CN112883278A - Bad public opinion propagation inhibition method based on big data knowledge graph of smart community - Google Patents
Bad public opinion propagation inhibition method based on big data knowledge graph of smart community Download PDFInfo
- Publication number
- CN112883278A CN112883278A CN202110307968.9A CN202110307968A CN112883278A CN 112883278 A CN112883278 A CN 112883278A CN 202110307968 A CN202110307968 A CN 202110307968A CN 112883278 A CN112883278 A CN 112883278A
- Authority
- CN
- China
- Prior art keywords
- community
- node
- network
- nodes
- knowledge
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000005764 inhibitory process Effects 0.000 title claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 5
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 230000001629 suppression Effects 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000002401 inhibitory effect Effects 0.000 abstract description 3
- 238000012916 structural analysis Methods 0.000 abstract 1
- 210000000349 chromosome Anatomy 0.000 description 17
- 230000003053 immunization Effects 0.000 description 13
- 238000002649 immunization Methods 0.000 description 11
- 230000035772 mutation Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000005541 medical transmission Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010353 genetic engineering Methods 0.000 description 2
- 230000036039 immunity Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a bad public opinion propagation inhibition method based on a big data knowledge graph of a smart community, which comprises the following steps: s1) constructing a knowledge graph and a community network based on the intelligent community bad public opinion propagation inhibition model; s2) dividing the community network into a plurality of communities by adopting a community detection algorithm, and converting the community detection problem into an optimized problem by adopting a BGLL algorithm; s3) selecting a corresponding node to obtain a candidate immune node set; s4) optimizing a propagation threshold function by using an improved Memetic algorithm to select a final immune node from the candidate immune node set, and inhibiting propagation of bad public opinions in the intelligent community. According to the invention, the big data knowledge graph of the smart community is subjected to deep structural analysis, and the bad public opinion suppression algorithm based on the big data knowledge graph of the smart community and artificial intelligence can realize low-cost, small-influence and high-efficiency bad public opinion suppression, improve the management effect of a manager and reduce the management burden.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the technical field of knowledge maps, and particularly relates to a bad public opinion propagation inhibition method based on a big data knowledge map of an intelligent community.
[ background of the invention ]
The social relationship in the community can be represented by a complex network, and the community structure is used as an important property of the complex network and is increasingly applied to complex network behavior prediction and structure mining. With the rapid development of information networks in recent years, information dissemination is a research hotspot of complex networks in recent years. How to understand and utilize information dissemination is significant and has great practical value. The maximum value can be obtained by advertising the nodes with large influence. However, the propagation of internet public opinion causes great loss to our life and health, so it is very necessary to research and control the model of the inhibition of the propagation of poor public opinion.
In recent years of research, information transmission is modeled as a disease transmission model by a learner, and the propagation of the speech is controlled by a propagation control method based on bionics. For the immunization strategy, a certain cost is needed for immunizing one node, so that the research point of immunization is how to obtain the maximum inhibition effect by immunizing the minimum number of nodes, and from the aspect of poor opinion transmission, how to realize the transmission detection and control of poor opinions by minimizing the freedom of opinions affecting the public. In the previous research, scholars propose a large number of immunization strategies, target immunization is a strategy commonly used in immunization, immunization nodes are selected according to different structural characteristics of a network, but with the proposal of a propagation threshold function, a propagation inhibition problem is modeled as an optimization problem, an optimal immunization node can be found through the optimization threshold, and the traditional immunization strategy is not suitable for an optimization model any more.
Therefore, there is a need to provide a new method for suppressing the propagation of bad public opinions based on the big data knowledge graph of the smart community to solve the above problems.
[ summary of the invention ]
The invention mainly aims to provide a bad public opinion propagation inhibition method based on a big data knowledge graph of a smart community.
