Information processing device, assistance method, and assistance program

Abstract

In order to make it possible to smoothly perform analysis using a causal graph, an information processing device (1) comprises: a determination unit (11) that, after a causal graph in which the result of causal analysis is represented by nodes corresponding to elements and an edge indicating a causal relationship between the elements has been displayed, determines an arrangement rule when the nodes in the causal graph are rearranged; and a display control unit (12) that displays a causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule. According to the information processing device (1), it is possible to assist a user in decision making by making it possible to smoothly perform analysis using the causal graph.

Description

Information processing device, support method, and support program

[0001] The present invention relates to an information processing device that supports causal analysis.

[0002] Recently, a technique called causal analysis for inferring causal relationships between data has been attracting attention, and accordingly, development of techniques for supporting causal analysis has also been progressing. For example, Patent Document 1 listed below discloses a data analysis device that receives input of variables indicating each phenomenon to be analyzed and input of causal directions between the variables, generates a causal relationship diagram indicating the causal relationships between the variables, and sets a variable designated as a target variable in the causal relationship diagram and a variable that is on the causal side of the target variable in the causal relationship diagram in an analysis tool that analyzes variables that affect the target variable.

[0003] Japanese Patent Application Publication No. 2020-86614

[0004] In the data analysis device described in Patent Document 1, blocks with variable names are displayed on a causal relationship diagram generation screen, and a causal relationship diagram showing the causal relationships between each variable is generated by accepting input of arrows connecting each block. In this way, when a causal relationship diagram is generated by an operator's operation, the generated causal relationship diagram is unlikely to be complicated and difficult to understand.

[0005] On the other hand, in causal analysis, there are cases where the causal relationships between elements are automatically inferred using a method such as causal discovery, which infers what kind of causal relationships (or lack thereof) exist between multiple elements from each element. In such cases, when a causal graph showing the causal relationships between each element is automatically generated, the edges connecting the elements may intersect irregularly, making it difficult to smoothly recognize the relationships between the elements.

[0006] As described above, conventionally, when a causal graph is automatically generated, there has been a problem that the generated causal graph makes it difficult to smoothly perform causal analysis. One aspect of the present invention has been made in consideration of such a problem, and one example of a purpose of the present invention is to provide a technology that enables smooth analysis using a causal graph.

[0007] An information processing device according to one aspect of the present invention displays a causal graph representing the results of a causal analysis performed on a plurality of elements, with nodes corresponding to each element and edges indicating the causal relationships between each element, and then includes a determination means for determining an arrangement rule for rearranging the nodes in the causal graph, and a display control means for displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0008] A support method according to one aspect of the present invention is a method for supporting causal analysis, which includes at least one processor displaying a causal graph representing the results of causal analysis performed on a plurality of elements, with nodes corresponding to each element and edges indicating causal relationships between each element, determining an arrangement rule for rearranging the nodes in the causal graph, and displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0009] An assistance program according to one aspect of the present invention is a support program for causal analysis that causes a computer to function as a determination means for determining placement rules for rearranging the nodes in the causal graph, and a display control means for displaying the causal graph in which the nodes have been rearranged in accordance with the determined placement rules, after displaying a causal graph in which the results of a causal analysis performed on a plurality of elements are represented by nodes corresponding to each element and edges indicating the causal relationships between each element.

[0010] According to one aspect of the present invention, analysis using a causal graph can be smoothly performed.

[0011] FIG. 1 is a block diagram showing the configuration of an information processing device according to a first exemplary embodiment of the present invention. FIG. 2 is a flow diagram showing the flow of a support method according to the first exemplary embodiment of the present invention. FIG. 3 is a diagram showing an example in which, after a causal graph is displayed, nodes in the causal graph are rearranged by a support method according to a second exemplary embodiment of the present invention. FIG. 4 is a block diagram showing the configuration of an information processing device according to a second exemplary embodiment of the present invention. FIG. 5 is a diagram showing an example of an arrangement rule and a method for determining the arrangement rule. FIG. 6 is a diagram showing an example in which nodes are rearranged after changing a threshold value for path coefficients. FIG. 7 is a diagram showing an example in which elements to be rearranged are extracted based on a specification by an operator and nodes are rearranged. FIG. 8 is a flow diagram showing the flow of a support method according to the second exemplary embodiment of the present invention. FIG. 9 is a diagram showing an example of a computer that executes instructions of a program that is software that realizes the functions of each device according to each exemplary embodiment of the present invention.

[0012] [First Exemplary Embodiment] A first exemplary embodiment of the present invention will be described in detail with reference to the drawings. This exemplary embodiment is a basic form of the exemplary embodiments described below.

[0013] (Configuration of Information Processing Device) The configuration of an information processing device 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. As shown in the figure, the information processing device 1 includes a determination unit 11 and a display control unit 12.

[0014] The determination unit 11 displays a causal graph representing the results of a causal analysis performed on multiple elements, with nodes corresponding to each element and edges indicating the causal relationships between each element, and then determines placement rules for rearranging nodes in the causal graph.

[0015] The display control unit 12 displays a causal graph in which the nodes have been rearranged in accordance with the arrangement rule determined by the determination unit 11. Note that rearrangement refers to an operation of optimizing the display of the causal graph based on the arrangement rule. Rearrangement can also be referred to as rearrangement, reconstruction, reconfiguration, reorganization, readjustment, reorganization, screen optimization, rearrangement, or restructuring.

[0016] As described above, the information processing device 1 according to this exemplary embodiment displays a causal graph representing the results of a causal analysis performed on a plurality of elements, using nodes corresponding to the elements and edges indicating the causal relationships between the elements, and then includes the determination unit 11 that determines an arrangement rule for rearranging the nodes in the causal graph, and the display control unit 12 that displays the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule. Therefore, the information processing device 1 according to this exemplary embodiment has the effect of enabling analysis using a causal graph to be performed smoothly.

[0017] (Assistance Program) The functions of the information processing device 1 described above can also be realized by a program. The assistance program according to this exemplary embodiment is an assistance program for causal analysis, and is configured to cause a computer to function as: a determining unit that determines an arrangement rule for rearranging nodes in the causal graph, after displaying the results of a causal analysis performed on a plurality of elements, the causal graph being represented by nodes corresponding to the elements and edges indicating the causal relationships between the elements; and a display control unit that displays the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule. Therefore, the assistance program according to this exemplary embodiment has the effect of enabling smooth analysis using a causal graph.

