JP2017167806A - Relation visualization device, method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To support understanding of information.SOLUTION: A relation visualization device of an embodiment comprises: a storage part; a display part; a reception part; and a determination part. The storage part associates at least two kinds of attributes and stores them. The display part displays the attributes by nodes, and displays a relation between the nodes by an edge. The reception part receives a selection instruction on change of a display form of the nodes or edge. The determination part determines a visualization method of the nodes or edge according to the selection instruction. The display part displays again, the nodes or the edge, according to the visualization method.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to a relationship visualization apparatus, method, and program.

  Proposed information extraction methods to extract relationships between documents, such as social relationships such as social network services and person correlation diagrams, information attributes such as product name and product price, and relationship between product name and product price Has been.

  By using such an information extraction method, for example, it becomes easy to organize specific information in a document such as extracting a product specification list from a document and collecting it in a table. In addition, the results of information extraction are often visualized to facilitate a bird's-eye view as a directed graph or an undirected graph.For example, a partial network related to the selected information is displayed, or information with overlapping edges is displayed. There is technology to do.

JP 2007-293430 A

  However, when analyzing a large-scale graph formed by the information extraction method, readability may be improved by switching an appropriate visualization method according to an analysis viewpoint (how to cut out a partial network).

  The present disclosure has been made to solve the above-described problem, and an object thereof is to provide a relationship visualization apparatus, method, and program capable of supporting understanding of information.

  The relationship visualization device according to the present embodiment includes a storage unit, a display unit, a reception unit, and a determination unit. The storage unit stores at least two types of attributes in association with each other. The display unit displays the attribute as a node and the relationship between the nodes as an edge. The accepting unit accepts a selection instruction regarding a change in the display format of the node or the edge. The determination unit determines a method of visualizing the node or the edge according to the selection instruction. The display unit redisplays the node or the edge according to the visualization method.

The block diagram which shows the relationship visualization apparatus which concerns on this embodiment. The flowchart which shows the information extraction process of an extraction part. The figure which shows an example of the data stored in an extraction result storage part. The flowchart which shows a visualization method determination process. The figure which shows an example of the visualization method of the whole network. The figure which shows the 1st visualization example of a partial network. The figure which shows the example which displays the document information of an extraction source. The figure which shows the 2nd example of visualization of a partial network. The figure which shows the modification of the 2nd visualization example. The figure which shows the example of a display of the detailed information of an attention node. The figure which shows the visualization example of a bipartite graph format. The figure which shows the visualization example of a bipartite graph format. The figure which shows the example which searches an attribute directly. The figure which shows an example in the case of highlighting. The figure which shows the example of a display in case a some relationship exists. The figure which shows the case where a user evaluates about an extraction result. The figure explaining the case where 3 or more types of attributes and the relationship between attributes are handled. The figure which shows the example of the bipartite graph in the case of handling the attribute between 3 or more types and the relationship between attributes. The figure which shows the example which distinguishes and displays a company according to the business condition of a company. The block diagram which shows the modification of an extraction part.

  Hereinafter, the relationship visualization apparatus, method, and program according to the present embodiment will be described in detail with reference to the drawings. In the following embodiments, the same reference numerals are assigned to the same operations, and duplicate descriptions are omitted as appropriate.

(First embodiment)
The relationship visualization apparatus according to the first embodiment will be described with reference to the block diagram of FIG.

  The relationship visualization apparatus 100 according to the first embodiment includes an acquisition unit 101, an extraction unit 102, an extraction result storage unit 103, a user operation reception unit 104, a display method determination unit 105, a display unit 106, and a user information input unit 107. .

  The acquisition unit 101 acquires one or more target documents to be analyzed. The target document may be acquired by being input by a user, or may be automatically collected from an external server or the like. The target document in the present embodiment is assumed to be text data expressed in a natural sentence such as a news article, a paper, or a patent specification uploaded on a Web page or the Internet. However, the present invention is not limited to this, and any data that can extract attributes and relationships between attributes may be used.

  The extraction unit 102 receives the target document from the acquisition unit 101, extracts at least two types of attributes and relationships between the attributes from the target document, and obtains an extraction result. The attribute indicates the type of information to be analyzed, and examples include a product name, a price, a company name, a material name, and a characteristic value. The relationship between attributes is extracted when there is some relationship between attributes. Hereinafter, in the present embodiment, a description will be given by taking, as an example, a relationship between a gene and a disease as attributes from a literature such as a paper or a patent, and a gene estimated to be related to a disease as a relationship between attributes.

