. However, many netizens have not just simply obtained information and resources through social networks, but rather have more active information creation and propagation. Meanwhile, along with the increase of information transmission quantity in the network, false public opinion information for achieving a certain negative influence also appears, but because the development and use speed of the social network are too high, the threshold of information release by users is lower, the editing and transmission modes are simpler and simpler, and the dependence of people on the network is more serious, so that the supervisor cannot effectively supervise all the information in the social network in time, and the social network also becomes a hotbed for the propagation of the network public opinion information. If a false public opinion information is left to be transmitted wantonly in the network and is not controlled, the false public opinion information can cause the public to be panicked and cause subsequent public trust crisis events, and bad social influence is caused.

The information propagated in a social network may be divided into positive and negative guide information. In particular, the unverified negative guide information can be used for exciting the interest of people after being subjected to deliberate exaggeration modification, and can always be transmitted with a certain scale and a certain heat degree. For example, in 2022, the widely-flowing "Tencent cloud database leaks", "dead birds can transmit simian poxviruses", "0 sucrose is sugar-free", and other false public opinion information, which can be rapidly transmitted in the crowd, and can cause confusion. Although the post-related departments and related institutions perform refute a rumour processing on the public opinion information, the post-related departments and related institutions still have adverse effects on the network, and even the development of social public welfare and economy can be possibly affected.

In the real world, when a user receives a false opinion information, the user may choose to trust or not trust. If the user does not believe that the piece of information is discarded directly, but if the user believes that the piece of information is transmitted to friends and relatives of the user, a certain probability exists, so that the transmission direction in the social network is characterized by multi-directionality and randomness.

Based on the above, a technical scheme of public opinion tracing is to be provided to solve the problem that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welcome and economy.

Disclosure of Invention

The disclosure provides a public opinion tracing method and device, electronic equipment and a storage medium technical scheme.

According to an aspect of the present disclosure, there is provided a public opinion tracing method, including:

Obtaining local social networks corresponding to public opinion, and generating an infection subgraph based on the local social networks;

establishing a search tree based on the infection subgraph;

calculating a propagation center value corresponding to a node by using the search tree and a priori estimated value corresponding to the node;

And tracing the public opinion according to the propagation center value and the prior estimated value, and determining a source node of the public opinion propagation.

Preferably, before the local social network corresponding to the public opinion is obtained, establishing the local social network corresponding to the public opinion includes:

Acquiring a user under preset information and address information;

And establishing the local social network corresponding to the public opinion based on the local social network.

Preferably, the method for generating an infection subgraph based on the local social network comprises the following steps:

Configuring infection probability for nodes of the local social network;

determining whether a node of the local social network is infected based on a set propagation round;

If yes, determining the infected node as an infected node, and generating an infected subgraph based on an infected node set constructed by the infected node and a corresponding adjacency matrix.

Preferably, the method for establishing the search tree based on the infection subgraph comprises the following steps: and determining a root node of the infected subgraph, and establishing a search tree based on the root node.

Preferably, the method for calculating the propagation center value corresponding to the node and the prior estimated value corresponding to the node by using the search tree includes:

Based on the search tree, respectively calculating a first probability value corresponding to the infected sub-graph under the node and a second probability value corresponding to the node;

and respectively configuring the first probability value and the second probability value as a propagation center value and a priori estimated value corresponding to the node.

Preferably, the method for tracing the public opinion according to the propagation center value and the prior estimation value to determine the source node of the public opinion propagation includes:

Determining the traceability probability of the node based on the propagation center value and the prior estimated value;

and tracing the public opinion according to the tracing probability and the set tracing probability to determine the source node of the public opinion propagation.

Preferably, the method for determining the traceability probability of the node based on the propagation center value and the prior estimated value comprises the following steps: and multiplying the propagation center value by the prior estimated value to determine the traceability probability of the node.

According to an aspect of the present disclosure, there is provided a public opinion tracing apparatus, including:

The generation unit is used for acquiring local social networks corresponding to public opinion and generating an infection subgraph based on the local social networks;

the establishing unit is used for establishing a search tree based on the infection subgraph;

the computing unit is used for computing a propagation center value corresponding to a node and a priori estimated value corresponding to the node by utilizing the search tree;

and the tracing unit is used for tracing the public opinion according to the propagation center value and the prior estimated value and determining a source node of the public opinion propagation.

