CN113434706A - Academic collaboration relation analysis method and device - Google Patents

Academic collaboration relation analysis method and device Download PDF

Info

Publication number
CN113434706A
CN113434706A CN202010207505.0A CN202010207505A CN113434706A CN 113434706 A CN113434706 A CN 113434706A CN 202010207505 A CN202010207505 A CN 202010207505A CN 113434706 A CN113434706 A CN 113434706A
Authority
CN
China
Prior art keywords
nodes
author
graph
cooperative relationship
document
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
Application number
CN202010207505.0A
Other languages
Chinese (zh)
Inventor
任卓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Gridsum Technology Co Ltd
Original Assignee
Beijing Gridsum Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Gridsum Technology Co Ltd filed Critical Beijing Gridsum Technology Co Ltd
Priority to CN202010207505.0A priority Critical patent/CN113434706A/en
Publication of CN113434706A publication Critical patent/CN113434706A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/382Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using citations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • G06F16/355Class or cluster creation or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367Ontology

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computational Linguistics (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides an academic cooperation relation analysis method and device, a document map is created based on basic document information of academic documents in a target field, cooperation relations are built between any two subject nodes in the document map, which are likely to have cooperation relations, cooperation relation weights corresponding to the two subject nodes are obtained, and an undirected cooperation relation right graph is built. And finally, performing spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result, namely all possible cooperative relationships in the target field. According to the process, the scheme considers the cooperative relationship of any two subjects in the document data set to obtain the final subject cooperative relationship, so that the accuracy of the analysis result is high. And further, the accuracy of recommending the recommendation result of the related scholars or related academic achievements by further utilizing the cooperative relationship analysis result is improved.