  The extraction result storage unit 103 receives extraction results of attributes and relationships between attributes from the extraction unit 102, and stores them in association with each other.

  The user operation reception unit 104 receives an operation (also referred to as a user operation) from a user. The user operation indicates, for example, a selection instruction regarding a change in the display format of the graph, and an operation such as confirmation and correction of an extraction result of attributes and relationships between attributes.

  The display method determination unit 105 receives the extraction result from the extraction result storage unit 103 and the user operation from the user operation reception unit 104, and determines the extraction result visualization method (for example, display format) according to the user operation. For example, as a default visualization method, a graph (entire network) in which attributes of extraction results are expressed by nodes and relationships between attributes are expressed by edges is determined.

  The display unit 106 receives the extraction result for which the display method has been determined from the display method determination unit 105, and displays the extraction result on a display device (not shown) such as a display according to the visualization method. Further, when receiving the newly determined visualization method from the display method determining unit 105, the display unit 106 redisplays the nodes and edges according to the newly determined visualization method.

  The user information input unit 107 acquires user information including document information and attribute information about the user and inputs the user information to the extraction result storage unit 103. Specifically, as user information, own research results and paper, gene of interest, analyzed gene, read paper, sequence indicating gene sequence, SNP information indicating gene sequence variation, attribute that user is interested in Information.

  Next, information extraction processing of the extraction unit 102 will be described with reference to the flowchart of FIG.

  In step S201, the extraction unit 102 selects a target document to be extracted.

  In step S202, the extraction unit 102 performs information extraction processing on the target document and obtains an extraction result. The information extraction process may be executed by a deterministic process such as text pattern matching for a fixed expression in a sentence, for example. Specifically, for example, if there is an expression “mutation of XX gene has an effect on △△ disease”, “OO gene” and “△△ disease” are extracted as attributes from the expression, and ( (○○, Δ △) can be extracted as a relationship between attributes. Since the information extraction process may be a general process, the information extraction process will not be described in detail.

  In step S203, it is determined whether or not all target documents have been processed. If all the target documents have not been processed, the process returns to step S201 and the same processing is repeated. If all the target documents have been processed, the extraction process ends.

  Next, an example of data stored in the extraction result storage unit 103 is shown in FIG.

  In the table 300 shown in FIG. 3, document ID 301, title 302, attribute A 303, and attribute B 304 are stored in association with each other.

  A document ID 301 is an identifier for identifying a target document, and indicates a document ID here. The title 302 is the title of the target document, and here shows the document title. The attribute A303 is an attribute extracted from the target document, and indicates a gene name here. The attribute B304 is an attribute extracted from the target document, which is different from the attribute A303, and indicates a disease name here.

  Specifically, in the example of FIG. 3, attribute A303 “EPHX2 gene” and attribute B304 “neutropenia” are obtained from the target document “Method of predicting side effects of docetaxel therapy” with document ID 301 “0000001”. You can see that it was extracted.

  Depending on the extraction method, values (probability, score, etc.) indicating the frequency of appearance and the likelihood of the extracted relationship may be stored.

  Next, the visualization method determination process according to the present embodiment will be described with reference to the flowchart of FIG. In the present embodiment, as a default display displayed on the display unit 106, all attributes stored in the storage unit are represented by nodes, and the entire network in which attributes are represented by edges is displayed. Suppose.

  In step S401, the display method determination unit 105 determines whether a part of display content is selected by the user. When the display content is selected, the process proceeds to step S403, and when the display content is not selected, the process proceeds to step S402.

  In step S402, the display method determination unit 105 determines to display the entire network for all attributes and the relationships between the attributes while maintaining the default display, and the display unit 106 remains displayed.

  In step S403, the display method determination unit 105 determines whether the selected part is a node or an edge. If the selected part is a node, the process proceeds to step S405. If the selected part is an edge, the process proceeds to step S404.

  In step S404, the display method determining unit 105 determines to display the partial network that is a part of the entire network and the information of the extraction source document for the relationship including the selected edge, and the display unit 106 extracts the partial network and the extracted network. Displays information of the original document.

  In step S405, the display method determination unit 105 determines whether there is a display request for related information. The related information display request may be determined to be a display request when the user operation receiving unit 104 receives an operation indicating the display request from the user (such as clicking or pressing a display request button prepared in advance). If there is a display request, the process proceeds to step S407, and if there is no display request, the process proceeds to step S406.

  In step S406, since there is no related information display request, the display method determination unit 105 determines to display the partial network including the node and the node information for the selected node, and the display unit 106 determines whether the partial network and the node information are displayed. Information and display.