The invention realizes the purpose through the following technical scheme: a bad public opinion propagation inhibition method based on a big data knowledge graph of a smart community comprises the following steps:
s1) constructing a knowledge graph based on the intelligent community bad public opinion propagation inhibition model, and constructing a community network of the bad public opinion propagation inhibition model based on the knowledge graph;
s2) for the constructed community network, dividing the community network into a plurality of communities by adopting a community detection algorithm, and converting the community detection problem into an optimized problem by defining a modularity function by adopting a classical BGLL algorithm;
s3) selecting corresponding nodes according to the property of the community structure to obtain a candidate immune node set;
s4) based on the candidate immune node set obtained in the step S3), combining the properties of the network community, and selecting a final immune node from the candidate immune node set by utilizing an improved Memetic algorithm optimized propagation threshold function, so that propagation of bad public opinions in the smart community is effectively inhibited.
Further, in the step S1), a knowledge graph based on the intelligent community bad public opinion propagation inhibition model is constructed, including extracting community knowledge from original community data through knowledge extraction and knowledge representation, then storing the extracted community knowledge into a data layer and a mode layer of a knowledge base, and solving the problems of redundancy and lack of logic of the existing community knowledge through knowledge fusion including entity linking and knowledge merging; and carrying out conflict resolution on conflicts generated by data sources or different construction methods in the knowledge graph formed by the community knowledge according to the reliability of the data sources or a machine learning method to form the big data knowledge graph of the intelligent community.
Further, the dividing the community network into a plurality of communities by using a community detection algorithm in step S2) specifically includes:
s21) a community detection algorithm is adopted to divide the complex social network into different sub-networks, and after the big data knowledge map of the intelligent community is constructed, a modularity function of the community knowledge map is established, which is defined as follows:
where A is the adjacency matrix of the network, m is the number of edges in the network, kiIs the degree of the node i, i.e. the sum of the weights of all edges occurring on the node i, when the node i and the node j are in the same community, δ (i, j) is 1, otherwise δ (i, j) is 0;
s22) adopting a BGLL algorithm based on modularity optimization, continuously aggregating from bottom to top, dividing each node in a community network into a sub-community, regarding each node i in the network, considering all neighbor nodes j, moving the node i from the community where the node i is located to the community where the neighbor j is located, changing modularity increment, moving the node i to the community where the node j with the largest modularity increment is located, and moving an isolated node to the community where the neighbor node is located each time with modularity gain of delta Q:
where Σ in is the sum of the weights of all edges within the community network, Σ tot is the sum of the weights of edges associated with all nodes in the community network, kiIs the node degree, i.e. the sum of the weights, k, of all edges occurring at node ii,inIs the sum of the weights of the edges from node i to all nodes in the community network, and m is the netThe sum of the weights of all edges in the network;
s23) regarding the community divided in the step S22) as a node, thereby obtaining a new network, wherein the weight of the edge between the new nodes is the sum of the original weights between the two new nodes, and the edge between the nodes in the same community causes the new node to have the edge of the self-loop in the new network; then, the method in S22) is used for iteration on the constructed new network, and the iteration is stopped when the network is not changed any more, that is, the maximum modularity appears, so that a plurality of community partitions are obtained.
Further, in the step S3), selecting a suitable node according to the property of the community structure to obtain a candidate immune node set; the method specifically comprises the following steps:
s31), calculating the node degree of each node of the community, wherein the calculation formula is as follows:
wherein the degree of penetration
Degree of delivery
When there is an edge between node i and node j ij1, otherwiseij＝0；
S32) taking the nodes with the maximum internal degrees in the preset number in each community as pivot nodes, taking all the nodes with the external degrees larger than 1 as bridge nodes, and taking the bridge nodes as candidate seed nodes.
Compared with the prior art, the harmful public opinion propagation inhibition method based on the big data knowledge graph of the smart community has the beneficial effects that: through big data knowledge map and artificial intelligence's bad public opinion suppression algorithm based on wisdom community, can realize low-cost, little influence, efficient bad public opinion suppression, promote managers' management effect, reduce the management burden. In particular, the method comprises the following steps of,
1) applying the big data map to community bad public opinion and disease transmission;
2) providing a disease propagation inhibition model, and inhibiting a rapid propagation mechanism of a complex network by node immunization through key nodes in the immune community complex network;
3) the community network is optimized based on a modularity function, a classic BGLL algorithm is based on an aggregation algorithm in modularity optimization, the community network is continuously aggregated from bottom to top, and the detection problem of the community structure and the search problem of a candidate set in a complex network are effectively solved by detecting the community network through the incremental change of the modularity Q;
4) in the generation of the candidate set, the seed nodes of the candidate set are quickly locked through the node degree of a complex network, and the propagation can be more efficiently inhibited through the immunity of the pivot nodes and the bridge nodes;
5) memetic algorithm is adopted to prevent the algorithm from falling into local optimum, and the complexity of calculation is reduced.
