Display device for related information, program and display method for related information

Abstract

A related information display device (100) comprises: a knowledge graph database (101) that stores a knowledge graph containing knowledge information with a plurality of nodes and links connecting the nodes; a related information inference unit (104) that infers related information associated with a keyword from the knowledge graph; a kinship calculation unit (105) that calculates the kinship between the keyword and the related information; and a display data generation unit (106) that generates display data to show a flow rate graph indicating a relationship between the keyword and the related information by connecting the keyword and the related information with a band, the width of which increases as the kinship increases.

Description

FIELD OF TECHNOLOGY

[0001] The disclosure relates to a related information display device, a program, and a related information display method. STATE OF THE ART

[0002] Previously, there was a technique for storing specialized knowledge information in a database (DB) using knowledge graphs representing related events or knowledge relationships, searching the knowledge information, and presenting the retrieved information. For example, PTL 1 describes a method for extracting words or sentences from an input document, extracting knowledge from a knowledge graph representing conceptual structural information associated with the extracted words or sentences by specifying search conditions or the DB to be searched based on conditions specified by a user, and converting the extracted knowledge into a graph structure or text. PRIOR ART PATENT REFERENCES

[0003] Patent Literature 1: Japanese Patent Application Publication No. 2020-140604 SUMMARY OF THE INVENTION TASK TO BE SOLVED BY THE INVENTION

[0004] In the conventional technique, the results of extracting data from a knowledge graph are directly represented as a graph structure to represent their relationships.

[0005] However, there is a problem with presenting the results in the form of a graph structure, because a graph structure is difficult to understand or the relationship between the extracted results and the input data is difficult to read unless the user has knowledge of graph structures.

[0006] Accordingly, it is an objective of one or more aspects of the disclosure to represent the relationship between a keyword and the knowledge extracted from a knowledge graph using the keyword in an easily understandable manner, even if a user does not have sufficient knowledge of the structures of a knowledge graph. MEANS TO SOLVED THE TASK

[0007] A related information display device according to one aspect of the disclosure includes: a knowledge graph storage unit configured to store a knowledge graph including knowledge information having a plurality of nodes and links connecting the nodes; a related information inference unit configured to derive related information related to a keyword from the knowledge graph; a relatedness calculation unit configured to calculate the relatedness between the keyword and the related information;and a display data generation unit configured to generate display data for displaying a flow rate diagram indicating a relationship between the keyword and the related information related to the keyword by connecting the keyword and the related information with a band, the width of the band increasing as the relatedness increases.;

[0008] A program according to one aspect of the disclosure causes a computer to function as follows: a knowledge graph storage unit configured to store a knowledge graph including knowledge information having a plurality of nodes and links connecting the nodes; a related information inference unit configured to derive related information related to a keyword from the knowledge graph; a relatedness calculation unit configured to calculate the relatedness between the keyword and the related information;and a display data generation unit configured to generate display data for displaying a flow rate diagram indicating a relationship between the keyword and the related information related to the keyword by connecting the keyword and the related information with a band, the width of the band increasing as the relatedness increases.;

[0009] A method for displaying related information according to one aspect of the disclosure includes: deriving related information related to a keyword from a knowledge graph including knowledge information having a plurality of nodes and links connecting the nodes; calculating the relatedness between the keyword and the related information; and generating display data for displaying a flow rate diagram indicating a relationship between the keyword and the related information related to the keyword by connecting the keyword and the related information with a band, wherein the width of the band increases as the relatedness increases. EFFECTS OF THE INVENTION

[0010] According to one or more aspects of the disclosure, it is possible to represent the relationship between a keyword and the knowledge extracted from a knowledge graph in an easily understandable manner, even if a user does not have sufficient knowledge of the structures of a knowledge graph. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a block diagram schematically showing a configuration of a related information display device according to a first embodiment. Fig. Figure 2 is a schematic diagram showing the structure or ontology of a knowledge graph revolving around a document. Fig. Figure 3 is a schematic diagram showing a first example of a knowledge graph. Fig. Figure 4 is a schematic diagram showing a first example of a Sankey diagram. Fig. Figure 5 is a schematic diagram showing a first example of a subgraph. Fig. Figure 6 is a schematic diagram showing a second example of a subgraph. Fig. 7 is a table that summarizes the relationship between an input query and related information or a search result. Fig. Figure 8 is a schematic diagram showing a second example of a knowledge graph. Fig. Figure 9 is a schematic diagram showing a third example of a subgraph. Fig. Figure 10 is a schematic diagram showing a second example of a Sankey diagram. Fig. 11 is a block diagram schematically showing an example of a hardware configuration. Fig. 12 is a flowchart illustrating the operation of the related information display device according to the first embodiment. Fig. 13 is a block diagram schematically showing a configuration of a related information display device according to a second embodiment. Fig. Figure 14 is a schematic representation of a third example of a Sankey diagram. Fig. Figure 15 is a schematic representation of a fourth example of a Sankey diagram. Fig. Figure 16 is a schematic diagram showing a fourth example of a subgraph. Fig. 17 is a flowchart illustrating the operation of the related information display device according to the second embodiment. Fig. Figure 18 is a schematic representation of a fifth example of a Sankey diagram. Fig. Figure 19 is a schematic diagram showing a sixth example of a Sankey diagram. Fig. 20 is a block diagram schematically showing a configuration of a related information display device according to a third embodiment. Fig. 21 is a flowchart illustrating the operation of the related information display device according to the third embodiment. Fig. 22 is a block diagram schematically showing a configuration of a related information display device according to a fourth embodiment. Fig. 23 is a block diagram schematically showing a configuration of a related information display device according to a fifth embodiment. Fig. Figure 24 is a schematic diagram showing an example of a pop-up displaying detailed information. Fig. 25 is a schematic diagram showing an example in which band information is displayed as detailed information. MODE FOR CARRYING OUT THE INVENTION FIRST EMBODIMENT

[0011] Fig. 1 is a block diagram schematically showing a configuration of a related information display device 100 according to the first embodiment.

[0012] The related information display device 100 includes a knowledge graph database (DB) 101, a DB operation unit 102, a user interface (I / F) unit 103, a related information inference unit 104, a relationship calculation unit 105, and a display data generation unit 106.

[0013] The knowledge graph DB 101 contains knowledge information. The knowledge graph database DB 101 is, for example, a knowledge graph database that contains knowledge information in a graph structure, where nodes represent the previously acquired knowledge information and links represent the relationships between the nodes. In other words, the knowledge graph DB 101 acts as a knowledge graph storage unit that stores knowledge graphs containing knowledge information with multiple nodes and links between the nodes.

[0014] There are various knowledge graph formats, such as property graphs and Resource Description Framework (RDF). In the following description, knowledge graphs are presented in property graph format. However, knowledge graphs can also be represented in other graph formats. The Knowledge Graph DB 101 contains knowledge information extracted from business documents, such as design documents and dissertations, as knowledge graphs.

[0015] Fig. 2 and Fig. 3 are schematic diagrams for explaining the knowledge graph according to the first embodiment.

[0016] Fig. Figure 2 is a schematic diagram showing the structure or ontology of a knowledge graph revolving around a document.

[0017] Fig. Figure 3 is a schematic diagram showing an example of a knowledge graph.

