CN117611374A - Information propagation analysis method and system based on diversified big data analysis - Google Patents
Information propagation analysis method and system based on diversified big data analysis Download PDFInfo
- Publication number
- CN117611374A CN117611374A CN202410091890.5A CN202410091890A CN117611374A CN 117611374 A CN117611374 A CN 117611374A CN 202410091890 A CN202410091890 A CN 202410091890A CN 117611374 A CN117611374 A CN 117611374A
- Authority
- CN
- China
- Prior art keywords
- propagation
- information
- network node
- real
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 238000007405 data analysis Methods 0.000 title claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 50
- 230000001133 acceleration Effects 0.000 claims abstract description 36
- 238000000855 fermentation Methods 0.000 claims abstract description 21
- 230000004151 fermentation Effects 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 230000000644 propagated effect Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 7
- 230000002411 adverse Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000009931 harmful effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an information propagation analysis method and system based on diversified big data analysis, which relate to the technical field of information and comprise the following steps: acquiring at least one propagation path of past information based on big data; acquiring the propagation length of the past information in the first network node; evaluating and grading the transmission range of the past information; analyzing and acquiring fermentation nodes of high-propagation past information propagation to form a trigger keyword package, and analyzing and acquiring acceleration points of the high-propagation past information propagation; acquiring the initial form of the high-transmission past information; obtaining key nodes in the network nodes; and evaluating whether the property of the real-time information is benign, judging whether the real-time information is high-propagation information, and judging whether the trend of the real-time information propagation is slowed down. By arranging the information propagation evaluation module, the high propagation analysis module, the node grading module and the information propagation judgment module, the effectiveness of limitation is enhanced, the limiting point positions are reduced, the limiting speed is ensured, and the calculation force is saved.
Description
Technical Field
The invention relates to the technical field of information, in particular to an information propagation analysis method and system based on diversified big data analysis.
Background
The information is propagated in the network, the propagation process is complex, the analysis of the propagation process is insufficient in the prior art, the trend of information propagation is not predicted sufficiently, reasonable judgment is difficult to be made according to the information propagation condition, high propagation information which possibly causes adverse effects is restrained in advance, meanwhile, the propagation of the adverse information cannot be restrained effectively due to insufficient judgment of burst nodes of the information propagation, and unnecessary adverse effects are generated.
Disclosure of Invention
In order to solve the technical problems, the technical scheme provides an information propagation analysis method and system based on diversified big data analysis, which solves the problems that the prior art proposed in the background art is insufficient in analysis of the propagation process, so that trend pre-judgment on information propagation is insufficient, reasonable judgment is difficult to be made according to the information propagation condition, high propagation information which possibly causes adverse effects is restrained in advance, and meanwhile, due to insufficient judgment on burst nodes of the information propagation, the propagation of the adverse information cannot be restrained effectively, and unnecessary adverse effects are generated.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an information propagation analysis method based on diversified big data analysis comprises the following steps:
acquiring at least one propagation path of past information based on big data, wherein the propagation path is formed by network nodes for past information transmission, and the network nodes are formed by various app users and network communities;
selecting any network node in a propagation path of the past information as a first network node, and acquiring the propagation length of the past information in the first network node;
evaluating and grading the propagation range of the past information according to the influence range and the propagation speed;
acquiring at least one piece of high-propagation past information with a past information evaluation level higher than a preset level;
analyzing and acquiring fermentation nodes of high-propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, and analyzing and acquiring acceleration points of the high-propagation past information propagation, wherein the fermentation nodes and the acceleration points are one of network nodes;
acquiring the initial form of the high-transmission past information;
classifying and grading the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
acquiring real-time information, evaluating whether the property of the real-time information is benign, if so, not performing any processing, if not, predicting the trend of real-time information propagation according to the initial state of high propagation past information, judging whether the real-time information propagation is high propagation information, if not, performing no processing, if so, prohibiting forwarding of the real-time information at an acceleration point, deleting the forwarded real-time information at the acceleration point, judging whether the trend of real-time information propagation is slow down, if not, performing no processing, prohibiting forwarding of the real-time information at a key node, and deleting the forwarded real-time information at the key node.
Preferably, the acquiring the propagation path of the at least one past information based on the big data includes the steps of:
and acquiring at least one past information, and acquiring all network nodes passing through in the past information transmission process to obtain a propagation path of the past information.