[ description of the drawings ]
FIG. 1 is a main method block diagram in an embodiment of the present invention;
FIG. 2 is a knowledge graph of an adverse public opinion propagation inhibition model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a candidate immunization node according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of cross operation in Memetic-based algorithm according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a variant operation based on Memetic algorithm in an embodiment of the present invention.
[ detailed description ] embodiments
Example (b):
referring to fig. 1 to 5, the present embodiment is a method for suppressing propagation of bad public opinion based on big data knowledge graph of smart community, which includes the following steps:
s1), firstly, constructing a knowledge graph based on the intelligent community bad public opinion propagation inhibition model, and constructing a community network of the bad public opinion propagation inhibition model based on the knowledge graph;
s2), for the constructed community network, dividing the community network into a plurality of communities by adopting a community detection algorithm, mainly using a classic BGLL algorithm, and changing community detection into an optimized problem by defining a modularity function;
s3), selecting proper nodes to obtain a candidate immune node set according to the property of the community structure based on the community structure which still cannot obtain immune nodes;
s4), based on the candidate immune node set obtained in the third step, combining the properties of the network community, and selecting a final immune node from the candidate immune node set by utilizing an improved Memetic algorithm optimized propagation threshold function, so that propagation of bad public opinions in the smart community is effectively inhibited.
In the step S1), a knowledge graph based on an intelligent community bad public opinion propagation inhibition model is constructed, wherein community knowledge is extracted from original community data through knowledge extraction and knowledge representation from the original data and a third-party database, then the extracted community knowledge is stored in a data layer and a mode layer of a knowledge base, and entity linkage and knowledge combination are included through knowledge fusion, so that the problems of redundancy and lack of logicality of the existing community knowledge are solved, and the community knowledge quality is improved; and carrying out conflict resolution on conflicts generated by data sources or different construction methods in the knowledge graph formed by the community knowledge according to the reliability of the data sources or a machine learning method to form the big data knowledge graph of the intelligent community.
The construction process of the big data knowledge graph of the smart community comprises the following steps: the method comprises four processes of knowledge extraction, knowledge representation, knowledge fusion and knowledge reasoning, wherein one period of each update comprises the four stages. The construction of the knowledge graph adopts a bottom-up mode, firstly, entities are extracted from some open-linked data, then, knowledge with high reliability is selected and added into a knowledge base, and then, a top-level ontology mode is constructed.
The original data source comprises community WeChat group chat information and chat information of community residents. The extracted community knowledge comprises life behavior characteristics of community personnel, and the behavior characteristics comprise working conditions, social relations, WeChat group chat information, publishing of community hot topics and the like.
In the step S2), a community detection algorithm is adopted to divide the community network into a plurality of communities, which specifically includes:
s21) community detection divides a complex social network into different sub-networks, and after a big data knowledge graph of the intelligent community is constructed, in view of the fact that numerous personnel characteristics and personnel individuals exist in the community and the fact that groups with high closeness of different nodes are difficult to obtain, a modularity function of the knowledge graph of the community is established and defined as follows:
where A is the adjacency matrix of the network, m is the number of edges in the network, kiIs the degree of the node i, i.e. the sum of the weights of all edges occurring on the node i, and δ (i, j) is 1 when the node i and the node j are in the same community, otherwise δ (i, j) is 0. Thus, the community detection becomes a community detection algorithm based on modularity optimization;
s22) adopting a BGLL algorithm based on modularity optimization, continuously aggregating from bottom to top, dividing each node in a community network into a sub-community, regarding each node i in the network, considering all neighbor nodes j, moving the node i from the community where the node i is located to the community where the neighbor j is located, wherein modularity increment changes, the node i is moved to the community where the node j with the largest modularity increment is located, and each time the node moves an isolated node to the community where the neighbor is located, wherein modularity gain is delta Q:
where Σ in is the sum of the weights of all edges within the community network, Σ tot is the sum of the weights of edges associated with all nodes in the community network, kiIs the node degree, i.e. the sum of the weights, k, of all edges occurring at node ii,inIs the sum of the weights of the edges from the node i to all the nodes in the community network, and m is the sum of the weights of all the edges in the network;
s23) regarding the community divided in the step S22) as a node, thereby obtaining a new network. The weight of the edge between the new nodes is the sum of the original weights between the two new nodes (namely between the two communities), and the edge between the nodes in the same community causes the new node to have the edge of the self-loop in the new network. Then, the method in S22) is used for iteration on the constructed new network, and the iteration is stopped when the network is not changed any more, that is, the maximum modularity appears, so that a plurality of community partitions are obtained.