[0018] In Fig. 2, the nodes represent information about information types such as "document," "person," "department," "product," and "feature word"; and the relationship between "document" and "author" is called "WRITE," the relationship between "document" and "department" that publishes the "document" is called "PUBLICATE," the relationship between "product" and "document" assigned to the "product" is called "ASSOCIATED," the relationship between "person" and "department" to which the "person" belongs is called "BELONGS_TO," and the relationship between "document" and "feature word" contained in "document" is called "CONTAINS." Here, the information type "feature word" refers to words that represent the content of a document. Each node in a knowledge graph always has a defined information type.

[0019] One in Fig. The knowledge graph 101#1 shown in Figure 3 contains knowledge information obtained from documents and information associated with the documents in the form of a graph which is based on the Fig. 2 presented ontology.

[0020] The Fig. The knowledge graph 101#1 shown in Figure 3 is an example that contains knowledge information related to business documents, but the knowledge graph 101#1 is only an example and may also contain other information.

[0021] Referring back to Fig. 1, the DB operation unit 102 operates the knowledge graph DB 101. For example, the DB operation unit 102 operates the knowledge graph DB 101 to register, update, or delete knowledge therein, and search the knowledge therein under specified conditions. The DB operation unit 102 performs processing corresponding to the type of the knowledge graph DB 101, receives keywords as input queries and the type of information to be retrieved from the related information inference unit 104, and performs the search using a specified search method. For example, the DB operation unit 102 applies a search method in which knowledge connected by specified route paths is searched based on the knowledge graph structure.

[0022] The user interface unit, or user I / F unit, 103 functions as an interface unit that detects keywords and information types. Here, the user interface unit 103 functions as an input accepting unit that accepts input from a user and as a display unit that displays the corresponding information. For example, the user I / F unit 103 accepts input from a user via an input device (not shown) such as a keyboard or mouse, which functions as an input unit, and forwards an accepted input query to the related information inference unit 104. The user I / F unit 103 then presents the related information and its relationship to the user on a display, which functions as a display unit, based on the display data received from the display data generation unit 106.

[0023] In other words, the user interface unit 103 presents a search screen that allows the user to retrieve related information and accepts the user's input of keywords, information types to which the keywords belong, and information types representing the type of information to be retrieved. Based on the display data, the user interface 103 then uses a flowchart representing the flow rates between processes represented by a Sankey diagram IM1, as shown in Fig. 4, to present the user with the relationships between the input queries and the associated information.

[0024] The display data of the display data generation unit 106 includes at least one or more keywords or input queries, related information, ie, the search results, the width of a band connecting each keyword and its search result, and width information used to display the keyword and its search result. Based on this information, the user interface 103 displays the corresponding information in the form of the Sankey diagram IM1 on the display.

[0025] The Sankey diagram IM1 illustrates keywords that are input queries, related information, and bands that connect the keywords and the related information.

[0026] The input queries are arranged on the left side of the Sankey diagram IM1, and the related information is arranged on the right side of the Sankey diagram IM1. The width of the band connecting a keyword and the related information increases as the relatedness between the keyword and the related information increases.

[0027] At this point, related information can be arranged in descending order of bandwidth from the top. This places information closely related to a search term at the top, making it easy to find results.

[0028] When pieces of related information can be grouped, such as grouping pieces of information about people and their affiliation information, this information can be displayed together as a group. This allows users to capture a collection of related information and easily view the results.

[0029] When returning to Fig. 1, the user interface unit 103 is implemented as a web application, for example, a user accesses a specific URL (Uniform Resource Locator) using a browser to display a search screen. The user then enters keywords using a keyboard. The related information obtained based on the user input is displayed in the form of a Sankey diagram in a web browser on a display. User input can also be accepted via voice.

[0030] In the Fig. In the example shown in Figure 4, the flow rate diagram is displayed two-dimensionally, but it can also be displayed three-dimensionally. For example, if multiple types of related information, such as people and documents related to input keywords, are to be displayed simultaneously, the relationships of the related information for each type of information can be displayed by displaying the relationships with the people in the lateral direction and the connections with the documents in the depth direction.

[0031] The related information inference unit 104 derives related information related to a keyword from a knowledge graph stored in the knowledge graph DB 101. Here, the related information inference unit 104 receives user input and derives related information therefrom. The related information inference unit 104 uses, for example, the DB operation unit 102 to extract the related information desired by the user based on keywords or input queries and the information type of the information to be retrieved, which were input by the user. Here, the related information inference unit 104 derives information related to the keywords and belonging to the information type as related information.

[0032] Specifically, the related information inference unit 104 specifies a path to be searched based on the knowledge graph structure to extract related information. For example, if a user wants to retrieve information about a "person" who has knowledge of "voice recognition" and "dialogue," the related information inference unit 104 uses the DB operation unit 102 to extract authors of documents containing the term "voice recognition" as a feature word and authors of documents containing the word "dialogue" as a feature word, and infers that individuals belonging to both sets of authors are related individuals who represent related information.In other words, the related information inference unit 104 derives related information by selecting a derivation method corresponding to the related information desired by a user.

[0033] The related information inference unit 104 can also infer the authors of documents containing the two feature words "speech recognition" and "dialogue" as related persons. If a graph structure is stored for each information type specified as the type of information to be retrieved by a user, the related information inference unit 104 can extract a subgraph similar to this graph structure and determine the nodes of the information type specified as the information to be retrieved in the subgraph as related information. Alternatively, the related information inference unit 104 can extract the related or related information by calculating a shortest route path from an input query.The related information inference unit 104 may also use other methods for extracting related information.

[0034] Furthermore, the related information inference unit 104 may present information of various information types as related information, rather than requiring a user to specify a specific information type. For example, the related information inference unit 104 may use a graph structure to extract information within a certain number of jumps from a keyword as related information. The related information inference unit 104 may predetermine the information type of the information to be extracted according to the information type of the input query and extract only relevant data.

[0035] The relationship calculation unit 105 calculates the relationships between keywords and related information. In this case, the relationship calculation unit 105 calculates the relationship between an input keyword and the inference result of the related information. The relationship calculation unit 105 uses, for example, the search results of related information extracted by the related information inference unit 104 and the graph structure of a knowledge graph used for extraction to calculate the relationships between the keywords, which are input queries, and the extracted related information.

[0036] A concrete example of calculating the relationships is now explained for a case where “Person A” and “Person B” are extracted as related persons, which are information about “dialogue” and “speech recognition”.

[0037] For example, if the relationship is to be defined by the number of documents between a keyword or a feature word and a person, the relationship between “dialogue” and each related person in the knowledge graph 101#1 is Fig. 3 is determined based on the structure of a subgraph 101#2 as shown in Fig. 5. Specifically, the degree of relationship between "Dialog" and "Person A" is "2" because "Dialog" and "Person A" are connected via "Document 4" and "Document 5." Furthermore, the degree of relatedness between "Dialog" and "Person B" is "1" because "Dialog" and "Person B" are connected via "Document 1."

[0038] Similarly, the degree of relatedness between “Speech Recognition” and “Document 4” is calculated based on the structure of a subgraph 101#3 as shown in Fig. 6 is determined as "1" because "Speech Recognition" is connected to "Person A" via "Document 4". Furthermore, the degree of relatedness between "Speech Recognition" and "Person B" is given as "1" because "Speech Recognition" is connected to "Person B" via "Document 1". The relationship between an input query and related information or a search result is shown in Fig. 7 summarized.