Preferably, the acquiring the propagation length of the past information in the first network node includes the following steps:
acquiring a propagation path of past information, and acquiring the position of a first network node in the propagation path;
acquiring an initial network node of a propagation path, and acquiring a first propagation path from the initial network node to a first network node in the propagation path of the past information;
the number of the network nodes in the first propagation path is obtained and used as the propagation length of the past information in the first network node.
Preferably, the step of evaluating and grading the propagation range of the past information according to the influence range and the propagation speed comprises the following steps:
acquiring a propagation path of the past information, and summarizing at least one network node with equal propagation length into a network node set;
arranging the network node sets from small to large according to the propagation length;
in the propagation path of the past information, calculating the propagation time of the network node, wherein the propagation time of the network node is the propagation time of the past information from the previous network node to the current network node;
calculating the average value of the propagation time of all network nodes in the network node set to obtain the propagation time of the network node set;
acquiring at least one first network node set with the number of elements exceeding a preset value in the network node set;
accumulating the number of elements in the first network node set to obtain a comprehensive judgment value;
accumulating the propagation time of the first network node set to obtain a time judgment value;
dividing the comprehensive judgment value by the time judgment value to obtain a proportion judgment value;
evaluating a first network node set with the proportion discrimination value smaller than a first preset proportion as a primary network node set;
evaluating a first network node set with a proportion discrimination value between a first preset proportion and a second preset proportion as a medium-level network node set;
evaluating a first network node set with a proportion discrimination value larger than a second preset proportion as an advanced network node set, wherein the first preset proportion is smaller than the second preset proportion;
if the network node sets in the past information are all not the first network node set, the past information is low propagation information;
if the first network node set exists in the network node set in the past information, but the highest level of the first network node set is the primary network node set, the past information is the next highest propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the intermediate network node set, the past information is the high-propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the advanced network node set, the past information is the ultrahigh propagation past information;
the ultrahigh-propagation past information is high-propagation past information.
Preferably, the analyzing the fermentation node for obtaining the high-propagation past information propagation comprises the following steps:
taking network nodes in the primary network node set as fermentation nodes;
analyzing and acquiring triggering reasons of the propagation burst, and forming a triggering keyword package comprises the following steps:
using a neural network model to identify high-frequency words in the high-propagation past information, and summarizing the high-frequency words to obtain a trigger keyword package;
analyzing and acquiring acceleration points of high-propagation past information propagation comprises the following steps:
and taking the network nodes in the advanced network node set as acceleration points.
Preferably, the initial form of acquiring the highly propagated past information includes the steps of:
summarizing all medium-level network node sets and high-level network node sets of at least one high-propagation past information;
obtaining the maximum value and the minimum value of the proportion discrimination values of the medium-level network node set and the high-level network node set;
the maximum value and the minimum value are combined to obtain a threshold section, which is a characteristic of the initial form of the high-transmission past information.
Preferably, the classifying and grading the network node according to the propagation path of the past information includes the following steps:
the network nodes as the fermentation node and the acceleration node are set as key nodes.
Preferably, the determining whether the real-time information propagation is high propagation information includes the steps of:
acquiring a real-time propagation path of real-time information propagation, and updating the real-time propagation path in real time according to the propagation condition of the real-time information;
summarizing at least one network node with equal propagation length into a real-time network node set;
arranging the real-time network node set from small to large according to the propagation length;
when a real-time network node set with the number of elements exceeding a preset value exists, the real-time network node set with the number of elements exceeding the preset value is used as a first real-time network node set;
accumulating the number of elements in the first real-time network node set to obtain a real-time comprehensive judgment value;
accumulating the propagation time of the first real-time network node set to obtain a real-time judgment value;
dividing the real-time comprehensive judgment value by the real-time judgment value to obtain a real-time proportion judgment value;
and judging whether the real-time proportion judging value is in a threshold value interval, if so, judging that the real-time information is transmitted as high transmission information, and if not, judging that the real-time information is transmitted as not high transmission information.
Preferably, the step of judging whether the trend of the real-time information propagation is slowed down comprises the following steps:
and judging whether the real-time proportion judging value is reduced, if so, slowing down the trend of real-time information transmission, and if not, not slowing down the trend of real-time information transmission.
