A method for predicting network information dissemination capability based on node energy model

Abstract

The present invention discloses a method for predicting the network information dissemination capability based on a node energy model, and relates to the field of network information dissemination. The method for predicting the network information dissemination capability based on a node energy model comprises the following steps: S1: acquiring network information and reading the information dissemination network, S2: judging the node status attributes on the information dissemination network, S3: calculating the success rate and infection rate of information dissemination from the first node to the second node, S4: calculating the success rate and infection rate of network information dissemination, S5: inputting the calculation results into the prediction model, and S6: obtaining the prediction results of the network information dissemination capability. The present invention solves the problem that the prior art is unable to predict the network information dissemination capability and cannot perform control according to the predicted network information dissemination results. The present invention can timely understand the dissemination status of network information, timely block risky network information, provide more response time for handling risks, and thus reduce negative impacts.

Description

Technical Field

[0001] The present invention relates to the technical field of network information dissemination, and in particular to a method for predicting network information dissemination capability based on a node energy model. Background Art

[0002] Measuring the ability of network information dissemination has a wide range of applications in public opinion research, information promotion, computer virus prevention and control, etc. Since people began to study complex networks, many indicators have been proposed to characterize network characteristics, such as network diameter, number of triangles, node intermediary coefficient, etc. These indicators can show the ability of the network to disseminate information from different aspects.

[0003] Chinese patent publication number CN110190999B discloses a method for measuring the information dissemination capability of a network based on a node energy model. The method uses an information dissemination model based on node energy to perform simulations on the network, and distinguishes the influence of nodes on the success rate and infection rate by screening nodes of different degrees. The overall success rate and infection rate of the network are then corrected by weighting coefficients. The method has good stability, and the experimental results on networks of the same nature and different scales are similar. Small-scale networks of the same nature can be used to evaluate large-scale networks. When measuring the information dissemination capability of the network, this method also takes into account the influence of the success rate on the information dissemination capability, and incorporates the success rate and infection rate into the evaluation indicators at the same time, which can fully and effectively measure the information dissemination capability of the network.

[0004] In actual use, the above patent is difficult to predict the ability of network information dissemination, so it is impossible to control the network information dissemination and take corresponding countermeasures based on the predicted network information dissemination results; therefore, it does not meet the existing needs. We have proposed a method for predicting the network information dissemination ability based on the node energy model. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for predicting the network information propagation capacity based on a node energy model. By predicting the propagation capacity of network information in an information propagation network, it is possible to timely understand the propagation status of network information, timely block risky network information, and provide more response time for handling risks, thereby reducing the risk of information propagation and further reducing negative impacts, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for predicting network information dissemination capacity based on a node energy model, comprising the following steps:

[0007] S1: Acquire network information, establish a historical network information dissemination attribute database, and read the information dissemination network of network information dissemination.

[0008] S2: After initializing the energy and related properties of the test network nodes, the first node is set and the state properties of the nodes on the information dissemination network are determined.

[0009] S3: Calculate the energy changes of nodes on the information dissemination network and the success rate and infection rate of the first node in disseminating information to the second node.

[0010] S4: Calculate the success rate and infection rate of the first node receiving the information transmitted from the second node, record the propagation status, and calculate the success rate and infection rate of the network information propagating in the information propagation network.

[0011] S5: The calculated success rate and infection rate as well as the node status attributes on the information dissemination network are input into the prediction model.

[0012] S6: Predict the dissemination capability of network information through the prediction model to obtain the prediction result of the dissemination capability of network information.

[0013] Preferably, the acquisition of network information and establishment of a historical network information propagation attribute database specifically includes:

[0014] Obtain network information, select one of the information publishers as the initial propagation node, and build the information propagation network based on the direct forwarding nodes and direct forwarding directed relationships of the initial propagation node.

[0015] Then, corresponding propagation networks are constructed for the multiple historical network information with historical information credibility and the corresponding network information.