According to an aspect of the present disclosure, there is provided an electronic apparatus including:

A processor;

a memory for storing processor-executable instructions;

Wherein the processor is configured to: executing the public opinion tracing method.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method of public opinion tracing.

In the embodiment of the disclosure, a public opinion tracing method and device, electronic equipment and storage medium technical scheme are provided to solve the problem that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welfare and economy.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.

FIG. 1 illustrates a method flow diagram for public opinion tracing according to an embodiment of the present disclosure;

FIG. 2 illustrates a local social network structure diagram in accordance with an embodiment of the present disclosure;

FIG. 3 illustrates a tracing algorithm flow chart according to an embodiment of the disclosure;

fig. 4 shows a block diagram of a public opinion tracing device according to an embodiment of the present disclosure;

FIG. 5 illustrates a detection rate analysis graph according to an embodiment of the present disclosure;

FIG. 6 illustrates an error distance analysis graph according to an embodiment of the present disclosure;

FIG. 7 is a block diagram of an electronic device 800, shown in accordance with an exemplary embodiment;

fig. 8 is a block diagram illustrating an electronic device 1900 according to an example embodiment.

Detailed Description

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

It will be appreciated that the above-mentioned method embodiments of the present disclosure may be combined with each other to form a combined embodiment without departing from the principle logic, and are limited to the description of the present disclosure.

In addition, the disclosure further provides a public opinion tracing device, an electronic device, a computer readable storage medium and a program, which can be used for implementing any public opinion tracing method provided by the disclosure, and corresponding technical schemes and descriptions and corresponding descriptions of method parts are omitted.

In the embodiments of the present disclosure and other possible embodiments, a social network in which each person is located is extracted to be a local social network with a smaller scale, a user is abstracted to be a node in the local social network, and friends and relatives of a certain user are neighbor nodes in the local social network, so that a local social network structure obtained by expanding each user as a root node is obtained. For a piece of public opinion information, it is assumed that a node has two states of belief and non-belief, and no designated transmission direction exists between the nodes, namely the public opinion information is transmitted in an undirected network, and an SI model (infectious disease transmission model) is adopted to simulate the diffusion of the public opinion information, so that the effectiveness of a public opinion tracing algorithm is verified.

Fig. 1 shows a flowchart of a method for public opinion tracing according to an embodiment of the disclosure, as shown in fig. 1, the method for public opinion tracing includes: step S101: obtaining local social networks corresponding to public opinion, and generating an infection subgraph based on the local social networks; step S102: establishing a search tree based on the infection subgraph; step S103: calculating a propagation center value corresponding to a node by using the search tree and a priori estimated value corresponding to the node; step S104: and tracing the public opinion according to the propagation center value and the prior estimated value, and determining a source node of the public opinion propagation. The method solves the problems that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welfare and economy.

Step S101: and obtaining local social networks corresponding to the public opinion, and generating an infection subgraph based on the local social networks.

In an embodiment of the present disclosure, before the obtaining the local social network corresponding to the public opinion, establishing the local social network corresponding to the public opinion includes: acquiring a user under preset information and address information; and establishing the local social network corresponding to the public opinion based on the local social network. The address information of the user can be configured as IP address information of the user, and the preset information can be configured as web page information corresponding to a browsing address of the user.

In an embodiment of the present disclosure and other possible embodiments, a method for establishing a local social network corresponding to the public opinion based on the address information and the setting information is provided, and the method further optimizes a user for constructing the local social network, including: determining potential users by using the address information of the users; and selecting the potential users by utilizing the preset information to obtain the end users for constructing the local social network.

In the embodiments of the present disclosure and other possible embodiments, the preset information may be configured as interest information of the user. For example, users who have a common interest, or who are co-located in a local area network, may abstract them as a local social network. However, after the preset information is configured as the interest information of the user, the local social network corresponding to the established public opinion is relatively single, and the corresponding user may be omitted or absent, so that the establishment of a relatively perfect local social network is insufficient.

