Sentence display device, sentence display method, and recording medium

Abstract

A sentence display device according to the present disclosure comprises: an extraction means for extracting, from text data described in a product maintenance record, a portion corresponding to an item of the maintenance record; a generation means for generating graph information shown in a graph format by setting an entity described in each extracted item as a node and connecting mutually related nodes with an edge; and a display means for displaying the generated graph information.

Description

Text display device, text display method, and recording medium

[0001] The present disclosure relates to a text display device, a text display method, and a recording medium.

[0002] In the manufacturing industry, a huge amount of information is managed, such as maintenance records, daily business reports, and inquiries from users. Therefore, there are technologies that make it easy to understand the contents of this information.

[0003] For example, Patent Document 1 discloses that, in order to easily understand the work that needs to be done during maintenance, text data of repair history that describes failures, causes, and treatments is analyzed to extract important words related to maintenance, and the important words are used to classify events, causes, and treatments, thereby forming a tree diagram that shows the relationships between events, causes, and treatments in a tree-like manner.

[0004] Japanese Patent Application Laid-Open No. 2023-074023

[0005] In Patent Document 1, a tree diagram is generated for each event and the tree diagram for each event is layered. With this configuration, when displaying multiple events, it is necessary to create multiple tree diagrams and check the content of each tree diagram, which makes it difficult to understand the content of the text data.

[0006] An example of an object of the present disclosure is to provide a text display device or the like that can reduce the effort required to understand the content of text data.

[0007] A text display device in one aspect of the present disclosure includes an extraction means for extracting portions corresponding to items in the maintenance record from text data recorded in the maintenance record of a product, a generation means for generating graph information shown in graph format by treating the objects recorded in each extracted item as nodes and connecting nodes that are related to each other with edges, and a display means for displaying the generated graph information.

[0008] In one aspect of the present disclosure, a text display method involves a computer extracting portions corresponding to items in a product maintenance record from text data recorded in the maintenance record, treating the objects recorded in each extracted item as nodes, connecting nodes that are related to each other with edges, thereby generating graph information shown in graph format, and displaying the generated graph information.

[0009] In one aspect of the present disclosure, a recording medium stores a program that causes a computer to extract portions corresponding to items in a product's maintenance record from text data recorded in the maintenance record, treat the objects recorded in each extracted item as nodes, connect nodes that are related to each other with edges, generate graph information shown in graph format, and display the generated graph information.

[0010] According to one example of the effect of the present disclosure, it is possible to reduce the effort required to understand the content of text data.

[0011] FIG. 1 is a block diagram showing the configuration of a text display device according to the present disclosure. FIG. 2 is a diagram showing a hardware configuration in which the text display device according to the present disclosure is realized by a computer device and its peripheral devices. FIG. 3 is an example of generating graph information of a maintenance record according to the present disclosure. FIG. 4 is an example of generating graph information of a maintenance record according to the present disclosure. FIG. 5 is another example of generating graph information of a maintenance record according to the present disclosure. FIG. 6 is a flowchart showing the operation of text display according to the present disclosure. FIG. 7 is a block diagram showing the configuration of a text display device according to the present disclosure. FIG. 8 is a diagram explaining an example of a method for estimating a cause from a symptom of a product according to the present disclosure. FIG. 9 is a diagram explaining an example of a method for estimating a cause from a symptom of a product according to the present disclosure. FIG. 10 is a diagram explaining an example of a method for estimating a cause from a symptom of a product according to the present disclosure. FIG. 11 is a block diagram showing the configuration of a text display device according to the present disclosure. FIG. 12 is an example of outputting the number of symptoms or causes according to the present disclosure. FIG. 13 is an example of outputting the number of causes according to the present disclosure. FIG. 14 is an example of outputting the number of causes according to the present disclosure.

[0012] Hereinafter, with reference to the accompanying drawings, embodiments of a text display device, a text display method, a program, and a non-transitory recording medium for recording the program according to the present disclosure will be described in detail. The present embodiments do not limit the disclosed technology.