[0016] The propagation nodes and propagation topology properties in the constructed information propagation network are extracted, and then the credibility of each historical network information is marked to establish a historical network information propagation property database.

[0017] Preferably, selecting one of the information publishers as the initial dissemination node includes:

[0018] Extracting information publishing data of each information publisher, wherein the information publishing data includes information publishing time interval, number of information published per unit time, and number of forwarding of published information;

[0019] The information release data is used to obtain the information release evaluation parameter corresponding to each information publisher; wherein the information release evaluation parameter is obtained by the following formula:

[0020] P=(1+X r +Y r )P0

[0021]

[0022] Where P represents the information release evaluation parameter; P0 represents the preset parameter benchmark value; X r and Y r represents the first coefficient and the second coefficient; n represents the number of unit time experienced by the information publisher; X i represents the number of information released in the i-th unit time; T p represents the average time interval between information releases; T max Indicates the maximum time interval for information release; Z max Indicates the maximum number of forwardings of information released;

[0023] Sorting the information release evaluation parameters in descending order to obtain an information release evaluation parameter sequence;

[0024] Retrieve the preset number M of candidate propagation points;

[0025] According to the number of candidate propagation points M, M information release evaluation parameters are selected from large to small in the information release evaluation parameter sequence, and information publishers corresponding to the M information release evaluation parameters are selected as candidate information publishers;

[0026] Retrieve the information release time of each candidate information publisher;

[0027] Obtaining an information release evaluation value corresponding to each candidate information publisher by utilizing the information release time in combination with the information release evaluation parameter of each candidate information publisher;

[0028] The candidate information publisher with the highest information publishing evaluation value is used as the initial propagation node.

[0029] Preferably, the information release evaluation value corresponding to each candidate information publisher is obtained by combining the information release time with the information release evaluation parameter of each candidate information publisher, including:

[0030] The information release compensation coefficient corresponding to each candidate information publisher is obtained by using each information release time in the historical information release record corresponding to each candidate information publisher, wherein the information release compensation coefficient is obtained by the following formula:

[0031]

[0032] Where S represents the information release compensation coefficient corresponding to each candidate information publisher; k represents the number of times each candidate information publisher first releases information in the historical information release record; C represents the total number of times each candidate information publisher releases information; T i represents the time when the i-th information is first released; T xiIndicates the time when the second publisher of information releases information for the i-th time;

[0033] The information release compensation coefficient is combined with the information release evaluation parameter of each candidate information publisher to obtain the information release evaluation value corresponding to each candidate information publisher, wherein the information release evaluation value is obtained by the following formula:

[0034]

[0035] Wherein, H represents the information release evaluation value corresponding to each candidate information publisher.

[0036] Preferably, the calculation of the success rate and infection rate of network information dissemination in the information dissemination network specifically includes:

[0037] According to the node degree on the information propagation network from small to large, the node sequence of the information propagation network is counted and the attributes of the nodes are initialized.

[0038] The weighted success rate and infection rate can be obtained by multiplying the success rate and infection rate of each node degree by the weight of the node degree in the total number of nodes.

[0039] Preferably, the predicting of the propagation capability of network information by using a prediction model specifically includes:

[0040] A propagation attribute between a first node and a second node in a preset information propagation network is preset, and a historical duration of propagation of historical network information corresponding to the preset propagation attribute from the first node to the second node is determined as a preset duration.

[0041] According to the preset propagation properties between the first node and the second node in the information propagation network, and the preset time length for the network information to be predicted to propagate from the first node to the second node, the first propagation success rate and infection rate of the network information to be predicted to propagate from the first node to the second node are determined.

[0042] According to the first propagation success rate and infection rate of the information propagation network to be predicted from each node connected to the second node to the second node, the second propagation success rate and infection rate of the network information to be predicted to be propagated to the second node are determined.