Compared with other community detection algorithms, the BGLL algorithm has many advantages: first, the BGLL algorithm works very well for community detection. Second, the time complexity of the BGLL algorithm is very low, so BGLL can perform community detection on large-scale networks. Third, the BGLL algorithm does not need to give the community number in advance, and is more universal.
In the step S3), selecting a suitable node according to the property of the community structure to obtain a candidate immune node set; the method specifically comprises the following steps:
s31), calculating the node degree of each node of the community, wherein the calculation formula is as follows:
wherein the degree of penetration
Degree of delivery
When there is an edge between node i and node j ij1, otherwiseij＝0。
After the community detection is finished, immune nodes cannot be obtained, the community detection is not suitable for optimizing an infection threshold, the candidate set is generated to search candidate seeds by using the properties of the community, the algorithm search space is reduced to the maximum extent, and based on the immune strategy of the community, in a network with an obvious community structure, junction nodes and bridge nodes are in poor opinion and diseasesThe influence is quite deep in the process of spreading the disease, the candidate seed nodes are selected according to the node degree in the community nodes, and for a directed community network, the node degree k isiComprises an in-degree and an out-degree;
s32) taking the node with the highest degree of internal degree (i.e. the node degree between the nodes in each community) of the top 20% in each community as a pivot node, and taking all the nodes with the degree of external degree (i.e. the node degree between the communities and the nodes between the communities) greater than 1 as bridge nodes, wherein the bridge nodes are candidate seed nodes. As shown in fig. 3, the node 2 is a pivot node, and the node 12 is a bridge node, i.e., a candidate seed node. In the transmission center of bad public opinion and disease, the node can be quickly transmitted to other nodes in the community, and the bridge node can transmit the transmission among different communities.
In the step S4), after the candidate set exists, it is still difficult to select the final immune node due to the great time complexity of the greedy algorithm, and in order to reduce the computational complexity, the technique selects the final immune node from the candidate immune node set based on the Memetic algorithm, which has the following framework:
the method comprises the following specific steps:
s41) representation and initialization of the solution: in the Memetic algorithm, each chromosome represents a set of nodes that need to be immunized, and each chromosome is encoded as an integer string:
x＝{x1,x2,L,xR} (4)
wherein R is the number of immunonodes, xiThe node is the ith node to be immunized in the candidate set, each node can only appear once in each chromosome, and each chromosome can be initialized randomly;
s42) genetic manipulation: in the Memetic algorithm, genetic manipulation is used for preventing the algorithm from falling into local optimization, and cross operation and mutation operation are redesigned according to the structural knowledge of the network and community.
