Information Display System

Abstract

To provide an information display system that quantitatively displays the degree of relevance of a keyword in a bird's eye view with respect to two different kinds of viewpoints.SOLUTION: An information display system sets two first and second viewpoints different from each other, and first and second keyword groups including a plurality of keywords respectively corresponding to the first and second viewpoints, calculates a plurality of links for coupling respective nodes using respective keywords included in the first viewpoint, the second viewpoint, and the first and second keyword groups as respective different nodes, calculates an index value obtained by quantifying the strength of coupling links for each link, obtains the sum total of index values of links from the first viewpoint through the keywords included in the first and second keyword groups to reach the second viewpoint, for each keyword included in the second keyword group, and displays the degree of relevance between the first viewpoint and each keyword included in the second keyword group on the basis of the sum total of index values for each keyword included in the second keyword group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information display system. [Background technology]

[0002] Text mining, which uses natural language processing technology to analyze data consisting of unstructured sentences, is gaining attention. Text mining has the function of analyzing the frequency of appearance, appearance trends, and co-occurrence relationships of keywords (feature words) present in sentences in response to search criteria entered by the user, and displaying the keywords and their relationships as a word graph. The word graph displays frequently occurring keywords as nodes, with links connecting the nodes based on co-occurrence relationships, and the thickness of the link lines changes depending on the co-occurrence strength between keywords (the strength of the link connection).

[0003] Patent Document 1 discloses a technology for more accurately outputting feature words and their feature degrees in text mining. In Patent Document 1, when performing linguistic analysis of input text data to be mined and counting each feature word in the input text, the counting results are corrected using statistical information indicating the properties of the input text and / or the reliability assigned to the input text. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-039983 Summary of the Invention [Problem to be solved by the invention]

[0005] It is conceivable to apply such conventional technology to display the connections between keywords corresponding to two different perspectives (for example, "issues" and their "measures") in a word graph. However, while conventional word graphs can visualize the strength of co-occurrence between keywords, they cannot quantitatively and comprehensively display the degree of association of keywords from one perspective to the other.

[0006] The present invention has been made in consideration of such problems, and an object of the present invention is to provide an information display system that quantitatively and comprehensively displays the relevance of keywords from two different perspectives. [Means for solving the problem]

[0007] An information display system according to one aspect of the present invention includes: a link calculation unit that sets a first perspective, a first keyword group including a plurality of keywords corresponding to the first perspective, a second perspective different from the first perspective, and a second keyword group including a plurality of keywords corresponding to the second perspective, and calculates a plurality of links connecting the first perspective, the keywords included in the first keyword group and the second keyword group, and the second perspective as different nodes; a quantification processing unit that calculates an index value that quantifies the strength of the connection of the links for each link, and calculates the sum of the index values ​​of the links from the first perspective through the keywords included in the first keyword group and the second keyword group to the second perspective for each keyword included in the second keyword group; and a display unit that displays the degree of relevance between the first perspective and each keyword included in the second keyword group based on the sum of the index values ​​for each keyword included in the second keyword group. [Effects of the Invention]

[0008] According to the present invention, it is possible to provide an information display system that quantitatively and comprehensively displays the relevance of keywords from two different perspectives. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing a configuration of an information display system according to an embodiment. [Figure 2] FIG. 1 is a flow chart showing an information display method according to an embodiment. [Figure 3] FIG. 10 is a diagram showing an example of a word graph generated in the information display system according to the embodiment. [Figure 4] FIG. 10 is a diagram for explaining a correlation quantification process used in the embodiment. [Figure 5] FIG. 10 is a diagram showing an example of a heat map generated in the information display system according to the embodiment. [Figure 6] FIG. 10 is a diagram showing an example of a heat map generated in the information display system according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In each drawing, the same components are designated by the same reference numerals, and redundant explanations will be omitted.

[0011] An information display system according to an embodiment includes: a link calculation unit that calculates a plurality of links connecting a first perspective, a first keyword group including a plurality of keywords corresponding to the first perspective, a second perspective different from the first perspective, and a second keyword group including a plurality of keywords corresponding to the second perspective, with the first perspective, each keyword included in the first keyword group and the second keyword group, and the second perspective being treated as different nodes; a quantification processing unit that calculates an index value that quantifies the strength of the connection of the link for each link and calculates, for each keyword included in the second keyword group, a sum of the index values ​​of the links from the first perspective through the keywords included in the first keyword group and the second keyword group to the second perspective; and a display unit that displays the magnitude of the relevance between the first perspective and each keyword included in the second keyword group based on the sum of the index values ​​for each keyword included in the second keyword group. This makes it possible to quantitatively and comprehensively display the relevance of keywords for two different perspectives.