[0043] According to the second propagation success rates and infection rates of the multiple nodes, a propagation capability prediction result of the network information to be predicted in the information propagation network is calculated.

[0044] Preferably, the prediction model specifically includes:

[0045] A determination module is used to determine the historical propagation success rate and infection rate of historical information, preset propagation parameters and preset duration based on the historical propagation results of historical information in the information propagation network, and calculate the first propagation success rate and infection rate and the second propagation success rate and infection rate of network information propagated from the first node to the second node.

[0046] The prediction module calculates the propagation capability prediction result of the network information to be predicted in the information propagation network according to the number of nodes to which the network information to be predicted is propagated.

[0047] Preferably, the determining module specifically includes:

[0048] The history determination module is used to determine the historical propagation success rate and infection rate of the historical information and the preset propagation parameters and the preset duration according to the historical propagation results of the historical information in the information propagation network.

[0049] The calculation module is used to calculate the first propagation success rate and infection rate of the network information to be predicted based on preset propagation parameters and preset time, and calculate the second propagation success rate and infection rate of the network information to be predicted based on the first propagation success rate and infection rate.

[0050] Preferably, the calculation module specifically includes:

[0051] The first calculation module is used to calculate the first propagation success rate and infection rate of the network information to be predicted from the first node to the second node based on the preset propagation parameters and the preset time between the first node and the second node in the information propagation network.

[0052] The second calculation module is used to calculate the second propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node based on the first propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node.

[0053] Preferably, the history determination module specifically includes:

[0054] The history propagation module is used to determine the history propagation success rate and infection rate of the history information between the first node and the second node according to the history propagation results of the history information in the information propagation network.

[0055] The parameter and duration determination module is used to determine the preset propagation parameters and the preset duration between the first node and the second node based on the historical propagation success rate and infection rate between the first node and the second node of a plurality of historical information.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] By predicting the propagation capability of network information in the information dissemination network, the present invention can timely understand the propagation status of network information, timely block risky network information, provide more response time for handling risks, thereby reducing the risk of information dissemination, and further reducing negative impacts, and improving the reliability and accuracy of predictions of network information propagation in the information dissemination network. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Schematic diagram of the flow of the method for predicting network information dissemination capability based on the node energy model of the present invention;

[0059] Figure 2 Schematic diagram of the network information dissemination capability prediction method module based on the node energy model of the present invention;

[0060] Figure 3 This is a schematic diagram of the prediction model of the network information dissemination capacity prediction method based on the node energy model of the present invention. DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] In order to solve the problem that the existing technology is difficult to predict the spread of network information in actual use, it is impossible to control the spread of network information and take corresponding countermeasures based on the predicted network information spread results. Figure 1-Figure 3 , this embodiment provides the following technical solutions:

[0063] The method for predicting network information dissemination capacity based on a node energy model includes the following steps:

[0064] S1: Acquire network information, establish a historical network information dissemination attribute database, and read the information dissemination network of network information dissemination.

[0065] Specifically, the entire established influence propagation network is divided into two parts, one is the training set and the other is the prediction set. The training set is then used to calculate the success rate and infection rate of edge generation in the prediction set. For each calculation, an existing network information and a non-existent network information are randomly selected from the prediction set. The scores of these two network information under the prediction algorithm are calculated based on the training set. If the existing network information has a higher score, it is recorded as 1, and the non-existent network information has a higher score, which is recorded as 0. If they are equal, it is recorded as 0.5. This calculation is performed multiple times, and then all 1s and 0.5s are added up and divided by the number of times to obtain the final calculation result. If the final calculation result is greater than 0.5, it means that the prediction algorithm effectively predicts the propagation ability of network information in the information propagation network.

[0066] S2: After initializing the energy and related properties of the test network nodes, the first node is set, and the state properties of the nodes on the information dissemination network are determined. The state properties of the nodes on the information dissemination network are ring paths and chain paths.