The technique adopts random crossing operation to give two chromosomes xAAnd xBThe elements common to both chromosomes remain unchanged. For each individual element in the chromosome, a random number is first generated, and if the random number is greater than 0.5, the corresponding element is exchanged, otherwise it remains unchanged. The process of the crossover operation is shown in fig. 4, where 6 nodes need to be immunized, two parent chromosomes have 3 nodes in common, these nodes remain unchanged, and nodes 16, 5, 15 in parent chromosome 1. Nodes 6, 10, 4 in parent chromosome 2 need to be interleaved, assuming that the random numbers for the three pairs of chromosomes are 0.7, 0.6 and 0.3, respectively, nodes 16 and 6 will be swapped, nodes 5 and 10 will also need to be swapped, and nodes 4 and 15 will remain unchanged. The newly generated offspring population of such crossover operations may inherit most of the elements in the parent chromosomes;
the technology adopts the operation of single-point variation to x in chromosomeAEach node in (1) first generates a random number. If the random number is greater than the mutation probability pmSelected node viWill be vjWherein v isjNot belonging to chromosome xAAnd v isjAnd viIn different communities. FIG. 5 shows the process of the mutation operation. In the figure, the network has three communities, wherein the nodes 1 and 2 belong to the community 1, the nodes 3, 4 and 5 belong to the community 2, and the nodes 6, 7, 8, 9 and 10 belong to the community 3. the node 10 is supposed to carry out mutation operation, and one node is randomly selected from the communities 1 and 2 to replace the node 10;
s43) in cross mutation, the parent obtains offspring chromosomes by exchanging part of chromosomes, there is no new node in the chromosomes, and mutation operation tends to search nodes of other communities, so the present technology adopts a local search algorithm based on a neighborhood, assuming that a node i is in a community C, the neighborhood of the node i is defined as all nodes except the node i in the community C, in the local search, the node i is replaced by a certain node in the neighborhood of the node i, the operation can obtain an optimal solution, and only the chromosome with the optimal objective function in the population is subjected to the local search operation, the local search proposed here focuses on searching the optimal solution in the community, and the following algorithm gives a local search process:
s44) verifying effectiveness of the poor public opinion propagation inhibition model through Matlab simulation software, obtaining a final immune node through a genetic algorithm based on Memetic, and completing the poor public opinion propagation inhibition based on the big data knowledge graph of the smart community by the immune target node.
According to the bad public opinion propagation inhibition method based on the big data knowledge graph of the smart community, the bad public opinion inhibition algorithm based on the big data knowledge graph of the smart community and artificial intelligence can achieve low-cost, small-influence and high-efficiency bad public opinion inhibition, the management effect of a manager is improved, and the management burden is reduced. In particular, the method comprises the following steps of,
1) applying the big data map to community bad public opinion and disease transmission;
2) providing a disease propagation inhibition model, and inhibiting a rapid propagation mechanism of a complex network by node immunization through key nodes in the immune community complex network;
3) optimizing a community network based on a modularity function, wherein a classic BGLL algorithm is based on an aggregation algorithm in modularity optimization, continuously aggregating from bottom to top, and detecting the community network through incremental change of modularity Q;
4) in the generation of the candidate set, the seed nodes of the candidate set are quickly locked through the node degree of a complex network, and the propagation can be more efficiently inhibited through the immunity of the pivot nodes and the bridge nodes;
5) memetic algorithm is used to prevent the algorithm from falling into local optima.
What has been described above are merely some embodiments of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept thereof, and these changes and modifications can be made without departing from the spirit and scope of the invention.
Claims (4)
1. A bad public opinion propagation inhibition method based on a big data knowledge graph of a smart community is characterized by comprising the following steps: which comprises the following steps:
s1) constructing a knowledge graph based on the intelligent community bad public opinion propagation inhibition model, and constructing a community network of the bad public opinion propagation inhibition model based on the knowledge graph;
s2) for the constructed community network, dividing the community network into a plurality of communities by adopting a community detection algorithm, and converting the community detection problem into an optimized problem by defining a modularity function by adopting a classical BGLL algorithm;
s3) selecting corresponding nodes according to the property of the community structure to obtain a candidate immune node set;
s4) based on the candidate immune node set obtained in the step S3), combining the properties of the network community, and selecting a final immune node from the candidate immune node set by utilizing an improved Memetic algorithm optimized propagation threshold function, so that propagation of bad public opinions in the smart community is effectively inhibited.
2. The method for suppressing the spread of bad public opinions based on the wisdom community big data knowledge graph of claim 1, wherein: in the step S1), a knowledge graph based on an intelligent community bad public opinion propagation inhibition model is constructed, wherein community knowledge is extracted from original community data through knowledge extraction and knowledge representation from the original data and a third-party database, then the extracted community knowledge is stored in a data layer and a mode layer of a knowledge base, and the problems of redundancy and lack of logicality of the existing community knowledge are solved through knowledge fusion including entity linking and knowledge merging; and carrying out conflict resolution on conflicts generated by data sources or different construction methods in the knowledge graph formed by the community knowledge according to the reliability of the data sources or a machine learning method to form the big data knowledge graph of the intelligent community.