In an embodiment of the present disclosure and other possible embodiments, before acquiring preset information, a method for determining the preset information includes: acquiring webpage information corresponding to browsing addresses of a plurality of network users in a set time period; extracting characters and images corresponding to the webpage information; identifying the image to obtain corresponding image content information; constructing an information vector to be processed based on the image information and the characters; and determining or selecting the preset information from the information vector to be processed by utilizing a preset target variable based on the information vector to be processed. And determining the preset target variable according to the public opinion content. For example, if the public opinion content is "0 sucrose is sugar-free", then "0 sucrose is sugar-free" is determined as the preset target variable. Further, the preset target variable may be configured as 0 or 1, for example, the preset target variable determined by "0 sucrose is sugar-free" is configured as 1, and other preset target variables corresponding to "0 sucrose is sugar-free" are configured as 0.

In an embodiment of the present disclosure and other possible embodiments, the method for identifying the image information to obtain corresponding image content information includes: identifying the image based on a preset image information extraction model to obtain corresponding image content information; wherein the image content information may include: the location or content or profile to which the image relates, etc. The preset image information extraction model can be configured to be a hundred-degree browser-based picture identification module or other image information extraction models.

In an embodiment of the present disclosure and other possible embodiments, the method for constructing an information vector to be processed based on the image information and the text includes: word segmentation is carried out on the image information and texts formed by the characters, so that a word list is obtained; based on a preset word vector model, converting each word in the word list into a word vector, and constructing an information vector to be processed from all the word vectors.

In the embodiment of the disclosure and other possible embodiments, the image information and the text formed by the characters are segmented to obtain a segmentation tool (e.g., jieba segmentation tool) of a word list and a custom dictionary in the segmentation tool, a stop word list is set, the stop word list is used for filtering the medical record text stop word, and the stop word can be added into the existing stop word list according to specific scenes to set the word to be removed. Stop words, such as mood words, auxiliary words, and/or punctuation marks. The word list is obtained after the image information and the text formed by the characters pass through a word segmentation tool, and the word list is a list with a plurality of words.

In embodiments of the present disclosure and other possible embodiments, the pre-set word vector model may select existing models, such as word2vec models and GloVe models, and train the word2vec models and GloVe models. And then converting each word in the word list into a word vector by using a trained preset word vector model.

In the embodiments of the present disclosure and other possible embodiments, the method for determining or selecting the preset information from the information vector to be processed by using a preset target variable based on the information vector to be processed includes: acquiring a preset selection model; and determining or selecting the preset information from the information vector to be processed by utilizing a preset target variable based on the preset selection model.

Wherein, in the embodiments of the present disclosure and other possible embodiments, the preset selection model may be configured as a model for executing a Lasso (Least accept SHRINKAGE AND selection operator, lasso) algorithm and/or a GLM (Generalized linear model, GLM) model (generalized linear model).

In embodiments of the present disclosure and other possible embodiments, the Lasso algorithm has been an effective means of feature selection by compressing the variable with a large parameter estimate to a small value of 0. The mathematical expression corresponding to the Lasso algorithm is shown as a formula (1).

In formula (1), x _ij represents an independent variable, namely the normalized information vector to be processed, y _i represents a preset target variable (0 or 1), λ represents a penalty parameter (λ is equal to or greater than 0), β _j represents a regression coefficient, i e [1, n ], j e [0, p ].

In embodiments of the present disclosure and other possible embodiments, the GLM model establishes a relationship between a mathematical expectation of a response variable and a linearly combined predicted variable through a join function. Unlike the Lasso algorithm, GLM can make feature selection by calculating the R ² value of each argument x _ij (feature). The mathematical expression of GLM is shown as formula (2).

Wherein the connection function g (μ _yi) =η will average μ _yi＝E(y_i) with the linear predictorEstablishing a connection; y _i represents a preset target variable (0 or 1); x _ij represents an argument, i.e., the normalized information vector to be processed; beta _j represents regression coefficients; i e [1, n ], j e [0, p ].