[0067] Specifically, according to the path information in the basic data of the information dissemination network, any node in the basic data of the information dissemination network is used as the starting point, that is, the first node, and a starting path is separately constructed for the starting point and all the relationship nodes having a connection relationship with it, and the starting node in each starting path is given a starting sequence identifier, and according to the path information in the first node data, the next hop nodes having a connection relationship with the relationship nodes in each starting path are continuously obtained as intermediate nodes, and all the obtained intermediate nodes are given sequence identifiers according to the order in which they are obtained and the starting path they are in. When the next hop node cannot be obtained or the obtained next hop node is a node in the starting path, the intermediate node at the end of the node sequence identifier of the starting path is determined to be the terminating node, and the starting path whose terminating node is a node in the starting path is determined to be a ring path, and the remaining starting paths are chain paths.

[0068] S3: Calculate the energy changes of nodes on the information dissemination network and the success rate and infection rate of the first node in disseminating information to the second node.

[0069] S4: Calculate the success rate and infection rate of the first node receiving the information transmitted from the second node, record the propagation status, and calculate the success rate and infection rate of the network information propagating in the information propagation network.

[0070] Calculate the success rate and infection rate of network information in the information dissemination network, including:

[0071] According to the node degree on the information propagation network from small to large, the node sequence of the information propagation network is counted and the attributes of the nodes are initialized.

[0072] The weighted success rate and infection rate can be obtained by multiplying the success rate and infection rate of each node degree by the weight of the node degree in the total number of nodes.

[0073] Specifically, by calculating the success rate and infection rate of the first node receiving information from the second node and recording the propagation status of the network information, the success rate and infection rate of the network information in the information propagation network can be accurately calculated, providing a strong basis for predicting the propagation capacity of network information.

[0074] S5: The calculated success rate and infection rate as well as the node status attributes on the information dissemination network are input into the prediction model.

[0075] Prediction models, specifically including:

[0076] A determination module is used to determine the historical propagation success rate and infection rate of historical information, preset propagation parameters and preset duration based on the historical propagation results of historical information in the information propagation network, and calculate the first propagation success rate and infection rate and the second propagation success rate and infection rate of network information propagated from the first node to the second node.

[0077] The prediction module calculates the propagation capability prediction result of the network information to be predicted in the information propagation network according to the number of nodes to which the network information to be predicted is propagated.

[0078] Determine the modules, including:

[0079] The history determination module is used to determine the historical propagation success rate and infection rate of the historical information and the preset propagation parameters and the preset duration according to the historical propagation results of the historical information in the information propagation network.

[0080] The calculation module is used to calculate the first propagation success rate and infection rate of the network information to be predicted based on preset propagation parameters and preset time, and calculate the second propagation success rate and infection rate of the network information to be predicted based on the first propagation success rate and infection rate.

[0081] Computing module, specifically including:

[0082] The first calculation module is used to calculate the first propagation success rate and infection rate of the network information to be predicted from the first node to the second node based on the preset propagation parameters and the preset time between the first node and the second node in the information propagation network.

[0083] The second calculation module is used to calculate the second propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node based on the first propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node.

[0084] History determination module, specifically including:

[0085] The historical propagation module is used to determine the historical propagation success rate and infection rate of historical information between the first node and the second node based on the historical propagation results of historical information in the information propagation network. The historical propagation results include the reference nodes that received the historical information among multiple nodes and the time when each reference node received the historical information.

[0086] The parameter and duration determination module is used to determine the preset propagation parameters and preset duration between the first node and the second node based on the historical propagation success rate and infection rate of multiple historical information between the first node and the second node. It can effectively predict the propagation influence under the interaction of different information, and can make a certain degree of prediction for the propagation of network information. Using the prediction algorithm, the influence propagation ability value is obtained.