An information propagation analysis system based on multi-element big data analysis is used for realizing the information propagation analysis method based on multi-element big data analysis, and comprises the following steps:
the path acquisition module acquires at least one propagation path of past information based on big data;
the transmission length acquisition module acquires the transmission length of the past information in the first network node;
the information propagation evaluation module evaluates and ranks the propagation range of the past information according to the influence range and the propagation speed;
the high propagation analysis module is used for analyzing and acquiring fermentation nodes of high propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, analyzing and acquiring acceleration points of the high propagation past information propagation, and acquiring initial forms of the high propagation past information;
the node classification module classifies and classifies the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
the information transmission judging module judges whether the real-time information transmission is high transmission information or not and judges whether the trend of the real-time information transmission is slowed down or not;
and the information node processing module prohibits the forwarding of the real-time information at the acceleration point, deletes the forwarded real-time information at the acceleration point, prohibits the forwarding of the real-time information at the key node, and deletes the forwarded real-time information at the key node.
Compared with the prior art, the invention has the beneficial effects that:
through setting up information propagation evaluation module, high propagation analysis module, node classification module and information propagation judgement module, can make reasonable prejudgement to the trend of information propagation according to the judgement model of establishing to decompose the process of information propagation, obtain the key node of information propagation outburst, according to the key node, to probably causing the high propagation information of harmful effect, carry out the pertinence to suppress, whether network node is exploded to the information propagation that probably produces, carry out propagation restriction, and then can strengthen the validity of restriction, reduce the point position of restriction, guarantee restriction speed, save the calculated power.
Drawings
FIG. 1 is a schematic flow diagram of an information propagation analysis method based on diversified big data analysis according to the present invention;
fig. 2 is a schematic flow chart of a propagation length of the acquired past information in the first network node according to the present invention;
FIG. 3 is a schematic diagram of a process for evaluating and grading a propagation range of past information according to an influence range and a propagation speed;
FIG. 4 is a schematic diagram of an initial morphology flow for obtaining highly propagated past information in accordance with the present invention;
FIG. 5 is a flow chart of the method for judging whether real-time information transmission is high transmission information according to the present invention;
fig. 6 is a schematic flow chart for judging whether the trend of real-time information transmission is slowed down or not according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, an information propagation analysis method based on a diversified big data analysis includes:
acquiring at least one propagation path of past information based on big data, wherein the propagation path is formed by network nodes for past information transmission, and the network nodes are formed by various app users and network communities;
selecting any network node in a propagation path of the past information as a first network node, and acquiring the propagation length of the past information in the first network node;
evaluating and grading the propagation range of the past information according to the influence range and the propagation speed;
acquiring at least one piece of high-propagation past information with a past information evaluation level higher than a preset level;
analyzing and acquiring fermentation nodes of high-propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, and analyzing and acquiring acceleration points of the high-propagation past information propagation, wherein the fermentation nodes and the acceleration points are one of network nodes;
acquiring the initial form of the high-transmission past information;
classifying and grading the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
acquiring real-time information, evaluating whether the property of the real-time information is benign, if so, not performing any processing, if not, predicting the trend of real-time information propagation according to the initial state of high propagation past information, judging whether the real-time information propagation is high propagation information, if not, performing no processing, if so, prohibiting forwarding of the real-time information at an acceleration point, deleting the forwarded real-time information at the acceleration point, judging whether the trend of the real-time information propagation is slow, if not, performing no processing, prohibiting forwarding of the real-time information at a key node, and deleting the forwarded real-time information at the key node;
the high-propagation information is consistent with the evaluation method of the high-propagation past information, the high-propagation information is an evaluation result of the real-time information, and the high-propagation past information is an evaluation result of the past information.
The method for acquiring at least one propagation path of past information based on big data comprises the following steps:
and acquiring at least one past information, and acquiring all network nodes passing through in the past information transmission process to obtain a propagation path of the past information.
Referring to fig. 2, acquiring a propagation length of past information at a first network node includes the steps of:
acquiring a propagation path of past information, and acquiring the position of a first network node in the propagation path;
acquiring an initial network node of a propagation path, and acquiring a first propagation path from the initial network node to a first network node in the propagation path of the past information;
acquiring the number of network nodes in a first propagation path, and taking the number of network nodes as the propagation length of past information in the first network node;
i.e. the number of network nodes through which the acquisition information propagates from the initial network node to any one of the network nodes.