3. The method for suppressing the spread of bad public opinions based on the wisdom community big data knowledge graph of claim 1, wherein: in the step S2), a community detection algorithm is adopted to divide the community network into a plurality of communities, which specifically includes:
s21) a community detection algorithm is adopted to divide the complex social network into different sub-networks, and after the big data knowledge map of the intelligent community is constructed, a modularity function of the community knowledge map is established, which is defined as follows:
where A is the adjacency matrix of the network, m is the number of edges in the network, kiIs the degree of the node i, i.e. the sum of the weights of all edges occurring on the node i, when the node i and the node j are in the same community, δ (i, j) is 1, otherwise δ (i, j) is 0;
s22) adopting a BGLL algorithm based on modularity optimization, continuously aggregating from bottom to top, dividing each node in a community network into a sub-community, regarding each node i in the network, considering all neighbor nodes j, moving the node i from the community where the node i is located to the community where the neighbor j is located, changing modularity increment, moving the node i to the community where the node j with the largest modularity increment is located, and moving an isolated node to the community where the neighbor node is located each time with modularity gain of delta Q:
where Σ in is the sum of the weights of all edges within the community network, Σ tot is the sum of the weights of edges associated with all nodes in the community network, kiIs the node degree, i.e. the sum of the weights, k, of all edges occurring at node ii,inIs the sum of the weights of the edges from the node i to all the nodes in the community network, and m is the sum of the weights of all the edges in the network;
s23) regarding the community divided in the step S22) as a node, thereby obtaining a new network, wherein the weight of the edge between the new nodes is the sum of the original weights between the two new nodes, and the edge between the nodes in the same community causes the new node to have the edge of the self-loop in the new network; then, the method in S22) is used for iteration on the constructed new network, and the iteration is stopped when the network is not changed any more, that is, the maximum modularity appears, so that a plurality of community partitions are obtained.
4. The method for suppressing the spread of bad public opinions based on the wisdom community big data knowledge graph of claim 1, wherein: in the step S3), selecting a suitable node according to the property of the community structure to obtain a candidate immune node set; the method specifically comprises the following steps:
s31), calculating the node degree of each node of the community, wherein the calculation formula is as follows:
wherein the degree of penetration
Degree of delivery
When there is an edge between node i and node jij1, otherwiseij＝0；
S32) taking the nodes with the maximum internal degrees in the preset number in each community as pivot nodes, taking all the nodes with the external degrees larger than 1 as bridge nodes, and taking the bridge nodes as candidate seed nodes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110307968.9A CN112883278A (en) | 2021-03-23 | 2021-03-23 | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110307968.9A CN112883278A (en) | 2021-03-23 | 2021-03-23 | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112883278A true CN112883278A (en) | 2021-06-01 |
Family
ID=76042748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110307968.9A Pending CN112883278A (en) | 2021-03-23 | 2021-03-23 | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112883278A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786126A (en) * | 2023-12-28 | 2024-03-29 | 永信至诚科技集团股份有限公司 | Knowledge graph-based naked-touch clue analysis method and device |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050243736A1 (en) * | 2004-04-19 | 2005-11-03 | International Business Machines Corporation | System, method, and service for finding an optimal collection of paths among a plurality of paths between two nodes in a complex network |
| WO2010051966A1 (en) * | 2008-11-07 | 2010-05-14 | Lingupedia Investments Sarl | Method for semantic processing of natural language using graphical interlingua |