[0087] Specifically, by determining the historical success rate and infection rate of information dissemination networks, the ability of network information to spread in information dissemination networks can be predicted. This allows timely understanding of the dissemination of network information, timely blocking of risky network information, and avoiding the unpredictable ability to spread network information, which allows risky network information to spread widely, providing more response time for dealing with risks, thereby reducing information dissemination risks and further reducing negative impacts, thereby improving the reliability and accuracy of predictions of network information dissemination in information dissemination networks.

[0088] S6: Predict the dissemination capability of network information through the prediction model to obtain the prediction result of the dissemination capability of network information.

[0089] Specifically, we use network information and the network information propagation network to mine the node state attributes on the network information propagation network. Based on the calculated success rate and infection rate and the node state attributes on the information propagation network, we obtain the propagation capacity of network information in the information propagation network through weighted calculation. The calculation formula is as follows:

[0090] P A =∑k∈U S ×U R

[0091] Among them, P A represents the ability of network information to spread on the information dissemination network, k represents the predicted network information, P A The larger the value is, the greater the ability of network information to spread on the information dissemination network is; U is the set of neighboring nodes that influence the network information, U S represents the success rate of influencing the information propagation network in the set of neighbor nodes, U R represents the infection rate of the information propagation network affecting the set of neighbor nodes.

[0092] Obtain network information and establish a database of historical network information dissemination attributes, including:

[0093] Obtain network information, select one of the information publishers as the initial propagation node, and build the information propagation network based on the direct forwarding nodes and direct forwarding directed relationships of the initial propagation node.

[0094] Then, corresponding propagation networks are constructed for the multiple historical network information with historical information credibility and the corresponding network information.

[0095] The propagation nodes and propagation topology properties in the constructed information propagation network are extracted, and then the credibility of each historical network information is marked to establish a historical network information propagation property database.

[0096] Specifically, one of the information publishers is selected as the initial dissemination node, including:

[0097] Extracting information publishing data of each information publisher, wherein the information publishing data includes information publishing time interval, number of information published per unit time, and number of forwarding of published information;

[0098] The information release data is used to obtain the information release evaluation parameter corresponding to each information publisher; wherein the information release evaluation parameter is obtained by the following formula:

[0099] P=(1+X r +Y r )P0

[0100]

[0101] Where P represents the information release evaluation parameter; P0 represents the preset parameter benchmark value; X r and Y r represents the first coefficient and the second coefficient; n represents the number of unit time experienced by the information publisher; X i represents the number of information released in the i-th unit time; T p represents the average time interval between information releases; T max Indicates the maximum time interval for information release; Z max Indicates the maximum number of forwardings of information released;

[0102] Sorting the information release evaluation parameters in descending order to obtain an information release evaluation parameter sequence;

[0103] Retrieve the preset number M of candidate propagation points;

[0104] According to the number of candidate propagation points M, M information release evaluation parameters are selected from large to small in the information release evaluation parameter sequence, and information publishers corresponding to the M information release evaluation parameters are selected as candidate information publishers;

[0105] Retrieve the information release time of each candidate information publisher;

[0106] Obtaining an information release evaluation value corresponding to each candidate information publisher by utilizing the information release time in combination with the information release evaluation parameter of each candidate information publisher;

[0107] The candidate information publisher with the highest information publishing evaluation value is used as the initial propagation node.

[0108] The technical effect of the above technical solution is that by analyzing information publishers' information release data and extracting key indicators such as the time interval between releases, the number of releases per unit time, and the number of forwarded releases, the publisher's influence in information dissemination can be accurately assessed. The information release evaluation parameters calculated using the formula can be used to sort the publishers from highest to lowest, forming a sequence of information release evaluation parameters. Based on a preset number M of candidate dissemination points, the publishers corresponding to the top M evaluation parameters in the sequence are selected as candidate dissemination points, ensuring the quality and quantity of the selected dissemination points. Combining the candidate information publishers' information release times and evaluation parameters, the information release evaluation value of each candidate information publisher is calculated, and the publisher with the highest evaluation value is selected as the initial dissemination point. This method ensures that the initial dissemination point plays the greatest role in the information dissemination process, improving the effectiveness and efficiency of information dissemination. The above technical solution of this embodiment allows for more scientific and accurate selection of initial dissemination points, thereby optimizing the overall information dissemination strategy. This not only helps to increase the speed and breadth of information dissemination, but also improves the accuracy and effectiveness of information dissemination, resulting in better dissemination results for information disseminators.