Description

Academic collaboration relation analysis method and device
Technical Field
The invention belongs to the technical field of machine learning, and particularly relates to an academic collaboration relation analysis method and device.
Background
With the rapid development of academic research in various fields, academic research results are obtained by the joint efforts of a plurality of research institutions and experts in the field, and the establishment of countless academic cooperation relations is not separated, so that the results of countless theoretical exchanges and experiments are aggregated. It follows that academic collaboration analysis can facilitate academic development.
However, the analysis method can only analyze and obtain the possible cooperation again between the mechanisms or scholars who have already cooperated, and cannot analyze the cooperation relationship between the mechanisms or scholars who have not cooperated, so that the accuracy rate of the academic cooperation relationship obtained by analysis is very low; further applications based on academic partnerships, such as recommending related scholars or related academic achievements, are resulted in lower recommendation accuracy.
Disclosure of Invention
In view of the above, an objective of the present application is to provide an academic collaboration analysis method and apparatus, so as to solve the technical problem of low accuracy of the traditional academic collaboration analysis result, and the disclosed technical solution is as follows:
in one aspect, the present application provides an academic collaboration relation analysis method, including:
acquiring a document map, wherein the document map is created based on information of academic documents in a target field, the document map comprises subject nodes and document content nodes, the subject nodes are used for representing subjects to which the academic documents belong, and the document content nodes are used for representing contents of the academic documents;
creating a cooperative relationship undirected authorized graph among the subject nodes based on the document graph, wherein any two subject nodes in the cooperative relationship undirected authorized graph are connected by edges, each edge comprises a cooperative relationship weight between the two connected subject nodes, the cooperative relationship weight is used for representing the degree of intersection of academic research results of the two subject nodes, and the cooperative relationship weight is obtained according to document content nodes connected with the two subject nodes in the document graph;
and carrying out spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result.
In one possible implementation, the subject nodes include author nodes, and creating a collaborative relationship undirected graph between the subject nodes based on the document graph includes:
extracting all author nodes from the document map, and connecting any two author nodes by edges;
according to document content nodes which are connected with two author nodes in the document map together, acquiring author cooperative relationship weights corresponding to the two author nodes, wherein the author cooperative relationship weights represent the degree of intersection of academic research results of the two authors;
and obtaining an undirected author cooperative relationship authorized graph based on all author nodes connected by edges and author cooperative relationship weights corresponding to any two author nodes.
In a possible implementation manner, the obtaining, according to a document content node to which two author nodes in the document map are commonly connected, an author cooperative relationship weight corresponding to the two author nodes includes:
calculating the product of the number of the title nodes which are connected with the two author nodes together and the title weight to obtain the first author cooperative relationship weight;
calculating the sum of the keyword connection weights of all keywords connected by the two author nodes together, and calculating the product of the keyword weight and the sum of the keyword connection weights to obtain a second author cooperative relationship weight; the keyword connection weight is obtained according to the number of documents containing the keyword, which are published by an author connected with the keyword;
and calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight to obtain the author cooperative relationship weights corresponding to the two author nodes.
In one possible implementation, the subject nodes include author nodes and research institution nodes, and creating the subject node partnership undirected authoritative graph based on the document map includes:
extracting all research institution nodes from the literature map, and connecting any two research institution nodes by edges;
calculating the sum of the author cooperative relationship weights between all author nodes connected with one research institution node and all author nodes connected with another research institution node to obtain an institution cooperative relationship weight between the two research institution nodes;
the author cooperation relationship weight represents the crossing degree of academic research results of two authors and is obtained according to document content nodes connected with two author nodes together;
and constructing an undirected authority graph of the mechanism cooperation relationship based on all the research mechanism nodes connected by the edges and the mechanism cooperation relationship weights corresponding to any two research mechanism nodes.
In a possible implementation manner, performing spectral clustering on the undirected ownership graph of the partnership to obtain a partnership analysis result includes:
clustering the undirected weighted graph of the cooperation relationship based on a spectral clustering algorithm to obtain a plurality of clustering clusters, wherein the probability of cooperation between main body nodes from the same clustering cluster is greater than the probability of cooperation between main body nodes from different clustering clusters.
In one possible implementation, the document map is created by:
respectively creating a main body node and a document content node corresponding to each academic document, wherein the document content node comprises at least one of a title node, a keyword node and a summary node, and the main body node comprises an author node and/or a research institution node;
respectively connecting document content nodes corresponding to the same academic document with author nodes of the academic document, and connecting the author nodes with research institution nodes to which authors belong;
the sides connected between the author nodes and the keyword nodes contain keyword connection weights, and the keyword connection weights are obtained according to the number of documents containing the keywords issued by the author.
On the other hand, the application also provides an academic collaboration relation analysis method, which comprises the following steps:
the system comprises a graph acquisition module, a graph acquisition module and a graph analysis module, wherein the graph acquisition module is used for acquiring a document graph, the document graph is created based on information of academic documents in a target field, the document graph comprises main body nodes and document content nodes, the main body nodes are used for representing main bodies to which the academic documents belong, and the document content nodes are used for representing contents of the academic documents;
the undirected authorized graph creating module is used for creating a cooperative relationship undirected authorized graph among the subject nodes based on the literature graph, any two subject nodes in the cooperative relationship undirected authorized graph are connected by edges, each edge contains a cooperative relationship weight between the two connected subject nodes, the cooperative relationship weight is used for representing the degree of intersection of academic research results of the two subject nodes, and the cooperative relationship weight is obtained according to literature content nodes connected with the two subject nodes in the literature graph;
and the cooperative relation analysis module is used for carrying out spectral clustering on the undirected authorized graph of the cooperative relation to obtain a cooperative relation analysis result.
In one possible implementation, the subject node includes an author node, and the undirected authoritative graph creation module includes:
the author node extraction submodule is used for extracting all author nodes from the document map and connecting any two author nodes by edges;
the author cooperative relationship weight acquisition sub-module is used for acquiring author cooperative relationship weights corresponding to two author nodes according to document content nodes which are connected with the two author nodes in the document map, and the author cooperative relationship weights represent the degree of intersection of academic research results of the two authors;