[0012] A specific configuration of an information display system according to an embodiment will be described below with reference to the drawings. FIG. 1 is a block diagram showing the configuration of an information display system 10 according to an embodiment. As shown in FIG. 1, the information display system 10 includes a search term input unit 11, a database 12, a word graph display unit 13, a relation quantification processing unit 14, and a heat map display unit 15. Here, an "issue (first perspective)" and a "countermeasure (second perspective)" are taken as examples of two different perspectives. Specifically, "slipperiness" is taken as an example of the "issue," and "friction" is taken as an example of the "countermeasure."

[0013] The search term input unit 11 is a device that accepts input of search terms from the outside. The search term input unit 11 includes, for example, an operating device such as a keyboard or a mouse that allows the user to perform various operations. A touch panel can also be used as the operating device. In this case, the user can perform various operations by touching the screen with a finger or a stylus. The user can input two different perspectives from which the user wishes to search using the search term input unit 11. For example, two search boxes are provided, and the user can input "slippage" as the first perspective into one search box and "friction" as the second perspective into the other search box.

[0014] The database 12 stores a plurality of different perspectives and a plurality of keyword groups corresponding to each perspective, in association with each other. The word graph display unit 13 reads out a first keyword group and a second keyword group corresponding to the input first perspective and second perspective, respectively, from the database 12. The word graph display unit 13 then calculates links connecting the nodes, treating the keywords included in the first perspective, the first keyword group, and the second keyword group, and the second perspective, as different nodes, and displays a word graph. In other words, the word graph display unit 13 corresponds to the "link calculation unit" recited in the claims.

[0015] FIG. 3 is a diagram showing an example of a word graph generated in the information display system 10 according to the embodiment. As shown in FIG. 3, in the embodiment, each viewpoint is represented by a pentagon, and each keyword is represented by a circle. Furthermore, links are represented by lines connecting the pentagons and circles. The thickness of the link lines is changed depending on the co-occurrence strength between nodes (the strength of the link connection). This visualizes the connections between keywords, allowing a bird's-eye view of the relevance between keywords. In other words, by referring to the word graph, it is possible to understand which items are included in the "measures" for the "issues."

[0016] However, it is difficult to quantitatively grasp the relevance of keywords from two different perspectives using a word graph. In this embodiment, the following configuration is provided to visualize the magnitude of the relevance between the first perspective and each keyword included in the second keyword group. Specifically, a heat map is displayed showing the relevance of each item (second keyword group) of "Problem: Slippage" to "Countermeasure: Friction."

[0017] The relation quantification processor 14 calculates an index value that quantifies the co-occurrence strength (strength of connection) of each link for each link. Then, for each keyword included in the second keyword group, the relation quantification processor 14 calculates the sum of the index values ​​of the links that lead from the first perspective to the second perspective via the keywords included in the first keyword group and the second keyword group. In other words, the relation quantification processor 14 corresponds to the "quantification processor" recited in the claims.

[0018] Here, the first group of keywords corresponding to "slip" are "FTZ," "tribology," "dynamic friction coefficient," "friction coefficient," and "sliding speed." The second group of keywords corresponding to "friction" are "thrust force," "low friction," "lubrication," "contact," and "friction loss."

[0019] 4 is a diagram for explaining the association quantification process used in the embodiment. As shown in FIG. 4, the strength of the link between “problem: slipping” and each keyword in the first keyword group is x i (i=1~5). The strength of the link between each keyword in the first keyword group and the second keyword group is expressed as y ji (i=1~5, j=1~5). The strength of the link between each keyword in the second keyword group and "Countermeasure: Friction" is z j (j=1 to 5). Note that there may be no link between the keywords in the first keyword group and the second keyword group. For example, there is no link between "friction coefficient" in the first keyword group and "lubrication" in the second keyword group.

[0020] The relation quantification processing unit 14 calculates the sum of index values ​​of links from the first perspective to the second perspective via keywords included in the first keyword group and the second keyword group, Σx i y ji z j As shown in FIG. 4, in this embodiment, for each keyword included in the second keyword group, Σx i y 1i z1, Σx i y 2i z2, Σx i y 3i z3, Σx i y 4i z4, Σx i y 5i Find z5 respectively. For example, Σx i y 1i z1=x3y 13 z1+x4y 14 z1.

[0021] The heat map display unit 15 creates a heat map that displays the magnitude of the relevance between the first perspective and each keyword included in the second keyword group based on the sum of the index values ​​for each keyword included in the second keyword group obtained by the relevance quantification processing unit 14. This heat map can quantitatively represent, for example, the frequency of occurrence of each keyword in the "measure" for the "issue" in the word graph. In other words, the heat map can display a list of the effectiveness of solutions to problems.