[0039] In the above example, the relatedness calculation unit 105 calculates the number of documents to be forwarded as the degree of relatedness based on a node structure. Alternatively, an importance degree may be set for the documents, and the relatedness degree may be calculated as the sum of the importance degrees of the documents to be forwarded. Alternatively, the relatedness calculation unit 105 may calculate the relatedness degree by calculating the importance of the keywords in the documents using frequency of occurrence-inverse document frequency (TF-IDF) or the like and summing the calculation results. Alternatively, the relatedness calculation unit 105 may also calculate the sum of the link weights set using PageRank as the degree of relatedness between an input query and related information.Alternatively, the relationship calculation unit 105 may change the calculation method for each type of node. Alternatively, the relationship calculation unit 105 may also calculate the degree of relationship by combining multiple methods. Furthermore, the relationship calculation unit 105 may also use information other than that described here to calculate the relationship.

[0040] The display data generation unit 106 generates display data for displaying a flowchart indicating the relationship between a keyword and the keyword's related information by connecting the keyword and the related information with a band. Here, the width of the band increases as the degree of relationship increases. The flowchart is, for example, a Sankey diagram, and the width of the bands is assumed to be normalized based on the width of the displayed keyword.

[0041] In the first embodiment, the display data generation unit 106 generates display data, which is data for display, based on related information and relationship. For example, the display data generation unit 106 generates display data required to represent the relationship between keywords and related information in a Sankey diagram based on the related information received from the related information inference unit 104 and the relationship received from the relationship calculation unit 105.Display data includes at least one or more keywords, which are input queries, related information, which are search results, bands connecting the input keywords and the search results, and information about the respective widths required to display this data. In addition, display data may also include the colors required for display, information about the position of the ad, or similar information.

[0042] Specifically, the display data generation unit 106 normalizes the width of a band connecting each keyword and related information for each keyword by using the degree of relatedness calculated by the relatedness calculation unit 105. In other words, the display data generation unit 106 calculates a value obtained by dividing the width of a keyword by the relatedness of the keyword and the related information as the band width, and the width of the node with the related information is defined as the sum of the widths of the bands connected to that node. At this time, it is assumed that the importance of the keywords input by the user is equal, and therefore the widths of the keywords are equal.

[0043] An example case is now described in which products with reference to “feature word X” and “feature word Z” are extracted from a Fig. 8 shown knowledge graph 101#4 can be retrieved.

[0044] As a first requirement, the width of “Feature Word X” and “Feature Word Z” must each be 30.

[0045] Related products associated with these attribute words are “Product 1” and “Product 2”, as shown in subgraph 101#5 in Fig. 9. Since the degree of relatedness between “feature word X” and “product 1” is “1” and the degree of relatedness between “feature word X” and “product 2” is “1”, the width of each band is 1 / 2 the width of “feature word X”, i.e., 15.

[0046] The degree of relatedness between "feature word Z" and "product 1" is 1, and the degree of relatedness between "feature word Z" and "product 2" is 2. Therefore, the width of the band connecting "feature word Z" and "product 1" is 1 / 3 of the width of "feature word Y," which is 10, and the width of the band connecting "feature word Z" and "product 2" is 2 / 3 of the width of "feature word Y," which is 20.

[0047] This means that the width of “Product 1” is 15+10=25 and the width of “Product 2” is 15+20=35. Therefore, in a displayed Sankey diagram, IM2, as shown in Fig. 10, the width of the node Product 2 is greater than the width of the node Product 1.

[0048] We now describe another example where the relatedness or connection of only one of the input queries is high. Here, the width of the bands is normalized for each keyword. This prevents the results from being influenced by the relatedness value of only one of the input queries, even if the relatedness value of one of the keywords is high, by normalizing the width with each keyword.

[0049] For example, if the degree of relatedness between "Feature Word A" and "Product P" is "18," the degree of relatedness between "Feature Word A" and "Product Q" is "12," the degree of relatedness between "Feature Word B" and "Product P" is "1," and the degree of relatedness between "Feature Word B" and "Product Q" is "4," then the sum of the relatedness degrees of "Product P" is 18+1=19, and the sum of the relatedness degrees of "Product Q" is 12+4=16, which means that the relatedness degree of "Product P" is higher. Here, the relatedness between "Product P" and "Feature Word B" is not high, but the relatedness between "Product P" and "Feature Word A" is high; therefore, the relatedness of "Product P" as a whole is considered high.

[0050] However, the user's original intention is to retrieve related information about both "feature word A" and "feature word B." Therefore, in the present embodiment, the display data generation unit 106 normalizes the bandwidths based on the relatedness. In this example, the width of the band connecting "feature word A" and "product P" is set to 30×18÷(18+12)=18, the width of the band connecting "feature word A" and "product Q" is set to 30×12÷(18+12)=12, the width of the band connecting "feature word B" and "product P" is set to 30×1÷(1+4)=6, and the width of the band connecting "feature word B" and "product Q" is set to 30×4÷(1+4)=24. The width of "Product P" is set to 18 + 6 = 24 and the width of "Product Q" is set to 12 + 24 = 36. This allows the width of Product Q to be displayed larger than the width of Product P.As a result, the display data generation unit 106 can display related information to the user that is highly related to both "feature word A" and "feature word B," which corresponds to the user's original intention when performing the search, as high-ranking results. This can also prevent any one of the input queries from affecting the overall relatedness.

[0051] This assumes that the importance of each input keyword is equal, so the widths of the keywords are equal. However, the user can, for example, specify the degree of importance of each keyword and change the width of the input keyword accordingly. In this case, the display data generation unit 106 performs a calculation in which each bandwidth is normalized according to the set width of the corresponding keyword.

[0052] Fig. 11 is a schematic hardware configuration diagram of the related information display device 100 according to the first embodiment.

[0053] As in Fig. 11, the related information display device 100 may be implemented by a computer 120 including an input I / F 121, an output I / F 122, an auxiliary storage device 123, a memory 124, and a processor 125.

[0054] The Input I / F 121 is an input device, such as a keyboard or mouse, for accepting input from a user. The Input I / F 121 functions as an input unit that accepts input from a user.

[0055] The Output I / F 122 is an output device, such as a display, that provides information to the user. The Output I / F 122 functions as a display unit for presenting information to a user.

[0056] The auxiliary storage device 123 is a memory such as a hard disk drive (HDD) or a solid state drive (SSD) on which information such as knowledge graphs and programs required for processing by the related information display device 100 are stored.

[0057] The memory 124 is a volatile or non-volatile memory that provides a working area to the processor 125.

[0058] The processor 125 loads a program stored in the auxiliary storage device 123 into the memory 124 and executes the program to perform the processing by the related information display device 100.

[0059] The knowledge graph DB 101 may be implemented, for example, by the additional storage device 123.

[0060] The DB operation unit 102, the user interface unit 103, the related information inference unit 104, the relationship calculation unit 105, and the display data generation unit 106 may be implemented by the processor 125, which loads the programs stored in the auxiliary storage device 123 into the memory 124 and executes the programs.

[0061] Such programs may be delivered over a network or may be recorded and provided on a recording medium. That is, such programs may, for example, be provided as a program product.

[0062] Fig. 12 is a flowchart illustrating the operation of the related information display device 100 according to the first embodiment.