[0013] [First embodiment] Fig. 1 is a block diagram showing the configuration of a text display device 100 according to the present disclosure. As shown in Fig. 1, the text display device 100 includes an extraction unit 101, a generation unit 102, and a display unit 103. The text display device 100 is a device for displaying text data of a product's maintenance record in a graph format.

[0014] Maintenance records are records that record the results of product inspections and an overview of maintenance in the manufacturing industry, for example, and are used to help maintain and manage the products. Analyzing maintenance records is useful for reducing corporate losses through early detection of recalls, ensuring user safety early, reducing maintenance man-hours by identifying the causes of defects and suggesting maintenance methods, and providing feedback to product development departments. A graph structure is composed of a set of nodes (vertices) and edges (edges) and can show the relationships between various events. While this disclosure mainly describes vehicle maintenance records, the products in this disclosure are not limited to vehicles as long as they require maintenance.

[0015] Fig. 2 is a diagram showing an example of a hardware configuration in which the text display device 100 according to the present disclosure is realized by a computer device 500 including a processor 501. As shown in Fig. 2, the text display device 100 includes the processor 501, memories such as a ROM (Read Only Memory) 502 and a RAM (Random Access Memory) 503, a storage device 505 such as a hard disk for storing a program 504, a communication I / F (Interface) 508 for network connection, and an input / output interface 511 for inputting and outputting data.

[0016] The processor 501 controls the entire computer device 500. The processor 501 may be, for example, a central processing unit (CPU), a digital signal processor (DSP), a graphics processing unit (GPU), 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, or a combination thereof. The processor 501 runs an operating system to control the entire text display device 100 according to the present disclosure. The processor 501 also reads programs and data from a recording medium 506 attached to a drive device 507 or the like into memory. The processor 501 also functions as the extraction unit 101, generation unit 102, and display unit 103, or parts thereof, according to the present disclosure, and executes processing or instructions in the flowchart shown in FIG. 6, which will be described later, based on the program.

[0017] The recording medium 506 is, for example, an optical disk, a flexible disk, a magneto-optical disk, an external hard disk, or a semiconductor memory. A part of the recording medium in the storage device is a non-volatile storage device, and the program is recorded therein. The program may also be downloaded from an external computer (not shown) connected to a communication network.

[0018] The input device 509 is realized by, for example, a mouse, a keyboard, built-in key buttons, etc., and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or built-in key buttons, and may be, for example, a touch panel. The output device 510 is realized by, for example, a display, and is used to check output.

[0019] As described above, the text display device 100 shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the means for realizing each part of the text display device 100 of FIG. 1 is not limited to the configuration described above. Furthermore, the text display device 100 may be realized by a single physically coupled device, or by two or more physically separate devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network. Furthermore, the text display device 100 shown in FIG. 1 can also be configured using cloud computing or the like.

[0020] The extraction unit 101 is a means for extracting portions corresponding to items in a maintenance record from text data recorded in a product maintenance record. Items in the maintenance record include, for example, the vehicle for which the maintenance record applies, the time when the malfunction occurred, and the maintenance process for addressing the malfunction. When a malfunction symptom such as an abnormal noise, the illumination of a warning light, or engine malfunction occurs during vehicle maintenance, maintenance processes are performed, such as checking the symptom, identifying the cause, taking action such as replacing parts, and checking the results of the action.

[0021] The extraction unit 101, for example, inserts a segment for each sentence into text data of a maintenance record stored in a server device or the like, and extracts a portion of each sentence corresponding to each item of the maintenance record. More specifically, the extraction unit 101 segments the text data into sentences using a machine learning model for estimating sentence segments. Then, for each sentence, the extraction unit 101 segments the text data into portions corresponding to each item using the machine learning model. The extraction unit 101 may extract text data for each portion corresponding to each item, for example, using a technique for extracting elements such as "subject," "verb," ​​and "object" using OpenIE (Open Information Extraction). In this case, the extraction unit 101 may extract text data in order of easiest-to-extract elements. Alternatively, the extraction unit 101 may classify the segmented text data into each item using named entity recognition.

[0022] The extraction unit 101 extracts text data corresponding to items such as "product name," "symptoms of the defect," "cause of the defect," "time of occurrence," "measures taken," and "results of the measures taken" from sentences related to product maintenance records. The extraction unit 101 outputs the extracted text data to the generation unit 102 while maintaining the relationships between the extracted items.