In an embodiment of the present disclosure and other possible embodiments, a preset information determining method based on a multi-preset selection model decision is provided. Specifically, the method for determining or selecting the preset information from the information vector to be processed by using a preset target variable based on the information vector to be processed comprises the following steps: acquiring a plurality of preset selection models; determining or selecting a plurality of groups of preset information from the information vector to be processed by utilizing preset target variables based on the plurality of preset selection models respectively; and determining final preset information based on the plurality of sets of preset information.

In an embodiment of the present disclosure and other possible embodiments, the method for determining final preset information based on the multiple sets of preset information includes: comparing element information in the plurality of sets of preset information; if the same element information exists, the same element information is configured to the preset information.

For example, a model for executing the Lasso algorithm and a GLM model (generalized linear model) are determined or selected from the information vectors [ a, b, c, d, e, f, g, h, i, j, k ] to be processed, respectively, resulting in a first set of preset information [ a, b, c, g, h, i ] and a second set of preset information [ b, c, d, e, i, j, k ]. Comparing element information in the first set of preset information and the second set of preset information; if the same element information [ b, c, i ] exists, the same element information [ b, c, i ] is configured to the preset information.

In the embodiments of the present disclosure and other possible embodiments, after the preset information has been determined by the above method, the user under the preset information and the address information (preset address information) may be obtained; and establishing the local social network corresponding to the public opinion based on the local social network.

More specifically, in the embodiments of the present disclosure and other possible embodiments, first, web page information corresponding to a user browsing address of preset address information within a set period of time is obtained; extracting characters and images corresponding to the webpage information; identifying the image to obtain corresponding image content information; constructing an information vector to be processed based on the image information and the characters; and if the information vector to be processed contains the preset information, determining the user as the user for establishing the local social network corresponding to the public opinion. For example, the information vector to be processed is [ a, b, c, d, e, f, g, h, i, j, k, o, p, q, z ], and the preset information is configured as [ b, c, i ], and then the user is determined to be the user for establishing the local social network corresponding to the public opinion.

In embodiments of the present disclosure and other possible embodiments, there is further provided a method for determining a user for establishing a local social network corresponding to the public opinion based on artificial intelligence technology, including: acquiring a preset classification model and an information vector to be processed (an information vector to be processed) corresponding to a user under preset address information; and determining the user for establishing the local social network corresponding to the public opinion by using the information vector to be processed (the information vector to be processed) based on the preset classification model.

In embodiments of the present disclosure and other possible embodiments, the preset classification model may be configured as a machine learning (MACHINE LEARNING, ML) classification model. For example, the classification model may include: support vector machine, decision tree, random forest, K neighbor, logistic regression, self-adaptive enhancement, linear discriminant analysis and multi-layer perceptron.

In an embodiment of the disclosure and other possible embodiments, the preset classification model is configured as a trained classification model, and before determining the user for establishing the local social network corresponding to the public opinion by using the information vector to be processed (information vector to be processed) based on the preset classification model, the preset classification model is trained by using information vectors to be processed (information vectors to be processed) corresponding to a plurality of network users and corresponding preset target variables, so as to obtain the preset classification model. Wherein the target variable is configurable to be 0 or 1; wherein, 1 represents a user who needs to be used for establishing a local social network corresponding to the public opinion; 0 denotes a user who does not need to establish a local social network corresponding to the public opinion.

In an embodiment of the present disclosure and other possible embodiments, the method for determining a user for establishing a local social network corresponding to the public opinion using the information vector to be processed (information vector to be processed) based on the preset classification model further includes: acquiring preset information; extracting corresponding preset information from an information vector to be processed (an information vector to be processed) of the user; and determining the user for establishing the local social network corresponding to the public opinion by utilizing the preset information based on the preset classification model.

Obviously, before determining the user for establishing the local social network corresponding to the public opinion by using the preset information based on the preset classification model, training the preset classification model by using preset information corresponding to a plurality of network users and corresponding preset target variables to obtain the preset classification model.

In an embodiment of the present disclosure and other possible embodiments, the method for determining a user for establishing a local social network corresponding to the public opinion based on the preset classification model and using the preset information includes: information fusion is carried out on the preset information to obtain fusion information; and determining the user for establishing the local social network corresponding to the public opinion by utilizing the preset information and the fusion information based on the preset classification model.