[0063] First, the user interface unit 103 receives inputs from a user regarding keywords, the information type of the keywords, and the information type of the target to be retrieved via an input unit (not shown) and a display unit (not shown) (step S10). In other words, the user interface 103 receives the keywords input by a user and the information type selected and input by the user.

[0064] Next, the related information inference unit 104 selects a related information inference method based on the information type of the keywords and the information type of the information to be retrieved (step S11). The related information inference unit 104 selects a method for searching the knowledge graphs DB from a plurality of predetermined search methods in accordance with the information types received from the user I / F unit 103. In other words, the search method to be used is predetermined depending on the information type.

[0065] Next, the related information inference unit 104 uses the selected inference method to derive related information associated with the input keywords (step S12). In other words, the inference unit 104 extracts the related knowledge information related to the keywords received from the user interface 103 from the knowledge graph using the selected inference method.

[0066] Next, the relationship calculation unit 105 uses a graph structure to calculate the relationship between each keyword and the derived related information (step S13). In other words, the calculation unit 105 calculates the degree of relatedness using information such as the number of propagated nodes or their importance based on the structure of a subgraph containing the keywords and the extracted related information.

[0067] Next, the display data generation unit 106 uses the calculated relatedness degrees to calculate the bandwidths and node widths required to construct a Sankey diagram and generates display data (step S14). In other words, the display data generation unit 106 calculates the widths of the bands representing the relationships between the keywords and the related information based on the related information extracted by the related information inference unit 104 and the relatedness degrees calculated by the relatedness calculation unit 105, and generates display data.The display data generation unit 106 normalizes the widths of the bands connecting the keywords and the associated information based on the widths of the keywords on the input side, and determines the value of the associated information width as the sum of the keyword width and the band width. The display data generation unit 106 then generates display data with the above values.

[0068] Finally, the user interface unit 103 draws a Sankey diagram on a display unit (not shown) based on the generated display data (step S15). In other words, the user interface unit 103 draws a Sankey diagram based on the received display data and presents it to the user.

[0069] As described above, according to the first embodiment, by representing the relationship between the keywords input by a user and the derived related information in the form of a Sankey diagram, the relationship between the input keywords and the obtained related information can be represented by the bandwidth. Therefore, a user can easily recognize the relationship between the input keywords and the obtained related information.

[0070] Since the values ​​obtained by normalizing the relatedness degrees obtained from a knowledge graph are used to calculate the bandwidths that represent the relationships between the keywords and the related information, information related to both keywords can be displayed at higher ranks, and the information desired by the user can be presented. SECOND EXAMPLE

[0071] In the first embodiment described above, related information of keywords is displayed. However, in the second embodiment described below, new related information is retrieved and displayed using the related information obtained from the keywords as input.

[0072] Fig. 13 is a block diagram schematically showing a configuration of a related information display device 200 according to the second embodiment.

[0073] The related information display device 200 includes a knowledge graph DB 101, a DB operation unit 102, a user I / F unit 203, a related information inference unit 204, a relationship calculation unit 205, a display data generation unit 206, and a display data storage unit 207.

[0074] The knowledge graph DB 101 and the DB operation unit 102 of the related information display device 200 according to the second embodiment are respectively the same as the knowledge graph DB 101 and the DB operation unit 102 of the related information display device 100 according to the first embodiment.

[0075] Similar to the first embodiment, the user I / F unit 203 functions as an input accepting unit that accepts inputs from a user and as a display unit that displays the corresponding information. For example, similar to the first embodiment, the user interface unit 203 presents a search screen that allows the user to retrieve related information, and accepts the user's input of keywords, information types to which the keywords belong, and information types that are the type of information to be retrieved. The user interface unit 203 then presents the degree of relationship between the input queries and the related information to the user using a flowchart based on the display data, as in the first embodiment.Here, related information derived based on the keywords entered by a user is also referred to as first related information. The information type retrieved and used for inferring the first related information is also referred to as the first information type.

[0076] The user interface unit 203 accepts the input of the type of information to be retrieved from the first related information as user input on a screen displaying the first related information via an input unit (not shown). As shown in Fig. For example, as shown in Figure 14, a selection area SA1 is provided on a screen displaying a Sankey diagram IM3 of the inference result of the first related information to enable selection of the information type to be retrieved by using the first related information as keywords. When an information type is selected in the selection area SA1, the user interface unit 203 passes the first related information to the related information inference unit 204 so that the first related information is used as keywords to retrieve information of the selected information type. The information type selected here is also referred to as a new information type or a second information type.In other words, in the second embodiment, the user interface unit 203 detects a new information type after the display data is generated.

[0077] Similar to the first embodiment, the related information inference unit 204 receives user inputs and derives first related information therefrom.

[0078] The related information inference unit 204 then receives keywords, which are the first related information, and a selected information type from the user interface 203, and derives second related information, which is related information to the keywords, based on the received keywords and the information type. For example, the related information inference unit 204 uses people 1 to 5, which are the first related information from the first search in Fig. 14, as input keywords and uses the DB operation unit 102 and the knowledge graphs DB 101 to extract related information of the selected information type from a knowledge graph. In other words, the related information inference unit 204 uses the first related information as new keywords and derives information related to the new keywords and belonging to a new information type as second related information, which is new related information.

[0079] When the first related information is "person" and information of the information type "product" is to be retrieved as related information about the persons, the related information inference unit 204 uses the structure of the knowledge graph to select an inference method for deriving the related information as products of documents authored by one of the input persons.

[0080] The relationship calculation unit 205 calculates the relationship between the keywords and the first or second related information based on the results of the first or second related information. The relationship calculation unit 205 calculates the relationship based on, for example, the number of propagated nodes in the graph or the importance levels of the propagated nodes when the first propagated information is an input node and the second propagated information is an output node. Specifically, the relationship calculation unit 205 calculates the relationship by calculating the sum of the number of nodes between the input nodes and the output nodes. The relationship calculation unit 205 may calculate the relationship by calculating the sum of the importance levels of the propagated nodes.

[0081] The kinship for the first related information is also called first kinship, and the kinship for the second related information is also called new kinship or second kinship.

[0082] The display data storage unit 207 stores the display data generated by the display data generation unit 206.

[0083] Similar to the first embodiment, the display data generation unit 206 generates display data based on the first related information and their relationship. The display data generated here is also referred to as first display data.

[0084] The display data generation unit 206 generates display data based on the first and second information and their relationship to each other. The display data generated here is also referred to as new display data or second display data.

[0085] However, the first display data also contains data to display a selection area for further inference based on the first related information.

[0086] For example, the display data generation unit 206 generates first display data through similar processing as in the first embodiment, and then passes the first display data to the user interface unit 203 and stores the first display data in the display data storage unit 207.

[0087] When the display data generation unit 206 receives the second related information from the related information inference unit 204 and the second relatedness from the relatedness calculation unit 205, the display data generation unit 206 calculates the widths of the bands connecting the first related information and the second related information, which are keywords, and the widths of the second related information by processing similar to the first embodiment.The display data generation unit 206 then reads the first display data stored in the display data storage unit 207 and generates second display data indicating the widths of the keywords in the first display data, the widths of the bands connecting the keywords and the first related information, the width of the node of the first related information, the widths of the bands connecting the first related information and the second related information, and the width of the node of the second related information.