Referring to fig. 3, the evaluation and grading of the propagation range of the past information according to the influence range and the propagation speed includes the steps of:
acquiring a propagation path of the past information, and summarizing at least one network node with equal propagation length into a network node set;
arranging the network node sets from small to large according to the propagation length;
in the propagation path of the past information, calculating the propagation time of the network node, wherein the propagation time of the network node is the propagation time of the past information from the previous network node to the current network node;
calculating the average value of the propagation time of all network nodes in the network node set to obtain the propagation time of the network node set;
acquiring at least one first network node set with the number of elements exceeding a preset value in the network node set;
accumulating the number of elements in the first network node set to obtain a comprehensive judgment value;
accumulating the propagation time of the first network node set to obtain a time judgment value;
dividing the comprehensive judgment value by the time judgment value to obtain a proportion judgment value;
evaluating a first network node set with the proportion discrimination value smaller than a first preset proportion as a primary network node set;
evaluating a first network node set with a proportion discrimination value between a first preset proportion and a second preset proportion as a medium-level network node set;
evaluating a first network node set with a proportion discrimination value larger than a second preset proportion as an advanced network node set, wherein the first preset proportion is smaller than the second preset proportion;
if the network node sets in the past information are all not the first network node set, the past information is low propagation information;
if the first network node set exists in the network node set in the past information, but the highest level of the first network node set is the primary network node set, the past information is the next highest propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the intermediate network node set, the past information is the high-propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the advanced network node set, the past information is the ultrahigh propagation past information;
the extra-high transmission past information is high transmission past information;
the method is characterized in that the prior information transmission range is evaluated and rated to divide the prior information according to the degree of the prior information transmission range, and nodes corresponding to the divided classification are used as fermentation nodes and acceleration points, and the prior information transmission range is further improved at the points, so that the nodes have remarkable effects on information transmission, fermentation nodes and acceleration points are preferentially considered when limitation is made, the limitation effect is more obvious, all the nodes are not required to be considered, pertinence can be improved, calculation force required for limitation is less, limitation speed is high, and the limitation effect is better.
The fermentation node for analyzing and acquiring the high-propagation past information propagation comprises the following steps of:
taking network nodes in the primary network node set as fermentation nodes;
analyzing and acquiring triggering reasons of the propagation burst, and forming a triggering keyword package comprises the following steps:
using a neural network model to identify high-frequency words in the high-propagation past information, and summarizing the high-frequency words to obtain a trigger keyword package;
analyzing and acquiring acceleration points of high-propagation past information propagation comprises the following steps:
and taking the network nodes in the advanced network node set as acceleration points.
Referring to fig. 4, the initial form of acquiring highly propagated past information includes the steps of:
summarizing all medium-level network node sets and high-level network node sets of at least one high-propagation past information;
obtaining the maximum value and the minimum value of the proportion discrimination values of the medium-level network node set and the high-level network node set;
summarizing the maximum value and the minimum value to obtain a threshold interval, wherein the threshold interval is used as the characteristic of the initial form of the high-transmission past information;
the prior information with the intermediate network node set and the advanced network node set is high-propagation prior information, and the prior information without the intermediate network node set and the advanced network node set is not high-propagation prior information, so that a threshold interval can be used as a basis for judging whether the real-time information is high-propagation information or not;
because, when the transmission of the real-time information starts to burst, the next-stage network node transmitted by the current network node is obviously increased, and the transmission speed is increased, the calculated real-time proportion discrimination value is increased, so that when the real-time information becomes high transmission information, the real-time proportion discrimination value is increased to be within the threshold value interval.
Classifying and grading the network nodes according to the propagation paths of the past information comprises the following steps:
the network nodes as the fermentation node and the acceleration node are set as key nodes.
Referring to fig. 5, determining whether the real-time information dissemination is high dissemination information includes the steps of:
acquiring a real-time propagation path of real-time information propagation, and updating the real-time propagation path in real time according to the propagation condition of the real-time information;
summarizing at least one network node with equal propagation length into a real-time network node set;
arranging the real-time network node set from small to large according to the propagation length;
when a real-time network node set with the number of elements exceeding a preset value exists, the real-time network node set with the number of elements exceeding the preset value is used as a first real-time network node set;
accumulating the number of elements in the first real-time network node set to obtain a real-time comprehensive judgment value;
accumulating the propagation time of the first real-time network node set to obtain a real-time judgment value;
dividing the real-time comprehensive judgment value by the real-time judgment value to obtain a real-time proportion judgment value;
judging whether the real-time proportion judging value is in a threshold value interval, if so, judging that the real-time information is transmitted as high transmission information, and if not, judging that the real-time information is transmitted as not high transmission information;
the real-time scale discrimination value can be approximately regarded as the number of network nodes through which the information is propagated per unit time, and the real-time scale discrimination value must be increased when the propagation of the real-time information is intensified, so that the real-time scale discrimination value must be increased to be within a threshold value interval when the real-time information becomes high propagation information.