Obviously, before determining the user for establishing the local social network corresponding to the public opinion by using the preset information based on the preset classification model, training the preset classification model by using the preset information, the fusion information and the corresponding preset target variable corresponding to a plurality of network users to obtain the preset classification model.

In an embodiment of the present disclosure and other possible embodiments, the method for fusing information to obtain fused information includes: acquiring a set information fusion model; and based on the set information fusion model, carrying out information fusion on the preset information to obtain fusion information.

In embodiments of the present disclosure and other possible embodiments, the set information fusion model is an information fusion model configured to be based on a principal component analysis (PRINCIPAL COMPONENT ANALYSIS, PCA) algorithm and/or a neural network model. Wherein the neural network model may be configured as a conventional artificial neural network or a convolutional neural network. For example, a conventional artificial neural network may be a BP neural network. Wherein, the BP neural network at least comprises: an input layer, an hidden layer and an output layer; the BP neural network can be trained by using preset information corresponding to a plurality of network users, and information fusion is performed on the preset information corresponding to the users by using the trained BP neural network.

In the local social network, users can be abstracted into different nodes, and the interaction relationship among the users represents that a connection relationship exists between two nodes. When public opinion information is transmitted in the local social network, the source node can be quickly positioned by using a tracing algorithm, and negative influence of the public opinion information on the network is minimized. Therefore, when performing the traceability calculation, an infection network needs to be constructed according to the structure of the local social network and the infected node set. And a tracing algorithm is applied to an infection network to quickly and accurately position the source node.

In a local social network, each edge connects two nodes, which can be represented by equation (3).

Wherein E represents a set of connected edges in the network, V represents a set of nodes in the network, and i and j represent different nodes in the network respectively. The local social network connection edge relationship obtained by the formula (1) can form an adjacency matrix so as to calculate.

Converting the local social network structure into a adjacency matrix can be represented as equation 4). In equation (4), if a ₁₂ =1 table has a connection relationship between node 1 and node 2 in the network environment, mapping to the real world represents that there is a connection between two users, which may be friends, classmates, etc.

Taking a classical infectious disease transmission model-an SI model as an example, S represents a susceptible person and is a user easy to be infected by diseases; i represents an infected person, and refers to a user who has been infected, and a patient in the I state has a certain probability to infect other users in the S state. In the field of information dissemination, infectious disease models are often employed to analogize the information dissemination process. In a local social network, for a piece of information, a node is in one of two states of belief and not belief, wherein belief is that the node is infected, and corresponds to an I state in an SI model; "not believed" means that this node is not infected, is in a susceptible state, and corresponds to the S state in the SI model. After public opinion information is transmitted in the local social network, the nodes in an infected state transmit infection to the surrounding nodes, and the local infection network is formed after a certain time step. Therefore, the node in the infected state at the initial time is a core node of the infected network, and other nodes in the infected network are all caused by the infection of the node, so that the importance of the node of the core node in the network is higher than that of other infected nodes. Since information propagation is characterized by randomness in the network, the propagation process is modeled by taking a native network containing 10 nodes as an example.

FIG. 2 illustrates a local social network structure diagram in accordance with an embodiment of the present disclosure. As shown in fig. 2, fig. 2 (a) represents a native network at a certain moment, where node No. 2 represents that the node is in an infected state, and the other nodes are in a susceptible state. When public opinion information starts to be transmitted by the No. 2 node, the No. 6, 8 and 10 nodes are infected in the first infection round t ₁; the second round t ₂ continuously infects nodes 1 and 4 on the basis of the infected nodes in the round t ₁; the third round t ₃ continues to infect node 7 after the two infection rounds described above. Thus, after three rounds of infection, the network shown in fig. 2 (a) sequentially infects nodes 6, 10, 1, 8, 4 and 7 in the network, and finally an infected network with a result of fig. 2 (b) is obtained. According to the features of the SI propagation model, in the network shown in fig. 2, if a node is infected, the node will be in an infected state all the time and will not be infected again.