[0088] For example, the display data generation unit 206 determines the width of the bands connecting the first related information and the second related information based on the width of the node of the first related information by normalizing the width of the bands relative to the width of the node of the first related information in accordance with the degrees of relatedness calculated by the relatedness calculation unit. In other words, the display data generation unit 206 determines the width of each band by dividing the width of the first related information in proportion to the relatedness with the second related information, and determines the width of the node of the second related information by adding the widths of the bands.In other words, the display data generation unit 206 connects new keywords and new related information of the new keywords with bands to generate new display data for displaying a new flowchart indicating the relationship between the new keywords and their new related information. Here, the width of the band between a new keyword and a new related information increases as the new relationship increases.

[0089] The second display data may include, as order information for displaying the first and second related information, sequence information indicating column numbers of columns in which the data is stored, information for displaying nodes in descending order of width, information representing a display order for grouped display, or the like.

[0090] By receiving second display data as described above, the user interface 203 causes a display unit (not shown) to display a Sankey diagram IM4 with keywords and first and second associated information as shown in Fig. 15 shown.

[0091] In the Sankey diagram IM4, the entered keywords are displayed at the left end, the first related information is displayed in the middle, and the second related information is displayed to the left of the first related information. The relationship between the respective search results is indicated by the width of the bands.

[0092] Specifically, “Person 1,” “Person 2,” “Person 3,” “Person 4,” and “Person 5,” which are the first related information, are displayed as people related to “Keyword X” and “Keyword Y,” the entered keywords.

[0093] "Products," which are information related to "Person 1," "Person 2," "Person 3," "Person 4," and "Person 5," are displayed as second related information. Products are displayed as second related information on the right and are connected to people by bands whose width represents the strength of the relationships between the products and people; for example, "Product A" and "Product D" are related to "Person 1" and thus connected, "Product A" and "Product C" are related to "Person 2" and thus connected, "Product B" and "Product E" are related to "Person 3" and thus connected, "Product C" and "Product D" are related to and thus connected to "Person 4," and "Product D" and "Product E" are related to and thus connected to "Person 5."

[0094] If the first related information is "people" and "products" related to the people are to be retrieved, the related information inference unit 204 uses a knowledge graph structure to select an inference method that derives products related to documents written by one of the people as related information. In a Fig. For example, the subgraphs 101#6 shown in Figure 16 are "Product 1," "Product 2," and "Product 3" related to "Document 2," "Document 3," "Document 4," and "Document 5" authored by "Person A," and "Product 1" and "Product 4" related to "Document 1" and "Document 6" authored by "Person B" are derived as related second product information. Alternatively, an inference method for calculating from a knowledge graph using PageRank, etc., or another inference method may be selected.

[0095] The above-described display device 200 for related information can also be implemented by the computer 120, as shown in Fig. 11. The display data storage unit 207 can be implemented, for example, by the additional storage device 123.

[0096] Fig. 17 is a flowchart illustrating the operation of the related information display device 200 according to the second embodiment.

[0097] Since the operation of the related information display device 200 according to the second embodiment up to the step of displaying the first related information is the same as the operation of the related information display device 100 according to the first embodiment, the operations from the steps of displaying the first related information up to the step of displaying the second related information will be explained here.

[0098] First, the user interface unit 203 accepts user input of an information type of the second related information to be retrieved via a screen with a flowchart representing the first related information (step S20). Here, the user interface unit 203 accepts a user's selection of the information type of the second related information to display information related to the first related information. Fig. In the example shown in Figure 18, a Sankey diagram IM5 shows first related information "Person A" and "Person B" related to "Keyword X" and "Keyword Y", and a selection area SA2 that allows a user to select an information type for retrieving second related information related to the first related information "Person A" and "Person B". Here, "Product" is selected as the information type for the second related information.

[0099] Next, the related information inference unit 204 selects an inference method based on the information type of the first related information and the information type of the second related information (step S21). In other words, the related information inference unit 204 selects a knowledge graph inference method predetermined in accordance with the information type of the first related information and the information type of the second related information received from the user interface unit 203. In the Fig. In the example shown in Figure 18, in order to infer related “products” from “persons,” an inference method is selected to retrieve “documents” written by a “person” and further extract “products” related to the “documents” as second related information.

[0100] Next, the related information inference unit 204 derives a second piece of information for the first piece of information by using the selected inference method (step S22). In other words, the related information inference unit 204 extracts from the knowledge graph knowledge information related to the first piece of related information received from the user interface 203 by using the selected inference method. In the example in Fig. 16, the documents authored by Person A are “Document 2”, “Document 3”, “Document 4” and “Document 5”, and the products related to these documents are “Product 1”, “Product 2” and “Product 3”, that is, the product information related to Person A is “Product 1”, “Product 2” and “Product 3”.

[0101] Documents authored by "Person B" are "Document 1" and "Document 6", and products related to these documents are "Product 1" and "Product 4", so products related to "Person B" are "Product 1" and "Product 4".

[0102] Next, the relationship calculation unit 205 uses a graph structure to calculate the relationship between the first related information and the derived second related information (step S23). In other words, the relationship calculation unit 205 calculates the relationship based on information such as the number of propagated nodes or the degree of importance of the propagated nodes, based on a subgraph structure including the first related information, which are the keywords, and the extracted second related information.

[0103] In the Fig. In the subgraph 101#6 shown in Figure 16, the number of propagated nodes is "1" because "Person A" and "Product 1" are related to each other through "Document 2." Since "Document 2" has a high degree of importance and is referenced by other documents, the degree of importance is "2." Therefore, the degree of their relatedness is calculated by the relatedness calculation unit 205 as 2×1=2.

[0104] Since "Person A" and "Product 2" are related through "Document 3" and "Document 4," the number of passed nodes is 2 and the importance level of each of these documents is 1. Therefore, their relatedness is calculated by the relatedness calculation unit 205 and is 1×2=2.

[0105] Since "Person A" and "Product 3" are related through "Document 5," the number of passed nodes is 1 and the degree of importance is 1. Therefore, their relatedness is calculated by the relatedness calculation unit 205 as 1×1=1.

[0106] Since "Person B" and "Product 1" are related to each other through "Document 1," the number of passed nodes is 1 and the degree of importance is 1. Therefore, their relatedness is calculated by the relatedness calculation unit 205 as 1×1=1.

[0107] Returning to Fig. 17, the display data generation unit 206 then acquires the display data for the first related information stored in the display data storage unit 207 (step S24). The display data generation unit 206 then sets the width of the keyword nodes, the width of the first related information node, and the width of the bands connecting the keywords and the first related information as display data for the keywords of the input queries that have already been displayed to the user and the first related information.

[0108] In the Fig. In the example shown in Figure 18, the width of the nodes "Keyword X" and "Keyword Y" or the feature words is "50" each, the width of the node "Person A" or the first associated information is "65", and the width of the node "Person B" is "35". The width of the band connecting "Keyword X" and "Person A" is "35", the width of the band connecting "Keyword Y" and "Person A" is "30", the width of the band connecting "Keyword X" and "Person B" is "15", and the width of the band connecting "Keyword Y" and "Person B" is "20".