[0022] Fig. 5 is a diagram showing an example of a heat map generated in an information display system according to an embodiment. In Fig. 5, four different "problems" - "slippage," "cracking," "cracking," and "cutting" - are shown in the rows, and five keywords - "countermeasure: friction" - are shown in the columns.

[0023] The heat map display unit 15 can create a heat map by changing the color or the intensity of the color according to the strength of the relevance of each keyword of "countermeasure: friction" to "problem: slippage" - "thrust force," "low friction," "lubrication," "contact," and "friction loss." For example, by displaying a heat map with red representing areas with high relevance and blue representing areas with low relevance, it is possible to display the effectiveness of countermeasures for the problem. By referring to this heat map, it is possible to grasp at a glance which of the "countermeasures" is more effective for the "problem," and more effective countermeasures can be implemented.

[0024] Similarly, by calculating the strength of association between each keyword "Countermeasure: Friction" for different "problems" such as "cracks," "cracking," and "cuts," it is possible to quantitatively and comprehensively display the degree of association between keywords for each "problem" and "countermeasure." This makes it easy to understand which "countermeasure" is more effective for various "problems."

[0025] Fig. 2 is a flow diagram showing an information display method according to an embodiment. As shown in Fig. 2, first, two different perspectives ("slippage" and "friction") are input as search terms (step S11). Then, by referring to the database 12, a first keyword group and a second keyword group corresponding to the input "slippage" and "friction", respectively, are read out, and a word graph is displayed (step S12). As described above, the word graph displays the first perspective, each keyword included in the first keyword group and the second keyword group, and the second perspective as different nodes, and displays links connecting each node.

[0026] Then, an index value that quantifies the co-occurrence strength (strength of connection) of each link is calculated from the word graph, and a quantification process is performed to calculate the sum of the index values ​​of the links that lead from the first perspective through the keywords included in the first keyword group and the second keyword group to the second perspective for each keyword included in the second keyword group (step S13).

[0027] Then, a heat map showing the degree of relevance between the first perspective and each keyword included in the second keyword group is displayed based on the sum of the index values ​​of each link obtained by the quantification process (step S14). By utilizing this heat map (step S15), it becomes possible to implement more effective "measures" for the "issues."

[0028] As described above, according to the embodiment, an index value that quantifies the strength of the connections between nodes on a word graph is calculated, and then mathematical processing is performed to find the sum of the index values ​​for each item of "measures," thereby creating a heat map that visualizes the effectiveness of each item included in the "measures."

[0029] In addition to "slippage," other examples of "issues (first viewpoint)" include "tear," "peeling," "leakage," "cut," "torn," "breakage," and "warping." FIG. 6 is a diagram showing another example of a heat map generated in the information display system according to the embodiment. In FIG. 6, a plurality of different "issues" are shown in the row direction, and five keywords, including "countermeasure: friction," are shown in the column direction. In FIG. 6, the degree of association between each viewpoint and the keyword is visualized by darkening the color of areas with large sums of index values.

[0030] The present invention is not limited to the above-described embodiments, and can be modified as appropriate without departing from the spirit of the invention. The system can also enjoy the effects of the present invention by downloading and reading a program for achieving the present invention from a server, database, or the like on a network. All configurations that combine the above-described embodiments with modified examples are included in the present invention. [Explanation of symbols]

[0031] 10 Information Display System 11 Search term input section 12 Databases 13 Word graph display section 14 Related Quantification Processing Section 15 Heat map display

Claims

[Claim 1] a link calculation unit that sets a first viewpoint, a first keyword group including a plurality of keywords corresponding to the first viewpoint, a second viewpoint different from the first viewpoint, and a second keyword group including a plurality of keywords corresponding to the second viewpoint, and calculates a plurality of links connecting the first viewpoint, the keywords included in the first keyword group and the second keyword group, and the second viewpoint as different nodes; a quantification processing unit that calculates an index value xi that quantifies the strength of connection of each link between the first perspective and each keyword of the first keyword group, an index value yji that quantifies the strength of connection of each link between each keyword of the first keyword group and the second keyword group, and an index value zj that quantifies the strength of connection of each keyword of the second keyword group and the second perspective, and calculates, for each keyword included in the second keyword group, the sum of the index values ​​of each link from the first perspective to the second perspective via the keywords included in the first keyword group and the second keyword group using the formula Σxiyjizj; a display unit that displays the degree of relevance between the first perspective and each keyword included in the second keyword group based on the sum of the index values ​​for each keyword included in the second keyword group; An information display system comprising:

Images