  In step S407, since there is a request to display related information, the display method determination unit 105 searches for a node within two hops from the selected node. Here, a node within one hop refers to a node adjacent to a selected node with one edge. A node within two hops refers to a node traced to a selected node by one edge, one node, and another edge.

  In step S408, the display method determination unit 105 determines to display a node within two hops from the selected node in a bipartite graph format. The display method determination process is thus completed.

  Next, an example of a method for visualizing the entire network in the display unit 106 in step S402 is shown in FIG.

  The network display shown in FIG. 5 is a display in which all attributes stored in the extraction result storage unit 103 are expressed as nodes, and attributes A303 and corresponding attributes B304 are connected by edges.

  Next, FIG. 6 shows a first visualization example of a partial network on the display unit 106 in step S404.

  The network display shown in FIG. 6 is an example of a state where a specific edge is selected. Here, the disease name node “breast neoplasms” and the edge connecting the node name “NOVA1” are highlighted together. In addition, when an edge is selected, the display of the extraction source document information may be selected for the relationship between two nodes including the edge.

  An example of displaying the document information of the extraction source is shown in FIG. An ID indicating a document, a disease name, a gene name, and a specific text of an extraction source are displayed. In addition, bibliographic information such as a title and an author name may be displayed.

  Next, FIG. 8 shows a second visualization example of the partial network on the display unit 106 in step S406.

  The network display shown in FIG. 8 is an example of a state where a specific node is selected. Here, when the disease name “breast neoplasms” is selected and set as the attention node 801, the node included in the region surrounded by the rectangle of FIG. 5 including the attention node and related to the attention node 801 Is displayed. Here, nodes indicating genes related to “breast neoplasms” and edges connecting them are extracted from the entire network and displayed as a partial network.

  FIG. 9 shows a modification of the second visualization example shown in FIG.

  In the example of FIG. 9, the name (attribute name) of a node related to the node of interest 901 may be displayed in a separate window. Here, the attribute names of nodes other than the node of interest 901 are displayed in the display window 902. This makes it easy to search for a node related to the node of interest 901 from the list display. The display on the display window 902 is, for example, as shown in FIGS. 8 to 9 when the display unit 106 displays a switching button or the like and is selected by the user clicking or pressing the switching button. Switch to.

  Detailed information of the node of interest may be displayed by further selecting the node of interest. A display example of the detailed information of the node of interest is shown in FIG.

  As shown in FIG. 10, a name 1001 (here, attribute name), a synonym list 1002, an explanatory sentence 1003, and a classification 1004 are displayed as detailed information of the node of interest. Further, a detailed display 1005 that allows the user to select related information display may be prepared. When the user selects one from the detailed display 1005, the display method determination unit 105 can determine that there is a request to display related information. Note that the synonyms may be expanded by designating a list of synonyms.

  Next, FIG. 11A and FIG. 11B show an example of bipartite graph visualization on the display unit 106 in step S408.

  For example, if the user operation accepting unit 104 accepts a user operation that “Bipartite Visualization” in the detail display 1005 of FIG. 10 is selected, and the display method determining unit 105 determines to display the bipartite visualization method. Good.

  A node adjacent to the node of interest 1101 (first node), that is, a node that is one hop ahead (second node) is displayed as a first stacked bar graph, and a node that is two hops away from the node of interest and the node of interest (third node) Is displayed as a second stacked bar graph, thereby providing a bipartite graph format. Specifically, for example, a node “Breast cancer 1 early onset” whose attribute is one hop ahead of the disease attention node 1101 “Break neoplasms” is displayed in the first graph 1102 and the node 1101 “ “Blast neoplasms” and “Lung neoplasms” whose attribute is 2 hops away from the node of interest 1101 are displayed in the second graph 1103. In the example of FIGS. 11A and 11B, the number of relationships indicates the number of documents in which the relationship between attributes appears. FIG. 11A displays the entire connection relationship, and FIG. 11B displays the connection relationship for one hop when a specific node (here, the node of interest) is selected. Instead of displaying all the relationships, filtering may be performed so that only edges whose number of documents is equal to or greater than a threshold value are displayed.

  When investigating other diseases that are susceptible to the influence of a common gene starting from a certain disease, it is necessary to examine a part of the relationship between the gene and the disease. In such a case, the readability is low simply by cutting out a partial network having a similar number of hops. By displaying the attribute and the relationship between the attributes in a bipartite graph as in the present embodiment, for example, what is the gene that has been reported to have many relationships with the node of interest 1101 “Break neoplasms”, common gene mutations It becomes easier to visually grasp the relationship between attributes such as what kind of disease is affected.

  As described above, instead of selecting a node and an edge, a state in which an attribute can be directly searched may be set. An example of directly retrieving attributes is shown in FIG.

  As shown in FIG. 12A, a text box may be displayed to allow the user to input directly. For example, by inputting document information such as gene name, disease name, literature author, title, etc., the relationship between attributes or bibliographic information of the document is searched. The search result may be displayed in a format such as a document list.

  Further, as shown in FIG. 12B, a text box may be displayed in a superimposed manner in a state where the partial network is displayed, and the user may search for a node or an edge. By doing in this way, it becomes easy to find a specific node in a large-scale network by displaying the node hit by the search on the screen or highlighting it as necessary.

  Note that the graphs to be displayed are displayed uniformly, but if the relationship that the user is interested in is known, they may be highlighted in advance.

  An example of highlighting is shown in FIG.

  FIG. 13 shows an example of highlighting the node or edge when the user information input unit 107 registers a document published or published by the user or a list of gene names or disease names of interest as user information. Based on the user information stored in the extraction result storage unit 103, the display method determination unit 105 highlights 1301 the attributes (nodes) matching the user information and the relationships (edges) between the attributes from the beginning on the graph. To decide. By doing in this way, it becomes easy to give an overview of how the surroundings of the attention portion are. If necessary, the part of interest may be arranged at the center of the drawing area, or may be displayed in an enlarged manner.

  Next, a display example in the case where there are a plurality of relationships between genes and diseases will be described with reference to FIG.

  In the above-described example, an edge is displayed based on a document that has a relationship between a gene and a disease, but there may be a document that has resulted in no relationship between a gene and a disease. For example, there is a document that supports or affirms the relationship between a gene and a disease, while there is a document that denies the relationship (for example, “the mutation of the xx gene was found to be unrelated to □□ disease”). There is also a description).

  When there are a plurality of relationships between a gene and a disease, and it is desired to display both a document that affirms the relationship and a document that denies the relationship, the display method determination unit 105 displays each of the documents as shown in FIG. You may determine so that a relationship may be distinguished and displayed. In the example of FIG. 14A, for a document that affirms the relationship, the edge is displayed with a solid line, for a document that negates the relationship, the edge is displayed with a broken line, and two types of relationships are represented by two edges. Good. When there are both a document that affirms the relationship and a document that negates the relationship, the edge may be expressed by an edge of a line type different from the above-described edge. For example, a solid line may be expressed only for documents that affirm the relationship, a broken line may be expressed only for documents that abate the relationship, and a dashed line if both relationships exist. In this way, a plurality of types of relationships can be expressed with one edge. For example, when the interaction network between genes and proteins is used as the subject, there are relationships such as “enzymatic reaction”, “activation”, “repression”, “activation of transcription”, “phosphorylation”, and “binding”, and these relationships are displayed. Therefore, it can be used as analysis support in pathway analysis.

  Furthermore, when the extraction unit 102 performs an extraction process on a new document, a new relationship, node, or edge may increase. In such a case, the display method determination unit 105 may determine a visualization method that reflects the confirmation status indicating whether the user has confirmed the edge indicating the difference or the new arrival status, and that can understand the difference or the new arrival status. For example, as illustrated in FIG. 14B, when the user operation reception unit 104 has not received a user operation indicating that the new arrival information has been confirmed by the user, the display method determination unit 105 indicates the presence of the difference or the new arrival information as character information. Alternatively, the visualization method may be determined so as to blink the edge, and the display unit 106 may display according to the visualization method. Moreover, you may make it display the detail of newly arrived information by the said edge being selected.

  Further, the user may evaluate the extraction result stored in the extraction result storage unit 103. A case where the user performs evaluation will be described with reference to FIG.

  In the table 1500 shown in FIG. 15, the extraction result storage unit 103 stores the evaluation 1501 and the registration status 1502 in association with each other in addition to the table shown in FIG.

  In the evaluation 1501, the result of the user evaluating whether or not the extracted attribute and the relationship between attributes are appropriate is input. Here, the user operation reception unit 104 receives a determination result from the user, for example, a result evaluated with “◯” or “×”, and the extraction result storage unit 103 stores the determination result in association with each other.

  The registration status 1502 indicates, for example, the registration status of attributes and relationships between attributes, and indicates, for example, whether the attributes and relationships between attributes are registered in a public database or a private database.