[0109] In summary, this technical solution optimizes the information dissemination strategy and improves the effectiveness and efficiency of information dissemination by scientifically and accurately evaluating and selecting information publishers.

[0110] Specifically, the information release evaluation value corresponding to each candidate information publisher is obtained by using the information release time in combination with the information release evaluation parameter of each candidate information publisher, including:

[0111] The information release compensation coefficient corresponding to each candidate information publisher is obtained by using each information release time in the historical information release record corresponding to each candidate information publisher, wherein the information release compensation coefficient is obtained by the following formula:

[0112]

[0113] Where S represents the information release compensation coefficient corresponding to each candidate information publisher; k represents the number of times each candidate information publisher first releases information in the historical information release record; C represents the total number of times each candidate information publisher releases information; T i represents the time when the i-th information is first released; T xi Indicates the time when the second publisher of information releases information for the i-th time;

[0114] The information release compensation coefficient is combined with the information release evaluation parameter of each candidate information publisher to obtain the information release evaluation value corresponding to each candidate information publisher, wherein the information release evaluation value is obtained by the following formula:

[0115]

[0116] Wherein, H represents the information release evaluation value corresponding to each candidate information publisher.

[0117] The technical effect of the above technical solution is that it further refines the evaluation of candidate information publishers by introducing an information release compensation coefficient S. This coefficient takes into account the number of times each candidate information publisher has been the first to publish information in its historical information release history, the number of times it has published information overall, and the time difference between each candidate and other publishers. This helps more comprehensively reflect the publisher's actual influence and contribution in the information dissemination process. The calculation of the information release evaluation value H not only considers the information release evaluation parameter P but also incorporates the information release compensation coefficient S. This evaluation value takes into account both the publisher's overall performance (such as the number of information releases, the time interval, and the number of reposts) and its performance at specific moments (such as when it was the first to publish information). This comprehensive evaluation method results in more accurate and comprehensive results. Furthermore, by introducing the information release compensation coefficient and comprehensively considering multiple factors, this technical solution can more accurately assess the actual influence and contribution of each candidate information publisher, thereby more scientifically selecting the initial dissemination node. This helps improve the effectiveness and efficiency of information dissemination, enabling information to be disseminated faster and more widely. Furthermore, comprehensively considering multiple factors and optimizing the selection of initial dissemination nodes can help improve the effectiveness and influence of information dissemination. This not only increases the exposure and reach of information, but also improves its credibility and acceptance, thereby helping information disseminators achieve better dissemination results.

[0118] In summary, this technical solution optimizes the selection process of the initial propagation node and improves the effect and efficiency of information dissemination by introducing the information release compensation coefficient and comprehensively considering multiple factors.

[0119] The prediction model is used to predict the dissemination capacity of network information, including:

[0120] A propagation attribute between a first node and a second node in a preset information propagation network is preset, and a historical duration of propagation of historical network information corresponding to the preset propagation attribute from the first node to the second node is determined as a preset duration.

[0121] Based on the preset propagation properties between the first node and the second node in the information propagation network, and the preset time for the network information to be predicted to propagate from the first node to the second node, the first propagation success rate and infection rate of the network information to be predicted to propagate from the first node to the second node are determined. The information propagation network includes multiple nodes and connections between the nodes. The first node and the second node are any two nodes connected to each other among the multiple nodes.

[0122] According to the first propagation success rate and infection rate of the information propagation network to be predicted from each node connected to the second node to the second node, the second propagation success rate and infection rate of the network information to be predicted to be propagated to the second node are determined.

[0123] According to the second propagation success rates and infection rates of the multiple nodes, a propagation capability prediction result of the network information to be predicted in the information propagation network is calculated.

[0124] In summary, the network information propagation capacity prediction method based on the node energy model of the present invention, by predicting the propagation capacity of network information in the information propagation network, can timely understand the propagation status of network information, timely block risky network information, avoid the unpredictable ability of network information propagation, which causes risky network information to spread widely and cause greater negative impacts. At the same time, according to the propagation capacity of network information, risky information can be blocked in time, providing more response time for handling risks, thereby reducing information propagation risks and further reducing negative impacts, thereby improving the reliability and accuracy of network information propagation predictions in the information propagation network.

[0125] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0126] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting network information dissemination capacity based on a node energy model, characterized by: The following steps are involved: S1: Obtain network information, establish a historical network information dissemination attribute database, and read the information dissemination network of network information dissemination; S2: After initializing the energy and related properties of the test network nodes, set the first node and determine the state properties of the nodes on the information dissemination network; S3: Calculate the energy change of nodes on the information propagation network and the success rate and infection rate of the first node propagating information to the second node; S4: Calculate the success rate and infection rate of the first node receiving the information transmitted from the second node, record the propagation status, and calculate the success rate and infection rate of the network information propagation in the information propagation network; S5: input the calculated success rate and infection rate as well as the node status attributes on the information propagation network into the prediction model; S6: predicting the network information dissemination capability through the prediction model to obtain the prediction result of the network information dissemination capability; The acquisition of network information and establishment of a historical network information propagation attribute database specifically includes: Obtain network information, select one of the information publishers as the initial propagation node, and build a propagation network for the information based on the direct forwarding nodes and the directed forwarding relationship of the initial propagation node; Then, corresponding propagation networks are constructed for the obtained multiple historical network information with historical information credibility and the corresponding network information; Extract the propagation nodes and propagation topology properties in the constructed information propagation network, then mark the credibility of each historical network information and establish a historical network information propagation property database; Select one of the information publishers as the initial dissemination node, including: Extracting information publishing data of each information publisher, wherein the information publishing data includes information publishing time interval, number of information published per unit time, and number of forwarding of published information; The information release data is used to obtain the information release evaluation parameter corresponding to each information publisher; wherein the information release evaluation parameter is obtained by the following formula: P=(1+X r +Y r )P0 Where P represents the information release evaluation parameter; P0 represents the preset parameter benchmark value; X r and Y r represents the first coefficient and the second coefficient; n represents the number of unit time experienced by the information publisher; X i represents the number of information released in the i-th unit time; T p represents the average time interval between information releases; T max Indicates the maximum time interval for information release; Z max Indicates the maximum number of forwardings of information released; Sorting the information release evaluation parameters in descending order to obtain an information release evaluation parameter sequence; Retrieve the preset number M of candidate propagation points; According to the number of candidate propagation points M, M information release evaluation parameters are selected from large to small in the information release evaluation parameter sequence, and information publishers corresponding to the M information release evaluation parameters are selected as candidate information publishers; Retrieve the information release time of each candidate information publisher; Obtaining an information release evaluation value corresponding to each candidate information publisher by utilizing the information release time in combination with the information release evaluation parameter of each candidate information publisher; The candidate information publisher with the highest information publishing evaluation value is used as the initial propagation node.

2. The method for predicting network information dissemination capacity based on a node energy model according to claim 1, characterized in that: The information release evaluation value corresponding to each candidate information publisher is obtained by using the information release time in combination with the information release evaluation parameter of each candidate information publisher, including: The information release compensation coefficient corresponding to each candidate information publisher is obtained by using each information release time in the historical information release record corresponding to each candidate information publisher, wherein the information release compensation coefficient is obtained by the following formula: Where S represents the information release compensation coefficient corresponding to each candidate information publisher; k represents the number of times each candidate information publisher first releases information in the historical information release record; C represents the total number of times each candidate information publisher releases information; T i represents the time when the i-th information is first released; T xi Indicates the time when the second publisher of information releases information for the i-th time; The information release compensation coefficient is combined with the information release evaluation parameter of each candidate information publisher to obtain the information release evaluation value corresponding to each candidate information publisher, wherein the information release evaluation value is obtained by the following formula: Wherein, H represents the information release evaluation value corresponding to each candidate information publisher.

3. The method for predicting network information dissemination capacity based on a node energy model according to claim 1, characterized in that: The calculation of the success rate and infection rate of network information dissemination in the information dissemination network specifically includes: According to the node degree on the information propagation network from small to large, the node sequence of the information propagation network is counted and the attributes of the nodes are initialized; The weighted success rate and infection rate can be obtained by multiplying the success rate and infection rate of each node degree by the weight of the node degree in the total number of nodes.

4. The method for predicting network information dissemination capacity based on a node energy model according to claim 1, characterized in that: The prediction model is used to predict the dissemination capacity of network information, including: Preset a propagation attribute between a first node and a second node in an information propagation network, and determine a historical duration of propagation of historical network information corresponding to the preset propagation attribute from the first node to the second node as a preset duration; Determining a first propagation success rate and an infection rate of the network information to be predicted from the first node to the second node based on a preset propagation property between the first node and the second node in the information propagation network and a preset time duration for the network information to be predicted to propagate from the first node to the second node; determining a second propagation success rate and infection rate of the network information to be predicted to be propagated to the second node based on a first propagation success rate and infection rate of the information propagation network to be predicted from each node connected to the second node to the second node; According to the second propagation success rates and infection rates of the multiple nodes, a propagation capability prediction result of the network information to be predicted in the information propagation network is calculated.

5. The method for predicting network information dissemination capacity based on a node energy model according to claim 1, characterized in that: The prediction model specifically includes: a determination module, configured to determine a historical propagation success rate and infection rate of the historical information, preset propagation parameters, and a preset duration based on historical propagation results of the historical information in the information propagation network, and calculate a first propagation success rate and infection rate and a second propagation success rate and infection rate of the network information propagating from the first node to the second node; The prediction module calculates the propagation capability prediction result of the network information to be predicted in the information propagation network according to the number of nodes to which the network information to be predicted is propagated.

6. The method for predicting network information dissemination capacity based on a node energy model according to claim 5, characterized in that: The determining module specifically includes: A history determination module, configured to determine a historical propagation success rate and infection rate of the historical information, preset propagation parameters, and a preset duration based on the historical propagation results of the historical information in the information propagation network; The calculation module is used to calculate the first propagation success rate and infection rate of the network information to be predicted based on preset propagation parameters and preset time, and calculate the second propagation success rate and infection rate of the network information to be predicted based on the first propagation success rate and infection rate.

7. The method for predicting network information dissemination capacity based on a node energy model according to claim 6, characterized in that: The calculation module specifically includes: a first calculation module, configured to calculate a first propagation success rate and an infection rate of the network information to be predicted from the first node to the second node based on a preset propagation parameter and a preset duration between the first node and the second node in the information propagation network; The second calculation module is used to calculate the second propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node based on the first propagation success rate and infection rate of the network information to be predicted from each node connected to the second node to the second node.

8. The method for predicting network information dissemination capacity based on a node energy model according to claim 6, characterized in that: The history determination module specifically includes: A historical propagation module, configured to determine a historical propagation success rate and an infection rate of the historical information between the first node and the second node based on the historical propagation results of the historical information in the information propagation network; The parameter and duration determination module is used to determine the preset propagation parameters and the preset duration between the first node and the second node based on the historical propagation success rate and infection rate between the first node and the second node of a plurality of historical information.

Images