Referring to fig. 6, determining whether the trend of real-time information propagation is slowed down includes the steps of:
judging whether the real-time proportion judging value is reduced, if so, slowing down the trend of real-time information transmission, and if not, not slowing down the trend of real-time information transmission;
when the real-time proportion judging value is reduced, the number of network nodes through which the unit time information is transmitted is reduced, when the real-time proportion judging value is increased, the number of network nodes through which the unit time information is transmitted is increased, and when the trend of the real-time information transmission is not slowed down, the limitation measure is required to be enlarged, so that the limitation network nodes are enlarged.
An information propagation analysis system based on multi-element big data analysis is used for realizing the information propagation analysis method based on multi-element big data analysis, and comprises the following steps:
the path acquisition module acquires at least one propagation path of past information based on big data;
the transmission length acquisition module acquires the transmission length of the past information in the first network node;
the information propagation evaluation module evaluates and ranks the propagation range of the past information according to the influence range and the propagation speed;
the high propagation analysis module is used for analyzing and acquiring fermentation nodes of high propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, analyzing and acquiring acceleration points of the high propagation past information propagation, and acquiring initial forms of the high propagation past information;
the node classification module classifies and classifies the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
the information transmission judging module judges whether the real-time information transmission is high transmission information or not and judges whether the trend of the real-time information transmission is slowed down or not;
and the information node processing module prohibits the forwarding of the real-time information at the acceleration point, deletes the forwarded real-time information at the acceleration point, prohibits the forwarding of the real-time information at the key node, and deletes the forwarded real-time information at the key node.
The working process of the information propagation analysis system based on diversified big data analysis is as follows:
step one: the path acquisition module acquires at least one propagation path of past information based on big data;
step two: the propagation length acquisition module selects any network node in a propagation path of the past information as a first network node, and acquires the propagation length of the past information in the first network node;
step three: the information propagation evaluation module evaluates and ranks the propagation range of the past information according to the influence range and the propagation speed;
step four: acquiring at least one piece of high-propagation past information with a past information evaluation level higher than a preset level;
step five: the high propagation analysis module analyzes and acquires fermentation nodes of high propagation past information propagation, analyzes and acquires triggering reasons of propagation bursts to form a triggering keyword packet, and analyzes and acquires acceleration points of the high propagation past information propagation;
step six: the high propagation analysis module acquires the initial form of the high propagation past information;
step seven: the node classification module classifies and classifies the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
step eight: the method comprises the steps that real-time information is obtained, an information propagation judging module evaluates whether the property of the real-time information is benign or not, if yes, no processing is carried out, if not, the trend of the real-time information propagation is predicted according to the initial state of the high-propagation past information, the information propagation judging module judges whether the real-time information propagation is the high-propagation information, if not, no processing is carried out, the information node processing module prohibits the forwarding of the real-time information at an acceleration point and deletes the forwarded real-time information at the acceleration point, if yes, the information propagation judging module judges whether the trend of the real-time information propagation is slow down, if not, the information node processing module prohibits the forwarding of the real-time information at a key node and deletes the forwarded real-time information at the key node.
Still further, the present solution also proposes a storage medium having a computer-readable program stored thereon, which when called performs the above-described information propagation analysis method based on diversified big data analysis.
It is understood that the storage medium may be a magnetic medium, e.g., floppy disk, hard disk, magnetic tape; optical media such as DVD; or a semiconductor medium such as a solid state disk SolidStateDisk, SSD, etc.
In summary, the invention has the advantages that: through setting up information propagation evaluation module, high propagation analysis module, node classification module and information propagation judgement module, can make reasonable prejudgement to the trend of information propagation according to the judgement model of establishing to decompose the process of information propagation, obtain the key node of information propagation outburst, according to the key node, to probably causing the high propagation information of harmful effect, carry out the pertinence to suppress, whether network node is exploded to the information propagation that probably produces, carry out propagation restriction, and then can strengthen the validity of restriction, reduce the point position of restriction, guarantee restriction speed, save the calculated power.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. An information propagation analysis method based on diversified big data analysis is characterized by comprising the following steps:
acquiring at least one propagation path of past information based on big data, wherein the propagation path is formed by network nodes for past information transmission, and the network nodes are formed by various app users and network communities;
selecting any network node in a propagation path of the past information as a first network node, and acquiring the propagation length of the past information in the first network node;
evaluating and grading the propagation range of the past information according to the influence range and the propagation speed;
acquiring at least one piece of high-propagation past information with a past information evaluation level higher than a preset level;
analyzing and acquiring fermentation nodes of high-propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, and analyzing and acquiring acceleration points of the high-propagation past information propagation, wherein the fermentation nodes and the acceleration points are one of network nodes;
acquiring the initial form of the high-transmission past information;
classifying and grading the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
acquiring real-time information, evaluating whether the property of the real-time information is benign, if so, not performing any processing, if not, predicting the trend of real-time information propagation according to the initial state of high propagation past information, judging whether the real-time information propagation is high propagation information, if not, performing no processing, if so, prohibiting forwarding of the real-time information at an acceleration point, deleting the forwarded real-time information at the acceleration point, judging whether the trend of real-time information propagation is slow down, if not, performing no processing, prohibiting forwarding of the real-time information at a key node, and deleting the forwarded real-time information at the key node.