[0018] (Flow of the Support Method) The flow of the support method according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the support method. Note that the execution entity of each step in this support method may be a processor provided in the information processing device 1, or a processor provided in another device, or each step may be executed by a processor provided in a different device.

[0019] In S11, at least one processor displays a causal graph representing the results of a causal analysis performed on multiple elements, with nodes corresponding to each element and edges indicating the causal relationships between each element, and then determines placement rules for rearranging nodes in the causal graph.

[0020] In S12, at least one processor displays a causal graph in which the nodes have been rearranged in accordance with the arrangement rule determined in S11.

[0021] As described above, the support method according to this exemplary embodiment is a method for supporting causal analysis, and includes the steps of: displaying a causal graph in which the results of a causal analysis performed on a plurality of elements are represented by nodes corresponding to the elements and edges indicating the causal relationships between the elements, determining an arrangement rule for rearranging the nodes in the causal graph, and displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule. Therefore, the support method according to this exemplary embodiment has the effect of enabling analysis using a causal graph to be performed smoothly.

[0022] [Exemplary Embodiment 2] (Outline of Support Method) The support method according to this exemplary embodiment (hereinafter referred to as the present method) is a method for supporting causal analysis. As will be described below, the present method enables smooth analysis using a causal graph. An outline of the present method will be described with reference to FIG. 3. FIG. 3 is a diagram showing an example in which nodes in a causal graph are rearranged using the present method after the causal graph is displayed. The causal graph G1 shown in FIG. 3 represents the results of a causal analysis performed on multiple elements, using nodes N1 to N9 corresponding to each element and edges (one-way arrows connecting nodes) indicating the causal relationships between the elements.

[0023] 3, each node is labeled with a name indicating the corresponding element. For example, "Cultural and artistic activities" listed in node N1 indicates the name given to the element of node N1. In this way, when displaying a causal graph, the name given to each element may be displayed in association with the node corresponding to that element.

[0024] The elements that are the subject of causal analysis can be classified into objective variables and explanatory variables that explain the objective variables. In the example of Figure 3, node N3 indicated by a double-line frame is an element that corresponds to the objective variable, and the other nodes are all elements that correspond to explanatory variables. Note that the elements that are the subject of causal analysis may include elements other than explanatory variables and objective variables.

[0025] In the causal graph G1 shown on the left side of Figure 3, the edges connecting the nodes intersect irregularly, making it difficult to smoothly recognize the relationships between the nodes from such a causal graph G1. When a causal graph is automatically generated based on the results of a causal analysis, a graph like this is often generated. This is because the results of the causal analysis do not include data indicating node placement rules that would make it easier to recognize the relationships between the nodes.

[0026] In this regard, according to the present method, after displaying a causal graph, an arrangement rule for rearranging nodes in the causal graph is determined, and a causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule is displayed. This allows the operator to easily recognize the relationships between nodes and smoothly perform analysis using the causal graph.

[0027] Specifically, in the example of Fig. 3, an object A1 and a cursor Cu for executing node rearrangement are displayed together with the causal graph G1. The operator can execute node rearrangement by manipulating the cursor Cu to select the object A1. That is, in the example of Fig. 3, this method is executed when the object A1 is selected by the cursor Cu. Note that the trigger for starting this method is arbitrary and is not limited to the example using the cursor Cu and the object A1.

[0028] The causal graph G1' shown on the right side of Fig. 3 is obtained by rearranging the nodes of the causal graph G1 using this method. More specifically, the causal graph G1' is obtained by rearranging the nodes of the causal graph G1 in accordance with an arrangement rule that arranges a series of nodes connected by edges in order from the node corresponding to the upstream element in the causal relationship to the node corresponding to the downstream element. This arrangement rule corresponds to "arrangement rule A" in Figs. 5 and 6.

[0029] Specifically, in the causal graph G1', node N3 of the objective variable is located at the top. Node N3 is the most downstream node in the causal relationship. Also, in the causal graph G1', nodes N1, N5, and N6, which are connected to node N3 by edges and are located upstream of node N3, are located below node N3. Node N8, which is upstream of nodes N1 and N5, is located below nodes N1 and N5, nodes N2 and N4, which are upstream of node N6, are located below node N6, and nodes N7 and N2, which are upstream of node N9, are located below node N9. As a result, the directions of the edges (in other words, the directions of the arrows) starting from each node are all upward.

[0030] According to the rearranged causal graph G1', the direction of the edges, i.e., the direction of the causal relationships (which element causes which element), is roughly consistent. This allows the operator to easily recognize the relationships between explanatory variables and "satisfaction with the educational environment" at node N3, enabling smooth and accurate analysis. For example, based on the causal graph G1', the operator can hypothesize that, in order to improve "satisfaction with the educational environment," it would be effective to improve public facilities, thereby stimulating cultural and artistic activities and strengthening childcare support.

[0031] In this way, the placement rule for rearranging the nodes may include a rule that a series of nodes connected by edges should be arranged in order from a node corresponding to an upstream element in the causal relationship to a node corresponding to a downstream element. This provides the effect of being able to display a causal graph that clearly shows the causal relationships between elements, in addition to the effect provided by the information processing device 1 according to the first exemplary embodiment. Note that, as will be described in detail later, various placement rules other than those shown in FIG. 3 can be applied.

[0032] (Configuration of Information Processing Device) The configuration of the information processing device 2 according to this exemplary embodiment will be described with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of the information processing device 2. The information processing device 2 is a device that has a function of supporting analysis using a causal graph. Note that the information processing device 2 may be a device whose main function is to support analysis using a causal graph, or may be a general-purpose device that also has other functions.

[0033] As shown in the figure, the information processing device 2 includes a control unit 20 that controls each unit of the information processing device 2, and a storage unit 21 that stores various data used by the information processing device 2. The information processing device 2 also includes a communication unit 22 that enables the information processing device 2 to communicate with other devices, an input unit 23 that accepts various data input to the information processing device 2, and an output unit 24 that enables the information processing device 2 to output various data. As shown in the figure, the control unit 20 of the information processing device 2 includes a data acquisition unit 201, an element extraction unit 202, a determination unit 203, and a display control unit 204. Note that each of the components from the storage unit 21 to the output unit 24 may be built into the information processing device 2 or may be an external device attached to the information processing device 2.

[0034] The data acquisition unit 201 acquires various data used for analysis support using a causal graph. For example, the data acquisition unit 201 acquires analysis result data indicating the results of a causal analysis. The analysis result data may be any data that can be used to display a causal graph, and may be, for example, data indicating each element that was the subject of the causal analysis and the relationship (causal relationship) between those elements.

[0035] The data acquisition unit 201 may acquire analysis result data by performing causal analysis. Causal analysis is a method of inferring the causal relationships (or lack thereof) between multiple elements through causal exploration from each of the elements, and estimating the strength of the inferred causal relationships. A specific causal exploration method known is, for example, a method using a structural equation model. The data acquisition unit 201 may acquire analysis result data generated by applying such a method. The results of the causal analysis may also be obtained by causal analysis using AI (artificial intelligence). By using AI, the causal relationships and their strengths between elements targeted for causal analysis can be automatically estimated to obtain analysis results. The AI ​​used for the causal analysis is not particularly limited, as long as it receives elements targeted for causal analysis and outputs information indicating the causal relationships and their strengths.

[0036] When the data acquisition unit 201 does not perform causal analysis, the data acquisition unit 201 may acquire analysis result data generated by another device. The method of acquiring the analysis result data is not particularly limited. For example, the data acquisition unit 201 may acquire analysis result data input by an operator of the information processing device 2 via the input unit 23, or may acquire analysis result data from another device by communication via the communication unit 22. This also applies to the case of acquiring data other than analysis result data.

[0037] The element extraction unit 202 extracts some of the elements that have been subjected to the causal analysis as elements to be rearranged. When the element extraction unit 202 extracts elements, the nodes corresponding to the extracted elements are rearranged in accordance with the arrangement rules determined by the determination unit 203.

[0038] The determination unit 203 determines an arrangement rule for rearranging nodes in the causal graph. The method for determining the arrangement rule will be described later in the section "Arrangement rule and its determination method."

[0039] The display control unit 204 causes the display device to display various information for supporting analysis using the causal graph. For example, the display control unit 204 causes the display device to display a causal graph generated from the analysis result data acquired by the data acquisition unit 201, or a causal graph in which nodes have been rearranged in accordance with the arrangement rule determined by the determination unit 203. The display device may be included in the information processing device 2, or may be an external device to the information processing device 2.

[0040] As described above, the information processing device 2 according to this exemplary embodiment includes a determination unit 203 that displays a causal graph representing the results of a causal analysis performed on a plurality of elements, with nodes corresponding to the elements and edges indicating the causal relationships between the elements, and then determines an arrangement rule for rearranging the nodes in the causal graph, and a display control unit 204 that displays the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule. Therefore, the information processing device 2 according to this exemplary embodiment has the effect of enabling analysis using a causal graph to be performed smoothly.

[0041] As described above, the information processing device 2 according to this exemplary embodiment includes the element extraction unit 202 that extracts some of the elements that have been subjected to causal analysis as elements to be rearranged, and the display control unit 204 displays a causal graph in which nodes corresponding to the elements extracted by the element extraction unit 202 are arranged according to the arrangement rule determined by the determination unit 203. This provides the effect of narrowing down the elements to be rearranged to some elements, in addition to the effect provided by the information processing device 1 according to the first exemplary embodiment, thereby providing the effect of enabling smooth analysis of the some elements.

[0042] (Placement rules and their determination method) The placement rules and their determination method will be described with reference to Fig. 5 and Fig. 6. Fig. 5 and Fig. 6 are diagrams showing examples of placement rules and their determination method. Fig. 5 and Fig. 6 show an example of determining the placement rule to be applied from a predetermined number of placement rules in accordance with the selection of an operator.

[0043] 5 shows an example in which the operator selects an arrangement rule using a drop-down list A11 in addition to the object A1 shown in FIG. 3. When displaying the initial causal graph (which may also be referred to as the causal graph before rearrangement), the display control unit 204 may also display object A1, and may display the drop-down list A11 in response to the selection of object A1. The drop-down list A11 shows arrangement rules A to E that the operator can select. Of these, arrangement rule A is the rule that was applied when displaying the causal graph G1' in FIG. 3. For this reason, the following description of arrangement rule A will be omitted, and arrangement rules B to E will be described in order.

[0044] (Arrangement Rule B) Like Arrangement Rule A, Arrangement Rule B arranges a series of nodes connected by edges in order from the node corresponding to the upstream element in the causal relationship to the node corresponding to the downstream element. However, Arrangement Rule B differs from Arrangement Rule A in that the most downstream node can be freely specified.

[0045] The method for specifying the most downstream node is not particularly limited. For example, as shown in Fig. 5 , when arrangement rule B is selected from drop-down list A11, display control unit 204 may display drop-down list A12 showing nodes that can be specified as the most downstream node, and allow the user to specify a node using drop-down list A12.

[0046] In the example shown at the top of Figure 5, arrangement rule B is selected from drop-down list A11, and node N1 is specified with cursor Cu. In this case, the causal graph after rearrangement will look like G2, for example. Causal graph G2 shows the causal relationships between nodes N1 to N8. In causal graph G2, the specified node N1 is displayed at the bottom, and the other nodes N2 to N8 are arranged so that the upstream elements in the causal relationships are arranged higher up.

[0047] Similarly, the operator may be allowed to specify the most upstream node. In this case, the display control unit 204 arranges the series of nodes connected by edges based on the specified node in order from the node corresponding to the upstream element in the causal relationship to the node corresponding to the downstream element.

[0048] It is not essential to have the operator select a node when applying placement rule B. For example, the display control unit 204 may place a node with a terminal node (a node for which there is an edge with the node as its end point but no edge with the node as its start point) as the most downstream node.

[0049] (Arrangement Rule C) Like arrangement rules A and B, arrangement rule C is a rule that arranges a series of nodes connected by edges in order from a node corresponding to an upstream element in a causal relationship to a node corresponding to a downstream element. Arrangement rule C differs from arrangement rule B in that the nodes are arranged in a circular pattern. Furthermore, when applying arrangement rule C, the operator may be able to freely specify some or all of the nodes to be arranged in a circular pattern.

[0050] In the example shown at the bottom of Figure 5, arrangement rule C is selected from drop-down list A11, and node N1 is specified with cursor Cu. In this case, the causal graph after rearrangement will look like G3, for example. Causal graph G3 shows the causal relationships between nodes N1 to N8. In causal graph G3, the specified node N1 and nodes N2 to N6 connected to node N1 by edges are arranged in a circular pattern. In addition, causal graph G3 also displays nodes N7 and N8, which are connected to the circularly arranged nodes.

[0051] When rearranging nodes according to the arrangement rule C, the display control unit 204 may, for example, extract a series of elements (which may also be referred to as an element string) that includes an element corresponding to a specified node and has a direct or indirect causal relationship with the element from the analysis result data of the causal analysis. Here, the display control unit 204 may extract the longest element string when extracting the element string. Then, the display control unit 204 may rearrange the nodes corresponding to each extracted element in a circular fashion in order of causal relationship, and then arrange other nodes connected to the circularly arranged nodes.

[0052] (Placement Rule D) Placement rule D is a rule that places nodes corresponding to explanatory variables around a node corresponding to a target variable. When applying placement rule D, the operator can freely specify the target variable (which can also be called a node) to be placed at the center.

[0053] In the example shown at the top of Figure 6, arrangement rule D is selected from drop-down list A11, and node N1 is specified with cursor Cu. In this case, the causal graph after rearrangement may look like G4. Causal graph G4 shows the causal relationships between nodes N1 to N9. In causal graph G4, nodes N2 to N9 corresponding to elements of node N1, i.e., elements that have a direct or indirect causal relationship with the objective variable, i.e., the explanatory variables that explain the objective variable, are arranged around the specified node N1.

[0054] When rearrangement is performed in accordance with arrangement rule D, the display control unit 204 extracts, from the analysis result data of the causal analysis, a series of elements that include a specified node, i.e., an element corresponding to the objective variable, and that have a direct or indirect causal relationship with the element. Then, the display control unit 204 arranges, among the extracted elements, a node representing the element corresponding to the specified objective variable at or near the center of the display area of ​​the causal graph, and arranges each node corresponding to the explanatory variable around it.

[0055] If there is a node corresponding to an element that has no causal relationship with the specified objective variable, the display control unit 204 may display or not display such a node. This is not limited to the case of arrangement rule D, but is also applicable to cases where other arrangement rules are applied.

[0056] As described above, the placement rules applied in the information processing device 2 include a rule that the node corresponding to the objective variable is placed at the center and the nodes corresponding to the explanatory variables are placed around the node. By applying these placement rules, in addition to the effect achieved by the information processing device 1 according to the exemplary embodiment 1, an effect can be obtained in which the relationship between each explanatory variable and the objective variable in which the operator is interested can be clearly shown.

[0057] (Arrangement Rule E) The arrangement rule E is a rule that groups and arranges nodes that are in the same hierarchical level indicated in the hierarchical information. When rearrangement is performed based on the arrangement rule E, hierarchical information indicating the hierarchical level to which each element to be subjected to causal analysis belongs is assigned in advance.

[0058] In the example shown at the bottom of Figure 6, arrangement rule E has been selected from drop-down list A11. The causal graph after rearrangement based on arrangement rule E looks like G5, for example. Causal graph G5 shows the causal relationships between nodes N1 to N9. In causal graph G5, nodes N1 and N2 belonging to layer 1, nodes N3 to N5 belonging to layer 2, and nodes N6 to N9 belonging to layer 3 are arranged in groups. Furthermore, nodes belonging to layer 1 are arranged on the left end, nodes belonging to layer 3 are arranged on the right end, and nodes belonging to layer 2 are arranged between them. As a result, among nodes connected by edges in the horizontal direction, the nodes on the right belong to a higher layer.

[0059] In the causal graph G5, nodes N1, N3, N4, N6, and N7 are connected by edges, and nodes N2, N5, N8, and N9 are also connected by edges. On the other hand, nodes N1, N3, N4, N6, and N7 are not connected by edges to nodes N2, N5, N8, and N9. In this way, the causal graph to be rearranged may include a group of nodes that are not connected to each other by edges (which may also be referred to as a group of elements that do not have a causal relationship).

[0060] When rearrangement is performed according to arrangement rule E, the data acquisition unit 201 acquires hierarchical information stored in advance in, for example, the storage unit 21. Next, the display control unit 204 refers to the acquired hierarchical information and classifies each element shown in the analysis result data of the causal analysis by the hierarchical level to which the element belongs. Then, the display control unit 204 groups and arranges nodes that belong to the same hierarchical level (in other words, nodes corresponding to elements that belong to the same hierarchical level).

[0061] In this case, it is preferable that the groups of nodes are arranged in the order of the hierarchical levels corresponding to the groups. For example, when the levels are represented by numbers as in Figure 6, the display control unit 204 may arrange the groups in ascending or descending hierarchical order. It is also preferable that the display control unit 204 arranges the nodes so as to satisfy the condition that edges do not cross each other.

[0062] In addition, if there is an element to which no hierarchical information has been assigned, the display control unit 204 may display a node corresponding to such an element, or may not display such a node.

[0063] As described above, each of the elements subjected to the causal analysis may be assigned hierarchical information indicating the hierarchical level to which the element belongs, and in this case, an arrangement rule may be applied in which nodes in the same hierarchical level indicated in the hierarchical information are grouped and arranged. This provides the effect of being able to display a hierarchical causal graph in addition to the effect provided by the information processing device 1 according to the first exemplary embodiment.

[0064] A hierarchical causal graph is useful, for example, in analysis related to product manufacturing management. For example, explanatory variables (or target variables) may be collected for each product manufacturing process, and hierarchical information indicating the manufacturing process may be associated with each explanatory variable. This makes it possible to display a causal graph that allows easy recognition of the relationship between explanatory variables or target variables in each manufacturing process and explanatory variables or target variables in other manufacturing processes.

[0065] (Another example of a method for determining an arrangement rule) As described above, the determination unit 203 may determine an arrangement rule selected by an operator as the arrangement rule for rearranging nodes. In this case, there is an advantage that the operator can check the causal graph before rearrangement and then select an arrangement rule that is suitable for rearranging nodes in the causal graph. Note that the arrangement rules that are candidates for selection can be set arbitrarily and are not limited to the above-mentioned arrangement rules A to E.

[0066] Furthermore, the determination unit 203 may determine a predetermined placement rule as the placement rule when rearranging nodes. In this case, the operator does not need to perform an operation to select a placement rule. For example, placement rule A may be set as the default placement rule, and in this case, the determination unit 203 basically determines placement rule A as the placement rule when rearranging nodes.

[0067] Here, it is assumed that the operator, upon viewing the causal graph in which the nodes have been rearranged, may wish to change the arrangement rule. Therefore, the determination unit 203 may accept an operation to change the arrangement rule after the nodes have been rearranged, and determine the arrangement rule selected by the operator as the arrangement rule for the third rearrangement of the nodes. In this case, the display control unit 204 displays the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0068] The determination unit 203 may also automatically determine which of a plurality of arrangement rules to apply. Criteria for determining which arrangement rule to apply may be determined in advance. For example, the determination unit 203 may determine the arrangement rule to apply based on at least one of the subject to whom the causal graph is presented, the elements targeted for the causal analysis, and the results of the causal analysis.

[0069] When determining the arrangement rule to be applied based on the subject to whom the causal graph is presented, for example, the arrangement rule to be applied may be registered in advance for each subject (which may be the operator or the person to whom the operator wants to show the causal graph). In this case, the determination unit 203 may identify the subject by having the subject input their identification information, etc., and apply the arrangement rule registered in association with the subject. The determination unit 203 may also determine the attributes of the subject and apply an arrangement rule registered in advance in association with the attribute. The attribute can be set arbitrarily. For example, an arrangement rule may be registered for each attribute such as occupation, age or age group, gender, etc.

[0070] When determining the placement rule to be applied based on the elements that were the subject of the causal analysis and the results of the causal analysis, for example, conditions for the elements that were the subject of the causal analysis and the results of the causal analysis, and the placement rule to be applied when the conditions are satisfied may be registered in advance. In this case, the determination unit 203 may identify the elements that were the subject of the causal analysis and the results of the causal analysis from the analysis result data, etc., determine which conditions are satisfied based on the identified contents, and apply the placement rule that is registered in association with the satisfied condition.

[0071] For example, the determination unit 203 may determine to apply placement rule D when a condition is satisfied that the number of explanatory variables having a direct causal relationship with the objective variable is equal to or greater than a threshold. As described above, placement rule D is a rule that places the nodes corresponding to the explanatory variables around a node corresponding to the objective variable, with the node being at the center. Therefore, by applying placement rule D when the above condition is satisfied, it is possible to display a well-balanced causal graph in which a certain number of nodes are placed around the node of the objective variable.

[0072] Furthermore, explanatory variables included in the elements subjected to causal analysis may include some that are intervenible (or easy to intervene in) and some that are not intervenible (or difficult to intervene in). Here, "intervention" means artificially changing the value of the explanatory variable. For example, for node N1 of "cultural and artistic activities" shown in FIG. 3, the value of the explanatory variable can be changed by implementing measures to stimulate cultural and artistic activities. Therefore, the explanatory variable of node N1 can be said to be an explanatory variable that is intervenible. Whether or not to intervene in each explanatory variable can be set in advance and stored in the storage unit 21, etc.

[0073] In causal analysis, when an intervention changes the value of a certain explanatory variable, it is possible to infer how other variables causally linked to that explanatory variable will change. In other words, it is possible to perform simulations of various interventions based on the results of the causal analysis. For this reason, it is preferable that the placement of each node be such that simulations of interventions can be easily performed. For example, the determination unit 203 may determine the placement rule to be applied depending on the number of elements that can be intervened (or that are easy to intervene).

[0074] For example, when the number of intervenible elements satisfies a predetermined condition, the determination unit 203 may determine to apply an arrangement rule (intervention variable rule) that displays nodes indicating intervenible variables in close proximity on the screen. When causal analysis is applied to improving an individual's lifestyle in the fields of healthcare and medicine, the number of intervenible variables, such as dietary content and exercise habits, may be large.

[0075] Even in such cases, the decision unit 203 uses the intervention variable rules, allowing the user to see at a glance how multiple intervention variables (i.e., lifestyle-related items that the user can improve) relate to the objective variable.

[0076] As described above, the determination unit 203 can support a user in changing their behavior to acquire healthy lifestyle habits by using the intervention variable rules. Note that the user is not limited to a person who is trying to acquire healthy lifestyle habits. For example, a medical professional or the like who supports a patient can use the results optimized by the intervention variable rules to give advice to the patient.

[0077] The condition for applying the intervention variable rule is not limited to a condition that the number of variables that can be intervened is large (e.g., the number of variables is equal to or greater than a predetermined threshold). For example, the determination unit 203 may determine to apply the intervention variable rule when the element that is the target of the causal analysis includes a predetermined keyword related to at least one of healthcare, medicine, and health. Furthermore, for example, the determination unit 203 may determine to apply the intervention variable rule when the user's attribute is a medical professional or a patient.

[0078] In addition, for example, the determination unit 203 may determine the placement rule to be applied depending on the number of elements that have been the subject of the causal analysis, the purpose of the causal analysis, etc. For example, the determination unit 203 may determine to apply placement rule A when the number of elements that have been the subject of the causal analysis is equal to or greater than a predetermined threshold. Furthermore, for example, the determination unit 203 may determine to apply placement rule E when performing causal analysis on a product manufacturing process. Furthermore, for example, the determination unit 203 may determine to apply placement rule E (a rule that groups and places nodes that are at the same hierarchical level indicated in the hierarchical information) when hierarchical information of each element is acquired.

[0079] (Regarding Display Mode of Causal Graph) When displaying a causal graph in which nodes have been rearranged, the display control unit 204 may vary the display mode depending on the person to whom the causal graph is presented, the timing of presenting the causal graph, etc. Note that the person may be the operator who operates the information processing device 2, or may be a person to whom the operator wants to show the causal graph.

[0080] In this case, if a display mode is registered in advance for each subject, the display control unit 204 can identify the subject by, for example, inputting the subject's identification information, and apply the display mode registered in association with the subject. The same applies to the presentation timing. If a display mode is registered in advance for each presentation timing, the display control unit 204 can apply a display mode corresponding to the presentation timing. This makes it possible to display each node and its background in different colors for each season, such as cherry blossom pink in spring and brown in autumn, or in bright colors during the day and subdued colors at night, or in the corporate color of the company to which the subject belongs. Similarly, at least one of the display mode and presentation timing may be registered for each attribute of the subject. This allows the display control unit 204 to present the causal graph in a display mode and presentation timing corresponding to the attribute of the subject.

[0081] As described above, the display control unit 204 may display the causal graph in a display mode that corresponds to at least one of the target person to whom the causal graph is presented and the timing at which the causal graph is presented. This provides the effect of enabling more effective presentation of the causal graph in addition to the effect provided by the information processing device 1 according to the first exemplary embodiment.

[0082] (Element Extraction Method) The following describes the element extraction method used by the element extraction unit 202. As described above, the element extraction unit 202 extracts some of the elements that have been subjected to causal analysis as elements to be rearranged. The element extraction method may be determined in advance.

[0083] (Extraction Based on Path Coefficients) For example, the element extraction unit 202 may extract elements to be rearranged based on path coefficients between elements. Note that the path coefficients are coefficients calculated using weight values ​​of paths connecting elements. The weight values ​​can be calculated using known causal inference or causal search techniques.

[0084] Specifically, the element extraction unit 202 may extract, as elements to be rearranged, elements that are the starting points of paths with path coefficients equal to or greater than a threshold, or elements that are the starting points of a predetermined number of paths with the highest path coefficients. This makes it possible to clearly identify paths with strong influence in the causal graph. The element extraction unit 202 may also extract, as elements to be rearranged, elements that are the ending points of paths with path coefficients equal to or greater than a threshold, or elements that are the ending points of a predetermined number of paths with the highest path coefficients.

[0085] The threshold value may be changed by an operator. This will be explained with reference to Fig. 7. Fig. 7 is a diagram showing an example in which nodes are rearranged after the threshold value of the path coefficient is changed.

[0086] The causal graph G6 shown in the upper left of FIG. 7 shows the causal relationships between the nodes N1 to N8. In the causal graph G6, edges connecting nodes are displayed with lines of a thickness corresponding to the path coefficient. In this way, the display control unit 204 may display edges in a display mode corresponding to the path coefficient. This allows the operator to recognize paths with a stronger influence, allowing for smooth analysis of the relationships between elements. Note that the path coefficient can also be represented by, for example, edge length or color, in addition to edge thickness.

[0087] 7, the display control unit 204 displays an object A1 and an object A2 together with the causal graph G6. The object A2 is a threshold value designation object that accepts designation of a threshold value for the path coefficient in the causal graph G6.

[0088] Specifically, object A2 is an object in which a slider that can be moved on a slider bar is arranged on the slider bar. The slider bar indicates a changeable range of the pass coefficient threshold, and the position of the slider indicates the pass coefficient threshold. By displaying such object A2 by the display control unit 204, the operator can change the pass coefficient threshold by an intuitive and simple operation of moving the slider on the slider bar.

[0089] As shown in the upper left of Fig. 7, the operator can display all of the nodes and edges that make up the causal graph G6 by using the object A2 to set the threshold to a smaller value. Also, as shown in the lower left of Fig. 7, the operator can change the threshold to a larger value by operating the object A2 with the cursor Cu. Note that the method of operating the object A2 is not limited to using the cursor Cu.

[0090] When the threshold is changed, the element extraction unit 202 extracts elements that are the starting points of paths whose path coefficients are equal to or greater than the changed threshold as elements to be rearranged. At this time, the display control unit 204 may hide nodes in the causal graph that correspond to elements that were not extracted by the element extraction unit 202. A causal graph G6' shown in the lower left of FIG. 7 is a causal graph G6 in which, of the nodes included in the causal graph G6, nodes that correspond to elements that were not extracted by the element extraction unit 202 after the threshold was changed are hidden. Compared to the causal graph G6, the causal graph G6' makes it easier to recognize the relationships between paths whose path coefficients are equal to or greater than the threshold and the nodes included in those paths.

[0091] After receiving the threshold value specification as described above, when object A1 is selected, the determination unit 203 determines an arrangement rule for rearranging nodes. Then, the display control unit 204 displays a causal graph in which nodes corresponding to the elements extracted by the element extraction unit 202 are arranged according to the arrangement rule determined by the determination unit 203. The causal graph G6" shown on the right side of Figure 7 is displayed in this manner. The determined arrangement rule is the above-mentioned arrangement rule B. According to the causal graph G6", it is possible to easily recognize influential paths in the causal graph G6 and the relationships between the nodes that make up those paths.

[0092] As described above, the display control unit 204 may display a threshold specification object that accepts specification of a threshold value for a path coefficient in a causal graph. Then, the element extraction unit 202 may extract, as an element to be rearranged, an element that is the starting point of a path having a path coefficient equal to or greater than the threshold value specified by the threshold specification object. This provides, in addition to the effects of the information processing device 1 according to the first exemplary embodiment, an effect of being able to display a causal graph that clearly shows the causal relationships between elements according to the threshold value specified by the operator.

[0093] (Extraction Based on Operator's Designation) The element extraction unit 202 may also extract elements to be rearranged based on the designation of an operator. In this case, it may be possible to designate elements to be rearranged on the displayed causal graph. This will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example in which elements to be rearranged based on the designation of an operator are extracted and nodes are rearranged.

[0094] The causal graph G7 shown on the left side of Figure 8 shows the causal relationships between each of the nodes N1 to N9. The causal graph G7 is before the rearrangement of the nodes, and the edges are intertwined, making it difficult to recognize the relationships between the nodes. Rearranging the nodes makes it easier to recognize the relationships between the nodes, but if there are a large number of nodes, it is expected that the relationships between the nodes may still be difficult to recognize even after rearrangement.

[0095] 8, the operator is allowed to specify the elements to be rearranged on the causal graph G7, which allows the operator to narrow down the rearrangement to the elements that interest him / her in the displayed causal graph G7, and makes it possible to easily recognize the relationships between those elements.

[0096] Specifically, in the example of Figure 8, the operator drags the cursor Cu with the mouse to encircle the desired nodes, thereby designating those nodes as targets for relocation, and the trajectory of the drag operation is shown by the curve A3. In this way, by designating the target for relocation by encircling the nodes to be relocated, the operator can designate the nodes with an intuitive operation, which is preferable. Of course, the operation for designating the target for relocation can be any operation and is not limited to this example.

[0097] In the example of Fig. 8, the element extraction unit 202 extracts nodes N2 to N6 surrounded by curve A3 as elements to be rearranged. Then, the determination unit 203 determines an arrangement rule for rearranging these nodes, and the display control unit 204 displays a causal graph in which the nodes corresponding to the elements extracted by the element extraction unit 202 are arranged in accordance with the arrangement rule determined by the determination unit 203. The causal graph G7' shown on the right side of Fig. 8 is displayed in this manner.

[0098] The display control unit 204 may hide nodes (nodes N1, N7 to N9 in the example of FIG. 8) corresponding to elements not extracted by the element extraction unit 202. The display control unit 204 may also change the display color of the area surrounded by the curve A3 and the display mode such as the color, size, or shape of the nodes corresponding to the elements extracted by the element extraction unit 202, thereby highlighting the nodes corresponding to the elements extracted by the element extraction unit 202.

[0099] (Other Extraction Methods) Furthermore, for example, the element extraction unit 202 may extract elements that can be intervened (or that are easy to intervene in), and may not extract elements that cannot be intervened (or that are difficult to intervene in). Furthermore, for example, the element extraction unit 202 may extract elements for which hierarchical information is set, and may not extract elements for which hierarchical information is not set. In this way, the element extraction unit 202 may determine elements to extract using various information related to node rearrangement.

[0100] (Flow of the Support Method) The flow of the support method according to this exemplary embodiment will be described with reference to Fig. 9. Fig. 9 is a flow chart showing the flow of the support method.

[0101] In S21, the data acquisition unit 201 acquires analysis result data indicating the result of the causal analysis. As described above, the data acquisition unit 201 may acquire analysis result data by performing a causal analysis, or may acquire analysis result data indicating the result of a causal analysis performed by another device.

[0102] In S22, the display control unit 204 displays a causal graph based on the analysis result data acquired in S21. The causal graph displayed in S22 is the graph before the nodes are rearranged.

[0103] In S23, the data acquisition unit 201 acquires associated data to be used for rearrangement. For example, if hierarchical information for each element that has undergone causal analysis is stored in the storage unit 21 or the like, the data acquisition unit 201 may acquire the hierarchical information as associated data. In addition, the data acquisition unit 201 may acquire, for example, identification information for the subject to whom the causal graph is to be presented, or information indicating the timing (e.g., time of day, season, etc.) for presenting the causal graph, as associated data. Note that the processing of S23 may be performed before S21, or may be performed in parallel with S21 to S22. Furthermore, if a causal graph in which nodes have been rearranged is displayed without using associated data, S23 is omitted.

[0104] In S24, the determination unit 203 determines an arrangement rule for rearranging nodes in the causal graph displayed in S22. As described above, the determination unit 203 may determine the arrangement rule based on an operator's specification, or may automatically determine the arrangement rule. When automatically determining the arrangement rule, the determination unit 203 may make the determination using the related data acquired in S23.

[0105] In S25, the element extraction unit 202 extracts some of the elements that have been subjected to the causal analysis as elements to be rearranged. As described above, the element extraction unit 202 may extract elements based on an operator's specification, or may extract elements automatically. When extracting elements automatically, the element extraction unit 202 may determine the elements to be extracted using the related data acquired in S23. Note that the processing of S25 may be performed before S24 or may be performed in parallel with S24.

[0106] In S26, the display control unit 204 displays the causal graph in which the nodes have been rearranged in accordance with the arrangement rule determined in S24. At this time, the display control unit 204 may display the causal graph in a display mode corresponding to the related data acquired in S23. When the processing of S26 ends, the support method shown in Fig. 9 ends. Note that after S26, a change to the arrangement rule by the operator may be accepted, in which case the processing returns to S24 after S26.

[0107] As described above, the support method according to this exemplary embodiment includes displaying a causal graph in which the results of a causal analysis performed on a plurality of elements are represented by nodes corresponding to the elements and edges indicating the causal relationships between the elements, determining an arrangement rule for rearranging the nodes in the causal graph (S24), and displaying the causal graph in which the nodes have been rearranged in accordance with the arrangement rule determined in S24 (S26). This provides the effect of enabling analysis using the causal graph to be performed smoothly.

[0108] [Modification] The execution entity of each process described in the above embodiment is arbitrary and is not limited to the above example. In other words, the functions of the information processing devices 1 and 2 can be realized by multiple devices (which can also be called processors) that can communicate with each other. For example, each process described in the flowcharts of Figures 2 and 9 can be shared and executed by multiple processors. In other words, the execution entity of the support method in the above embodiment may be one processor or multiple processors.

[0109] [Example of Software Implementation] Some or all of the functions of the information processing device 1 or 2 may be implemented by hardware such as an integrated circuit (IC chip), or may be implemented by software.

[0110] In the latter case, the information processing device 1 or 2 is realized, for example, by a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in FIG. 10. The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program (support program) P for operating the computer C as the information processing device 1 or 2. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing each function of the information processing device 1 or 2.

[0111] The processor C1 may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0112] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, a mouse, a display, and a printer.

[0113] The program P can also be recorded on a non-transitory, tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0114] [Additional Note 1] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means disclosed in the above-described embodiments are also included in the technical scope of the present invention.

[0115] [Additional Note 2] Part or all of the above-described embodiment can also be described as follows: However, the present invention is not limited to the following described aspects.

[0116] (Supplementary Note 1) An information processing device comprising: a determination means for determining an arrangement rule for rearranging the nodes in a causal graph after displaying the results of a causal analysis performed on a plurality of elements, the causal graph being represented by nodes corresponding to each element and edges indicating the causal relationships between the elements; and a display control means for displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0117] (Appendix 2) An information processing device as described in Appendix 1, comprising an element extraction means for extracting some of the plurality of elements that have been causally analyzed as elements to be rearranged, and the display control means displays the causal graph in which the nodes corresponding to the elements extracted by the element extraction means are arranged in accordance with the arrangement rule determined by the determination means.

[0118] (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein the display control means displays a threshold designation object that accepts designation of a threshold value for a path coefficient in the causal graph, and the element extraction means extracts an element that is the starting point of a path having a path coefficient equal to or greater than the threshold value designated by the threshold designation object as an element to be rearranged.

[0119] (Supplementary Note 4) The information processing device according to any one of Supplementary Notes 1 to 3, wherein the arrangement rule includes a rule that the series of nodes connected by the edges are arranged in order from a node corresponding to an upstream element in a causal relationship to a node corresponding to a downstream element.

[0120] (Supplementary Note 5) The information processing device according to any one of Supplementary Notes 1 to 4, wherein the placement rule includes a rule that the nodes corresponding to explanatory variables are placed around the node corresponding to the objective variable, with the node corresponding to the objective variable at the center.

[0121] (Appendix 6) An information processing device described in any of Appendices 1 to 5, wherein each of the plurality of elements is assigned hierarchical information indicating the hierarchical level to which the element belongs, and the placement rule includes a rule that the nodes having the same hierarchical level indicated in the hierarchical information are grouped and placed.

[0122] (Supplementary Note 7) The information processing device according to any one of Supplementary Notes 1 to 6, wherein the display control means displays the causal graph in a display mode according to at least one of a target person to whom the causal graph is presented and a timing at which the causal graph is presented.

[0123] (Supplementary Note 8) The information processing device according to any one of Supplementary Notes 1 to 7, wherein the result of the causal analysis is obtained by causal analysis using AI (Artificial Intelligence).

[0124] (Supplementary Note 9) A support method including: displaying a causal graph in which at least one processor represents the results of a causal analysis performed on a plurality of elements, with nodes corresponding to each element and edges indicating causal relationships between each element; determining an arrangement rule for rearranging the nodes in the causal graph; and displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0125] (Supplementary Note 10) A support program that causes a computer to function as a determination means for determining an arrangement rule for rearranging the nodes in a causal graph, after displaying the results of a causal analysis performed on a plurality of elements, in which the nodes are represented by nodes corresponding to the elements and edges indicating the causal relationships between the elements, and a display control means for displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0126] [Additional Note 3] Some or all of the above-described embodiments can also be expressed as follows: An information processing device including at least one processor, wherein the processor displays a causal graph representing the results of a causal analysis performed on a plurality of elements, with nodes corresponding to the elements and edges indicating the causal relationships between the elements, and then executes a determination process of determining an arrangement rule for rearranging the nodes in the causal graph, and a display control process of displaying the causal graph in which the nodes have been rearranged in accordance with the determined arrangement rule.

[0127] The information processing device may further include a memory that stores an assistance program for causing the processor to execute the determination process and the display control process. The assistance program may be recorded on a computer-readable, non-transitory, tangible recording medium.

[0128] REFERENCE SIGNS LIST 1 Information processing device 11 Determination unit (determination means) 12 Display control unit (display control means) 2 Information processing device 202 Element extraction unit (element extraction means) 203 Determination unit (determination means) 204 Display control unit (display control means)

Claims

1. A determination means for determining the placement rules when rearranging the nodes in a causal graph, which is a representation of the results of a causal analysis performed on multiple elements, using nodes corresponding to each element and edges indicating the causal relationships between each element. An information processing device comprising: display control means for displaying the causal graph in which the nodes have been rearranged according to the determined arrangement rules.

2. The system includes an element extraction means for extracting a portion of the aforementioned multiple elements that have undergone causal analysis as elements to be rearranged, The information processing apparatus according to claim 1, wherein the display control means causes the node corresponding to the element extracted by the element extraction means to display the causal graph in which the node is arranged according to the arrangement rule determined by the determination means.

3. The display control means displays a threshold specification object that accepts the specification of a threshold for the path coefficient in the causal graph, The information processing apparatus according to claim 2, wherein the element extraction means extracts elements that are the starting points of paths with path coefficients greater than or equal to a threshold specified by the threshold specifying object as elements to be rearranged.

4. The information processing apparatus according to any one of claims 1 to 3, wherein the arrangement rule includes a rule that arranges a series of nodes connected by the edge in order from the node corresponding to the upstream element in the causal relationship to the node corresponding to the downstream element.

5. The information processing apparatus according to any one of claims 1 to 3, wherein the arrangement rule includes the rule of arranging the nodes corresponding to explanatory variables around the node corresponding to the objective variable, with the node corresponding to the objective variable as the center.

6. Each of the aforementioned elements is assigned hierarchical information indicating the hierarchy to which that element belongs. The information processing apparatus according to any one of claims 1 to 3, wherein the arrangement rule includes a rule for grouping and arranging nodes that are of the same hierarchy as shown in the hierarchical information.

7. The information processing device according to any one of claims 1 to 3, wherein the display control means causes the causal graph to be displayed in a display manner corresponding to at least one of the target person to whom the causal graph is presented and the timing of the presentation of the causal graph.

8. The information processing device according to any one of claims 1 to 3, wherein the results of the aforementioned causal analysis are obtained by causal analysis using AI (Artificial Intelligence).

9. At least one processor, The process involves displaying a causal graph representing the results of a causal analysis performed on multiple elements, using nodes corresponding to each element and edges indicating the causal relationships between those elements, and then determining the placement rules for rearranging the nodes in the causal graph. A support method comprising displaying the causal graph in which the nodes have been rearranged according to the determined arrangement rules.

10. Computers, A determination means for determining the placement rules when rearranging nodes in a causal graph, which is a representation of the results of a causal analysis performed on multiple elements, using nodes corresponding to each element and edges indicating the causal relationships between each element, and A support program that functions as a display control means for displaying the causal graph in which the nodes have been rearranged according to the determined arrangement rules.