[0023] The generation unit 102 is a means for generating graph information shown in a graph format by treating the objects described in each extracted item as nodes and connecting nodes that have relationships with each other with edges. The generation unit 102, for example, extracts any item from the text data and sets it as a parent node. The generation unit 102 also generates text data indicating the content described regarding the object as an edge label. The generation unit 102 may also generate text data indicating the relationship between nodes among the content described regarding the object.

[0024] The generation unit 102 may generate graph information for multiple maintenance records. In this case, the generation unit 102 may add graph information for other maintenance records to already generated graph information, or may generate graph information for multiple maintenance records simultaneously. When generating graph information for multiple maintenance records, the generation unit 102 generates graph information for maintenance records for vehicles of the same model or model number, for example. The generation unit 102 sets the model or model number as a parent node, and generates graph information by setting the target of each item in the maintenance record for a vehicle of that model or model number as a node.

[0025] When the objects described in each of the multiple maintenance records are included in the same category, the generation unit 102 may generate graph information in which the nodes of each object are branched. For example, when the causative parts described in each of the multiple maintenance records are included in the same category, the generation unit 102 generates graph information in which the nodes of each causative part are branched. The part category information is stored in advance in the storage device 505. The generation unit 102 refers to the category information and determines whether or not to branch the node of each causative part.

[0026] The display unit 103 is a means for displaying the generated graph information in a graph format on a display device such as a display etc. The display unit 103 may transmit the generated graph information to a terminal device used by the user, or may display the graph information in a graph format in response to a trigger such as a user's operation to display the product maintenance record in a graph format.

[0027] 3 and 4 show an example of generating graph information of a maintenance record in the present disclosure. The example of FIG. 3 is an example of extracting portions corresponding to items of the maintenance record from text data written in the maintenance record. As shown in FIG. 3, the extraction unit 101 extracts text data corresponding to "model number," "occurrence status," "symptoms," "cause," "treatment," and "results of treatment" from the text data.

[0028] The example in FIG. 4 is an example of graph information that displays extracted text data in a graph format. As shown in FIG. 4, each object is a node, and the nodes are connected by edges. In addition, the edge labels display text data indicating the content described regarding the object. For example, between "Model Number A-2" and "Idling," it is displayed that idling "occurs while the vehicle is stopped" and "is unstable." Furthermore, between "Idling" and "Fuel System," it is displayed that the fuel system is the "causative part." Similarly, between "Fuel System" and "Metal Powder," it is displayed that the "contamination" of metal powder is the cause of the malfunction symptoms. Furthermore, between "Metal Powder" and "Engine," it is displayed that the engine was "replaced" as a remedial action.

[0029] FIG. 5 illustrates another example of generating graph information of a maintenance record in the present disclosure. The graph information in FIG. 5 differs in the order of node connection. That is, in FIG. 4, the nodes are connected in the order of vehicle model → model number → symptoms → causative part → cause → treatment. In contrast, the graph information in FIG. 5 connects the nodes in the order of vehicle model → model number → cause → causative part → symptoms → treatment. Furthermore, in the graph information in FIG. 4, the causative part is the fuel system. In contrast, in the graph information in FIG. 5, the causative part is listed as a part name of a subcategory of the fuel system. Specifically, as shown in FIG. 5, the causative part, "fuel system," is displayed as a subcategory of the fuel system, such as "fuel tank," "fuel injection pump," and "fuel filter," each of which is displayed in a branched manner. As shown in FIG. 5, by displaying multiple parts included in lower categories, detailed contents of the maintenance record can be displayed.

[0030] The operation of the text display device 100 configured as above will be described with reference to the flowchart of FIG.

[0031] 6 is a flowchart showing an outline of the operation of the text display device 100 according to the present disclosure. Note that the processing according to this flowchart may be executed based on program control by the processor described above.