In fig. 2, the information propagation process in the local social network can be known, and in order to summarize the calculation flow of the public opinion algorithm, the following public opinion tracing steps can be listed.

Step one: initialization processing stage: and acquiring a data set, preprocessing the data, and constructing a local social network G. At this time, the network G is a native network, and all nodes are in an easy-to-infect state, and have a certain probability of being infected.

Step two: information propagation stage: within a certain propagation round, a set of infected nodes is constructed. If the node is infected, it is added to the infected node set S _I. And after information transmission is stopped, obtaining all infected nodes and an infected sub graph G _I according to the infected node set and the adjacency matrix.

In an embodiment of the present disclosure, the method for generating an infection subgraph based on the local social network includes: configuring infection probability for nodes of the local social network; determining whether a node of the local social network is infected based on a set propagation round; if yes, determining the infected node as an infected node, and generating an infected subgraph based on an infected node set constructed by the infected node and a corresponding adjacency matrix.

In embodiments of the present disclosure and other possible embodiments, the infection probability may be configured as an easy-to-infect state, or an infection probability corresponding to an easy-to-infect state.

Step three: and (3) a calculation stage: and calculating by adopting a tracing algorithm according to the result in the infection subgraph G _I to obtain a final information tracing result.

The idea of the public opinion tracing algorithm (KRC) is as follows: according to the infection subgraph G _I induced in the original network G, a breadth-first search tree T _bfs (v) taking a node v as a root node is constructed on the basis of G _I, and then a tracing operation is carried out. The KRC algorithm calculation flow is shown in FIG. 3.

Fig. 3 shows a flowchart of a tracing algorithm according to an embodiment of the disclosure. As shown in fig. 3, in step S101: after obtaining the local social network corresponding to the public opinion and generating the infection subgraph based on the local social network, step S102: and establishing a search tree based on the infection subgraph.

In an embodiment of the present disclosure, the method for building a search tree based on the infection subgraph includes: and determining a root node of the infected subgraph, and establishing a search tree based on the root node. In embodiments of the present disclosure and other possible embodiments, establishing a search tree based on the root node may be a breadth-first search tree established based on the root node.

Step S103: and calculating a propagation center value corresponding to the node by using the search tree and a priori estimated value corresponding to the node.

In an embodiment of the present disclosure, the method for calculating a propagation center value corresponding to a node and an a priori estimated value corresponding to the node by using the search tree includes: based on the search tree, respectively calculating a first probability value corresponding to the infected sub-graph under the node and a second probability value corresponding to the node; and respectively configuring the first probability value and the second probability value as a propagation center value and a priori estimated value corresponding to the node.

Step S104: and tracing the public opinion according to the propagation center value and the prior estimated value, and determining a source node of the public opinion propagation.

In an embodiment of the disclosure, the method for tracing the public opinion according to the propagation center value and the prior estimated value to determine a source node of the public opinion propagation includes: determining the traceability probability of the node based on the propagation center value and the prior estimated value; and tracing the public opinion according to the tracing probability and the set tracing probability to determine the source node of the public opinion propagation. Wherein, the person skilled in the art can set the setting traceability probability according to actual needs.

In the embodiments of the present disclosure and other possible embodiments, the method for tracing the public opinion according to the tracing probability and the set tracing probability to determine a source node of the public opinion propagation includes: if the traceability probability is larger than or equal to the set traceability probability, determining a source node of the public opinion propagation by a node corresponding to the set traceability probability; otherwise, the node corresponding to the set traceability probability determines the non-source node of the public opinion propagation.

In an embodiment of the disclosure, the method for determining the traceability probability of the node based on the propagation center value and the a priori estimate value includes: and multiplying the propagation center value by the prior estimated value to determine the traceability probability of the node.

The calculation flow of fig. 3 realizes a tracing algorithm based on an SI information propagation model, and can quickly locate a source node of public opinion propagation through tracing calculation, further process the source node in a network, purify the user internet environment, and provide powerful guarantee for information security in the network.

The execution subject of the public opinion tracing method may be a public opinion tracing device, for example, the public opinion tracing method may be executed by a terminal device or a server or other processing device, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and so on. In some possible implementations, the method of public opinion tracing may be implemented by a processor invoking computer readable instructions stored in a memory.

It will be appreciated by those skilled in the art that in the above-described public opinion tracing method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possible inherent logic of each step.

Fig. 4 shows a block diagram of a public opinion tracing device according to an embodiment of the disclosure, as shown in fig. 4, the public opinion tracing device includes: a generating unit 101, configured to obtain a local social network corresponding to public opinion, and generate an infection subgraph based on the local social network; an establishing unit 102, configured to establish a search tree based on the infection subgraph; a calculating unit 103, configured to calculate a propagation center value corresponding to a node and an a priori estimated value corresponding to the node using the search tree; and the tracing unit 104 is configured to trace the public opinion according to the propagation center value and the prior estimation value, and determine a source node of the public opinion propagation. The method solves the problems that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welfare and economy.

In some embodiments, the functions or modules included in the apparatus provided by the embodiments of the present disclosure may be used to perform the public opinion tracing method described in the above method embodiments, and specific implementation of the public opinion tracing method may refer to the description of the above method embodiments, which is not repeated herein for brevity.

The embodiment of the disclosure also provides a computer readable storage medium, on which computer program instructions are stored, which when executed by a processor, implement the above-mentioned public opinion tracing method. The computer readable storage medium may be a non-volatile computer readable storage medium. The method solves the problems that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welfare and economy.

The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing processor-executable instructions; the processor is configured as the public opinion tracing method. The method solves the problems that the current public opinion information has adverse effect on the network and possibly even affects the development of social public welfare and economy. Wherein the electronic device may be provided as a terminal, server or other modality of device.

In order to verify the effectiveness of the traceability algorithm, a simulation comparison experiment is designed for verification. The comparison method adopts representative methods in the current traceability field, namely a distance centrality algorithm (DC), a Jordan centrality algorithm (JC) and a propagation centrality algorithm (RC). During the experiment, SI model was used to simulate information propagation, representing that nodes in the network can only be in an infected state (I state) and a susceptible state (S state). Under this model, an infected node will always be in an infected state and will continue to infect its neighbors with a certain probability. Meanwhile, three representative networks are selected for simulation experiments, namely an artificial network SCALE-FREE, a real network HARM and a POWER-GRID. The details of the three networks are shown in table 1.

Table 1 network information table

The method selects three representative networks, and the number of nodes and the number of connecting edges of the three representative networks accord with the characteristics of the local area network, so that experimental results are more convincing.

To evaluate the effectiveness of a traceability algorithm, the traceability Detection Rate (Detection Rate) and the error distance (Error Hops) are generally used for measurement. The calculation mode of the tracing detection rate can be expressed as follows by adopting the formula (5):

In the above formula, M represents the total number of times of tracing calculation, and MT represents the number of times of monitoring the real source node. Therefore, if the value of the detection rate is larger, the accuracy of the tracing method is higher.

The error distance can be calculated by the following equation (6):

ErrorHops＝d(v₁,v₂) (6)

in the above formula, v ₁ represents a source node calculated by a tracing algorithm, and v ₂ represents a real source node in the network. The error distance represents the difference between the two. Therefore, if the value of the error distance is smaller, the smaller the distance between the source node calculated by the tracing method and the real source node in the network is, the higher the accuracy of the tracing result is.

Fig. 5 shows a detection rate analysis graph according to an embodiment of the present disclosure. As shown in fig. 4, the four algorithms detect changes in rate as the number of infected nodes increases in three networks, SCALE-FREE, HARM, and POWER-GRID. In the experimental process, in order to overcome the randomness of the calculation result, each group of data is obtained by 1000 times of averaging calculation through information transmission model infection. As can be seen from the graph, as the network scale and the number of infected nodes increase, the accuracy of all calculation methods is in a decreasing trend, but the overall performance of the KRC algorithm is still better than that of other algorithms.