2. The information propagation analysis method based on the diversified big data analysis of claim 1 wherein the propagation path for acquiring at least one past information based on big data comprises the steps of:
and acquiring at least one past information, and acquiring all network nodes passing through in the past information transmission process to obtain a propagation path of the past information.
3. The information propagation analysis method based on the diversified big data analysis according to claim 2, wherein the acquiring the propagation length of the past information at the first network node includes the steps of:
acquiring a propagation path of past information, and acquiring the position of a first network node in the propagation path;
acquiring an initial network node of a propagation path, and acquiring a first propagation path from the initial network node to a first network node in the propagation path of the past information;
the number of the network nodes in the first propagation path is obtained and used as the propagation length of the past information in the first network node.
4. The information propagation analysis method based on the diversified big data analysis according to claim 3, wherein the evaluating and grading the propagation range of the past information according to the influence range and the propagation speed comprises the following steps:
acquiring a propagation path of the past information, and summarizing at least one network node with equal propagation length into a network node set;
arranging the network node sets from small to large according to the propagation length;
in the propagation path of the past information, calculating the propagation time of the network node, wherein the propagation time of the network node is the propagation time of the past information from the previous network node to the current network node;
calculating the average value of the propagation time of all network nodes in the network node set to obtain the propagation time of the network node set;
acquiring at least one first network node set with the number of elements exceeding a preset value in the network node set;
accumulating the number of elements in the first network node set to obtain a comprehensive judgment value;
accumulating the propagation time of the first network node set to obtain a time judgment value;
dividing the comprehensive judgment value by the time judgment value to obtain a proportion judgment value;
evaluating a first network node set with the proportion discrimination value smaller than a first preset proportion as a primary network node set;
evaluating a first network node set with a proportion discrimination value between a first preset proportion and a second preset proportion as a medium-level network node set;
evaluating a first network node set with a proportion discrimination value larger than a second preset proportion as an advanced network node set, wherein the first preset proportion is smaller than the second preset proportion;
if the network node sets in the past information are all not the first network node set, the past information is low propagation information;
if the first network node set exists in the network node set in the past information, but the highest level of the first network node set is the primary network node set, the past information is the next highest propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the intermediate network node set, the past information is the high-propagation past information;
if the first network node set exists in the network node sets in the past information, but the highest level of the first network node set is the advanced network node set, the past information is the ultrahigh propagation past information;
the ultrahigh-propagation past information is high-propagation past information.
5. The information propagation analysis method based on the diversified big data analysis of claim 4 wherein the fermenting node for analyzing and obtaining the high propagation past information propagation comprises the steps of:
taking network nodes in the primary network node set as fermentation nodes;
analyzing and acquiring triggering reasons of the propagation burst, and forming a triggering keyword package comprises the following steps:
using a neural network model to identify high-frequency words in the high-propagation past information, and summarizing the high-frequency words to obtain a trigger keyword package;
analyzing and acquiring acceleration points of high-propagation past information propagation comprises the following steps:
and taking the network nodes in the advanced network node set as acceleration points.
6. The information propagation analysis method based on the diversified big data analysis of claim 5 wherein the initial morphology of the acquired highly propagated past information comprises the steps of:
summarizing all medium-level network node sets and high-level network node sets of at least one high-propagation past information;
obtaining the maximum value and the minimum value of the proportion discrimination values of the medium-level network node set and the high-level network node set;
the maximum value and the minimum value are combined to obtain a threshold section, which is a characteristic of the initial form of the high-transmission past information.
7. The information propagation analysis method based on the diversified big data analysis of claim 6 wherein classifying and grading the network node according to the propagation path of the previous information comprises the steps of:
the network nodes as the fermentation node and the acceleration node are set as key nodes.