  If the evaluation 1501 is “◯” and the registration status 1502 is “unregistered”, the user operation accepting unit 104 accepts an operation for registration. As a specific example, a procedure for registering a relationship between a document and an extraction result may be started by pressing registration of the registration status 1502. With such display, the database can be expanded along with the evaluation and confirmation of the extracted relationship.

  Although two types of attributes of gene and disease name have been described above, three or more types of attributes and relationships between attributes may be handled. For example, the business relationship (supply relationship) between companies will be described with reference to the example of FIG. In the partial network display shown in FIG. 16, the company name is drawn as a node and the supply relationship is drawn as an edge. Company A or Company I indicates the company name.

  FIG. 17 shows an example of creating a bipartite graph by paying attention to B company.

  In the example of FIG. 17, the appearance frequency is not displayed, and only the presence or absence of the relationship is expressed. The graph on the right side, which is a group of companies one hop away from “Company B”, shows companies that have a business relationship with Company B. The graph on the left side including “Company B” displays Company B and a group of companies that are nodes that are two hops away. By referring to this bipartite graph, you can see at a glance the common business partners, and further examine the relationship to determine whether it is a competitor or a partner that can form a cooperative relationship such as joint procurement. It becomes.

  In addition, when the business type of a company is known, a display that distinguishes the business type is also conceivable. FIG. 18 shows an example of displaying a company by distinguishing it according to the business type of the company.

The example of FIG. 18 shows a case where the company group can be divided into three types: material manufacturer, component manufacturer, and terminal manufacturer. In this example, it is displayed as a directed graph in which an arrow is directed from the supply source to the supply destination. In this way, by making a three-part graph, it is possible to more easily grasp the industry structure such as the supply chain. The graph format is not limited to the format described above, and any format that makes it easy to grasp the attribute relationship, such as displaying a scatter diagram according to the situation, may be used.
(Modification of this embodiment)
The information extraction process in the extraction unit 102 described above may be performed using machine learning.

  A modification of the extraction unit 102 will be described with reference to FIG.

  The extraction unit 102 according to the modification illustrated in FIG. 19 includes a candidate extraction unit 1901, a clue information extraction unit 1902, a training case assignment unit 1903, and a learning unit 1904.

  The candidate extraction unit 1901 receives the target document from the acquisition unit 101 and extracts attributes and relationships between attributes.

  The clue information extraction unit 1902 receives the target document from the acquisition unit 101 and the attributes and the relationship between attributes from the candidate extraction unit 1901. The clue information extraction unit 1902 extracts clue information indicating features that serve as clues when acquiring attributes and relationships between attributes from the target document. The clue information includes, for example, meta information of the target document (for example, creation date and time, document file format, language, etc.), extracted attribute word phrases (nouns, verbs and other parts of speech, personal names, place names, etc. Classification of expressions, phrases or syntax appearing before and after words, n-grams, etc.).

  The training case giving unit 1903 receives the attribute and the relationship between the attributes from the candidate extracting unit 1901, and gives a label to the training case data using the known information in which the correct answer is labeled in advance for training. In addition, since the method used in the process of general learning should just use the method of providing a label with respect to a training example, detailed description here is abbreviate | omitted.

  The learning unit 1904 receives attributes and relationships between attributes and clue information from the clue information extraction unit 1902, and a training case with a label from the training case assignment unit 1903. The learning unit 1904 learns the same evaluation criteria as those of the training examples, and learns by evaluating whether or not the extracted attribute and the relationship between attributes are desired attribute information. As a learning method, for example, the priority of clue information attached to attribute information determined to be correct in the training case is set high, and the priority of clue information attached to attribute information determined to be incorrect in the training case is set. A general learning method may be used, such as setting a low value.

  As a result, the table of FIG. 3 is given a score indicating the likelihood of the attribute relationship. Further, the user operation receiving unit 104 may receive an operation for setting an upper limit of the display number or a threshold value based on a score. Further, in the display output from the display unit 106, it may be output so as to superimpose and display what kind of clue information each relationship is extracted.

  According to the present embodiment described above, it is possible to support the understanding of the user's information by determining the node and edge visualization method in accordance with the operation from the user. The corresponding analysis can be easily performed.

The instructions shown in the processing procedure shown in the above-described embodiment can be executed based on a program that is software. A general-purpose computer system stores this program in advance and reads this program, so that the same effect as that obtained by the above-described relationship visualization device can be obtained. The instructions described in the above-described embodiments are, as programs that can be executed by a computer, magnetic disks (flexible disks, hard disks, etc.), optical disks (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD). ± R, DVD ± RW, Blu-ray (registered trademark) Disc, etc.), semiconductor memory, or a similar recording medium. As long as the recording medium is readable by the computer or the embedded system, the storage format may be any form. If the computer reads the program from the recording medium and causes the CPU to execute instructions described in the program based on the program, the same operation as that of the relationship visualization device of the above-described embodiment can be realized. Of course, when the computer acquires or reads the program, it may be acquired or read through a network.
In addition, the OS (operating system), database management software, MW (middleware) such as a network, etc. running on the computer based on the instructions of the program installed in the computer or embedded system from the recording medium realize this embodiment A part of each process for performing may be executed.
Furthermore, the recording medium in the present embodiment is not limited to a medium independent of a computer or an embedded system, but also includes a recording medium in which a program transmitted via a LAN, the Internet, or the like is downloaded and stored or temporarily stored.
Further, the number of recording media is not limited to one, and when the processing in this embodiment is executed from a plurality of media, it is included in the recording medium in this embodiment, and the configuration of the media may be any configuration.

The computer or the embedded system in the present embodiment is for executing each process in the present embodiment based on a program stored in a recording medium. The computer or the embedded system includes a single device such as a personal computer or a microcomputer. The system may be any configuration such as a system connected to the network.
In addition, the computer in this embodiment is not limited to a personal computer, but includes an arithmetic processing device, a microcomputer, and the like included in an information processing device. ing.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 100 ... Relationship visualization apparatus, 101 ... Acquisition part, 102 ... Extraction part, 103 ... Extraction result storage part, 104 ... User operation reception part, 105 ... Display method determination part, 106 ... Display unit, 107 ... User information input unit, 300 ... Table, 301 ... Document ID, 302 ... Title, 303 ... Attribute A, 304 ... Attribute B, 801 901, 1101 ... Node of interest, 902 ... Display window, 1001 ... Name, 1002 ... List, 1003 ... Description, 1004 ... Classification, 1005 ... Detailed display, 1102, 1103 ... Graph, 1301 ... Highlighting, 1500 ... Table, 1501 ... Evaluation, 1502 ... Registration status, 1901 ... Candidate extraction unit, 1902 ... Information extraction unit, 19 3 ... training examples applying section, 1904 ... learning unit.

Claims (9)

A storage unit for storing at least two types of attributes in association with each other;
A display unit that displays the attribute as a node and the relationship between the nodes as an edge;
A reception unit that receives a selection instruction regarding a change in the display format of the node or the edge;
A determination unit that determines a method of visualizing the node or the edge in response to the selection instruction;
The relationship visualization device, wherein the display unit redisplays the node or the edge according to the visualization method.   The determining unit displays a first graph that displays a second node that is one hop ahead of the first node, and a third graph that displays the first node and a third node that is two hops away from the first node. The relation visualization device according to claim 1, wherein a bipartite graph including two graphs is determined as the visualization method. The reception unit receives a determination result as to whether the attribute is appropriate,
The relationship visualization apparatus according to claim 1, wherein the storage unit stores the determination result in association with the attribute. A user information input unit for acquiring user information including literature information and attribute information;
The relation visualizing device according to claim 1, wherein the determination unit determines to highlight an attribute that matches the user information.   The relationship visualization apparatus according to claim 1, further comprising an extraction unit that extracts the attribute based on machine learning.   The determination unit according to any one of claims 1 to 5, wherein when there are a plurality of relationships between two attributes, the determination unit determines to separately display the relationships between the attributes. The relationship visualization device described.   The relation visualization according to any one of claims 1 to 6, wherein the determination unit determines to reflect and display a user confirmation status with respect to the attribute and the relationship between the attributes. apparatus. Store at least two types of attributes in association with each other,
Display the attribute as a node and the relationship between the nodes as an edge,
Accepting a selection instruction for changing the display format of the node or the edge,
In accordance with the selection instruction, determine a method of visualizing the node or the edge,
A relation visualization method, wherein the node or the edge is redisplayed according to the visualization method. Computer
Storage means for associating and storing at least two types of attributes;
Display means for displaying the attribute as a node and the relationship between the nodes as an edge;
Accepting means for accepting a selection instruction regarding a change in the display format of the node or the edge;
In response to the selection instruction, function as a determination unit that determines a visualization method of the node or the edge,
The display means is a relation visualization program for redisplaying the node or the edge according to the visualization method.