Notably, in the POWER-GRID network, the detection rate of all algorithms is lower than that of other networks, and analysis finds that this is due to the characteristics of the network itself. The POWER-GRID is a sparse network, and after a certain number of nodes in the network are infected, other nodes in the network are difficult to be infected again due to the sparse characteristic of the sparse nodes, so that the problem of low detection rate is caused. However, as can be seen from the experimental results, the KRC algorithm performs better than other algorithms despite the different network densities.

FIG. 6 illustrates an error distance analysis graph according to an embodiment of the present disclosure. Likewise, in the POWER-GRID network, the error distance of all algorithms is higher than that of other networks, since details are already made at the detection rate analysis and therefore will not be described here.

Experimental results combining the traceability detection rate and the error distance show that in a local area network, the traceability algorithm KRC provided herein has the advantages of high accuracy and smaller error distance.

The method focuses on a local social network, aims at the current situation that the existing algorithm is insufficient in analysis of network structural characteristics, and therefore the accuracy of a tracing result is low, analyzes structural characteristics of the local social network and characteristics of nodes, provides an information tracing algorithm integrating prior estimation and posterior estimation, and overcomes the defects of the existing tracing algorithm. After information propagates in a network for a certain time step, sorting and processing according to the importance values of the infected nodes in the infected network snapshot, and taking the sorted information as the priori estimation of the traceability algorithm; and then, adopting a propagation centrality algorithm as posterior estimation to obtain an information traceability algorithm integrating the prior estimation and the posterior estimation. And through multi-dimensional comparison experiments, the algorithm designed in the method is superior to other algorithms in terms of both detection rate and error distance.

Therefore, the public opinion tracing algorithm which is designed in the text and integrates the prior estimation and the posterior estimation can be considered to be applied to the real local social network, and the source point of the public opinion information transmitted in the local social network can be accurately locked and managed, so that the network environment is purified, and the network security is maintained.

Fig. 7 is a block diagram of an electronic device 800, according to an example embodiment. For example, electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 7, an electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the method of public opinion tracing described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen between the electronic device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the electronic device 800. For example, the sensor assembly 814 may detect an on/off state of the electronic device 800, a relative positioning of the components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in position of the electronic device 800 or a component of the electronic device 800, the presence or absence of a user's contact with the electronic device 800, an orientation or acceleration/deceleration of the electronic device 800, and a change in temperature of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices, either wired or wireless. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including computer program instructions executable by processor 820 of electronic device 800 to perform the above-described methods.

Fig. 8 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, electronic device 1900 may be provided as a server. Referring to fig. 8, electronic device 1900 includes a processing component 1922 that further includes one or more processors and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by processing component 1922. The application programs stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, processing component 1922 is configured to execute instructions to perform the methods described above.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1932, including computer program instructions executable by processing component 1922 of electronic device 1900 to perform the methods described above.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as SMALLTALK, C ++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for tracing public opinion, comprising:

establishing a search tree based on the infection subgraph;

2. The method of claim 1, wherein establishing the local social network corresponding to public opinion prior to the obtaining the local social network corresponding to public opinion comprises:

Acquiring a user under preset information and address information;

3. The method of any of claims 1-2, wherein the method of generating an infection subgraph based on the local social network comprises:

Configuring infection probability for nodes of the local social network;

4. A method according to any of claims 1-3, characterized in that the method of building a search tree based on the infected sub-graph comprises: and determining a root node of the infected subgraph, and establishing a search tree based on the root node.

5. The method according to any one of claims 1-4, wherein the method for calculating propagation center values corresponding to nodes and prior estimated values corresponding to the nodes using the search tree comprises:

6. The method of any one of claims 1-5, wherein the method for tracing the public opinion based on the propagation center value and the prior estimate to determine a source node of the public opinion propagation comprises:

7. The method of claim 6, wherein the method of determining the traceability probability of the node based on the propagation center value and the a priori estimate comprises: and multiplying the propagation center value by the prior estimated value to determine the traceability probability of the node.

8. The utility model provides a device of public opinion traceability which characterized in that includes:

9. An electronic device, comprising:

A processor;

a memory for storing processor-executable instructions;

Wherein the processor is configured to invoke the instructions stored in the memory to perform the method of public opinion tracing of any of claims 1 to 7.

10. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of public opinion tracing of any one of claims 1 to 7.