8. The information dissemination analysis method based on the multiple big data analysis according to claim 7, wherein the judging whether the real-time information dissemination is the high dissemination information comprises the steps of:
acquiring a real-time propagation path of real-time information propagation, and updating the real-time propagation path in real time according to the propagation condition of the real-time information;
summarizing at least one network node with equal propagation length into a real-time network node set;
arranging the real-time network node set from small to large according to the propagation length;
when a real-time network node set with the number of elements exceeding a preset value exists, the real-time network node set with the number of elements exceeding the preset value is used as a first real-time network node set;
accumulating the number of elements in the first real-time network node set to obtain a real-time comprehensive judgment value;
accumulating the propagation time of the first real-time network node set to obtain a real-time judgment value;
dividing the real-time comprehensive judgment value by the real-time judgment value to obtain a real-time proportion judgment value;
and judging whether the real-time proportion judging value is in a threshold value interval, if so, judging that the real-time information is transmitted as high transmission information, and if not, judging that the real-time information is transmitted as not high transmission information.
9. The information dissemination analysis method based on the multiple big data analysis according to claim 8, wherein the judging whether the trend of the real-time information dissemination is slowed down comprises the following steps:
and judging whether the real-time proportion judging value is reduced, if so, slowing down the trend of real-time information transmission, and if not, not slowing down the trend of real-time information transmission.
10. An information propagation analysis system based on a multiplex big data analysis for realizing the information propagation analysis method based on a multiplex big data analysis according to any one of claims 1 to 9, comprising:
the path acquisition module acquires at least one propagation path of past information based on big data;
the transmission length acquisition module acquires the transmission length of the past information in the first network node;
the information propagation evaluation module evaluates and ranks the propagation range of the past information according to the influence range and the propagation speed;
the high propagation analysis module is used for analyzing and acquiring fermentation nodes of high propagation past information propagation, analyzing and acquiring triggering reasons of propagation bursts to form a triggering keyword packet, analyzing and acquiring acceleration points of the high propagation past information propagation, and acquiring initial forms of the high propagation past information;
the node classification module classifies and classifies the network nodes according to the propagation paths of the past information to obtain key nodes in the network nodes;
the information transmission judging module judges whether the real-time information transmission is high transmission information or not and judges whether the trend of the real-time information transmission is slowed down or not;
and the information node processing module prohibits the forwarding of the real-time information at the acceleration point, deletes the forwarded real-time information at the acceleration point, prohibits the forwarding of the real-time information at the key node, and deletes the forwarded real-time information at the key node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410091890.5A CN117611374B (en) | 2024-01-23 | 2024-01-23 | Information propagation analysis method and system based on diversified big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410091890.5A CN117611374B (en) | 2024-01-23 | 2024-01-23 | Information propagation analysis method and system based on diversified big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117611374A true CN117611374A (en) | 2024-02-27 |
| CN117611374B CN117611374B (en) | 2024-05-07 |
Family
ID=89948331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410091890.5A Active CN117611374B (en) | 2024-01-23 | 2024-01-23 | Information propagation analysis method and system based on diversified big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117611374B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016124116A1 (en) * | 2015-02-04 | 2016-08-11 | 阿里巴巴集团控股有限公司 | Method and device for disseminating information |
| CN106127590A (en) * | 2016-06-21 | 2016-11-16 | 重庆邮电大学 | A kind of information Situation Awareness based on node power of influence and propagation management and control model |
| CN110837608A (en) * | 2019-11-07 | 2020-02-25 | 中科天玑数据科技股份有限公司 | Public opinion topic propagation path analysis system and method based on multi-source data |
| CN113282841A (en) * | 2021-07-19 | 2021-08-20 | 中国传媒大学 | Modeling-based public topic propagation evaluation method and system |