and the first undirected authorized graph constructing sub-module is used for obtaining the undirected authorized graph of the author cooperative relationship based on all the author nodes connected by edges and the author cooperative relationship weights corresponding to any two author nodes.
In yet another aspect, the present application further provides an apparatus comprising: at least one processor, and at least one memory, bus connected with the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to call program instructions in the memory to perform the academic partnership analysis method according to any one of the possible implementations of the first aspect.
In yet another aspect, the present application further provides a storage medium having a program stored thereon, where the program is loaded into and executed by a processor to implement the academic collaboration relation analysis method according to any one of the possible implementation manners of the first aspect.
The academic cooperation relation analysis method provided by the application acquires the literature map, creates the cooperation relation undirected authorized graph based on the literature map, wherein any two main body nodes in the cooperation relation undirected authorized graph are connected by edges, each edge contains the cooperation relation weight between the two connected main body nodes, and the cooperation relation weight represents the crossing degree of academic research results of the two main body nodes. And then carrying out spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result, namely all possible cooperative relationships in the target field. According to the process, the scheme considers the cooperative relationship between any two subjects of the same type in the document data set to obtain the final subject cooperative relationship, and the obtained analysis result has high accuracy. And further, the accuracy of recommending the recommendation result of the related scholars or related academic achievements by further utilizing the cooperative relationship analysis result is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of an academic collaboration analysis method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of an example of a document map provided by an embodiment of the present application;
FIG. 3 is a flowchart of a process for obtaining an author partnership undirected ownership graph based on a document map, provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of an example of an author partnership undirected ownership graph provided by an embodiment of the present application;
FIG. 5 is a flow chart of a process for constructing an organization partnership undirected competency graph between research organizations based on document atlases provided by embodiments of the present application;
FIG. 6 is a schematic diagram of an example of an undirected graph of an institution provided by an embodiment of the present application;
fig. 7 is a schematic structural diagram of an academic collaboration analysis apparatus according to an embodiment of the present application;
FIG. 8 is a block diagram of an undirected authorized graph creation module according to an embodiment of the present application;
FIG. 9 is a block diagram of another undirected authorized graph creation module provided by embodiments of the present application;
fig. 10 is a schematic structural diagram of an apparatus provided in an embodiment of the present application.
Detailed Description
The key point for promoting the development of academic collaboration is the analysis and mining of the collaboration relationship, and the analysis and mining of the relationship mainly depends on the existing collaboration results and data, so that the collaboration closeness among a plurality of mechanisms and scholars is reasonably measured, and the community discovery of the academic collaboration network is realized. However, the conventional academic collaboration analysis scheme is limited to only result data of whether collaboration is performed or not, so that the accuracy of the academic collaboration analysis result is low.
In order to solve the technical problems, the application provides an academic collaboration relation analysis method and device, the scheme is that corresponding document maps are constructed for all academic documents in the field, a collaboration relation analysis result is obtained based on the collaboration relation analysis between any two subjects in the document maps, namely, the final subject collaboration relation is obtained by considering the collaboration relation of any two subjects in the current document data set in the field, and therefore the accuracy rate of the analysis result is high. When the scheme extracts the undirected cooperation relationship authorized graph from the literature graph, the cooperation relationship weight between any two subject nodes is calculated, the cooperation relationship weight represents the degree of intersection between the research results of the two subjects, the larger the cooperation relationship weight is, the higher the probability of cooperation relationship between the two subjects is, and the cooperation relationship weight has interpretability.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a flowchart of an academic collaboration analysis method provided in an embodiment of the present application is shown, where the method is applied to a device with computing capability, such as a server, a PC, a mobile phone, a PDA, and the like. As shown in fig. 1, the method mainly comprises the following steps:
and S110, acquiring a document map.
A document map of the text is created based on information of academic documents of the target field, and the document map includes a subject node and a document content node; the subject nodes are used for representing subjects to which the academic mosquito incense belongs, and for example, the subject nodes comprise author nodes and/or research institution nodes; the document content nodes are used to represent the content of the academic document, for example, the document content nodes include at least one of title nodes, keyword nodes, and summary nodes.
The target field may be any academic field, such as oil and gas, electricity, medicine, computer, etc. Academic literature includes, but is not limited to, articles, books, and other literature data. Fig. 2 is a schematic diagram of an example of a document map provided in the embodiment of the present application.
In one embodiment of the present application, a document map may be created by:
1) and respectively creating a main body node and a document content node corresponding to each academic document.
The basic information of each academic document in the current document data set, such as title, keyword, author, research institution, abstract, published periodical and the like, is respectively counted, and corresponding title nodes are respectively created for different titles, corresponding keyword nodes are created for different keywords, corresponding author nodes are created for different authors, and corresponding research institution nodes are created for different research institutions. If the academic literature also relates to other contents which can create the nodes, the nodes which create the corresponding contents are not described in detail herein.
2) Document content nodes corresponding to the same academic document are respectively connected with an author node of the academic document, and the author node is connected with a research institution node to which the author belongs.
In one embodiment of the present application, it is contemplated that the same author may publish multiple documents containing the same keyword, or may only publish literature containing the keyword. If the number of documents of the same keyword published by a certain author is larger, the author's contribution to the subdivided fields of the keyword is larger, and conversely, if the number of documents of the same keyword published by a certain author is smaller, the author's contribution to the subdivided fields of the keyword is smaller. Therefore, the author's contribution to the keyword is characterized by setting a connection weight between the author node and the keyword node (i.e., a keyword connection weight). The keyword connection weight is obtained according to the number of documents which are published by an author and contain the keyword.
And S120, creating a cooperative relation undirected authorized graph among the main body nodes based on the literature graph.
Any two subject nodes in the collaborative relationship undirected weighted graph are connected by edges, and each edge is provided with a weight which represents the collaborative relationship between the two subject nodes connected by the edge, namely the collaborative relationship weight. The cooperative relationship weight represents the degree of intersection of academic research results of the two subjects, and is obtained according to document content nodes connected with the two subject nodes in the document map.
When the undirected ownership graph corresponding to the main node is extracted from the literature map, the calculation mode of the ownership weight has interpretability and supports flexible incorporation of multi-dimensional information, and the relevance among the nodes is ensured and the utilization rate of data information is improved.
The subject in the document map of the present embodiment includes authors and research institutions, and the collaboration may occur between different authors, or between different research institutions, or between authors and research institutions, and a corresponding collaboration unoriented permission map may be created for each type of collaboration, for example, at least one of an author collaboration unoriented permission map, an organization collaboration unoriented permission map, and an author organization collaboration orientation permission map may be extracted from the document map.
And S130, performing spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result.
The spectral clustering is a clustering algorithm based on graph theory, and utilizes a spectrogram segmentation theory to obtain an undirected weighted graph from graph structure data and segment the undirected weighted graph into a plurality of disjoint subgraphs, so that nodes in the subgraphs have high similarity, and the similarity of the nodes in different subgraphs is low. The higher the similarity between the nodes is, the higher the probability of representing the cooperative relationship between the nodes is, and conversely, the lower the similarity between the nodes is, the lower the probability of representing the cooperative relationship between the nodes is.
The method comprises the steps of extracting an author cooperative relationship undirected authorized graph from a document graph, segmenting the author cooperative relationship undirected authorized graph based on a spectral clustering algorithm, and obtaining a plurality of disjoint subgraphs (namely a plurality of author cooperative relationship clustering clusters), so that author nodes in the subgraphs have high similarity, and author nodes in different subgraphs have low similarity. I.e. the probability of collaboration between authors in a sub-graph is greater than the probability of collaboration between authors in different sub-graphs.
Similarly, the mechanism cooperation undirected authorized graph is extracted from the literature graph, and the mechanism cooperation undirected authorized graph is segmented based on the spectral clustering algorithm to obtain a plurality of disjoint subgraphs (namely a plurality of mechanism cooperation clustering clusters), so that research mechanism nodes in the subgraphs have high similarity, and research mechanism nodes of different subgraphs have low similarity. That is, the probability of collaboration between research institutions within the subgraph is greater than the probability of collaboration between different research institutions.
Similarly, for an author-institution cooperative relationship undirected graph, the similarity between author nodes and research-institution nodes in the same sub-graph is higher, while the similarity between author nodes and research-institution nodes in different sub-graphs is lower.
Before clustering the nondirectional weighted graph of the cooperative relationship, a similar matrix can be constructed for the nondirectional weighted graph of the cooperative relationship, then characteristic vectors are extracted from the similar matrix, and then traditional clustering is carried out based on the distance between the characteristic vectors to obtain at least two clustering clusters. The spectral clustering can be based on the global associated information (namely the cooperative relationship between any two authors, the cooperative relationship between any two research institutions, and the cooperative relationship between any one author node and any one research institution node) in the cooperation undirected authorized graph, and then the feature vectors containing the associated information are extracted, and the vector representation of multiple dimensions is not required to be constructed manually aiming at the graph structure data, so that the feature vectors used in clustering are more accurate, the dimensions are more comprehensive, and the accuracy of the finally obtained clustering result (namely the cooperation relationship analysis result) is higher.
And after a plurality of subgraphs are obtained by using a spectral clustering algorithm, evaluating a clustering result by using the modularity. The modularity is used to scale whether the partitioning of the sub-graph is a relatively good result, one relatively good partitioning result is that the similarity of the nodes inside the sub-graph is high and the similarity with the nodes outside the sub-graph is low.
When clustering is performed by using the spectral clustering algorithm, parameters in the spectral clustering algorithm can be repeatedly adjusted, and model evaluation can be repeatedly performed by using a model evaluation standard (namely, modularity) so as to improve the clustering effect. In addition, secondary examination can be performed by experts in the academic field to ensure the accuracy of the clustering result.
The academic collaboration relation analysis method provided in this embodiment obtains a document map, and creates a collaborative relation undirected authorized graph between subject nodes based on the document map, where any two subject nodes in the collaborative relation undirected graph are connected by an edge, and each edge includes a collaborative relation weight between the two connected subject nodes, and the collaborative relation weight represents a degree of intersection of academic research results of the two subject nodes. And finally, performing spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result, namely all possible cooperative relationships in the target field. According to the process, the scheme considers the cooperative relationship of any two subjects in the document data set to obtain the final subject cooperative relationship, so that the accuracy of the analysis result is high. The accuracy of recommending the recommendation result of the related scholars or the related academic achievements by using the cooperative relationship analysis result is further improved.
Moreover, when the scheme extracts the undirected cooperation relationship diagram from the literature map, the cooperation relationship weight capable of representing the degree of intersection between the research results of any two subjects is used, the cooperation relationship weight is more interpretable and supports flexible incorporation of multi-dimensional information, and the utilization rate of data information is improved while the relevance between nodes is maintained.
In one embodiment of the present application, as shown in FIG. 3, the process of obtaining an author partnership undirected competency graph based on a document map is as follows:
s1211, extracting all author nodes from the document map, and connecting any two author nodes with edges.
And connecting any two author nodes with edges to establish a cooperative relationship between any two author nodes.
And S1212, obtaining the author cooperative relationship weight corresponding to the two author nodes according to the document content node connected by the two author nodes in the document map.
Wherein the author cooperative relationship weight characterizes the degree to which the academic research results of the two authors cross.
The document content node connected by two author nodes is used for measuring the degree of possibility of cooperation between the two authors, and in one embodiment of the application, the process of calculating the author cooperative relationship weight is as follows:
1) calculating the product of the number of the title nodes which are connected with the two author nodes together and the title weight to obtain the first author cooperative relationship weight;
the basic document information commonly connected by two author nodes comprises a title and a keyword, wherein the title can relatively comprehensively reflect the main content of a document, and the keyword in a document material usually comprises a plurality of keywords, so that one keyword cannot generally reflect the main content of the document, and therefore, different weights, namely a title weight w1 and a keyword weight w2, can be respectively set for the title node and the keyword node.
Typically the title weight is greater than the keyword weight and the sum of the title weight and the keyword weight is equal to 1, i.e. w1+ w2 is 1 and w1 > w 2.
For example, if the number of header nodes to which the author node a and the author node B are commonly connected is n, the first author partnership weight corresponding to the author nodes a and B is w1 × n.
2) Calculating the sum of the keyword connection weights of all keywords connected by two author nodes together, and calculating the product of the keyword weight and the sum of the keyword connection weights to obtain a second author cooperative relationship weight;
the keyword connection weight is obtained from the number of documents containing the keyword published by an author connected with the keyword.
As described above, there is a keyword connection weight between the author node and the keyword node, denoted as wijWhere i represents an author node and j represents a keyword node.
For example, the author node a and the author node B are connected to the keyword node a, the keyword node B, and the keyword node C, and the second author cooperative relationship weight corresponding to the author nodes a and B is: w2 (w)AA+wAB+wAC+wBA+wBB+wBC)
3) And calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight to obtain the author cooperative relationship weights corresponding to the two author nodes.
And calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight corresponding to the same pair of author nodes to obtain the author cooperative relationship weight corresponding to the pair of author nodes. Still taking the above author nodes a and B as examples, the corresponding author cooperative relationship weights are: w1 × n + w2 (w)AA+wAB+wAC+wBA+wBB+wBC)。
S1213, based on the cooperation relationship between any two author nodes and the corresponding author cooperation relationship weight, an undirected authority graph of the author cooperation relationship is constructed.
Any two author nodes are connected by an edge, and an author partnership weight between the two author nodes connected by the edge is added to each edge. FIG. 4 shows an example of an author partnership undirected ownership graph, where the nodes are author nodes and edges between any two author nodes have author partnership weights between the two authors.
In another embodiment of the present application, as shown in FIG. 5, the process of constructing an organizational partnership undirected competency graph between research organizations based on a document map is as follows:
and S1221, extracting all research institution nodes from the literature map, and connecting any two research institution nodes by edges.
And establishing a cooperative relationship between any two research institution nodes in the literature graph.
And S1222, calculating the sum of the cooperative relationship weights between all the author nodes connected with one research institution node and all the author nodes connected with another research institution node to obtain the institution cooperative relationship weight between the two research institution nodes.
For example, if the author nodes connected to the research institution node a are author nodes A, B, C, D, respectively, and all the author nodes connected to the research institution node B are author nodes E, F, G, H, respectively, the author cooperation weight sum between the author nodes A, B, C, D and E, F, G, H is calculated, and the institution cooperation weight between the research institution nodes a and B is obtained.
That is, the author cooperation weights between author node A and author node E, F, G, H, respectively, the author node B and author node E, F, G, H, the author node C and author node E, F, G, H, respectively, and the author node D and author node E, F, G, H, respectively, are summed. Finally, the sum of the four author partnership weights is calculated as the organizational partnership weight.
The cooperative relationship weight between the two author nodes may be calculated by the above-mentioned calculation process of S1212.
And S1223, constructing an undirected authority graph of the mechanism cooperation relationship based on the cooperation relationship between any two research mechanism nodes and the corresponding mechanism cooperation relationship weight.
Any two research institution nodes are connected by edges, and an institution cooperation relationship weight between the two research institution nodes connected by the edge is added to each edge, as shown in fig. 6, which is an example of an undirected weighted graph of a research institution, in which the nodes are research institution nodes and the edges between any two research institution nodes have the institution cooperation relationship weight between the two research institutions.
The process of constructing the undirected authorized graph of the cooperative relationship provided by the embodiment is more interpretable, supports flexible incorporation of multidimensional information, and improves the utilization rate of data information while maintaining the relevance between nodes.
Corresponding to the embodiment of the academic cooperation relation analysis method, the application also provides an embodiment of an academic cooperation relation analysis device.
Referring to fig. 7, a schematic structural diagram of an academic collaboration relation analysis apparatus provided in an embodiment of the present application is shown, where the apparatus is applied to a device with computing capability, and as shown in fig. 7, the apparatus mainly includes: a graph acquisition module 110, an undirected authorized graph creation module 120, and a partnership analysis module 130.
And the map acquisition module 110 is used for acquiring a document map.
Wherein the document graph is created based on information of academic documents of the target domain, the document graph including subject nodes and document content nodes. The main body node is used for representing a main body to which the academic literature belongs, and the literature content node is used for representing the content of the academic literature.
In one embodiment of the present application, the atlas acquisition module 110 is created by:
(1) respectively creating a main body node and a document content node corresponding to each academic document, wherein the document content node comprises at least one of a title node, a keyword node and a summary node, and the main body node comprises an author node and/or a research institution node;
(2) respectively connecting document content nodes corresponding to the same academic document with author nodes of the academic document, and connecting the author nodes with research institution nodes to which authors belong;
the sides connected between the author nodes and the keyword nodes contain keyword connection weights, and the keyword connection weights are obtained according to the number of documents containing the keywords issued by the author.
An undirected authoritative graph creation module 120 for creating a collaborative relationship undirected authoritative graph between the subject nodes based on the document graph.
Any two main body nodes in the cooperation undirected weighted graph are connected by edges, each edge comprises a cooperation weight between the two connected main body nodes, the cooperation weight is used for representing the degree of intersection of academic research results of the two main body nodes, and the cooperation weight is obtained according to document content nodes connected with the two main body nodes in the document graph.
In an application scenario of the present application, the topic node includes an author node, and in this application scenario, as shown in fig. 8, the undirected authorized graph creation module 120 includes: an author node extraction sub-module 1211, an author partnership weight obtaining sub-module 1212, and a first undirected authorized graph construction sub-module 1213.
An author node extraction submodule 1211, configured to extract all author nodes from the document map, and connect any two author nodes with an edge;
the author cooperative relationship weight obtaining sub-module 1212 is configured to obtain, according to a document content node to which two author nodes in the document map are commonly connected, an author cooperative relationship weight corresponding to the two author nodes.
Wherein the author cooperative relationship weight characterizes the degree to which the academic research results of the two authors cross.
In an embodiment of the present application, the author partnership weight obtaining sub-module 1212 is specifically configured to:
calculating the product of the number of the title nodes which are connected with the two author nodes together and the title weight to obtain the first author cooperative relationship weight;
calculating the sum of the keyword connection weights of all keywords connected by the two author nodes together, and calculating the product of the keyword weight and the sum of the keyword connection weights to obtain a second author cooperative relationship weight; the keyword connection weight is obtained according to the number of documents containing the keyword, which are published by an author connected with the keyword;
and calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight to obtain the author cooperative relationship weights corresponding to the two author nodes.
The first undirected authorized graph constructing sub-module 1213 is configured to obtain an undirected authorized graph of the author's cooperative relationship based on all author nodes connected by edges and the author's cooperative relationship weights corresponding to any two author nodes.
In another application scenario of the present application, the subject node includes a research institution node, and in this application scenario, as shown in fig. 9, the undirected authorized graph creating module 120 mainly includes:
the institution node extraction submodule 1221 is configured to extract all research institution nodes from the literature map, and connect any two research institution nodes with each other;
the organization cooperative relationship weight obtaining submodule 1222 is configured to calculate a sum of author cooperative relationship weights between all author nodes connected to one research organization node and all author nodes connected to another research organization node, so as to obtain an organization cooperative relationship weight between two research organization nodes.
And a second undirected full graph construction submodule 1223, configured to construct an undirected weighted graph of the mechanism cooperative relationship based on all the research institution nodes connected by edges and the mechanism cooperative relationship weights corresponding to any two research institution nodes.
And the cooperative relationship analysis module 130 is configured to perform spectral clustering on the undirected ownership graph of the cooperative relationship to obtain a cooperative relationship analysis result.
In an embodiment of the application, the undirected weighted graph of the cooperation relationship is clustered based on a spectral clustering algorithm to obtain a plurality of clustering clusters, wherein the probability of cooperation between subject nodes from the same clustering cluster is greater than the probability of cooperation between subject nodes from different clustering clusters.
The academic cooperation relation analysis device acquires a document map, and creates a cooperation relation undirected authorized graph based on the document map, wherein any two subject nodes in the cooperation relation undirected authorized graph are connected by edges, each edge contains cooperation relation weight between the two connected subject nodes, and the cooperation relation weight represents the degree of intersection of academic research results of the two subject nodes. And then carrying out spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result, namely all possible cooperative relationships in the target field. According to the process, the scheme considers the cooperative relationship between any two subjects of the same type in the document data set to obtain the final subject cooperative relationship, and the obtained analysis result has high accuracy. And further, the accuracy of recommending the recommendation result of the related scholars or related academic achievements by further utilizing the cooperative relationship analysis result is improved.
The academic cooperation relation analysis device comprises a processor and a memory, wherein the map acquisition module, the undirected authorized graph creation module, the cooperation relation analysis module and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the accuracy of the academic cooperation relation analysis result is improved by adjusting the kernel parameters, and the accuracy of the recommendation result of the related scholars or the related academic achievements is further recommended by utilizing the cooperation relation analysis result.
An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the academic collaboration relation analysis method when being executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the academic collaboration relation analysis method is executed when the program runs.
An embodiment of the present invention provides an apparatus, as shown in fig. 10, including at least one processor 210, and at least one memory 220 connected to the processor 210, a bus 230; the processor 210 and the memory 220 complete communication with each other through the bus 230; the processor 210 is used to call program instructions in the memory 220 to perform the academic partnership analysis method described above. The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
acquiring a document map, wherein the document map is created based on information of academic documents in a target field, the document map comprises subject nodes and document content nodes, the subject nodes are used for representing subjects to which the academic documents belong, and the document content nodes are used for representing contents of the academic documents;
creating a cooperative relationship undirected authorized graph among the subject nodes based on the document graph, wherein any two subject nodes in the cooperative relationship undirected authorized graph are connected by edges, each edge comprises a cooperative relationship weight between the two connected subject nodes, the cooperative relationship weight is used for representing the degree of intersection of academic research results of the two subject nodes, and the cooperative relationship weight is obtained according to document content nodes connected with the two subject nodes in the document graph;
and carrying out spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result.
In one possible implementation, the subject nodes include author nodes, and creating a collaborative relationship undirected graph between the subject nodes based on the document graph includes:
establishing all author nodes extracted from the document map, and connecting any two author nodes by edges;
according to document content nodes which are connected with two author nodes in the document map together, acquiring author cooperative relationship weights corresponding to the two author nodes, wherein the author cooperative relationship weights represent the degree of intersection of academic research results of the two authors;
and obtaining an undirected author cooperative relationship authorized graph based on all author nodes connected by edges and author cooperative relationship weights corresponding to any two author nodes.
In a possible implementation manner, the obtaining, according to a document content node to which two author nodes in the document map are commonly connected, an author cooperative relationship weight corresponding to the two author nodes includes:
calculating the product of the number of the title nodes which are connected with the two author nodes together and the title weight to obtain the first author cooperative relationship weight;
calculating the sum of the keyword connection weights of all keywords connected by the two author nodes together, and calculating the product of the keyword weight and the sum of the keyword connection weights to obtain a second author cooperative relationship weight; the keyword connection weight is obtained according to the number of documents containing the keyword, which are published by an author connected with the keyword;
and calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight to obtain the author cooperative relationship weights corresponding to the two author nodes.
In one possible implementation, the subject nodes include author nodes and research institution nodes, and creating the subject node partnership undirected authoritative graph based on the document map includes:
establishing all research institution nodes extracted from the literature map, and connecting any two research institution nodes by edges;
calculating the sum of the author cooperative relationship weights between all author nodes connected with one research institution node and all author nodes connected with another research institution node to obtain an institution cooperative relationship weight between the two research institution nodes;
the author cooperation relationship weight represents the crossing degree of academic research results of two authors and is obtained according to document content nodes connected with two author nodes together;
and constructing an undirected authority graph of the mechanism cooperation relationship based on all the research mechanism nodes connected by the edges and the mechanism cooperation relationship weights corresponding to any two research mechanism nodes.
In a possible implementation manner, performing spectral clustering on the undirected ownership graph of the partnership to obtain a partnership analysis result includes:
clustering the undirected weighted graph of the cooperation relationship based on a spectral clustering algorithm to obtain a plurality of clustering clusters, wherein the probability of cooperation between main body nodes from the same clustering cluster is greater than the probability of cooperation between main body nodes from different clustering clusters.
In one possible implementation, the document map is created by:
respectively creating a main body node and a document content node corresponding to each academic document, wherein the document content node comprises at least one of a title node, a keyword node and a summary node, and the main body node comprises an author node and/or a research institution node;
respectively connecting document content nodes corresponding to the same academic document with author nodes of the academic document, and connecting the author nodes with research institution nodes to which authors belong;
the sides connected between the author nodes and the keyword nodes contain keyword connection weights, and the keyword connection weights are obtained according to the number of documents containing the keywords issued by the author.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. An academic collaboration relation analysis method, comprising:
acquiring a document map, wherein the document map is created based on information of academic documents in a target field, the document map comprises subject nodes and document content nodes, the subject nodes are used for representing subjects to which the academic documents belong, and the document content nodes are used for representing contents of the academic documents;
creating a cooperative relationship undirected authorized graph among the subject nodes based on the document graph, wherein any two subject nodes in the cooperative relationship undirected authorized graph are connected by edges, each edge comprises a cooperative relationship weight between the two connected subject nodes, the cooperative relationship weight is used for representing the degree of intersection of academic research results of the two subject nodes, and the cooperative relationship weight is obtained according to document content nodes connected with the two subject nodes in the document graph;
and carrying out spectral clustering on the undirected weighted graph of the cooperative relationship to obtain a cooperative relationship analysis result.
2. The method of claim 1, wherein the subject nodes comprise author nodes, and wherein creating the partnership undirected graph between the subject nodes based on the document graph comprises:
extracting all author nodes from the document map, and connecting any two author nodes by edges;
according to document content nodes which are connected with two author nodes in the document map together, acquiring author cooperative relationship weights corresponding to the two author nodes, wherein the author cooperative relationship weights represent the degree of intersection of academic research results of the two authors;
and obtaining an undirected author cooperative relationship authorized graph based on all author nodes connected by edges and author cooperative relationship weights corresponding to any two author nodes.
3. The method according to claim 2, wherein obtaining the author cooperative relationship weight corresponding to two author nodes according to document content nodes commonly connected to the two author nodes in the document map comprises:
calculating the product of the number of the title nodes which are connected with the two author nodes together and the title weight to obtain the first author cooperative relationship weight;
calculating the sum of the keyword connection weights of all keywords connected by the two author nodes together, and calculating the product of the keyword weight and the sum of the keyword connection weights to obtain a second author cooperative relationship weight; the keyword connection weight is obtained according to the number of documents containing the keyword, which are published by an author connected with the keyword;
and calculating the sum of the first author cooperative relationship weight and the second author cooperative relationship weight to obtain the author cooperative relationship weights corresponding to the two author nodes.
4. The method of claim 1, wherein the subject nodes include author nodes and research institution nodes, and wherein creating the subject node partnership undirected graph based on the document graph comprises:
extracting all research institution nodes from the literature map, and connecting any two research institution nodes by edges;
calculating the sum of the author cooperative relationship weights between all author nodes connected with one research institution node and all author nodes connected with another research institution node to obtain an institution cooperative relationship weight between the two research institution nodes;
the author cooperation relationship weight represents the crossing degree of academic research results of two authors and is obtained according to document content nodes connected with two author nodes together;
and constructing an undirected authority graph of the mechanism cooperation relationship based on all the research mechanism nodes connected by the edges and the mechanism cooperation relationship weights corresponding to any two research mechanism nodes.
5. The method according to any one of claims 1-4, wherein performing spectral clustering on the undirected weighted graph of partnership to obtain a partnership analysis result comprises:
clustering the undirected weighted graph of the cooperation relationship based on a spectral clustering algorithm to obtain a plurality of clustering clusters, wherein the probability of cooperation between main body nodes from the same clustering cluster is greater than the probability of cooperation between main body nodes from different clustering clusters.
6. The method according to any one of claims 1-4, wherein the literature profile is created by:
respectively creating a main body node and a document content node corresponding to each academic document, wherein the document content node comprises at least one of a title node, a keyword node and a summary node, and the main body node comprises an author node and/or a research institution node;
respectively connecting document content nodes corresponding to the same academic document with author nodes of the academic document, and connecting the author nodes with research institution nodes to which authors belong;
the sides connected between the author nodes and the keyword nodes contain keyword connection weights, and the keyword connection weights are obtained according to the number of documents containing the keywords issued by the author.
7. An academic collaboration relation analysis method, comprising:
the system comprises a graph acquisition module, a graph acquisition module and a graph analysis module, wherein the graph acquisition module is used for acquiring a document graph, the document graph is created based on information of academic documents in a target field, the document graph comprises main body nodes and document content nodes, the main body nodes are used for representing main bodies to which the academic documents belong, and the document content nodes are used for representing contents of the academic documents;
the undirected authorized graph creating module is used for creating a cooperative relationship undirected authorized graph among the subject nodes based on the literature graph, any two subject nodes in the cooperative relationship undirected authorized graph are connected by edges, each edge contains a cooperative relationship weight between the two connected subject nodes, the cooperative relationship weight is used for representing the degree of intersection of academic research results of the two subject nodes, and the cooperative relationship weight is obtained according to literature content nodes connected with the two subject nodes in the literature graph;
and the cooperative relation analysis module is used for carrying out spectral clustering on the undirected authorized graph of the cooperative relation to obtain a cooperative relation analysis result.
8. The apparatus of claim 7, wherein the subject node comprises an author node, and wherein the undirected authoritative graph creation module comprises:
the author node extraction submodule is used for extracting all author nodes from the document map and connecting any two author nodes by edges;
the author cooperative relationship weight acquisition sub-module is used for acquiring author cooperative relationship weights corresponding to two author nodes according to document content nodes which are connected with the two author nodes in the document map, and the author cooperative relationship weights represent the degree of intersection of academic research results of the two authors;
and the first undirected authorized graph constructing sub-module is used for obtaining the undirected authorized graph of the author cooperative relationship based on all the author nodes connected by edges and the author cooperative relationship weights corresponding to any two author nodes.
9. An apparatus, comprising: at least one processor, and at least one memory, bus connected with the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to invoke program instructions in the memory to perform the academic partnership analysis method of any one of claims 1-6.
10. A storage medium having a program stored thereon, wherein the program when loaded and executed by a processor implements the academic partnership analysis method of any one of claims 1 to 6.
CN202010207505.0A 2020-03-23 2020-03-23 Academic collaboration relation analysis method and device Pending CN113434706A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010207505.0A CN113434706A (en) 2020-03-23 2020-03-23 Academic collaboration relation analysis method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010207505.0A CN113434706A (en) 2020-03-23 2020-03-23 Academic collaboration relation analysis method and device

Publications (1)

Publication Number Publication Date
CN113434706A true CN113434706A (en) 2021-09-24

Family

ID=77752494

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010207505.0A Pending CN113434706A (en) 2020-03-23 2020-03-23 Academic collaboration relation analysis method and device

Country Status (1)

Country Link
CN (1) CN113434706A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115062732A (en) * 2022-08-18 2022-09-16 睿驰(深圳)智能有限公司 Resource sharing cooperation recommendation method and system based on big data user tag information

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577579A (en) * 2013-11-08 2014-02-12 南方电网科学研究院有限责任公司 Resource recommendation method and system based on potential demands of users
CN104346446A (en) * 2014-10-27 2015-02-11 百度在线网络技术(北京)有限公司 Paper associated information recommendation method and device based on mapping knowledge domain
KR20160041277A (en) * 2014-10-07 2016-04-18 동국대학교 산학협력단 Apparatus and method for recommending technical cooperation partner
CN109145087A (en) * 2018-07-30 2019-01-04 大连理工大学 A kind of scholar's recommendation and collaborative forecasting method based on expression study and competition theory
CN110533253A (en) * 2019-09-04 2019-12-03 安徽大学 A kind of scientific research cooperative Relationship Prediction method based on Heterogeneous Information network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103577579A (en) * 2013-11-08 2014-02-12 南方电网科学研究院有限责任公司 Resource recommendation method and system based on potential demands of users
KR20160041277A (en) * 2014-10-07 2016-04-18 동국대학교 산학협력단 Apparatus and method for recommending technical cooperation partner
CN104346446A (en) * 2014-10-27 2015-02-11 百度在线网络技术(北京)有限公司 Paper associated information recommendation method and device based on mapping knowledge domain
CN109145087A (en) * 2018-07-30 2019-01-04 大连理工大学 A kind of scholar's recommendation and collaborative forecasting method based on expression study and competition theory
CN110533253A (en) * 2019-09-04 2019-12-03 安徽大学 A kind of scientific research cooperative Relationship Prediction method based on Heterogeneous Information network

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115062732A (en) * 2022-08-18 2022-09-16 睿驰(深圳)智能有限公司 Resource sharing cooperation recommendation method and system based on big data user tag information
CN115062732B (en) * 2022-08-18 2022-11-11 睿驰(深圳)智能有限公司 Resource sharing cooperation recommendation method and system based on big data user tag information

Similar Documents

Publication Publication Date Title
CN108287864B (en) Interest group dividing method, device, medium and computing equipment
Lieberman et al. Adaptive context features for toponym resolution in streaming news
Wei et al. On the spatial distribution of buildings for map generalization
Praveen et al. Big data environment for geospatial data analysis
CN107341220A (en) A kind of multi-source data fusion method and device
Deng et al. Recognizing building groups for generalization: a comparative study
Amirkhanyan et al. Real-time clustering of massive geodata for online maps to improve visual analysis
Choi et al. Multimodal location estimation of consumer media: Dealing with sparse training data
Liu et al. Detecting industry clusters from the bottom up based on co-location patterns mining: A case study in Dongguan, China
CN112241458B (en) Text knowledge structuring processing method, device, equipment and readable storage medium
CN113434706A (en) Academic collaboration relation analysis method and device
Li et al. Cardinal directions: a comparison of direction relation matrix and objects interaction matrix
Muppidi et al. Identification of natural disaster affected area using twitter
Rao et al. An approach to clustering of text documents using graph mining techniques
Khamespanah et al. Granular computing and Dempster–Shafer integration in seismic vulnerability assessment
CN114896461A (en) Information resource management method and device, electronic equipment and readable storage medium
Imtiyazi et al. Word association network approach for summarizing Twitter conversation about public election
Zhang et al. Semantic web and geospatial unique features based geospatial data integration
Borowik et al. Fast algorithm for feature extraction
Shi et al. Three-way spectral clustering
Murata Modularity for bipartite networks
CN110309432B (en) Synonym determining method based on interest points and map interest point processing method
Renteria-Agualimpia et al. Identifying geospatial inconsistency of web services metadata using spatial ranking
Ranjith et al. Privacy-preserving data mining in spatiotemporal databases based on mining negative association rules
CN117634894B (en) Ecological environment risk assessment method and device, electronic equipment and storage medium

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