[0032] As shown in Figure 6, first, the extraction unit 101 extracts sections corresponding to maintenance record items from text data written in the product's maintenance record (step S101). Next, the generation unit 102 generates graph information shown in graph format by treating the objects written in each extracted item as nodes and connecting nodes that have mutual relationships with each other with edges (step S102). Finally, the display unit 103 displays the generated graph information (step S103). This completes the text display operation of the text display device 100.

[0033] In the text display device 100, the extraction unit 101 extracts sections corresponding to maintenance record items from text data written in a product's maintenance record. The generation unit 102 then generates graph information in a graph format by treating the objects written in each extracted item as nodes and connecting nodes that have relationships with each other with edges. This makes it easier to understand the relationships between the objects written in the maintenance record items. In this case, there is no need to refer to multiple tree diagrams created for each malfunction symptom, thereby reducing the effort required to understand the contents of the maintenance record.

[0034] [Second Embodiment] Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Below, descriptions of content that overlaps with the above description will be omitted to the extent that the description of this embodiment is not unclear. As with the computer device shown in FIG. 2, the functions of each component in each embodiment of the present disclosure can be realized not only by hardware but also by a computer device or software based on program control.

[0035] FIG. 7 is a block diagram showing the configuration of a text display device 110 according to the present disclosure. Referring to FIG. 7 , the text display device 110 will be described, focusing on the differences from the text display device 100. In this embodiment, a case is assumed in which a treatment for a defect symptom is estimated based on generated graph information displayed in a graph format. The text display device 110 includes an extraction unit 111, a generation unit 112, a display unit 113, and a first estimation unit 114. The extraction unit 111 and the generation unit 112 in this embodiment are the same as the corresponding components in the first embodiment.

[0036] The first estimation unit 114 is a means for estimating the cause of a product defect from its symptoms based on graph information shown in a graph format. More specifically, the first estimation unit 114 estimates the cause of the symptom by searching for the shortest path on the graph between the symptom (abnormal noise) of unknown cause and the treatment for the symptom based on graph information showing, in a graph format, nodes including the product symptoms and the treatment for resolving the symptoms.

[0037] The display unit 113 displays the contents of the estimated cause. The display unit 113 may highlight the node on the graph, the shortest path, or the like that is the basis for the cause of the symptom.

[0038] Here, a method for inferring the cause from a product's symptoms will be described. FIGS. 8 to 10 are diagrams illustrating an example of a method for inferring the cause from a product's symptoms according to the present disclosure. The graph information shown in FIG. 8 had already been created based on past maintenance records. These past maintenance records contained the following entry: The engine of the vehicle being serviced was replaced to fix an unstable idling problem. There were multiple other symptoms, each of which needed to be addressed. However, after the engine was replaced, the abnormal noise that was scheduled to be addressed next also disappeared. Based on these maintenance records, the maintenance technician inferred that replacing the engine had resolved the abnormal noise. In this case, as shown in FIG. 8 , the abnormal noise symptom is displayed at the same level as the idling problem, and the parent node (model number) and child node (causing part) are connected by an edge.

[0039] Next, based on the graph information, the first estimation unit 114 estimates the cause of the symptom (noise) that has been fixed from the node (engine) that is the same as the treatment that was performed on the vehicle to be repaired. As shown in Figure 9, the first estimation unit 114 searches the path of the graph information and estimates that the cause (fuel system - mixed - metal powder) on the shortest path between the node of the symptom (noise) that has been fixed and the treatment node is the cause of the symptom that has been fixed.

[0040] Furthermore, as shown in FIG. 10 , the first estimation unit 114 may detect a closed loop including a node of a symptom of unknown cause (abnormal noise) and a node of a causative component (fuel system), and estimate that the symptom (idling - unstable) included in the detected closed loop is a symptom caused by the same causative component (fuel system).

[0041] In this embodiment, the first estimation unit 114 estimates the cause of the product malfunction from the symptoms based on the graph information displayed in the form of a graph, thereby enabling the user to understand the cause of the malfunction without having to carefully read the maintenance record.

[0042] [Third Embodiment] Next, a third embodiment of the present disclosure will be described in detail with reference to the drawings. Below, descriptions of content that overlaps with the above description will be omitted to the extent that the description of this embodiment is not unclear. As with the computer device shown in FIG. 2, the functions of each component in each embodiment of the present disclosure can be realized not only by hardware but also by a computer device or software based on program control.

[0043] FIG. 11 is a block diagram showing the configuration of a text display device 120 according to the present disclosure. Referring to FIG. 11 , the text display device 120 will be described, focusing on differences from the text display device 100. In this embodiment, it is assumed that the frequency of a malfunction symptom or its cause is identified from graph information displayed in a generated graph format. The text display device 120 includes an extraction unit 121, a generation unit 122, a display unit 123, a compilation unit 124, and a second estimation unit 125. The extraction unit 121 and the generation unit 122 in this embodiment are the same as the corresponding components in the first embodiment. In this embodiment, it is assumed that the graph structure of maintenance records created over a predetermined period in the past is compiled. However, in this embodiment, the second estimation unit 125 is an optional component.

[0044] The counting unit 124 counts the number of product defect symptoms or causes based on the graph information of the maintenance records created over a predetermined period. For example, the counting unit 124 counts the number of cases each time the same symptom or the same cause is displayed in the graph information.

[0045] The second estimation unit 125 estimates the defective part of the product based on the counted number of symptoms or causes. For example, the second estimation unit 125 identifies the defective part related to a node that has a larger number of cases compared to other symptoms or causes. "Related" means, for example, that the nodes on the graph are within a predetermined path.

[0046] The display unit 123 outputs the counted number of symptoms or causes. The display unit 123 may output nodes or edges in different modes based on the counted number of symptoms or causes. For example, the display unit 123 may change the size of the nodes depending on the counted number of symptoms or causes.

[0047] FIG. 12 is an example of a display of the number of symptoms or causes according to the present disclosure. In the example of FIG. 12, assume that 100 maintenance records were compiled and the number of unstable idling incidents was "90" and the number of abnormal noise incidents was "10." In this case, as shown in FIG. 12, the display unit 123 displays the idling node larger than the abnormal noise node. Furthermore, since the 100 maintenance records were compiled and there were 100 incidents of fuel system and metal powder, the display unit 123 displays the fuel system and metal powder nodes larger than the other nodes. This allows the user to infer that there is a design problem in the product's fuel system, such as the presence of metal powder.

[0048] Furthermore, as shown in the lower part of FIG. 12 , a function may be provided that allows the period of maintenance records to be displayed to be changed using a slider. When the user moves the slider on the screen, the size and color of the nodes and edges change according to the number of cases included in the period specified by the user. This makes it possible to visualize the chronological changes in the number of cases of symptoms or causes. Furthermore, by displaying the number of cases for a period including before and after a design change, it is possible to quantitatively show the extent to which defects have been reduced as a result of design improvements.

[0049] The display unit 123 may also output the counted number of symptoms or causes in the form of a table or graph. For example, Fig. 13 is a diagram showing the number of causes in the present disclosure in the form of a table. Fig. 14 is a diagram showing the number of causes in the present disclosure in the form of a graph. As shown in Fig. 14, by displaying the number of causes in the form of a line graph or bar graph, it is possible to grasp the transition of the number of causes.

[0050] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0051] For example, although multiple operations are described in a sequential order in the form of a flowchart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed within the scope that does not affect the content.

[0052] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0053] (Supplementary Note 1) A text display device comprising: an extraction means for extracting portions corresponding to items in a maintenance record from text data recorded in the maintenance record of a product; a generation means for generating graph information shown in a graph format by treating the objects recorded in each extracted item as nodes and connecting nodes that are related to each other with edges; and a display means for displaying the generated graph information.

[0054] (Supplementary Note 2) The text display device according to Supplementary Note 1, wherein the items of the maintenance record include any one of a symptom of the malfunction, a cause of the symptom, or a treatment for the symptom.

[0055] (Supplementary Note 3) The text display device according to Supplementary Note 1 or Supplementary Note 2, wherein the generating means generates text data indicating content described regarding the target in a label of the edge.

[0056] (Supplementary Note 4) The text display device according to any one of Supplementary Note 1 to Supplementary Note 3, wherein the generating means generates the graph information from text data described in a plurality of maintenance records.

[0057] (Supplementary Note 5) The text display device according to Supplementary Note 4, wherein the generating means generates graph information in which the nodes of each causative part are branched when the causative parts described in each of the multiple maintenance records are included in the same category.

[0058] (Appendix 6) A text display device as described in any of Appendices 1 to 5, further comprising a first estimation means for estimating a cause from the symptoms of the defect in the product based on the graph information shown in the graph format, and the display means displays the content of the estimated cause.

[0059] (Appendix 7) A text display device as described in any of Appendices 1 to 6, wherein the generating means generates the graph information from text data written in a plurality of the maintenance records created over a predetermined period, and further comprises a counting means for counting the number of symptoms of product defects or causes of the symptoms based on the graph information, and the display means displays the number of the symptoms or causes.

[0060] (Supplementary Note 8) The text display device according to Supplementary Note 7, wherein the predetermined period is a period designated by a user.

[0061] (Supplementary Note 9) The text display device according to Supplementary Note 7 or Supplementary Note 8, wherein the display means displays the nodes or the edges in different modes based on the number of the symptoms or the causes that have been counted.

[0062] (Appendix 10) A text display device as described in any one of Appendices 7 to 9, further comprising a second estimation means for estimating a defective part of the product based on the number of symptoms or causes that have been collected, and the display means for displaying the defective part.

[0063] (Supplementary Note 11) A text display method in which a computer extracts portions corresponding to items in a maintenance record from text data recorded in the maintenance record of a product, generates graph information shown in a graph format by treating the objects recorded in each extracted item as nodes and connecting nodes that are related to each other with edges, and displays the generated graph information.

[0064] (Supplementary Note 12) The text display method according to Supplementary Note 11, wherein the maintenance record items include any one of a symptom of the malfunction, a cause of the symptom, or a treatment for the symptom.

[0065] (Supplementary Note 13) The text display method according to Supplementary Note 11 or Supplementary Note 12, further comprising generating text data indicating the content of the description regarding the object in the label of the edge.

[0066] (Supplementary Note 14) The text display method according to any one of Supplementary Note 11 to Supplementary Note 13, wherein the graph information is generated from text data written in a plurality of maintenance records.

[0067] (Supplementary Note 15) The text display method according to Supplementary Note 14, wherein when the causative parts described in each of the multiple maintenance records are included in the same category, graph information is generated in which the nodes of each causative part are branched.

[0068] (Supplementary Note 16) A text display method according to any one of Supplementary Note 11 to Supplementary Note 15, which estimates a cause from the symptoms of a defect in the product based on the graph information shown in the graph format, and displays the details of the estimated cause.

[0069] (Supplementary Note 17) A text display method according to any one of Supplementary Note 11 to Supplementary Note 16, which generates the graph information from text data written in a plurality of the maintenance records created over a predetermined period, tallying up the number of symptoms of product defects or the causes of the symptoms based on the graph information, and displaying the number of the symptoms or the causes.

[0070] (Supplementary Note 18) The text display method according to Supplementary Note 17, wherein the nodes or edges are displayed in different modes based on the number of symptoms or causes that have been counted.

[0071] (Supplementary Note 19) The text display method according to Supplementary Note 17 or Supplementary Note 18, further comprising: estimating a defective part of the product based on the number of symptoms or causes that have been collected; and displaying the defective part.

[0072] (Supplementary Note 20) A recording medium storing a program that causes a computer to execute the following: extracting portions corresponding to items in a maintenance record from text data recorded in the maintenance record of a product; generating graph information shown in a graph format by treating the objects recorded in each extracted item as nodes and connecting nodes that have mutual relationships with each other with edges; and displaying the generated graph information.

[0073] Some or all of the configurations described in Supplements 2 to 10 that are dependent on Supplement 1 above may also be dependent on Supplement 20 in the same dependency relationship as Supplements 2 to 10. Not limited to Supplements 1, 11, and 20, but also to various hardware, software, various recording devices for recording software, or systems, some or all of the configurations described as Supplements may be made dependent on each other within the scope of the above-mentioned embodiments.

[0074] 100, 110, 120 Text display device 101, 111, 121 Extraction unit 102, 112, 122 Generation unit 103, 113, 123 Display unit 114 First estimation unit 124 Aggregation unit 125 Second estimation unit 500 Computer device 501 Processor 502 ROM 503 RAM 504 Program 505 Storage device 506 Recording medium 507 Drive device 508 Communication interface 511 Input / output interface 512 Bus

Claims

1. An article display device comprising: extraction means for extracting, from text data recorded in a maintenance record of a product, portions corresponding to items of the maintenance record; generation means for generating graph information represented in a graph format by using, as nodes, objects described in each of the extracted items and connecting nodes having a relationship with each other by edges; and display means for displaying the generated graph information.

2. The article display device according to claim 1, wherein the items of the maintenance record include any one of a symptom of a defect, a cause of the symptom, or a treatment for the symptom.

3. The article display device according to claim 1 or 2, wherein the generation means generates text data indicating the content described regarding the object as a label of the edge.

4. The article display device according to any one of claims 1 to 3, wherein the generation means generates the graph information from text data recorded in a plurality of maintenance records.

5. The article display device according to claim 4, wherein the generation means generates graph information in which nodes of each cause part are branched when the cause parts described in each of the plurality of maintenance records are included in the same category.

6. The article display device according to any one of claims 1 to 5, further comprising first estimation means for estimating a cause from a symptom of a defect of the product based on the graph information represented in the graph format, wherein the display means displays the content of the estimated cause.

7. The article display device according to any one of claims 1 to 6, wherein the generation means generates the graph information from text data recorded in a plurality of the maintenance records created during a predetermined period, further comprising counting means for counting the number of symptoms of a defect of the product or the number of causes of the symptom based on the graph information, and wherein the display means displays the number of the symptoms or the number of the causes.

8. The article display device according to claim 7, wherein the predetermined period is a period specified by a user.

9. The article display device according to claim 7 or 8, wherein the display means displays the nodes or the edges in different modes based on the counted number of the symptoms or the number of the causes.

10. The article display device according to any one of claims 7 to 9, comprising second estimation means for estimating a defective part of the product based on the counted number of the symptoms or the number of the causes, and wherein the display means displays the defective part.

11. A method for displaying text, wherein a computer extracts portions corresponding to items of maintenance records from text data recorded in the maintenance records of a product, uses the objects described in each of the extracted items as nodes, connects the nodes having a relationship with each other by edges, generates graph information represented in a graph format, and displays the generated graph information.

12. The method for displaying text according to claim 11, wherein the items of the maintenance records include any one of a symptom of a defect, a cause of the symptom, or a treatment for the symptom.

13. The method for displaying text according to claim 11 or 12, wherein text data indicating the content described regarding the object is generated as a label of the edge.

14. The method for displaying text according to any one of claims 11 to 13, wherein the graph information is generated from text data recorded in a plurality of maintenance records.

15. The method for displaying text according to claim 14, wherein when the cause parts described in each of the plurality of maintenance records are included in the same category, graph information in which the nodes of the respective cause parts are branched is generated.

16. The method for displaying text according to any one of claims 11 to 15, wherein based on the graph information represented in the graph format, a cause is estimated from the symptom of a defect of the product, and the content of the estimated cause is displayed.

17. The method for displaying text according to any one of claims 11 to 16, wherein the graph information is generated from text data recorded in a plurality of the maintenance records created within a predetermined period, the number of cases of the symptom of a defect of the product or the cause of the symptom is tabulated based on the graph information, and the number of cases of the symptom or the cause is displayed.

18. The method for displaying text according to claim 17, wherein the node or the edge is displayed in a different manner based on the tabulated number of cases of the symptom or the cause.

19. The method for displaying text according to claim 17 or 18, wherein a defective part of the product is estimated based on the tabulated number of cases of the symptom or the cause, and the defective part is displayed.

20. A recording medium storing a program for causing a computer to perform: extracting portions corresponding to items of maintenance records from text data recorded in the maintenance records of a product; using the objects described in each of the extracted items as nodes; connecting the nodes having a relationship with each other by edges to generate graph information represented in a graph format; and displaying the generated graph information.

Images