| KR20230025200A (en) * | 2021-08-13 | 2023-02-21 | 청주대학교 산학협력단 | Method for analyzing propagation characteristics of cross-border news influence and information analysis system using thereof |
| CN116016199A (en) * | 2023-02-21 | 2023-04-25 | 山东海量信息技术研究院 | Information control method, system, electronic equipment and readable storage medium |
| CN116319379A (en) * | 2023-05-17 | 2023-06-23 | 云目未来科技(湖南)有限公司 | Network information guiding intervention method and system based on propagation chain |
| CN116822931A (en) * | 2022-12-30 | 2023-09-29 | 河南科技大学 | False information propagation control method based on key node propagation risk analysis |
| CN117093762A (en) * | 2023-07-18 | 2023-11-21 | 南京特尔顿信息科技有限公司 | Public opinion data evaluation analysis system and method |
| CN117332161A (en) * | 2023-10-11 | 2024-01-02 | 深圳市网联安瑞网络科技有限公司 | Social network topic discussion influence detection method and system |
-
2024
- 2024-01-23 CN CN202410091890.5A patent/CN117611374B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016124116A1 (en) * | 2015-02-04 | 2016-08-11 | 阿里巴巴集团控股有限公司 | Method and device for disseminating information |
| CN106127590A (en) * | 2016-06-21 | 2016-11-16 | 重庆邮电大学 | A kind of information Situation Awareness based on node power of influence and propagation management and control model |
| CN110837608A (en) * | 2019-11-07 | 2020-02-25 | 中科天玑数据科技股份有限公司 | Public opinion topic propagation path analysis system and method based on multi-source data |
| CN113282841A (en) * | 2021-07-19 | 2021-08-20 | 中国传媒大学 | Modeling-based public topic propagation evaluation method and system |
| KR20230025200A (en) * | 2021-08-13 | 2023-02-21 | 청주대학교 산학협력단 | Method for analyzing propagation characteristics of cross-border news influence and information analysis system using thereof |
| CN116822931A (en) * | 2022-12-30 | 2023-09-29 | 河南科技大学 | False information propagation control method based on key node propagation risk analysis |
| CN116016199A (en) * | 2023-02-21 | 2023-04-25 | 山东海量信息技术研究院 | Information control method, system, electronic equipment and readable storage medium |
| CN116319379A (en) * | 2023-05-17 | 2023-06-23 | 云目未来科技(湖南)有限公司 | Network information guiding intervention method and system based on propagation chain |
| CN117093762A (en) * | 2023-07-18 | 2023-11-21 | 南京特尔顿信息科技有限公司 | Public opinion data evaluation analysis system and method |
| CN117332161A (en) * | 2023-10-11 | 2024-01-02 | 深圳市网联安瑞网络科技有限公司 | Social network topic discussion influence detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张博;李竹君;: "微博信息传播效果研究综述", 现代情报, no. 01, 15 January 2017 (2017-01-15), pages 165 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117611374B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111614627B (en) | SDN-oriented cross-plane cooperation DDOS detection and defense method and system | |
| US8307459B2 (en) | Botnet early detection using hybrid hidden markov model algorithm | |
| WO2022036801A1 (en) | Method and system for achieving coexistence of heterogeneous networks | |
| CN112235288B (en) | NDN network intrusion detection method based on GAN | |
| Yan et al. | Low-rate dos attack detection based on improved logistic regression | |
| CN107276696A (en) | Signal detection algorithm under a kind of Low SNR | |
| CN111224984A (en) | Snort improvement method based on data mining algorithm | |
| Althunibat et al. | Novel energy-efficient reporting scheme for spectrum sensing results in cognitive radio | |
| CN111600876A (en) | Slow denial of service attack detection method based on MFOPA algorithm | |
| CN113626812A (en) | Machine learning Trojan horse detection method based on structural feature screening and load expansion | |
| Wu et al. | Mitigation measures of collusive interest flooding attacks in named data networking | |
| CN117611374B (en) | Information propagation analysis method and system based on diversified big data analysis | |
| CN108566382B (en) | Firewall self-adaption capability improving method based on rule life cycle detection | |
| Yasin et al. | Feature Selection for Black Hole Attacks. | |
| US8417783B1 (en) | System and method for improving feature selection for a spam filtering model | |
| JP2001077813A (en) | Network information management system, network information management method and recording medium recording its processing program | |
| CN117014182A (en) | Malicious traffic detection method and device based on LSTM | |
| CN115664777A (en) | Slow flow table overflow attack detection and mitigation method based on two-stage threshold | |
| Yin et al. | An improved bayesian algorithm for filtering spam e-mail | |
| Deng et al. | Abnormal traffic detection of IoT terminals based on Bloom filter | |
| CN109995663B (en) | Network information propagation method based on length constraint and no repeated path | |
| Deng et al. | Self-adaptive Threshold Traffic Anomaly Detection Based on $\varphi $-Entropy and the Improved EWMA Model | |
| Reviriego et al. | Improving packet flow counting with fingerprint counting | |
| Sannomiya et al. | Cardinality counting circuit for real-time abnormal traffic detection | |
| CN115037392B (en) | Signal detection method, terminal, medium and aircraft based on random forest |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |