Program and display system

Abstract

This technology provides a way to easily check how root cause analysis (why-why analysis) has been performed in the past to identify the causal events that caused a particular event to occur. [Solution] The program (221) causes the computer (2) to execute a tree diagram generation process (B8) that generates tree diagram data (D) in which a first node (N1) indicating the target event that was the subject of the analysis or the category to which the target event belongs, and at least one second node (N2) indicating the cause of the target event, are connected, based on aggregated data obtained by aggregating the results of multiple analyses performed in the past to identify the causal event that caused a particular event to occur.

Description

Technical Field

[0001] The present invention relates to a program and a display system.

Background Art

[0002] As one of the methods for analyzing the causes of mistakes and troubles caused by human actions in operations such as manufacturing processes and maintenance, for example, as described in Non-Patent Document 1 and Document 2, time-series factor analysis (Variation Tree Analysis: VTA) and why-why analysis are known. In particular, the why-why analysis or the method called root cause analysis is considered to be a simple and effective means because analysts describe the text logically to pursue the cause.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Non-Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] If a learned model for assisting why-why analysis can be constructed, or when performing why-why analysis in the future, it is possible to check how why-why analysis has been performed in the past, then a more accurate learned model can be constructed, or why-why analysis can be easily performed. However, conventionally, such confirmation has been difficult.

[0005] One aspect of the present invention aims to provide a technique that allows for easy verification of how a causal analysis (why-why analysis) to identify the causal event that caused a particular event to occur has been performed in the past. [Means for solving the problem]

[0006] The program according to aspect 1 of the present invention is configured to cause a computer to execute a tree diagram generation process that generates tree diagram data in which a first node indicating the target event targeted in the analysis or the category to which the target event belongs, and at least one second node indicating the cause of the target event, are connected, based on aggregated data obtained by aggregating the results of multiple analyses performed in the past to identify the causal event that caused a particular event to occur.

[0007] The program according to aspect 2 of the present invention may be configured such that, in the tree diagram generation process described above, it generates data for the tree diagram to which the second node, which represents the concept of the event that caused the target event, is connected.

[0008] The program according to aspect 3 of the present invention may be configured such that, in the tree diagram generation process described in aspect 1 or 2 above, a tree diagram is generated in which information indicating the frequency with which the cause shown in the corresponding second node was adopted in past analyses as the cause of an event belonging to the category shown in the first node. This information is attached near the line connecting the first node and the second node, or near the second node.

[0009] The program according to aspect 4 of the present invention may be configured such that, in any of the above aspects 1 to 3, the computer further executes a candidate generation process that generates at least one candidate text indicating a candidate cause of the target event based on the content of the target event.

[0010] The program according to aspect 5 of the present invention may be configured such that, in the candidate generation process described in aspect 4 above, the program refers to the tree diagram and adopts at least one cause text shown in the second node as at least one candidate text.

[0011] The program according to aspect 6 of the present invention may be configured such that, in aspect 4 or 5 described above, the computer further executes an accumulation process to store the results of the analysis in a predetermined database after the completion of the analysis.

[0012] A display system according to aspect 7 of the present invention comprises: a database that stores the results of analyses performed in the past to identify a causal event that caused one event to occur and to further identify other causal events that caused that causal event; an aggregation unit that aggregates the results of the analysis and generates aggregated data; a tree diagram generation unit that generates tree diagram data based on the aggregated data, in which a first node indicating the target event targeted in the analysis or the category to which the target event belongs and at least one second node indicating the cause of the target event to occur are connected; and an output unit that outputs the tree diagram. [Effects of the Invention]

[0013] According to one aspect of the present invention, it is possible to easily confirm how analysis to identify the causal event that caused a particular event to occur has been performed in the past. [Brief explanation of the drawing]

[0014] [Figure 1] This is a block diagram showing an example of a schematic configuration of the display system according to the embodiment of Disclosure 1. [Figure 2] This block diagram shows an example of the functional configuration of the terminals included in the system. [Figure 3] This block diagram shows an example of the functional configuration of the information processing device included in the system. [Figure 4] This figure shows an example of the information stored in the device. [Figure 5]This is a diagram showing an example of information stored in the same device. [Figure 6A] This is a flowchart showing an example of the first half of the process flow executed by the same device. [Figure 6B] This is a flowchart showing an example of the second half of the process flow executed by the same device. [Figure 7] This is a diagram for explaining a part of the process executed by the same device. [Figure 8] This is a diagram showing an example of a tree diagram output (displayed) by the same device. [Figure 9] This is a diagram for explaining a part of the process executed by the same device. [Figure 10] This is a diagram for explaining a part of the process executed by the same device. [Figure 11] This is a diagram for explaining a part of the process executed by the same device. [Figure 12] This is a diagram showing an example of a tree diagram output (displayed) by the same device. [Figure 13] This is a diagram for explaining an example of a prompt input to the same device. [Figure 14] This is a diagram showing an example of information output by the same device. [Figure 15] ]>This is a diagram for explaining an example of a prompt input to the same device. [Figure 16] This is a diagram showing an example of a tree diagram output (displayed) by the same device.

Embodiments for Carrying Out the Invention

[0015] <Disclosure 1: Embodiment of Display System 100> Hereinafter, a detailed description will be given of an embodiment of the display system 100 according to Disclosure 1.

[0016] When an incident (mistake or trouble) occurs at a manufacturing site, the person in charge at the manufacturing site (hereinafter referred to as the user) analyzes the cause of the incident. The display system 100 is a system that assists the user in analyzing the cause. As shown in Figure 1, the display system 100 comprises one or more terminal devices 1 and an information processing device 2. The terminal devices 1 and the information processing device 2 communicate with each other via a communication network N.

[0017] [Terminal device 1] As shown in Figure 2, the terminal device 1 according to this embodiment includes a reception unit 11, an output unit 12, a terminal communication unit 13, and a terminal calculation unit 14. The terminal device 1 according to this embodiment is composed of, for example, a PC (Personal Computer), a smartphone, a tablet terminal, etc.

[0018] [Reception area 11] The reception unit 11 receives input regarding the content of the target event. The reception unit 11 may be, for example, a keyboard, a pointing device (such as a mouse), or a touch panel.

[0019] [Output section 12] The output unit 12 outputs at least the tree diagram D. Details of the tree diagram D will be described later. The output unit 12 in this embodiment is composed of a display device. That is, the output unit 12 in this embodiment displays the tree diagram D. The output unit 12 may also be composed of, for example, a printer, a communication module that communicates with other output devices (display, printer, etc.) that have a function to display the tree diagram D, terminals that are connected to other output devices, etc.

[0020] [Terminal communication unit 13] The terminal communication unit 13 communicates with the information processing device 2. In this embodiment, the terminal communication unit 13 is composed of a wireless communication module. That is, in this embodiment, the terminal communication unit 13 communicates wirelessly with the information processing device 2. However, the terminal communication unit 13 may also be configured to communicate with the information processing device 2 via a wired connection.

[0021] [Terminal processing unit 14] The terminal processing unit 14 controls the terminal communication unit 13 when the receiving unit 11 receives input from the user. This causes the terminal communication unit 13 to transmit the received input to the information processing device 2. Furthermore, the terminal processing unit 14 controls the output unit 12 when the terminal communication unit 13 receives information, or data from a web page containing that information, from the information processing device 2. This causes the output unit 12 to display the information received by the terminal communication unit 13, or the web page containing that information. In this embodiment, the terminal processing unit 14 consists of a processor and memory.

[0022] [Information Processing Device 2] As shown in Figure 3, the information processing device 2 comprises a first storage unit 22 and a device calculation unit 25. The information processing device 2 according to this embodiment further comprises a device communication unit 21 and a second storage unit 23.

[0023] [Device communication unit 21] The device communication unit 21 communicates with the terminal device 1. As described above, the terminal communication unit 13 of the terminal device 1 according to this embodiment is composed of a wireless communication module. Therefore, the device communication unit 21 according to this embodiment is also composed of a wireless communication module. In other words, the device communication unit 21 according to this embodiment communicates with the terminal device 1 wirelessly. The device communication unit 21 may also be configured to communicate with the terminal device 1 via a wired connection.

[0024] [First storage section 22] The first storage unit 22 stores the program 221. The program 221 describes the processing to be executed by the device calculation unit 25. In other words, the program 221 is a program 221 that causes the computer to function as an information processing device 2, and is a program 221 that causes the computer to function as each control block of the device. In this embodiment, the first storage unit 22 is composed of a semiconductor memory, a hard disk drive, etc.

[0025] [Second storage unit 23] The second memory unit 23 stores a list of conceptual examples, such as those shown in Figure 4. The second memory unit 23 also contains a database 231. The database 231 stores multiple text entries representing past events, such as those shown in Figure 5. Furthermore, the database 231 stores multiple results from past root cause analyses. A root cause analysis is an analysis that identifies a causal event that caused a particular event, and then further identifies other causal events that caused that causal event. This process of identifying other causal events is repeated until the analyst determines that they have identified the root cause. Specifically, the database 231 stores multiple text entries, such as those found in the nodes of a tree diagram D (conceptual tree) representing the analysis results generated in past root cause analyses. Hereafter, root cause analysis will simply be referred to as analysis. Also, the aggregated results of multiple past analyses will be referred to as aggregated data. The second memory unit 23 also stores a dictionary of words (multiple words and their respective vector values). The second storage unit 23 in this embodiment is composed of a semiconductor memory, a hard disk drive, and the like.

[0026] [Third memory section 24] The third storage unit 24 stores a classification prediction model 241, a first concept prediction model 242, an event prediction model 243, and a second concept prediction model 244. In this embodiment, the third storage unit 24 is composed of a semiconductor memory, a hard disk drive, or the like.

[0027] (Classification prediction model 241) The classification prediction model 241 is a model constructed to output at least one classification to which a target event belongs when the content of the target event is input. In this embodiment, the classification prediction model 241 receives the text vector value as the content of the target event. Furthermore, the classification prediction model 241 in this embodiment outputs multiple classifications along with the probability to which the input target event belongs.

[0028] (First Concept Prediction Model 242) The first concept prediction model 242 is a model constructed to output a concept that is the cause of an event belonging to a given category when a category is input. In this embodiment, the first concept prediction model 242 is constructed to acquire a list of concept examples stored in the second memory unit 23, which includes a category selected or created by the user or computer, as a candidate concept. In addition, the category is input to the first concept prediction model 242 in this embodiment in the form of a vector value. Furthermore, the first concept prediction model 242 in this embodiment outputs multiple concepts along with their probabilities of being included in the input category. Note that the first concept prediction model 242 may be a pre-trained model constructed to generate a candidate concept when a category is input.

[0029] (Event prediction model 243) The event prediction model 243 is a model constructed to output text indicating causal events included in a concept when a sentence indicating a concept is input. A causal event is an event that causes the target event to occur. The event prediction model 243 according to this embodiment is constructed to obtain text indicating past events included in a concept selected or created by the user or computer from the database 231 as candidate text and output it. In addition, concepts are input to the event prediction model 243 according to this embodiment in the form of vector values. The first concept prediction model 242 may be a trained model constructed to generate text indicating causal events when a sentence indicating a concept is input.

[0030] (Second Concept Prediction Model 244) The second concept prediction model 244 is a model constructed to output other concepts when a sentence describing a causal event is input. These other concepts are concepts representing the causes of the causal event. In this embodiment, the vector value of the sentence is input to the second concept prediction model 244 as the content of the causal event. Furthermore, the second concept prediction model 244 in this embodiment outputs multiple other concepts along with the probability of including the input causal event.

[0031] [Device calculation section 25] The device calculation unit 25 controls each part of the information processing device 2. The device calculation unit 25 includes an acquisition unit 251, a first generation unit 252, a second generation unit 253, a first judgment unit 254, a second judgment unit 255, an update unit 256, a registration unit 257, a tree diagram generation unit 258, an aggregation unit 259, a storage unit 260, and an output control unit 261. In this embodiment, the device calculation unit 25 is composed of a processor. That is, the information processing device 2 is composed of a computer. Therefore, each function of each control block 251 to 258 is realized by the device calculation unit 25 executing various processes B1 to B9 in the flow shown in Figures 6A and 6B according to the program 221 stored in the first storage unit 22. Among the various processes, the acquisition process B1 is executed each time the terminal device 1 receives input of various information (the terminal communication unit 13 transmits various information). Furthermore, the tree diagram generation process B8 is executed each time the data for the tree diagram D is generated or updated. Additionally, the output control process B11 is executed each time the device calculation unit 25 generates various information, including the tree diagram D.

[0032] (Acquisition process B1) In the initial acquisition process B1, the acquisition unit 251 acquires the content of the target event received by the device communication unit 21. In this embodiment, the acquisition unit 251 acquires text that indicates the content of the target event. The acquisition unit 251 may also be configured to acquire the content of the target event in a form other than text (e.g., an image). Furthermore, when the terminal device 1 receives input of a new word from the user (A0), in acquisition process B1, the acquisition unit 251 acquires the word pair received by the device communication unit 21.

[0033] (First generation process B2) After the acquisition process B1 is executed, the process moves to the first generation process B2. In the first generation process B2, the first generation unit 252 generates at least one candidate text based on the content of the target event. The candidate text is text that indicates a candidate cause for the occurrence of the target event. In other words, the first generation process B2 is the candidate generation process in this disclosure. In the first generation process B2 according to this embodiment, the first generation unit 252 executes the classification generation process B21, the concept generation process B22, and the event generation process B23.

[0034] • Classification generation process B21 In the classification generation process B21, the first generation unit 252 inputs the content of the target event into the classification prediction model 241, as shown in Figure 7, and obtains at least one output from the classification prediction model 241 as a candidate classification for the target event. As described above, the classification prediction model 241 according to this embodiment receives the vector value of a sentence as the content of the target event. Therefore, the first generation unit 252 according to this embodiment decomposes the sentence representing the content of the target event into multiple words (morphological analysis) and vectorizes each word. Then, the first generation unit 252 converts the vector of each word into a sentence vector. One conversion method is to calculate the average of the vector values ​​of each word as the sentence vector value. When calculating the sentence vector value according to this embodiment, the first generation unit 252 performs weighting based on the importance of each word input into the classification prediction model 241 (for example, giving higher importance to words that are input relatively frequently).

[0035] In the output control process B11 following the execution of the category generation process B21, the output control unit 261 controls the device communication unit 21 according to the processing result of the category generation process B21. As a result, the device communication unit 21 sends data of candidate categories or data of a web page indicating candidate categories to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the candidate categories (A2). The user, after confirming the candidate categories displayed on the terminal device 1, performs an operation to select one of the candidate categories or an operation to create a category based on the content of the candidate categories. As a result, the reception unit 11 of the terminal device 1 receives input of the selected or created category (A3), and the terminal communication unit 13 transmits it to the information processing device 2.

[0036] Furthermore, in the acquisition process B1 following the execution of the classification generation process B21, the acquisition unit 251 acquires the selected or created classification received by the device communication unit 21. In the tree diagram generation process B8 following the execution of the acquisition process B1, the tree diagram generation unit 258 generates the first node N1, which is the starting point of the tree diagram D and indicates the classification to which the target event targeted in the analysis belongs. In the output control process B11 following the execution of the tree diagram generation process B8, the output control unit 261 controls the device communication unit 21 according to the processing result of the tree diagram generation unit 258. As a result, the device communication unit 21 transmits the data of the tree diagram D (first node N1) to the terminal device 1. The terminal device 1, having received the data, displays the tree diagram D (first node N1) as shown in Figure 8 (A4A).

[0037] • Concept generation process B22 After the execution of the classification generation process B21 (after the acquisition unit 251 acquires the selected or created classification), the process moves to the concept generation process B22. In the concept generation process B22, the first generation unit 252 inputs the selected or created classification into the first concept prediction model 242, as shown in Figure 9, and acquires at least one output from the first concept prediction model 242 as a candidate concept belonging to the selected or created classification.

[0038] In the output control process B11 following the execution of the concept generation process B22, the output control unit 261 controls the device communication unit 21 according to the processing result of the concept generation process B22. As a result, the device communication unit 21 transmits data of candidate concepts or data of a web page showing candidate concepts to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the candidate concepts (A4B). Note that the output of the candidate concepts may occur simultaneously with the display of the tree diagram D. After the user has confirmed the candidate concepts displayed on the terminal device 1, they perform operations to select one of the candidate concepts or to create a concept based on the content of the candidate concepts. As a result, the receiving unit 11 of the terminal device 1 receives input of the selected or created concept (A5), and the terminal communication unit 13 transmits it to the information processing device 2.

[0039] Furthermore, in the acquisition process B1 after the execution of the concept generation process B22, the acquisition unit 251 acquires the selected or created concept received by the device communication unit 21.

[0040] • Event generation process B23 After the execution of concept generation process B22 (after the acquisition unit 251 acquires the selected or created category), the process moves to event generation process B23. In event generation process B23, the first generation unit 252 generates candidate text based on the concept selected from the candidate concept or the concept created based on the candidate concept. Specifically, as shown in Figure 10, the first generation unit 252 inputs a sentence indicating the selected or created concept into the event prediction model 243 stored in the third storage unit 24, and acquires at least one output from the event prediction model 243 as candidate text corresponding to the selected or created concept.

[0041] In the output control process B11 following the execution of the event generation process B23, the output control unit 261 controls the device communication unit 21 according to the processing result of the event generation process B23. As a result, the device communication unit 21 sends candidate text data or data of a web page showing the candidate text to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the candidate text (A6). The user, after confirming the candidate text displayed on the terminal device 1, performs operations to select one of the candidate texts or to create a sentence indicating the cause event based on the content of the candidate text. As a result, the reception unit 11 of the terminal device 1 further accepts the input of the sentence indicating the cause event, which was selected from the candidate texts or created based on the candidate texts (A7), and the terminal communication unit 13 transmits it to the information processing device 2.

[0042] Furthermore, in the acquisition process B1 after the execution of the event generation process B23, the acquisition unit 251 acquires the selected or created text received by the device communication unit 21.

[0043] • Modified form of the first generation process B2 In addition, during the first generation process B2, the first generation unit 252 may refer to the previously generated tree diagram D and select at least one cause text indicated in at least one second node N2 as at least one candidate text.

[0044] (Second generation process B3) After the execution of the first generation process B2, the process moves to the second generation process B3. In the second generation process B3, the second generation unit 253 inputs sentences indicating causal events, selected by the user or computer from among the candidate texts, or created by the user or computer based on the candidate texts, into the second concept prediction model 244, as shown in Figure 11, and obtains at least one output from the second concept prediction model 244 as a candidate for other concepts corresponding to the sentence indicating the causal event.

[0045] In the output control process B11 following the execution of the second generation process B3, the output control unit 261 controls the device communication unit 21 according to the processing result of the second generation process B3. As a result, the device communication unit 21 sends data of other concept candidates or data of a web page showing other concept candidates to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the other concept candidates (A8A). The user, after confirming the other concept candidates displayed on the terminal device 1, performs an operation to select one of the other concept candidates or an operation to create another concept based on the content of the other concept candidates. As a result, the reception unit 11 of the terminal device 1 receives input of the selected or created other concept (A9), and the terminal communication unit 13 transmits it to the information processing device 2.

[0046] Furthermore, in the acquisition process B1 after the execution of the second generation process B3, the acquisition unit 251 acquires other selected or created concepts received by the device communication unit 21. In the tree diagram generation process B8 after the execution of the acquisition process B1, the tree diagram generation unit 258 generates data for tree diagram D in which the second node N2, which indicates the other acquired concepts (the cause of the target event), is connected to the first node N1. In the output control process B11 after the execution of the tree diagram generation process B8, the output control unit 261 controls the device communication unit 21 according to the processing result of the tree diagram generation unit 258. As a result, the device communication unit 21 transmits the data of tree diagram D to the terminal device 1. The terminal device 1, having received the data, displays tree diagram D as shown in Figure 12 (A8B). Note that the display of tree diagram D may be simultaneous with the output of other concept candidates.

[0047] • Event generation process B23 If another concept is selected or created based on other candidate concepts, i.e., if the acquisition unit 251 acquires the selected or created other concept and the analysis is not yet complete (B12:NO), the process moves back to event generation process B23. The second event generation process B23 is based on the other concept. That is, in the second event generation process B23, the first generation unit 252 inputs a sentence representing the selected or created other concept into the event prediction model 243, and acquires at least one output from the event prediction model 243 as candidate text corresponding to the selected or created other concept.

[0048] In the output control process B11 following the execution of the event generation process B23 again, the output control unit 261 controls the device communication unit 21 according to the processing result of the event generation process B23 again. As a result, the device communication unit 21 sends data of candidate text generated in correspondence with another concept, or data of a web page showing the candidate text, to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the candidate text (A6). The user, after confirming the candidate text displayed on the terminal device 1, performs an operation to select one of the candidate texts, or an operation to create a sentence indicating the cause event based on the content of the candidate text. As a result, the reception unit 11 of the terminal device 1 further accepts input of the sentence indicating the cause event, which was selected from the candidate texts or created based on the candidate texts (A7), and the terminal communication unit 13 transmits it to the information processing device 2.

[0049] Furthermore, in the acquisition process B1 after the execution of the event generation process B23, the acquisition unit 251 acquires the selected or created text received by the device communication unit 21.

[0050] (Second generation process B3) After the execution of the event generation process B23 based on the first other concept, the process moves again to the second generation process B3. The second generation process B3 is based on candidate text generated in response to the first other concept. That is, in the second generation process B3, the second generation unit 253 inputs a sentence indicating the causal event, selected by the user or computer from among the candidate texts, or created by the user or computer based on the candidate texts, into the second concept prediction model 244, and obtains at least one output from the second concept prediction model 244 as a candidate for the other concept corresponding to the sentence indicating the causal event.

[0051] In the output control process B11 following the execution of the second generation process B3, the output control unit 261 controls the device communication unit 21 according to the processing result of the second generation process B3. As a result, the device communication unit 21 sends data of other concept candidates or data of a web page showing other concept candidates to the terminal device 1. Upon receiving the data, the terminal device 1 outputs (displays) the other concept candidates. The user, after confirming the other concept candidates displayed on the terminal device 1, performs an operation to select one of the other concept candidates, an operation to create another concept based on the content of the other concept candidates, or an operation to instruct the end of the analysis (A9). As a result, the reception unit 11 of the terminal device 1 receives the input of the selected or created other concept or the instruction to end the analysis, and the terminal communication unit 13 transmits it to the information processing device 2.

[0052] Furthermore, in the acquisition process B1 after the execution of the second generation process B3, the acquisition unit 251 acquires other selected or created concepts received by the device communication unit 21. In the tree diagram generation process B8 after the execution of the second generation process B3, the tree diagram generation unit 258 generates tree diagram D data in which the second node N2 generated in the tree diagram generation process B8 corresponding to the previous second generation process B3 is connected to the second node N2 corresponding to the previous second generation process B3. In the output control process B11 after the execution of the tree diagram generation process B8, the output control unit 261 controls the device communication unit 21 according to the processing result of the tree diagram generation unit 258. As a result, the device communication unit 21 transmits the tree diagram D data to the terminal device 1. The terminal device 1, having received the data, displays the tree diagram D (A8B). In this way, because the tree diagram D is automatically generated, a visually consistent analysis result can be obtained regardless of who performed the analysis.

[0053] If terminal device 1 transmits another selected or created concept, in acquisition process B1 after execution of second generation process B3, the acquisition unit 251 acquires the other selected or created concept received by device communication unit 21. Then, event generation process B23 based on the other concept is executed again. On the other hand, if terminal device transmits an analysis termination instruction (A10:YES), device calculation unit 25 terminates processing.

[0054] (First decision processing B4) If the execution of event generation process B23 is repeated, the process moves to first decision process B4. In first decision process B4, the first decision unit 254 determines whether the causal relationship between the content of a sentence selected from candidate texts generated in one event generation process, or created based on such candidate texts, and the content of a sentence selected from candidate texts generated in an event generation process executed before the one event generation process, or created based on such candidate texts, is logically correct. Specifically, the first decision unit 254 generates a prompt, for example, as shown in Figure 13, in response to input received from the user, and inputs the generated prompt to a trained model (e.g., ChatGPT, Claude, etc.) that determines causal relationships. The first decision unit 254 then obtains the output from the trained model as the decision result. In the first decision process B4 according to this embodiment, the first decision unit 254 outputs the decision result three times for a single user input. This is because the trained model does not necessarily output the same result for the same input. The first determination unit 254 may be configured to output a determination result two or four or more times in response to a single user input.

[0055] In the output control process B11 following the execution of the first judgment process B4, the output control unit 261 controls the device communication unit 21 according to the processing result of the first judgment process B4. As a result, the device communication unit 21 transmits the judgment result data, or the data of a web page showing the judgment result, to the terminal device 1. The terminal device 1, having received the data, outputs (displays) the judgment result (A11). As described above, in the first judgment process B4, the first judgment unit 254 outputs the judgment result three times for a single user input. Therefore, the terminal device 1 displays the three judgment results in a list, as shown in Figure 14. This allows the user to finally confirm whether there are any problems with the causal relationship, even if there is variation in the judgment results. After the user has confirmed the judgment result displayed on the terminal device 1, they perform an operation to correct the sentences they entered that were pointed out as having incorrect causal relationships, if necessary. As a result, the receiving unit 11 of the terminal device 1 receives the corrected sentences, and the terminal communication unit 13 transmits them to the information processing device 2.

[0056] If terminal device 1 sends a modified text, in acquisition process B1 after the execution of first decision process B4, the acquisition unit 251 acquires the modified text received by the device communication unit 21. Then, the second generation process B3 based on the modified text is executed again.

[0057] (Second decision processing B5) The second decision process B5 is executed at the appropriate time (for example, when terminal device 1 receives a predetermined processing start instruction from the user). In the second decision process B5, the second decision unit 255 determines whether the candidate of other concepts output by the second concept prediction model 244 for the sentence indicating the causal event was valid. Specifically, the second decision unit 255 generates a prompt, for example, as shown in Figure 15, in response to the input received from the user, and inputs the generated prompt to a trained model that judges the validity of the candidates. The second decision unit 255 then obtains the output of the trained model as the decision result.

[0058] (Update process B6) Update process B6 is a process that is executed at the appropriate time (for example, when terminal device 1 receives input from the user for a predetermined process start instruction). In update process B6, update unit 256 evaluates the quality of the list of conceptual examples stored in second memory unit 23 and updates the list based on the evaluation result. Quality is at least one of the following: comprehensiveness of conceptual examples, clarity of distinction between conceptual examples, and accuracy of representation of each conceptual example. Specifically, update unit 256 generates a prompt in response to input received from the user and inputs the generated prompt into a trained model (at least one of a trained model that evaluates comprehensiveness, a trained model that evaluates clarity of distinction, and a trained model that evaluates accuracy of representation). Then, update unit 256 obtains the output from the trained model as the evaluation result.

[0059] (Registration process B7) Registration process B7 is performed as needed (for example, when terminal device 1 receives input of a new word from the user (A0)). In registration process B7, the registration unit 257 vectorizes the input word and registers it in the dictionary stored in the second storage unit 23. The registration unit 257 creates a group of words that are similar in meaning to the word to be newly registered from among the words that are already registered, and uses the average value of the vector values ​​of the words included in the group as the vector value of the word to be newly registered.

[0060] (Aggregation process B9) After the analysis is complete, the process moves to aggregation process B9. In aggregation process B9, the aggregation unit 259 aggregates the results of the analysis to generate aggregated data. In aggregation process B9, the aggregation unit 259 may aggregate other concepts acquired by the acquisition unit 251 in each acquisition process B1 during the analysis (the cause of the target event: the content displayed in the second node N2) as they are, or it may abstract them into higher-level concepts (for example, the sentence "He was not wearing goggles" is abstracted into the higher-level concept "He was not wearing protective equipment") and then aggregated.

[0061] (Storage process B10) After the analysis is complete, the process moves to storage process B10. In storage process B10, the storage unit 260 stores the results of the analysis in a predetermined database. In storage process B10 according to this embodiment, the storage unit 260 stores the analysis results in the database 231 of the second storage unit 23. If the database 231 is provided by a device other than the information processing device 2, in storage process B10, the storage unit 260 controls the device communication unit 21 to transmit the analysis results to the other device. The other device that receives the analysis results stores the received analysis results in the database 231. Furthermore, storage process B10 may be executed before aggregation process B9, or it may be executed in parallel with aggregation process B9.

[0062] Furthermore, in the tree diagram generation process B8 after the aggregation process B9 or storage process B10 is executed, the tree diagram generation unit 258 generates tree diagram D data in which a first node and a second node are connected based on the aggregated data. In the tree diagram generation process B8 according to this embodiment, the tree diagram generation unit 258 generates tree diagram D data in which a second node is connected that represents a higher-level concept (a concept of the event that caused the target event to occur) that abstracts other concepts. If other concepts are treated as higher-level concepts in the aggregation process B9, the aggregated data is used as is to generate tree diagram D data. On the other hand, if other concepts are not treated as higher-level concepts in the aggregation process B9, the tree diagram generation unit B abstracts each of the other concepts in the aggregated data into a higher-level concept to generate tree diagram D data. The tree diagram generation unit 258 may also generate tree diagram D data in which a second node representing other concepts as they are is connected. In other words, the "cause of the target event" shown in the second node N2 includes the other concept itself (the event that caused the target event to occur) and the higher-level concept of the other concept (the concept of the event that caused the target event to occur). In the output control process B11 after the execution of the tree diagram generation process B8, the output control unit 261 controls the device communication unit 21 according to the processing result of the tree diagram generation unit 258. As a result, the device communication unit 21 transmits the tree diagram D data to the terminal device 1. The terminal device 1, having received the data, displays the tree diagram D as shown in Figure 16 (A8B). In the tree diagram generation process B8 according to this embodiment, the tree diagram generation unit 258 generates a tree diagram D in which information indicating the frequency with which the cause shown in the corresponding second node N2 was adopted as the cause of an event belonging to the category shown in the first node N1 in past analyses is attached near the line connecting the first node N1 and the second node N2, or near the second node N2. "Information indicating frequency" includes, for example, a number indicating the number of times it was adopted, characters indicating the frequency (many / few), and the display method of the lines connecting the nodes (thickness, color intensity, etc.). Note that the tree diagram generation process B8 may be executed before the aggregation process B9 or the storage process B10. In this case, the tree diagram will display tree diagram D before the latest analysis is added to the aggregation.

[0063] [Effects of the Information Processing Device 2 (Display System 100)] The information processing device 2 (display system 100) described above visually outputs the analysis results in the form of a tree diagram D. By referring to the child tree diagram, it becomes easier to identify patterns in the causes of events. Therefore, according to the information processing device 2 (display system 100), it is easy to check how the analysis to identify the causal events that caused a particular event (why-why analysis) was performed in the past. As a result, it is possible to build a more accurate trained model, or to perform the analysis more easily.

[0064] [Differentiation] The present invention is not limited to the embodiments described above, and various modifications and / or selections are possible within the scope of the claims.

[0065] For example, in the above embodiment, the database 231 was provided by the information processing device 2. However, the database 231 may be provided by a device other than the information processing device 2. In that case, the aggregation unit 259 (function for executing aggregation processing B9) may be provided by a device other than the information processing device 2.

[0066] Furthermore, in the first generation process B2 according to the above embodiment, the category generation process B21, the concept generation process B22, and the event generation process B23 were executed. However, the concept generation process B22 does not need to be executed in the first generation process B2. In that case, in the event generation process B23, the first generation unit 252 will generate candidate text based on a category selected from the category candidates or a category created based on the category candidates. Specifically, for example, a selected or created category is input to a trained model that is constructed to output candidate text when a category is input, and at least one output from the trained model is obtained as candidate text. Alternatively, only the generation of categories and the generation of candidate text may be repeated (concept generation may not be performed).

[0067] Furthermore, in the first generation process B2, it is not necessary to execute the classification generation process B21 and the concept generation process B22. In this case, in the event generation process B23, the first generation unit 252 will generate at least one candidate text based on the content of the target event. Specifically, for example, a selected or created sentence is input to a trained model that is constructed to output a candidate text when a sentence indicating the content of the target event is input, and at least one output from the trained model is obtained as the candidate text. Also in this case, in the tree diagram generation process B8, the tree diagram generation unit 258 will generate data for a tree diagram D in which the first node N1 and the second node N2, which indicate the target event (not classification) that was the subject of the analysis, are connected.

[0068] Furthermore, in the above embodiment of the display system 100, the terminal device 1 outputs various candidates generated by the information processing device 2, and the user selects a candidate or creates a document based on the candidates. However, the display system 100 may be configured to automatically select various candidates or create a document based on the various candidates.

[0069] Furthermore, the display system 100 according to the above embodiment was composed of multiple devices (terminal device 1 and information processing device 2). However, the display system 100 may be composed of a single device. Specifically, the information processing device 2 may have a configuration corresponding to the receiving unit and output unit of the terminal device 1. In this case, the information processing device 2 does not need to have a device communication unit 21.

[0070] Furthermore, at least two of the first storage unit 22, the second storage unit 23, and the third storage unit 24 may be configured as a single unit. Also, the database 231 and at least one of the various prediction models may be stored in a storage device provided separately from the information processing device 2. In that case, the information processing device 2 does not need to have the second storage unit 23 or the third storage unit 24.

[0071] Furthermore, the program 221 may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the device. In the latter case, the program 221 may be supplied to the device via any wired or wireless transmission medium.

[0072] Furthermore, some or all of the functions of each of the control blocks 251 to 258 described above can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the control blocks 251 to 258 described above are formed is also included in the scope of the present invention. [Explanation of symbols]

[0073] 100 Display Systems 1 Terminal device 11 Reception Department 12 Output section 13 Terminal Communication Unit 14 Terminal Processing Unit (Processor) 2. Information Processing Equipment (Computer) 21. Device Communication Unit 22 First memory section 221 Programs 23 Second memory section 231 Databases 24 Third Memory 241 Classification Prediction Models 242 First Concept Prediction Model 243 Event Prediction Models 244 Second Concept Prediction Model 25 Device calculation section 251 Acquisition Department 252 First generation part 253 Second generation part 254 First Judgment Department 255 Second Judgment Department 256 Update Department 257 Registration Department 258 Tree Diagram Generation Unit 259 Aggregation Department 260 Storage Unit 261 Output Control Unit D. Tree diagram N1 First Node N2 Second Node

Claims

1. On the computer, Based on aggregated data obtained by aggregating the results of multiple analyses conducted in the past to identify the causal events that caused a particular event, a tree diagram generation process is executed to generate tree diagram data in which a first node indicating the target event targeted in the analysis or the category to which the target event belongs, and at least one second node indicating the cause of the target event, are connected. program.

2. In the tree diagram generation process, data of the tree diagram is generated in which the second node, which represents the concept of the event that caused the target event, is connected. The program according to claim 1.

3. In the tree diagram generation process, the tree diagram is generated in which information is attached near the line connecting the first node and the second node, or near the second node, indicating the frequency with which the cause shown in the corresponding second node was adopted as the cause of an event belonging to the category shown in the first node in past analyses. The program according to claim 1.

4. To the aforementioned computer, Based on the content of the target event, a candidate generation process is further executed to generate at least one candidate text indicating a possible cause of the target event. The program according to claim 1.

5. In the candidate generation process, the tree diagram is referenced, and the cause text shown in at least one of the second nodes is selected as at least one candidate text. The program according to claim 4.

6. To the aforementioned computer, After the completion of the aforementioned analysis, a further storage process is performed to accumulate the results of the analysis in a predetermined database. The program according to claim 4.

7. A database that stores the results of analyses conducted in the past to identify the causal event that caused a particular event, and to further identify other causal events that caused that causal event, An aggregation unit that aggregates the results of the above analysis and generates aggregated data, A tree diagram generation unit generates tree diagram data in which a first node indicating the target event or category to which the target event belongs, and at least one second node indicating the cause of the target event, are connected based on the aggregated data. An output unit that outputs the aforementioned tree diagram, Equipped with, Display system.

Images