[0109] Next, the display data generation unit 206 uses the calculated relatedness degrees to calculate the bandwidths and node widths required to construct a Sankey diagram and generates new display data (step S25). For example, the display data generation unit 206 calculates the widths of bands representing the relationship between the first related information and the second related information based on the second related information derived by the related information inference unit 204 and the relationship calculated by the relatedness calculation unit 205, and generates new display data.Here, the display data generation unit 206 normalizes the width of the bands connecting the first related information and the second related information based on the width of the node of the first related information of the input side, and determines the width of the node of the second related information as the sum of the bandwidths.

[0110] Fig. Figure 19 is a schematic representation of an example screen with an IM6 Sankey diagram drawn with new display data.

[0111] In the Fig. In the example shown in Figure 19, the widths of the bands connecting the first associated information and the second associated information and the width of the second associated information node are determined as follows.

[0112] The width of the node "Person A" is "65," and the products related to "Person A" are "Product 1" with a relatedness degree of 2, "Product 2" with a relatedness degree of 2, and "Product 3" with a relatedness degree of 1. The display data generation unit 206 calculates (node ​​width of the input page) × (relatedness degree) / (total relatedness degree) to normalize the bandwidth according to the relatedness of the related products. Therefore, the width of the band between "Person A" and "Product 1" is 65 × 2 / (2 + 2 + 1) = 26. Similarly, the width of the band connecting “Person A” and “Product 2” is 65×2 / (2+2+1)=26, and the width of the band connecting “Person A” and “Product 1” is 65×1 / (2+2+1)=13.

[0113] The width of the band connecting Person B and Product 1 is 35×1 / (1+1)=17.5, and the width of the band connecting Person B and Product 4 is also 35×1 / (1+1)=17.5.

[0114] Since the width of the "Product 1" node is equal to the sum of the widths of the bands emanating from "Person A" and "Person B," the width of "Product 1" is 26 + 17.5 = 43.5, as can be seen from the above. The widths of the "Product 2" node, the "Product 3" node, and the "Product 4" node are 26, 13, and 17.5, respectively.

[0115] Referring back to Fig. Finally, in Figure 17, the user interface unit 203 draws a Sankey diagram based on the new display data (step S26). For example, the user interface 203 draws a Sankey diagram based on the received display data and presents it to the user.

[0116] As described above, according to the second embodiment, by further displaying information related to the related information by using the retrieved results as input, more related information can be retrieved without restarting the search, and the relationship between the pieces of related information can be displayed, so that related information desired by a user can be found more efficiently.

[0117] Since the width of a node of the first information that is closely related to the input queries is increased and the width is used to represent the width of other related information, the degree of relatedness to the input queries can be easily read from the bandwidth.

[0118] The second embodiment describes a method for displaying second related information using first related information. Similarly, third related information can be displayed using second related information as input queries, and furthermore, fourth related information can be displayed using third related information as input queries. In other words, related information can be retrieved sequentially using the search results of related information. THIRD EXAMPLE

[0119] In the first embodiment, the user inputs keywords. However, in the third embodiment, the keywords are automatically extracted from the input text or document, and the keywords and feature words can be displayed as related information.

[0120] Fig. 20 is a block diagram schematically showing a configuration of a related information display device 300 according to the third embodiment.

[0121] The related information display device 300 includes a knowledge graph DB 101, a DB operation unit 102, a user interface unit 303, a related information inference unit 304, a relationship calculation unit 105, a display data generation unit 106, and an important word extraction unit 308.

[0122] The knowledge graph DB 101, the DB operation unit 102, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 300 according to the third embodiment are respectively the same as the knowledge graph DB 101, the DB operation unit 102, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 100 according to the first embodiment.

[0123] Similar to the first embodiment, the user interface unit 303 accepts the user's input of keywords and the information type of the keywords. Since the operation of the related information display device 300 in this case is the same as that of the related information display device 300 according to the first embodiment, explanations will be omitted below.

[0124] The user interface 303 according to the third embodiment can also accept user input in the form of text or a document and the information type of the information to be retrieved, instead of keywords and the information type. In this way, the user interface 303 captures the text and the information type. The user interface 303 then passes the captured text to the related information inference unit 304. The user input can be in any format, e.g., text data or document files capable of capturing text. For example, an input field can accept input of a character string or a file name of a document file to accept text from a user.If a file name of a document file is accepted, the user interface unit 303 may extract text data from the document file with that file name as text and pass the text to the inference unit 304 for related information.

[0125] Similar to the first embodiment, the user interface unit 303 receives display data from the display data generation unit 106 and displays the relationships between input queries and related information to the user using a flowchart based on the display data.

[0126] Similar to the second embodiment, the user interface unit 303 may accept input of the type of information to be further retrieved on a screen displaying the corresponding information and provide information about the corresponding information.

[0127] The related information inference unit 304 forwards the text received from the user interface 303 to the important word extraction unit 308. The related information inference unit 304 then receives the extracted important words from the important word extraction unit 308.

[0128] The related information inference unit 304 uses the received important words as keywords, determines the information type "feature word," determines an inference method based on the information type of the information to be retrieved input by the user, and derives related information. Here, the related information inference unit 304 infers information related to the keywords and belonging to the information type of the information to be retrieved as related information.

[0129] The related information inference unit 304 then passes the derived related information to the kinship calculation unit 105.

[0130] The important word extraction unit 308 extracts important words from the text received from the related information inference unit 304. The extracted important words are forwarded to the related information inference unit 304. The important words can be extracted using known techniques. The important word extraction unit 308 morphologically analyzes the text and extracts important words from the text using frequency of occurrence-reverse document frequency (TF-IDF). In addition, pre-registered words or nouns can be extracted as important words. Since the important words extracted here are treated as keywords, the important word extraction unit 308 functions as a unit for extracting keywords from the text.

[0131] The processing by the relationship calculation unit 105 and the display data generation unit 106 is the same as in the first embodiment. However, the display data generation unit 106 may change the widths of keywords that are important words in accordance with the degree of importance (e.g., the degree of importance calculated by TF-IDF) in the important word extraction by the important word extraction unit 308. Alternatively, the user may also specify the width of the bands of the input keywords.

[0132] The above-described related information display device 300 may also be implemented by the computer 120, as shown in Fig. 11. The important word extraction unit 308 can be implemented, for example, by the processor 125 loading a program stored in the auxiliary storage device 123 into the memory 124 and executing the program.

[0133] Fig. 21 is a flowchart illustrating the operation of the related information display device 300 according to the third embodiment.

[0134] In the Fig. The flowchart shown in Figure 21 shows the steps of the same processing as in the flowchart shown in Fig. 12 shown flowchart of the first embodiment with the same reference numerals as in Fig. 12 marked.

[0135] First, the user interface unit 203 acquires the text and information type of the information to be retrieved from a user (step S30). The user interface unit 203 accepts, for example, the input of a character string or a file name of a document file into an input field. If the user input is the file name of a document file, the user interface unit 203 extracts the text from the document file. Specifically, the user interface unit 203 accesses the document file and extracts text from the document file. The text is passed to the important word extraction unit 308 via the related information inference unit 304.

[0136] Next, the important word extraction unit 308 extracts important words from the text of the related information inference unit 304 (step S31). For example, the important word extraction unit 308 processes the text, extracts important words, and passes them to the related information inference unit 304 as input keywords used as related information.

[0137] The processing of steps S11 to S15 in Fig. 21 is the same as the processing of steps S11 to S15 in Fig. 12.

[0138] However, the related information inference unit 304 derives related information by using the important words from the important word extraction unit 308 as keywords having the information type “feature word”.

[0139] As described above, the third embodiment enables searching for related information from the text, so that a user can obtain related information without considering keywords and thus the information desired by the user can be easily found.

[0140] Since the automatically extracted important words are displayed and the user can make corrections such as deleting words, it is possible to perform a search using only the keywords most important to the user, and the results desired by the user are displayed.

[0141] Here, important words automatically extracted from the text are displayed as input nodes. Document files can also be displayed as input nodes, and related information extracted from important words can be displayed as information about the files in the form of a Sankey diagram. This allows for the input of multiple document files to retrieve information about the files without requiring the user to enter important keywords. FOURTH EXAMPLE

[0142] In the first or third embodiment described above, related information is retrieved using a data structure on a knowledge graph. The fourth embodiment describes a case where a database other than the knowledge graph DB 101 is used together with the knowledge graph DB 101 to retrieve related information.

[0143] Fig. 22 is a block diagram schematically showing a configuration of a related information display device 400 according to the fourth embodiment.

[0144] The related information display device 400 includes a knowledge graph DB 101, a DB operation unit 402, a user interface unit 303, a related information inference unit 404, a relationship calculation unit 105, a display data generation unit 106, and a full-text search DB 409.

[0145] The knowledge graph DB 101, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 400 according to the fourth embodiment are respectively the same as the knowledge graph DB 101, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 100 according to the first embodiment.

[0146] The user interface unit 303 of the related information display device 400 according to the fourth embodiment is the same as the user interface unit 303 of the related information display device 300 according to the third embodiment. Thus, the user interface 303 according to the fourth embodiment accepts the input of keywords and their information types, or of sentences or text and information types of the information to be retrieved. In other words, the user interface unit 303 functions as an interface unit for acquiring keywords or text.

[0147] The related information inference unit 404 receives keywords or text and their information type from the user interface unit 303 and, depending on the keywords or text, selects an inference method that also uses full text. In other words, the related information inference unit 404 searches the full-text search database 409 for documents related to the keywords or text and derives related information about the retrieved documents using a knowledge graph structure.

[0148] For example, the related information inference unit 404 causes the DB operation unit 402 to perform a full-text search using input keywords or text as queries and obtains document information indicating related documents in order of relationship from the DB operation unit 402. The related information inference unit 404 then causes the DB operation unit 402 to retrieve related information by inputting the documents in the document information representing the search results into the knowledge graphs DB 101.

[0149] If the input keywords are "knowledge graph" and "summary" and the information type of the information to be retrieved is "person," the related information inference unit 404 causes the DB operation unit 402 to search the full-text search DB 409 for documents related to the words "knowledge graph" and "summary." As a result of the search, "Document 1," "Document 2," and "Document 3" for the word "knowledge graph," and "Document 2," "Document 4," and "Document 5" for the word "summary" are found as documents with high relatedness. The related information inference unit 404 may determine documents with high relatedness based on a threshold or specify a predetermined number of documents in descending order of relatedness.

[0150] Next, the related information inference unit 404 causes the DB operation unit 402 to input "Document 1," "Document 2," and "Document 3" into the knowledge graphs DB 101 and search the knowledge graphs DB 101 for people related to these documents (e.g., information about the authors of the documents). The information type of "Document 1," "Document 2," and "Document 3" is "Document." Here, it is assumed that "Person A" and "Person B" are retrieved. Similarly, the related information inference unit 404 causes the DB operation unit 402 to input "Document 2," "Document 4," and "Document 5" into the knowledge graphs DB 101 and search the knowledge graphs DB 101 for people related to these documents. Here, it is assumed that "Person A," "Person B," and "Person C" are retrieved.In this case, the DB operation unit 402 returns “Person A” and “Person B” as search results to the related information inference unit 404 as persons related to the “knowledge graph” and the “summary”.

[0151] As described above, the related information inference unit 404 according to the fourth embodiment derives documents related to keywords or text from a plurality of documents including the text specified in the text information stored in the full-text search DB 409, and derives related information related to the related documents from a knowledge graph.

[0152] The full-text search DB 409 is a database that stores text information indicating the text of documents represented by nodes of an information type "document" in the knowledge graph DB 101. In other words, the full-text search DB 409 acts as a storage unit for text information, storing text information that points to the text of multiple documents.

[0153] The DB operation unit 402 receives keywords or text from the related information inference unit 404, performs a full-text search on the text information stored in the full-text search DB 409 using the keywords or text, and retrieves documents in order of relatedness, which indicates the degree of relatedness between the documents and the keywords or text. The DB operation unit 402 then passes document information indicating the retrieved documents to the related information inference unit 404.

[0154] The above-described display device 400 for related information can also be implemented by the computer 120, as in Fig. 11. The full-text search DB 409 can be implemented, for example, by the additional storage device 123.

[0155] As described above, according to the fourth embodiment, it is possible to extract related documents that are not displayed in a knowledge graph by also using the full-text search DB 409 for related information inference. In this way, a larger amount of related information can be presented to the user, and any desired information can be displayed.

[0156] In the third embodiment, when a file name of a document file is input, related information is extracted by extracting important words from the text of the document and performing a search based on the important words, which are keywords. In the fourth embodiment, the text received by the related information inference unit 404 is used as input for a full-text search, and related information is extracted by extracting documents similar to the text. In this way, the user does not have to pay attention to important words, and since documents more similar to the input text can be extracted by inputting the entire text, related information that the user desires can be presented. FIFTH EXAMPLE

[0157] The fifth embodiment describes a case in which the related information of the first to fourth embodiments is provided with further detailed information.

[0158] Fig. 23 is a block diagram schematically showing a configuration of a related information display device 500 according to the fifth embodiment.

[0159] The related information display device 500 includes a knowledge graph DB 501, a DB operation unit 502, a user interface unit 503, a related information inference unit 104, a relationship calculation unit 105, a display data generation unit 106, and a detailed information acquisition unit 510.

[0160] The related information inference unit 104, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 500 according to the fifth embodiment are respectively the same as the related information inference unit 104, the relationship calculation unit 105, and the display data generation unit 106 of the related information display device 100 according to the first embodiment.

[0161] The knowledge graph DB 501 contains knowledge information as in the first embodiment.

[0162] The knowledge graph DB 501 according to the fifth embodiment also stores detailed information about each node constituting a knowledge graph, i.e., knowledge information. Detailed information includes, for example, information about node properties or information about neighboring nodes. When the related information is a "document," its property information includes, for example, information such as the title, creation date, update date, or number of pages; and adjacent node information is information indicating nodes adjacent to nodes corresponding to the related information, such as nodes of people who are authors, reviewers, updaters, etc., nodes of issuing departments, and nodes of related products, projects, solutions, etc.

[0163] In addition to performing similar processing as in the first embodiment, the DB operation unit 502 acquires detailed information related to the related information received from the detailed information acquisition unit 510 from the knowledge graph DB 501 in response to instructions from the detailed information acquisition unit 510 and passes the detailed information to the detailed information acquisition unit 510.

[0164] In addition to the processing similar to that performed by the user interface unit 103 according to the first embodiment, the user interface unit 503 performs the following processing.

[0165] When the user interface unit 503 receives display data from the display data generation unit 106, the user interface unit 503 receives related information and detailed information about the bands included in the display data from the detailed information acquisition unit 510. Similar to the first embodiment, the user interface unit 503 then displays a flowchart based on the display data on a display unit (not shown), and when an instruction is received from a user, causes a display unit (not shown) to display related information or detailed information about the bands on the flowchart.

[0166] The detailed information acquisition unit 510 receives related information from the user interface unit 503 and acquires detailed information from the knowledge graph DB 501 using the DB operation unit 502. In other words, in order to obtain detailed information about the related information received from the user interface unit 503, the detailed information acquisition unit 510 uses the DB operation unit 502 to acquire the detailed information from the knowledge graph DB 501.

[0167] Alternatively, the detailed information acquisition unit 510 may also acquire band information representing the relationship between keywords and related information as detailed information. The band information is information used by the related information inference unit 104 for an inference process for the related information. In other words, when determining the nodes to be forwarded to draw a conclusion using a knowledge graph structure, the band information is the information indicating the node to be forwarded. In addition, the band information may also include information about the properties and neighboring nodes of the forwarded nodes. The band information may also include information about the relatedness of the bands.

[0168] The detailed information acquisition unit 510 passes detailed information such as that described above to the user interface unit 503.

[0169] The user interface unit 503 presents the acquired detailed information to a user. For example, when a Sankey diagram is displayed on a display unit (not shown), detailed information about the related information contained in the Sankey diagram is displayed in a pop-up window when a user clicks on the related information in the Sankey diagram via an input unit (not shown). Fig. 24 is a schematic diagram showing an example of a pop-up displaying detailed information. When the user interface unit 503 displays a Sankey diagram via a browser on a display unit (not shown), detailed information can be displayed on a browser tab. In other words, the user interface unit 503 according to the fifth embodiment acquires an instruction to acquire detailed information about related information or bands and causes the detailed information acquisition unit 510 to acquire corresponding detailed information in response to the instruction.

[0170] When a user clicks on a band included in a Sankey diagram displayed on a display unit (not shown) via an input unit (not shown), the user interface unit 503 may display a list of detailed information about relayed nodes in a pop-up window based on the band information and may also display detailed information about relayed nodes. Fig. 25 is a schematic diagram showing an example in which band information is displayed as detailed information.

[0171] The above-described display device 500 for related information can also be implemented by the computer 120, as in Fig.11. The detailed information acquisition unit 510 can be implemented, for example, by the processor 125 loading a program stored in the auxiliary storage device 123 into the memory 124 and executing the program.

[0172] As described above, according to the fifth embodiment, a user can easily determine which of the related information is desired by obtaining detailed information about the related information.

[0173] Note that user interface unit 503 may include a filter unit (not shown) that uses detailed information to filter the related information to be displayed on a display unit (not shown) and extract only a portion of the related information related to specific display data. The filter unit uses detailed information to filter related information.

[0174] The filter unit extracts only a portion of the display data that meets the conditions specified by a user via an input unit (not shown), and the user interface unit 503 updates the display data using only the extracted portion. In other words, the user interface unit 503 presents the user with information about properties or information about neighboring nodes obtained with detailed information as filter information. By allowing the user to select conditions for the filter unit, only related information that meets specific conditions can be displayed. At this time, the filter unit can perform filtering with band information. For example,only results are displayed that have a specific value in the property, only bands that contain a specific property in the detailed information, or only related information whose relatedness is higher than the specific value.

[0175] By only displaying related information that meets the conditions specified by the user, the user is prevented from seeing unnecessary information when searching for related information and can only retrieve the necessary information. DESCRIPTION OF REFERENCE SYMBOLS

[0176] 100, 200, 300, 400, 500 related information display device; 101, 501 knowledge graph DB; 102, 402, 502 DB operation unit; 103, 203, 303, 503 user interface unit; 104, 204, 304, 404 related information inference unit; 105, 205 relationship calculation unit; 106, 206 display data generation unit; 207 display data storage unit; 308 important word extraction unit; 409 full-text search DB; 510 detailed information acquisition unit. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] JP 2020-140604

[0003]

Claims

[1] A display device for related information comprising: a knowledge graph storage unit configured to store a knowledge graph including knowledge information having a plurality of nodes and links connecting the nodes; a related information inference unit configured to derive related information to a keyword from the knowledge graph; a relationship calculation unit configured to calculate a relationship between the keyword and the related information; and a display data generation unit configured to generate display data for displaying a flowchart indicating a relationship between the keyword and the information related to the keyword by connecting the keyword and the related information with a band, The width of the band increases with increasing relatedness. [2] The related information display device according to claim 1, wherein the flowchart is a Sankey diagram. [3] The related information display device according to claim 2, wherein the width of the band in the Sankey diagram is normalized based on a width at which the keyword is displayed. [4] A related information display device according to any one of claims 1 to 3, further comprising: an interface unit configured to capture the keyword and an information type, where the related information inference unit infers information related to the keyword and belonging to the information type as the related information. [5] A related information display device according to any one of claims 1 to 3, further comprising: an interface unit configured to obtain text and an information type; and a keyword extraction unit configured to extract the keyword from the text, where the related information inference unit infers information related to the keyword and belonging to the information type as the related information. [6] A related information display device according to claim 4 or 5, wherein the interface unit obtains a new information type after the display data has been generated, the related information inference unit uses the related information as a new keyword and derives information related to the new keyword and belonging to the new information type as new related information, the relationship calculation unit calculates the new relationship between the new keyword and the new related information, the display data generation unit connects the new keyword and the new information related to the new keyword with a band to generate new display data for displaying a new flow rate diagram indicating a relationship between the new keyword and the new related information, and the width of the band between the new keyword and the new related information increases as the new relatedness increases. [7] A related information display device according to any one of claims 1 to 3, further comprising: a text information storage unit configured to store text information indicating the text of each of a plurality of documents; and an interface unit configured to obtain the keyword or text, wherein the related information inference unit derives a document related to the keyword or the text from the plurality of documents, and derives the related information related to the related document from the knowledge graph. [8] A related information display device according to any one of claims 4 to 7, wherein the interface unit acquires an instruction to obtain detailed information regarding the related information or the tape, and the related information display device further comprises a detailed information acquisition unit configured to acquire detailed information relating to the related information or the tape in response to the instruction. [9] A related information display device according to claim 8, further comprising: a filter unit configured to filter the related information with the detailed information. [10] Program that causes a computer to act as: a knowledge graph storage unit configured to store a knowledge graph including knowledge information having a plurality of nodes and links connecting the nodes; a related information inference unit configured to derive related information to a keyword from the knowledge graph; a relationship calculation unit configured to calculate a relationship between the keyword and the related information; and a display data generation unit configured to generate display data for displaying a flowchart indicating a relationship between the keyword and the information related to the keyword by connecting the keyword and the related information with a band, The width of the band increases with increasing relatedness. [11] A method for displaying related information, comprising: Deriving related information related to a keyword from a knowledge graph containing knowledge information having a plurality of nodes and links connecting the nodes; Calculating the relationship between the keyword and the related information; and Generating display data for displaying a flow rate diagram indicating a relationship between the keyword and the information related to the keyword by connecting the keyword and the related information with a band, The width of the band increases with increasing relatedness.

Images