| US20150120717A1 (en) * | 2013-10-25 | 2015-04-30 | Marketwire L.P. | Systems and methods for determining influencers in a social data network and ranking data objects based on influencers |
| US20170206276A1 (en) * | 2016-01-14 | 2017-07-20 | Iddo Gill | Large Scale Recommendation Engine Based on User Tastes |
| CN107016068A (en) * | 2017-03-21 | 2017-08-04 | 深圳前海乘方互联网金融服务有限公司 | Knowledge mapping construction method and device |
| CN107315734A (en) * | 2017-05-04 | 2017-11-03 | 中国科学院信息工程研究所 | A kind of method and system for becoming pronouns, general term for nouns, numerals and measure words standardization based on time window and semanteme |
| US20180373699A1 (en) * | 2017-06-26 | 2018-12-27 | International Business Machines Corporation | Adaptive evaluation of meta-relationships in semantic graphs |
| CN109189935A (en) * | 2018-07-02 | 2019-01-11 | 北京市天元网络技术股份有限公司 | A kind of the APP propagation analysis method and system of knowledge based map |
| US20190155961A1 (en) * | 2017-11-17 | 2019-05-23 | Microsoft Technology Licensing, Llc | Resource-Efficient Generation of a Knowledge Graph |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
| CN110866126A (en) * | 2019-11-22 | 2020-03-06 | 福建工程学院 | College online public opinion risk assessment method |
| CN111309824A (en) * | 2020-02-18 | 2020-06-19 | 中国工商银行股份有限公司 | Entity relationship map display method and system |
| CN111401700A (en) * | 2020-03-05 | 2020-07-10 | 平安科技（深圳）有限公司 | Data analysis method, device, computer system and readable storage medium |
| WO2020185900A1 (en) * | 2019-03-11 | 2020-09-17 | Roam Analytics, Inc. | Methods, apparatus and systems for annotation of text documents |
| CN111784508A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | Enterprise risk assessment method and device and electronic equipment |
| CN111881302A (en) * | 2020-07-23 | 2020-11-03 | 民生科技有限责任公司 | Bank public opinion analysis method and system based on knowledge graph |
| CN111914096A (en) * | 2020-07-06 | 2020-11-10 | 同济大学 | Public transport passenger satisfaction evaluation method and system based on public opinion knowledge graph |
| CN112101769A (en) * | 2020-09-09 | 2020-12-18 | 复旦大学 | Supply chain risk management system |
| CN112328801A (en) * | 2020-09-28 | 2021-02-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Method for predicting group events by event knowledge graph |
| CN112395282A (en) * | 2019-08-13 | 2021-02-23 | 华为技术有限公司 | Graph reconstruction method and device |
-
2021
- 2021-03-23 CN CN202110307968.9A patent/CN112883278A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050243736A1 (en) * | 2004-04-19 | 2005-11-03 | International Business Machines Corporation | System, method, and service for finding an optimal collection of paths among a plurality of paths between two nodes in a complex network |
| WO2010051966A1 (en) * | 2008-11-07 | 2010-05-14 | Lingupedia Investments Sarl | Method for semantic processing of natural language using graphical interlingua |
| US20150120717A1 (en) * | 2013-10-25 | 2015-04-30 | Marketwire L.P. | Systems and methods for determining influencers in a social data network and ranking data objects based on influencers |
| US20170206276A1 (en) * | 2016-01-14 | 2017-07-20 | Iddo Gill | Large Scale Recommendation Engine Based on User Tastes |
| CN107016068A (en) * | 2017-03-21 | 2017-08-04 | 深圳前海乘方互联网金融服务有限公司 | Knowledge mapping construction method and device |
| CN107315734A (en) * | 2017-05-04 | 2017-11-03 | 中国科学院信息工程研究所 | A kind of method and system for becoming pronouns, general term for nouns, numerals and measure words standardization based on time window and semanteme |
| US20180373699A1 (en) * | 2017-06-26 | 2018-12-27 | International Business Machines Corporation | Adaptive evaluation of meta-relationships in semantic graphs |
| US20190155961A1 (en) * | 2017-11-17 | 2019-05-23 | Microsoft Technology Licensing, Llc | Resource-Efficient Generation of a Knowledge Graph |
| CN109189935A (en) * | 2018-07-02 | 2019-01-11 | 北京市天元网络技术股份有限公司 | A kind of the APP propagation analysis method and system of knowledge based map |
| WO2020185900A1 (en) * | 2019-03-11 | 2020-09-17 | Roam Analytics, Inc. | Methods, apparatus and systems for annotation of text documents |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
| CN112395282A (en) * | 2019-08-13 | 2021-02-23 | 华为技术有限公司 | Graph reconstruction method and device |
| CN110866126A (en) * | 2019-11-22 | 2020-03-06 | 福建工程学院 | College online public opinion risk assessment method |
| CN111309824A (en) * | 2020-02-18 | 2020-06-19 | 中国工商银行股份有限公司 | Entity relationship map display method and system |
| CN111401700A (en) * | 2020-03-05 | 2020-07-10 | 平安科技（深圳）有限公司 | Data analysis method, device, computer system and readable storage medium |
| CN111784508A (en) * | 2020-07-01 | 2020-10-16 | 北京知因智慧科技有限公司 | Enterprise risk assessment method and device and electronic equipment |
| CN111914096A (en) * | 2020-07-06 | 2020-11-10 | 同济大学 | Public transport passenger satisfaction evaluation method and system based on public opinion knowledge graph |
| CN111881302A (en) * | 2020-07-23 | 2020-11-03 | 民生科技有限责任公司 | Bank public opinion analysis method and system based on knowledge graph |
| CN112101769A (en) * | 2020-09-09 | 2020-12-18 | 复旦大学 | Supply chain risk management system |
| CN112328801A (en) * | 2020-09-28 | 2021-02-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Method for predicting group events by event knowledge graph |
Non-Patent Citations (3)
| Title |
|---|
| SHREYANSH BHATT: "Knowledge Graph Enhanced Community Detection and Characterization", 《PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING》, pages 51 - 59 * |
| 张莹: "基于事件检测的微博社交网络社区识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技》, pages 138 - 2793 * |
| 王善峰: "基于进化计算的复杂网络结构分析与行为预测", 《中国博士学位论文全文数据库 基础科学》, pages 003 - 34 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117786126A (en) * | 2023-12-28 | 2024-03-29 | 永信至诚科技集团股份有限公司 | Knowledge graph-based naked-touch clue analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Generative adversarial learning for intelligent trust management in 6G wireless networks | |
| US11748628B2 (en) | Method for optimizing reservoir operation for multiple objectives based on graph convolutional neural network and NSGA-II algorithm | |
| Cheng | Topological optimization of a reliable communication network | |
| Valdez et al. | Modular neural networks architecture optimization with a new nature inspired method using a fuzzy combination of particle swarm optimization and genetic algorithms | |
| CN107784598A (en) | A kind of network community discovery method | |
| Hao et al. | Efficient and robust emergence of norms through heuristic collective learning | |
| CN111709560A (en) | Method for solving vehicle path problem based on improved ant colony algorithm | |
| CN102722750A (en) | Updating method and device of community structure in dynamic network | |
| CN114969367B (en) | Cross-language entity alignment method based on multi-aspect subtask interaction | |
| CN112883278A (en) | Bad public opinion propagation inhibition method based on big data knowledge graph of smart community | |
| CN115277115A (en) | Method and system for solving robust information propagation problem on network | |
| Li et al. | Improved shuffled frog leaping algorithm on system reliability analysis | |
| Nguyen et al. | Context tree maximizing | |
| CN115994459A (en) | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects | |
| Sharma et al. | Power law-based local search in artificial bee colony | |
| Brownlee et al. | Mining Markov network surrogates to explain the results of metaheuristic optimisation | |
| CN111523636B (en) | Optimization method for improving scale-free network elasticity | |
| CN109120438B (en) | Data cooperative transmission method and system under opportunity network | |
| Yu et al. | Ontology-based knowledge management framework: Toward CBR-supported risk response to hydrological cascading disasters | |
| Deng et al. | Personalized federated learning for in-hospital mortality prediction of multi-center ICU | |
| CN107578136A (en) | The overlapping community discovery method extended based on random walk with seed | |
| CN102136975B (en) | Large-scale network environment-oriented similarity network construction method | |
| CN110458290A (en) | A kind of genetic Algorithm Design method based on self-adjusting dynamic network | |
| CN114723005B (en) | Multi-layer network collapse strategy deducing method based on depth map representation learning | |
| Luo et al. | Automatic Business Location Selection through Particle Swarm Optimization and Neural Network |
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 |